From e481288a3a5fdf05f4bcc491dc120820975710d3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:04:11 +0800 Subject: [PATCH 001/140] refactor: derive snapshot session fixtures from disk --- .../2026-07-08-shared-acp-snapshot-package.md | 2 +- .../2026-06-20-discover-package-inventory.md | 5 +- examples/acp-agent/tests/acp.snapshot.ts | 10 +-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/suite.ts | 68 +++++++++++-------- .../support/acp-snapshot/tests/suite.spec.ts | 44 +++++++++--- 6 files changed, 85 insertions(+), 46 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index c622a7f1be..eca3661b33 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. -**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. +**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). A scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are its ordered primary/child inventory, so the scenario table declares policy without duplicating a child count. The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`sessionFixtureNames`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. ## Alternatives considered diff --git a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md index 3587393efe..a091203da9 100644 --- a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md +++ b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md @@ -4,7 +4,7 @@ Status: proposed ## Problem -Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). The ACP snapshot suite's scenario table (`examples/acp-agent/tests/acp.snapshot.ts`) hand-maintains a `childSessions` count per scenario that duplicates the number of `session..jsonl` fixture siblings on disk. These lists are small today, but every new package or scenario class creates another manual synchronization point. +Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). These lists are small today, but every new package creates another manual synchronization point. The [package hierarchy](../../implemented/architecture/2026-06-20-package-hierarchy.md) already removed several of these by hand: `scripts/publint-all.ts` now derives its list from the `packages//` layout, and the two `tsconfig` `paths` maps collapsed to one `@deepseek-ai/dsh-*` wildcard. What remains is the inventory that cannot be globbed away — chiefly `tsconfig.build.json`'s project `references`, which TypeScript requires as an explicit array (no wildcard form). @@ -16,7 +16,7 @@ Make the remaining package/gate inventories discoverable. A single canonical sou The hierarchy does not need to encode every fact about a package, but it should encode the broad maintenance policy: core/product packages, integrations, capability seams, and support/test/example packages should not all require a hand-maintained exception list before scripts can tell them apart. -Two of the cataloged items need no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright, and `childSessions` can be discovered from each scenario's fixture directory, leaving the scenario table to declare only policy (`recorded`, `hasModelTurn`, `comparesLog`) — and even those track fixture-derivable facts today (`comparesLog` ⟺ the committed log has entries beyond its header line; `recorded` ⟺ `hasModelTurn` with no `replay.override.json` sibling), so each new scenario class keeps adding knobs the fixture directory already answers. +One cataloged item needs no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright. ## Acceptance criteria @@ -25,7 +25,6 @@ Two of the cataloged items need no generator at all: folding the e2e entry glob - Docs describe the source of truth rather than repeating generated inventories. - CI invokes the aggregate commands and lets those commands own their sub-gate lists. - `knip.json` carries a per-package override only where it encodes real information (an extra entry file, an ignored dependency), never a restatement of the default stanza. -- Snapshot scenarios declare policy, not facts discoverable from their fixture directories. ## Risks diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index eaa4e0381a..b1a43b83db 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -67,14 +67,14 @@ const SCENARIOS: Scenario[] = [ // tiers (gentle at 3, detailed at 5) as context/message in transcript and log. { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, - { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 }, - { name: 'subagent-fork', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-mixed', hasModelTurn: true, recorded: true, childSessions: 2 }, + { name: 'subagent-spawn', hasModelTurn: true, recorded: true }, + { name: 'subagent-multi', hasModelTurn: true, recorded: true }, + { name: 'subagent-fork', hasModelTurn: true, recorded: true }, + { name: 'subagent-mixed', hasModelTurn: true, recorded: true }, // The workflow tool: the model writes a one-child orchestration script; the // child runs as a spawn subagent under the worker-thread engine (its session is the // child fixture), and the tool result carries the script's return value. - { name: 'workflow-run', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'workflow-run', hasModelTurn: true, recorded: true }, // Hook matrix — one scenario per hook point × its headline Decision outcome, // across BOTH bridges (Claude `hooks.json`, Codex `codex-hooks.json`, seeded in // workspace/). The block scenarios need no model call: a UserPromptSubmit hook diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 13dd1ab247..ac9c0ceee3 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -6,7 +6,7 @@ Three layers, importable separately: - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). -- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time. +- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. A consuming `*.snapshot.ts` is the scenario table plus one factory call: diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 523092bf09..6311a15031 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -80,14 +80,6 @@ export interface Scenario { * false (replay derives from the fixture's `assistant/chunk` events). */ overridden?: boolean - /** - * How many SUBAGENT child sessions this scenario records beyond the top-level - * one (0 for a single-session scenario). Each child rides in a sibling fixture - * `session..jsonl` (1-based); replay forwards them to `dsh-llm-replay` so - * each child session replays from its own script, and record mode writes the - * harvested child logs back to those files. Defaults to 0. - */ - childSessions?: number /** * Whether THIS scenario pins its header class's model-facing request-header * content. Its actual composed prompt is maintained as a readable @@ -150,14 +142,40 @@ export interface SnapshotSuiteOptions { } /** - * The sibling child-fixture paths for a scenario (`session.1.jsonl` …). + * Validate and order a scenario directory's session-fixture filenames. * - * @param dir The scenario's snapshots directory (`/`). - * @param childSessions How many subagent child sessions the scenario records. - * @returns One path per child, 1-based, in fixture order. + * The primary fixture is always `session.jsonl`; child sessions are discovered + * from contiguous `session.1.jsonl` … filenames. The directory is the source of + * truth, so scenario tables do not duplicate a child count that can drift from + * the files. A session-like JSONL with any other suffix fails loud. + * + * @param names File names in one scenario directory. + * @returns The primary and child fixture names in replay/harvest order. */ -export function childFixturePaths(dir: string, childSessions: number): string[] { - return Array.from({ length: childSessions }, (_, i) => join(dir, `session.${i + 1}.jsonl`)) +export function sessionFixtureNames(names: readonly string[]): string[] { + if (!names.includes('session.jsonl')) throw new Error('missing session.jsonl') + const children: { name: string; index: number }[] = [] + for (const name of names) { + if (name === 'session.jsonl') continue + if (!name.startsWith('session.') || !name.endsWith('.jsonl')) continue + const match = /^session\.([1-9]\d*)\.jsonl$/.exec(name) + if (match === null) throw new Error(`invalid child session fixture name: ${name}`) + children.push({ name, index: Number(match[1]) }) + } + children.sort((a, b) => a.index - b.index) + for (const [offset, child] of children.entries()) { + const expected = offset + 1 + if (child.index !== expected) { + throw new Error(`child session fixtures must be contiguous: expected session.${expected}.jsonl, found ${child.name}`) + } + } + return ['session.jsonl', ...children.map(child => child.name)] +} + +/** Read one scenario directory's validated session-fixture inventory. */ +async function sessionFixtures(dir: string): Promise { + const entries = await readdir(dir, { withFileTypes: true }) + return sessionFixtureNames(entries.filter(entry => entry.isFile()).map(entry => entry.name)) } /** @@ -392,7 +410,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const childSessions = scenario.childSessions ?? 0 + const fixtureFiles = await sessionFixtures(dir) + const childFixtureFiles = fixtureFiles.slice(1) + const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -401,7 +421,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixturePaths(dir, childSessions) } : {}, + ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -432,7 +452,6 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const scrub = scenario.pinsHeader === true ? scrubSystemPrompts : scrubRequestHeaders - const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)] const existingFixtures = REFRESHING ? await Promise.all(fixtureFiles.map(file => readFile(join(dir, file), 'utf8'))) : [] @@ -543,7 +562,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(onDisk).toEqual(registered) }) - it('every registered scenario has its required fixture files', () => { + it('every registered scenario has its required fixture files', async () => { // Every scenario has an input script and an stdout golden. EVERY scenario // also needs `session.jsonl`: the suite boots `llm-replay` with that path // as the replay source for ALL scenarios (the factory passes @@ -556,7 +575,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // `overridden` flag: required when set, forbidden when not — the harness // forwards the file purely on existence, so an unregistered stray sidecar // would silently replace the derived script. - for (const { name, overridden, childSessions, pinsHeader } of scenarios) { + for (const { name, overridden, pinsHeader } of scenarios) { const dir = join(snapshotsDir, name) expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true) expect(existsSync(join(dir, 'stdout.golden.jsonl')), `${name}/stdout.golden.jsonl`).toBe(true) @@ -565,11 +584,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { .toBe(overridden === true) expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``) .toBe(pinsHeader === true) - // A nested-agent scenario ships one child fixture per recorded subagent - // session (`session.1.jsonl` …), the replay source for that child session. - for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) { - expect(existsSync(childFixture), childFixture).toBe(true) - } + await expect(sessionFixtures(dir), `${name}: session fixture inventory`).resolves.toBeDefined() } }) @@ -615,10 +630,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // all header bulk. Fixed-point checks make both storage rules fail loud. for (const scenario of scenarios) { const dir = join(snapshotsDir, scenario.name) - const files = [ - 'session.jsonl', - ...Array.from({ length: scenario.childSessions ?? 0 }, (_, i) => `session.${i + 1}.jsonl`), - ] + const files = await sessionFixtures(dir) for (const file of files) { const fixture = await readFile(join(dir, file), 'utf8') expect(scrubSystemPrompts(fixture), `${scenario.name}/${file} carries an unscrubbed system prompt`) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index 4ca9c8573d..f27f36c564 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -6,13 +6,13 @@ import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts' import { - childFixturePaths, fixtureContext, formatSystemPromptSnapshot, headerChangeCount, normalizedHeaders, normalizedSystemPrompts, refreshFixtureReplacements, + sessionFixtureNames, stabilizeRefreshLog, } from '../src/suite.ts' @@ -51,7 +51,7 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. // example's code-mode scenarios). const REPLAY_SCENARIOS: Scenario[] = [ { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, - { name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath }, + { name: 'plain-turn', hasModelTurn: true, recorded: true, headerClass: 'main', configPath: AGENT.configPath }, { name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' }, { name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' }, { name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' }, @@ -59,7 +59,7 @@ const REPLAY_SCENARIOS: Scenario[] = [ const RECORD_SCENARIOS: Scenario[] = [ { name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true }, - { name: 'rec-child', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'rec-child', hasModelTurn: true, recorded: true }, // recorded:false in record mode → registered but skipped (never re-recorded). { name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true }, ] @@ -180,13 +180,41 @@ describe('defineAcpSnapshotSuite: registration contract', () => { }) }) -describe('childFixturePaths', () => { - it('yields one sibling path per child, 1-based', () => { - expect(childFixturePaths('/snap/s', 2)).toEqual(['/snap/s/session.1.jsonl', '/snap/s/session.2.jsonl']) +describe('sessionFixtureNames', () => { + it('orders the primary and contiguous child fixtures while ignoring other files', () => { + expect(sessionFixtureNames([ + 'stdout.golden.jsonl', + 'session.2.jsonl', + 'session.jsonl', + 'session.1.jsonl', + 'input.json', + ])).toEqual(['session.jsonl', 'session.1.jsonl', 'session.2.jsonl']) }) - it('yields nothing for a single-session scenario', () => { - expect(childFixturePaths('/snap/s', 0)).toEqual([]) + it('accepts a primary-only scenario', () => { + expect(sessionFixtureNames(['session.jsonl'])).toEqual(['session.jsonl']) + }) + + it('rejects a directory without the primary fixture', () => { + expect(() => sessionFixtureNames(['session.1.jsonl'])).toThrow('missing session.jsonl') + }) + + it('rejects gapped child fixtures', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.2.jsonl'])) + .toThrow('expected session.1.jsonl, found session.2.jsonl') + }) + + it.each(['session.0.jsonl', 'session.child.jsonl', 'session.01.jsonl'])( + 'rejects invalid child fixture name %s', + (name) => { + expect(() => sessionFixtureNames(['session.jsonl', name])) + .toThrow(`invalid child session fixture name: ${name}`) + }, + ) + + it('rejects duplicate child indexes', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.1.jsonl', 'session.1.jsonl'])) + .toThrow('expected session.2.jsonl, found session.1.jsonl') }) }) From 0e7d539bbc5b75ad224b312a11cc1e15e1ba527a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:18:00 +0800 Subject: [PATCH 002/140] refactor: share the ACP test launcher --- .../2026-07-08-shared-acp-snapshot-package.md | 10 +- examples/acp-agent/tests/acp.e2e.ts | 182 +++--------------- examples/acp-agent/tests/hooks.e2e.ts | 68 ++----- .../sandbox-acp-agent/tests/escalation.e2e.ts | 79 +++----- packages/support/README.md | 4 +- packages/support/acp-snapshot/README.md | 5 +- packages/support/acp-snapshot/package.json | 2 +- packages/support/acp-snapshot/src/harness.ts | 130 ++----------- packages/support/acp-snapshot/src/index.ts | 24 ++- packages/support/acp-snapshot/src/launcher.ts | 152 +++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 33 ++++ 11 files changed, 292 insertions(+), 397 deletions(-) create mode 100644 packages/support/acp-snapshot/src/launcher.ts diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index eca3661b33..59734535b8 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -6,13 +6,15 @@ Status: implemented The ACP snapshot tier ([snapshot RFC](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure golden normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout-golden and log compares, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). -A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was already triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness (`TODO(acp-test-harness)`). Location also decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. +A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was also triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness. Location decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. ## Decision The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/support/acp-snapshot/README.md) (`@deepseek-ai/dsh-acp-snapshot`); an example's `*.snapshot.ts` is its scenario table, its agent paths, and one factory call, over its own `snapshots/` fixtures and `cordis.snapshot.yml` overlay ([single-source replay config](2026-07-04-single-source-acp-replay-config.md)). Reading `DSH_SNAPSHOT` stays at that edge — the library takes a resolved `mode`. -**`src/harness.ts`** — `runScenario` and the input-script/result types, parameterized by an `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`; absolute paths the consuming suite resolves from its own `import.meta.url`). The client's `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. +**`src/launcher.ts`** — `launchAcpTestAgent` owns the common unbuilt-process boundary: absolute tsx loader resolution, `TSX_TSCONFIG_PATH`, isolated harness homes, stdio wiring, a raw-byte stdout tee, stderr and update capture, fail-closed permission fallback, update waiters, and graceful or signalled shutdown. Snapshot scenarios and ordinary e2e suites supply the same `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`); a test that plays a user supplies only its permission handler. The ACP and hook e2e suites plus the sandbox/approval e2e suite use this launcher instead of rebuilding the SDK client boundary. + +**`src/harness.ts`** — `runScenario` and the input-script/result types layer deterministic steps, temp workspaces, snapshot environment, and persisted-log harvest over the launcher. Its `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. @@ -29,8 +31,8 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su ## Testing -Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the REAL spawn path by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` covers every step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), env forwarding, workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. Two structurally unreachable guards carry reasoned `v8 ignore` comments. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). +Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the real launcher by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` directly covers launcher defaults, captures, update waiting, shutdown, and environment/config variants, then covers every scenario step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). ## Consequences -A new example gets the whole snapshot tier from a scenario table plus fixtures — the sandbox branch merges master down and adds its own suite (own pin scenario, own overlay, fixtures via `test:snapshot:record`, approvals via `permissionAnswers`). The costs: `suite.ts` imports vitest, so the package is importable only inside a vitest run — a shape no other package has, stated in its README; each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard); and the e2e launcher duplication remains (`TODO(acp-test-harness)`) — the harness is the extraction target when that migration lands. +A new example gets the whole snapshot tier from a scenario table plus fixtures, while an ordinary ACP e2e gets the same tested process/client boundary from one launcher call. The costs: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run — a shape no other package has, stated in its README; and each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard). diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 8ff012c2c3..4b6c675208 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -26,127 +20,18 @@ import { * WITHOUT a key, since it only needs the server to boot and answer initialize. */ -// The dsh-acp-agent bin (the demo:acp entry) and this example's cordis.yml. The -// bin resolves its config-path arg from CWD; the subprocess runs from a temp -// workdir, so pass the example config's ABSOLUTE path. -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -// Resolve tsx's loader to an ABSOLUTE path: the subprocess runs with cwd set to -// a temp workdir (this test launches there and uses it as the session cwd; the -// bridge no longer requires cwd === the launch dir, but a temp dir keeps the -// test hermetic), where a bare `--import tsx` would not resolve from -// node_modules. import.meta.resolve gives the worktree's tsx regardless of cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// Absolute path to the repo-root tsconfig. Dev/test/demo run UNBUILT: the -// `@deepseek-ai/dsh-*` workspace imports resolve through the `paths` map in the -// root tsconfig (tsx reads it), NOT through built `lib/` output. But tsx finds -// that tsconfig by searching UP from the child's cwd — and the child's cwd is a -// temp workdir OUTSIDE the repo, so the search misses and the dsh-* imports fail -// (the child dies before writing a byte). Point tsx at the repo tsconfig -// explicitly via TSX_TSCONFIG_PATH so resolution is cwd-independent. (Without -// this the suite only passed by accident when a stale built `lib/` happened to -// exist — exactly the contamination that masked the inject bug this suite now -// guards.) The repo root is four levels up from this file (examples/acp-agent/tests). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -// TODO(acp-test-harness): this subprocess/client boot glue is duplicated with -// hooks.e2e.ts and partly with dsh-acp-snapshot's harness. Migrate both e2e -// files onto that launcher before the TSX/env/permission-stub details drift. -function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - env: { - ...env, - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - // This example composes no ask-producing policy (no hooks), so the - // bridge never prompts here; answer cancelled (fail closed) if it ever - // does — an unexpected prompt must not grant anything. - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined -function hasStdoutLine(out: string[]): boolean { - return out.join('').split('\n').some(line => line.trim().length > 0) -} - -async function waitForStdoutLine(child: ChildProcessWithoutNullStreams, out: string[], stderr: string[], timeoutMs: number): Promise { - await new Promise((resolve, reject) => { - const cleanup = () => { - clearTimeout(timeout) - child.stdout.off('data', onData) - child.off('exit', onExit) - child.off('error', onError) - } - const pass = () => { - cleanup() - resolve() - } - const fail = (reason: string) => { - cleanup() - reject(new Error(`${reason}; stderr: ${stderr.join('')}`)) - } - const onData = () => { - if (hasStdoutLine(out)) pass() - } - const onExit = (code: number | null, signal: NodeJS.Signals | null) => { - fail(`ACP child exited before emitting a stdout frame (code ${code ?? 'null'}, signal ${signal ?? 'null'})`) - } - const onError = (error: Error) => { - fail(`ACP child failed before emitting a stdout frame: ${error.message}`) - } - const timeout = setTimeout(() => { - fail(`ACP child did not emit a stdout frame within ${timeoutMs}ms`) - }, timeoutMs) - - child.stdout.on('data', onData) - child.on('exit', onExit) - child.on('error', onError) - onData() - }) -} - afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -154,39 +39,18 @@ afterEach(async () => { describe('acp-agent over real stdio (no key required)', () => { it('emits only framed JSON-RPC on stdout', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - // Collect raw stdout bytes directly (bypass the SDK framing) to inspect. + // Inspect the launcher's raw-byte tee in addition to driving its SDK client. // A dummy key lets the deepseek adapter APPLY (it only checks the key is // present at boot, not valid — the key is used only on a real model call, // which this purity test never triggers). So this runs WITHOUT real creds. - const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], { + spawned = launchAcpTestAgent({ + agent: AGENT, cwd: workdir, - env: { - ...process.env, - DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(workdir, '.dsh'), - DSH_AGENTS_HOME: join(workdir, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, }) - const out: string[] = [] - const stderr: string[] = [] - child.stdout.setEncoding('utf8') - child.stderr.setEncoding('utf8') - child.stdout.on('data', (c: string) => out.push(c)) - child.stderr.on('data', (c: string) => stderr.push(c)) + await spawned.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - // Send a single initialize request as a newline-delimited JSON-RPC frame. - const req = JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} } }) - child.stdin.write(req + '\n') - - try { - await waitForStdoutLine(child, out, stderr, 15_000) - } finally { - child.kill('SIGKILL') - } - - const lines = out.join('').split('\n').filter(l => l.trim().length > 0) + const lines = spawned.rawStdout().split('\n').filter(line => line.trim().length > 0) expect(lines.length).toBeGreaterThan(0) for (const line of lines) { // Every stdout line MUST parse as JSON (a JSON-RPC frame). A non-JSON @@ -210,7 +74,11 @@ describe('acp-agent over real stdio (no key required)', () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) // A dummy key lets the deepseek adapter boot (it only checks presence, not // validity, at apply time); no model call is made, so the key is never used. - spawned = spawnAcpAgent(workdir, { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }) + spawned = launchAcpTestAgent({ + agent: AGENT, + cwd: workdir, + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + }) const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -223,7 +91,7 @@ describe('acp-agent over real stdio (no key required)', () => { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over ACP', () => { it('runs a real turn and the agent writes the requested file (verified on disk)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -264,7 +132,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over it('with the terminal_output capability, a real bash call renders as a terminal card (content + _meta + exit)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned // Advertise the Zed `_meta.terminal_output` capability so the bridge emits diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index bdb800186a..a553addc96 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -34,54 +28,18 @@ import { * only a real model deciding to call bash exercises the PreToolUse seam live. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -function spawnAcpAgent(cwd: string): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -96,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: 'echo "bash blocked by policy" >&2; exit 2' }] }] }, })) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index 93915717a1..a7e8787e36 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -1,20 +1,18 @@ -import { spawn, spawnSync, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' +import { spawnSync } from 'node:child_process' import { mkdtemp, readFile, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' import { - ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, } from '@agentclientprotocol/sdk' +import { + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * examples/sandbox-acp-agent end to end. @@ -35,12 +33,11 @@ import { * escalation target the model picks can land the write. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// The subprocess runs from a temp cwd OUTSIDE the repo; point tsx at the repo -// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), +} // A usable confining runner, probed the same way the executor suites do: // bwrap on Linux, Seatbelt's sandbox-exec on macOS. Without one the strict @@ -56,44 +53,19 @@ const hasSeatbelt = process.platform === 'darwin' && spawnSync('sandbox-exec', [ }).status === 0 const hasRunner = hasBwrap || hasSeatbelt -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] +interface Spawned extends LaunchedAcpTestAgent { permissionRequests: RequestPermissionRequest[] - stderr: string[] } /** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */ -function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - // A dummy key lets the deepseek adapter boot keyless (presence-checked at - // apply, used only on a real model call); the with-key tests carry the - // real key, so the fallback is inert there. - env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] +function launchSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { const permissionRequests: RequestPermissionRequest[] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(params: RequestPermissionRequest): Promise { + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd, + // A dummy key lets the adapter boot keylessly; live tests carry the real key. + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + requestPermission(params) { permissionRequests.push(params) const option = params.options.find(o => o.optionId === answer) // The scripted human: pick the requested option when the prompt offers @@ -102,15 +74,14 @@ function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once') return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, permissionRequests, stderr } + return Object.assign(launched, { permissionRequests }) } let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - if (spawned !== undefined && spawned.child.exitCode === null) spawned.child.kill('SIGKILL') + await spawned?.close('SIGKILL') spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined @@ -119,7 +90,7 @@ afterEach(async () => { describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { it('boots the tree — sandbox executor + approval service + bridge — and opens a session', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned // A dummy key boots the adapter; no prompt is ever sent, so no model call // and no sandbox runner probe happen. This drives the fiber tree the same @@ -132,7 +103,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () it('advertises both session config options and honors a switch end to end (no key, no model)', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) // This tree composes bash-sandbox (mode: read-only) + approval → both @@ -164,7 +135,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent e2e: the live approval loop', () => { it('denial → model escalation → editor prompt → allow-once → the retried write lands on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'allow-once') + spawned = launchSandboxAcpAgent(workdir, 'allow-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -193,7 +164,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent it('a rejected escalation stays denied: no write lands, the turn still ends', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/packages/support/README.md b/packages/support/README.md index c8883a89ff..9a05ad3c9a 100644 --- a/packages/support/README.md +++ b/packages/support/README.md @@ -4,9 +4,9 @@ Packages that exist to serve development, testing, and the examples rather than | Package | Role | ctx key | |---|---|---| -| `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) | +| `acp-snapshot/` | ACP test kit: shared subprocess/client launcher + snapshot harness, normalizers, and suite factory | (library — imported by ACP e2e and `*.snapshot.ts` suites) | | `invariants/` | Dev-mode event-contract assertions | (listens on `session/*`, `agent/*`) | | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) | | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) | -`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery so every example's suite is a scenario table over one shared, gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. +`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, so e2e tests share one launcher and every snapshot suite is a scenario table over one gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index ac9c0ceee3..4a43d0eef9 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -2,8 +2,9 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tier (`pnpm run test:snapshot`, [testing policy](../../../docs/testing.md)). An example gets a full snapshot suite from a scenario table plus a fixtures directory; every compare/guard mechanic lives here, under the per-file coverage gate, instead of being copied per example. -Three layers, importable separately: +Four layers, importable separately: +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. @@ -39,4 +40,4 @@ A scenario booting a differently-composed tree sets its own `configPath` (an ove The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log goldens, and each pin's Markdown prompt snapshot from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md). -Constraints: `suite.ts` imports vitest, so the package is importable only inside a vitest run (the harness and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the harness speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). +Constraints: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run (the launcher, harness, and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). diff --git a/packages/support/acp-snapshot/package.json b/packages/support/acp-snapshot/package.json index 363bc86e25..b14be09c5b 100644 --- a/packages/support/acp-snapshot/package.json +++ b/packages/support/acp-snapshot/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-acp-snapshot", - "description": "ACP snapshot suite kit: real-subprocess scenario harness, golden normalizers, and the suite factory behind the keyless snapshot tier", + "description": "ACP test kit: shared subprocess launcher, snapshot scenario harness, golden normalizers, and suite factory", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 491d3ea884..93bb556ba6 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -16,54 +16,20 @@ * @module @deepseek-ai/dsh-acp-snapshot/harness */ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises' import { existsSync } from 'node:fs' import { tmpdir } from 'node:os' import { join, delimiter } from 'node:path' -import { fileURLToPath } from 'node:url' -import { Readable, Writable } from 'node:stream' import { ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, type RequestPermissionResponse, type SessionNotification, } from '@agentclientprotocol/sdk' +import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } from './launcher.ts' -// Resolve tsx's ESM loader to an ABSOLUTE path once: the child runs with its -// cwd in a temp dir OUTSIDE the repo, where a bare `--import tsx` would not -// resolve from node_modules. import.meta.resolve gives this package's tsx -// regardless of the child cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) - -/** - * The agent composition a scenario runs against: which bin to boot and which - * leaf config it loads. All paths are ABSOLUTE — the subprocess cwd is a temp - * dir outside the repo, so relative resolution would miss; a suite resolves - * them from its own `import.meta.url`. - */ -export interface AgentUnderTest { - /** The agent bin entry (e.g. `packages/ui/acp-agent/src/bin.ts`), run unbuilt via tsx. */ - binScript: string - /** - * The example's live `cordis.yml`. Under `DSH_SNAPSHOT=replay` the bin swaps - * it for the sibling `cordis.snapshot.yml` (the keyless replay overlay), so - * one path serves both modes. - */ - configPath: string - /** - * The repo-root tsconfig whose `paths` map resolves the unbuilt workspace - * imports. Passed to the child as `TSX_TSCONFIG_PATH`: tsx finds a tsconfig - * by searching UP from the child's cwd — a temp dir outside the repo — so - * without the explicit pin the dsh-* imports fail before the bin writes a - * byte. - */ - tsconfigPath: string -} +export type { AgentUnderTest } from './launcher.ts' /** * One step of a scenario's deterministic input script (`input.json`). The @@ -194,11 +160,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Everything past the temp-dir creation runs under a try/finally that always // removes both dirs — so a failure in workspace seeding, spawn, or any step // never leaks them (the "e2e tests own their resources" rule). - let child: ChildProcessWithoutNullStreams | undefined + let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - const rawBuffers: Buffer[] = [] - const stderrChunks: string[] = [] try { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens @@ -207,51 +171,15 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cp(opts.workspaceDir, cwd, { recursive: true }) } const env: NodeJS.ProcessEnv = { - ...process.env, - TSX_TSCONFIG_PATH: opts.agent.tsconfigPath, DSH_SNAPSHOT: opts.mode, DSH_SNAPSHOT_FILE: opts.fixtureFile, DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), ...opts.overrideFile !== undefined ? { DSH_SNAPSHOT_OVERRIDE: opts.overrideFile } : {}, ...opts.childFiles !== undefined && opts.childFiles.length > 0 ? { DSH_SNAPSHOT_CHILD_FILES: opts.childFiles.join(delimiter) } : {}, } - child = spawn( - process.execPath, - ['--import', tsxLoader, opts.agent.binScript, opts.configPath ?? opts.agent.configPath], - { cwd, env, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - - child.stderr.setEncoding('utf8') - child.stderr.on('data', (c: string) => stderrChunks.push(c)) - - // Tee raw stdout: accumulate the bytes for the golden + purity check, and ALSO - // feed the same bytes to the SDK client through a passthrough. Buffer the raw - // bytes (not per-chunk utf8 strings) and decode once at the end, so a - // multibyte sequence split across two 'data' events can't corrupt the golden. - const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buf: Buffer) => { - rawBuffers.push(buf) - passthrough.push(buf) - }) - child.stdout.on('end', () => passthrough.push(null)) - - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(passthrough) as ReadableStream, - ) - // Watcher so a step can block until the client OBSERVES a particular - // session/update — used by promptAndCancel to pin frame order (send cancel - // only after the streamed agent_message_chunk has arrived, so those frames - // deterministically precede the cancelled prompt response). - const updateWaiters: { match: (u: SessionNotification['update']) => boolean; resolve: () => void }[] = [] - const waitForUpdate = (match: (u: SessionNotification['update']) => boolean): Promise => - new Promise(resolve => updateWaiters.push({ match, resolve })) - // Permission answers are consumed FIFO across the whole run; exhaustion // falls back to `cancelled` so approval-free scenarios keep the plain stub. const permissionQueue = [...input.permissionAnswers ?? []] @@ -263,22 +191,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // callback answers `cancelled` (a well-defined path for the agent), // captures the error here, and the step loop fails the run on it. let scriptError: Error | undefined - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - for (let i = updateWaiters.length - 1; i >= 0; i--) { - const waiter = updateWaiters[i] - // The index is always in-bounds (i only decreases; splice removes at - // i, so lower entries stay valid); the guard satisfies - // noUncheckedIndexedAccess. - /* v8 ignore next 1 -- unreachable in-bounds guard, see above */ - if (waiter === undefined) continue - if (waiter.match(params.update)) { - updateWaiters.splice(i, 1) - waiter.resolve() - } - } - return Promise.resolve() - }, + launched = launchAcpTestAgent({ + agent: opts.agent, + cwd, + ...opts.configPath !== undefined ? { configPath: opts.configPath } : {}, + env, requestPermission(params: RequestPermissionRequest): Promise { const answer = permissionQueue.shift() if (answer === undefined) return Promise.resolve({ outcome: { outcome: 'cancelled' } }) @@ -296,10 +213,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) + const active = launched + const { client } = active for (const step of input.steps) { - await runStep(client, step, cwd, waitForUpdate, () => sessionId, (id) => { sessionId = id }) + await runStep(client, step, cwd, match => active.waitForUpdate(match), () => sessionId, (id) => { sessionId = id }) // A permission exchange happens while a step's request is in flight, so // by the time the step settles any script bug it exposed is captured — // fail the run HERE, as a harness error, rather than hoping the agent's @@ -308,26 +226,22 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise } // Done driving: close stdin so the server disposes gracefully (flushing // persistence) and exits. Then await exit so the harvested log is complete. - child.stdin.end() - await waitForExit(child) + await active.close() // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) } finally { // Failure-safe teardown: kill a still-running child and drop the temp dirs // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `child` is undefined only if spawn itself threw. - if (child !== undefined && child.exitCode === null && child.signalCode === null) { - child.kill('SIGKILL') - await waitForExit(child) - } + // process or dir. `launched` is undefined only if launch itself threw. + await launched?.close('SIGKILL') await rm(cwd, { recursive: true, force: true }) await rm(sessionsRoot, { recursive: true, force: true }) } return { - rawStdout: Buffer.concat(rawBuffers).toString('utf8'), - stderr: stderrChunks.join(''), + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), cwd, ...sessionId !== undefined ? { sessionId } : {}, sessionLogs, @@ -339,7 +253,7 @@ async function runStep( client: ClientSideConnection, step: InputStep, cwd: string, - waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, + waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, getSessionId: () => string | undefined, setSessionId: (id: string) => void, ): Promise { @@ -433,16 +347,6 @@ async function runStep( } } -/** Resolve once the child process exits (any code/signal). */ -function waitForExit(child: ChildProcessWithoutNullStreams): Promise { - // Race guard: both call sites run within one synchronous frame of - // stdin.end()/kill(), so the exit event cannot have been delivered yet; - // kept for any future caller that awaits in between. - /* v8 ignore next 1 -- unreachable race guard, see above */ - if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() - return new Promise(resolve => child.once('exit', () => { resolve() })) -} - /** * Harvest EVERY persisted `.jsonl` session log under a sessions root, parse each * header line, and return them ordered primary-first: the top-level session (no diff --git a/packages/support/acp-snapshot/src/index.ts b/packages/support/acp-snapshot/src/index.ts index 74bee95385..402bd3aa3d 100644 --- a/packages/support/acp-snapshot/src/index.ts +++ b/packages/support/acp-snapshot/src/index.ts @@ -1,13 +1,14 @@ /** * ACP snapshot suite kit — the shared machinery behind the keyless snapshot - * tier (`pnpm run test:snapshot`). Three layers, composable per example: - * the subprocess scenario harness ({@link runScenario}), the pure golden - * normalizers ({@link normalizeStdout} / {@link normalizeSessionLog} / - * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite factory - * ({@link defineAcpSnapshotSuite}) that registers a scenario table as a full - * describe/it tree. An example's `*.snapshot.ts` supplies only its - * {@link AgentUnderTest} paths, its snapshots directory, and its - * {@link Scenario} table. + * tier (`pnpm run test:snapshot`). Four layers, composable per example: the + * shared subprocess/client launcher ({@link launchAcpTestAgent}), the scripted + * scenario harness ({@link runScenario}), the pure golden normalizers + * ({@link normalizeStdout} / {@link normalizeSessionLog} / + * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite + * factory ({@link defineAcpSnapshotSuite}) that registers a scenario table as a + * full describe/it tree. Ordinary ACP e2e tests can use the launcher directly; + * an example's `*.snapshot.ts` supplies only its {@link AgentUnderTest} paths, + * snapshots directory, and {@link Scenario} table. * * NOTE: ./suite.ts imports vitest, so this package is importable only inside a * vitest run — a support-tier constraint stated in the README. @@ -17,7 +18,6 @@ export { runScenario, - type AgentUnderTest, type HarvestedLog, type InputScript, type InputStep, @@ -25,6 +25,12 @@ export { type RunOptions, type RunResult, } from './harness.ts' +export { + launchAcpTestAgent, + type AcpTestLaunchOptions, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from './launcher.ts' export { normalizeSessionLog, normalizeStdout, diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts new file mode 100644 index 0000000000..635a02ca35 --- /dev/null +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -0,0 +1,152 @@ +/** + * Shared launcher for ACP tests that drive an unbuilt agent subprocess over + * JSON-RPC stdio. It owns the tsx loader, workspace-resolution environment, + * stdout tee, SDK client, update collection, permission fallback, and process + * shutdown so e2e and snapshot suites do not each reconstruct that boundary. + * + * @module @deepseek-ai/dsh-acp-snapshot/launcher + */ + +import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { Readable, Writable } from 'node:stream' +import { + ClientSideConnection, + ndJsonStream, + type Agent as AcpAgent, + type Client, + type RequestPermissionRequest, + type RequestPermissionResponse, + type SessionNotification, +} from '@agentclientprotocol/sdk' + +// The child runs from a temp directory outside the repo, where a bare +// `--import tsx` cannot resolve. Resolve this package's loader once instead. +const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) + +/** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ +export interface AgentUnderTest { + /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + binScript: string + /** The leaf `cordis.yml` loaded by the bin. */ + configPath: string + /** The repo tsconfig whose paths resolve unbuilt workspace imports. */ + tsconfigPath: string +} + +/** Options for one ACP test subprocess. */ +export interface AcpTestLaunchOptions { + /** The agent composition to boot. */ + agent: AgentUnderTest + /** Process cwd and default session-home root. */ + cwd: string + /** Alternate leaf config for this launch. */ + configPath?: string + /** Extra environment values layered over the parent environment. */ + env?: NodeJS.ProcessEnv + /** Permission handler; omitted requests fail closed as `cancelled`. */ + requestPermission?: (params: RequestPermissionRequest) => Promise +} + +/** A running ACP test process and its captured client-side surfaces. */ +export interface LaunchedAcpTestAgent { + /** The child process, exposed for process-level assertions. */ + child: ChildProcessWithoutNullStreams + /** The SDK connection backed by the child's stdio. */ + client: ClientSideConnection + /** Session updates in receive order. */ + updates: SessionNotification['update'][] + /** Decode all stdout bytes captured so far. */ + rawStdout(): string + /** Decode all stderr chunks captured so far. */ + stderr(): string + /** Resolve when a future session update matches the predicate. */ + waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise + /** Gracefully close stdin, or send a signal, and wait for process exit. */ + close(signal?: NodeJS.Signals): Promise +} + +/** + * Boot an ACP agent subprocess and connect an SDK client to its stdio. + * + * @param options Agent paths, cwd, environment, and optional permission handler. + * @returns The running process, connected client, captures, and shutdown handle. + */ +export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTestAgent { + const { agent, cwd } = options + const child = spawn( + process.execPath, + ['--import', tsxLoader, agent.binScript, options.configPath ?? agent.configPath], + { + cwd, + env: { + ...process.env, + ...options.env, + TSX_TSCONFIG_PATH: agent.tsconfigPath, + DSH_HOME: join(cwd, '.dsh'), + DSH_AGENTS_HOME: join(cwd, '.agents'), + }, + stdio: ['pipe', 'pipe', 'pipe'], + }, + ) + + const stderrChunks: string[] = [] + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => stderrChunks.push(chunk)) + + const rawBuffers: Buffer[] = [] + const passthrough = new Readable({ read() {} }) + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => passthrough.push(null)) + + const updates: SessionNotification['update'][] = [] + const updateWaiters: { + match: (update: SessionNotification['update']) => boolean + resolve: (update: SessionNotification['update']) => void + }[] = [] + const stream = ndJsonStream( + Writable.toWeb(child.stdin) as WritableStream, + Readable.toWeb(passthrough) as ReadableStream, + ) + const makeClient = (_agent: AcpAgent): Client => ({ + sessionUpdate(params: SessionNotification): Promise { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + if (!waiter.match(params.update)) continue + updateWaiters.splice(index, 1) + waiter.resolve(params.update) + } + return Promise.resolve() + }, + requestPermission: options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + }) + const client = new ClientSideConnection(makeClient, stream) + + return { + child, + client, + updates, + rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), + stderr: () => stderrChunks.join(''), + waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + async close(signal?: NodeJS.Signals): Promise { + if (child.exitCode !== null || child.signalCode !== null) return + if (signal === undefined) child.stdin.end() + else child.kill(signal) + await waitForExit(child) + }, + } +} + +/** Resolve once a running child exits. */ +function waitForExit(child: ChildProcessWithoutNullStreams): Promise { + return new Promise(resolve => child.once('exit', () => { resolve() })) +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index b0817a8d04..ec1ed5cf6f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,7 +3,9 @@ import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' +import { launchAcpTestAgent } from '../src/launcher.ts' /** * Unit tests for the subprocess harness, driven through the REAL spawn path @@ -38,6 +40,37 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) + const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) + tempDirs.push(sessionsRoot) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + configPath: AGENT.configPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: fixtureFile, + DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') + expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) + expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') + expect(launched.stderr()).toContain('launcher stderr') + await launched.close() + await launched.close('SIGKILL') + + // The minimal shape needs no environment or config override. + const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await minimal.close() + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From b579a13db759c38c41541a021bbbac188f4bf8a8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:28:20 +0800 Subject: [PATCH 003/140] test: trim PostToolUse snapshot retries --- .../2026-07-04-hook-snapshot-matrix.md | 4 +- examples/acp-agent/tests/acp.snapshot.ts | 3 - .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 694 +----------------- .../stdout.golden.jsonl | 434 +---------- .../hook-codex-posttool-block/input.json | 2 +- .../hook-codex-posttool-block/session.jsonl | 2 +- 7 files changed, 16 insertions(+), 1125 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 47db2cd793..1b3e70eb13 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,6 +29,8 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook- Date: Tue, 14 Jul 2026 00:46:46 +0800 Subject: [PATCH 004/140] fix: let snapshot recording create fixture inventory --- packages/support/acp-snapshot/src/suite.ts | 38 ++++++++++++++----- .../support/acp-snapshot/tests/suite.spec.ts | 17 ++++++++- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 6311a15031..4d87093c8a 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -31,7 +31,7 @@ * @module @deepseek-ai/dsh-acp-snapshot/suite */ -import { readFile, readdir, writeFile } from 'node:fs/promises' +import { readFile, readdir, rm, writeFile } from 'node:fs/promises' import { existsSync } from 'node:fs' import { join } from 'node:path' import { describe, expect, it } from 'vitest' @@ -410,9 +410,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const fixtureFiles = await sessionFixtures(dir) + // Replay/refresh need the committed inventory up front because those + // files drive the model scripts. Record mode creates that inventory + // from the harvested live logs, so it must also work for a brand-new + // scenario with no session.jsonl yet. + let fixtureFiles = RECORDING ? [] : await sessionFixtures(dir) const childFixtureFiles = fixtureFiles.slice(1) - const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -421,7 +424,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, + ...!RECORDING && childFixtureFiles.length > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -460,18 +463,35 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { || (REFRESHING && comparesLog) if (writesSessionFixtures) { expect(result.sessionLogs.length, `${mode} produced no session log to harvest`).toBeGreaterThan(0) - expect(result.sessionLogs.length, `expected ${childSessions + 1} session logs (parent + children)`) - .toBe(childSessions + 1) + if (REFRESHING) { + expect(result.sessionLogs.length, `expected ${fixtureFiles.length} session logs (parent + children)`) + .toBe(fixtureFiles.length) + } + const outputFixtureFiles = [ + 'session.jsonl', + ...Array.from({ length: result.sessionLogs.length - 1 }, (_, i) => `session.${i + 1}.jsonl`), + ] const primary = (result.sessionLogs[0] as HarvestedLog).content - await writeFile(join(dir, 'session.jsonl'), scrub( + await writeFile(join(dir, outputFixtureFiles[0] as string), scrub( REFRESHING ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements) : primary, )) for (let i = 1; i < result.sessionLogs.length; i++) { const child = (result.sessionLogs[i] as HarvestedLog).content - await writeFile(join(dir, `session.${i}.jsonl`), scrub( + await writeFile(join(dir, outputFixtureFiles[i] as string), scrub( REFRESHING ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements) : child, )) } + if (RECORDING) { + const outputNames = new Set(outputFixtureFiles) + const entries = await readdir(dir, { withFileTypes: true }) + await Promise.all(entries + .filter(entry => entry.isFile() + && entry.name.startsWith('session.') + && entry.name.endsWith('.jsonl') + && !outputNames.has(entry.name)) + .map(entry => rm(join(dir, entry.name)))) + fixtureFiles = outputFixtureFiles + } if (scenario.pinsHeader === true) { const primary = result.sessionLogs[0] as HarvestedLog const prompts = normalizedSystemPrompts(primary.content, ctx) @@ -498,7 +518,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // prompt becomes the fixture's `{{system}}`; non-pinning scenarios // additionally tokenize tools/prefix. The dedicated header guard below // compares those omitted values against their class's pin artifacts. - expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1) + expect(result.sessionLogs.length, 'this scenario must persist one log per session fixture').toBe(fixtureFiles.length) for (let i = 0; i < fixtureFiles.length; i++) { const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content) const fixture = scrub(await readFile(join(dir, fixtureFiles[i] as string), 'utf8')) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index f27f36c564..7aa218526c 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -1,4 +1,4 @@ -import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs' +import { cpSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' @@ -69,7 +69,13 @@ const RECORD_SCENARIOS: Scenario[] = [ // committed record fixtures/goldens in place. const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1' const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-')) -if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true }) +if (!BOOTSTRAP) { + cpSync(RECORD_SRC, recordDir, { recursive: true }) + // Record mode owns its output inventory: a new scenario has no primary yet, + // while a changed child count can leave old numbered fixtures behind. + rmSync(join(recordDir, 'rec-pin', 'session.jsonl')) + writeFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'stale child\n') +} const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-')) cpSync(REPLAY_DIR, refreshDir, { recursive: true }) staleRefreshFixtures(refreshDir) @@ -141,6 +147,13 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => { }) }) +describe('defineAcpSnapshotSuite: record inventory write-back', () => { + it('creates a missing primary fixture and prunes stale child fixtures', () => { + expect(readFileSync(join(recordDir, 'rec-pin', 'session.jsonl'), 'utf8')).toContain('"type":"session"') + expect(() => readFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'utf8')).toThrow() + }) +}) + describe('defineAcpSnapshotSuite: registration contract', () => { it("throws when a scenario's header class has no pinning scenario", () => { expect(() => { From f95a411b0ac7d5f347c602308df1123dc1aecd5f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:09:07 +0800 Subject: [PATCH 005/140] fix: record self-limiting hook snapshot --- .../2026-07-04-hook-snapshot-matrix.md | 2 +- .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 253 ++++++++++++------ .../stdout.golden.jsonl | 83 +++++- .../workspace/hooks.json | 2 +- .../workspace/posttool-once.sh | 7 + 6 files changed, 259 insertions(+), 90 deletions(-) create mode 100644 examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 1b3e70eb13..0327662d3d 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,7 +29,7 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook-&2; exit 2" } + { "type": "command", "command": "sh posttool-once.sh" } ] } ] diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh new file mode 100644 index 0000000000..2acc98bb58 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh @@ -0,0 +1,7 @@ +#!/bin/sh +if test -e .posttool-blocked; then + exit 0 +fi +: > .posttool-blocked +printf '%s\n' 'tool output rejected by policy: retry once' >&2 +exit 2 From d7de8a8d138b70d79e7066195ac11a512cbf4249 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:24:20 +0800 Subject: [PATCH 006/140] refactor: narrow compaction surface --- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/compaction.md | 14 +- .../2026-06-18-compaction-capability-seam.md | 4 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/index.ts | 24 ++- .../compact-basic/tests/compact-basic.spec.ts | 147 +++++++----------- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/index.ts | 11 +- packages/compact/compact/src/types.ts | 8 - .../compact/compact/tests/compact.spec.ts | 23 ++- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- 11 files changed, 95 insertions(+), 148 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index ecb68913df..bfb31749d5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -113,12 +113,12 @@ Implementations MUST honor: ```ts cordis-catalog abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise -abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` Types: [Message](../core-data-structures/core.md) -Source: [`packages/compact/compact/src/index.ts:65`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:66`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 2f402be57d..de350df9f3 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -1,6 +1,6 @@ # Compaction -The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). +The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) @@ -20,18 +20,10 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the seqs of the three appended `compact/*` events, the summary blocks, and the shadowed range/seqs plus the estimated token count. +What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. ```ts type-equiv interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A @@ -50,6 +42,6 @@ interface CompactionResult { ## The service -`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(session, start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. +`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` from `agent.session` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. Auto-compaction runs on the serial `agent/pre-step` loop seam (fired once per step, after `turn/start` and BEFORE the step opens and its request history is derived), not the `agent/request` waterfall: compaction mutates the session surface in place — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives the request from the already-compacted surface. Retention is turn-agnostic — the only structural guard is tool-pairing balance (a compacted region's edges are balanced cuts on the surface, so it never splits a step's tool-calls from their results), so a single runaway turn that alone exceeds the window compacts its own early closed steps rather than being retained verbatim. The backend that ships this (`dsh-compact-basic`) documents the retention walk, summary shrink validation, bounded re-compaction, and the crash/recoverable failure taxonomy. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index e0835dcaa6..b99bdfc3b3 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -22,7 +22,7 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation -The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs are defined *over* a `Session` (`compactRegion(session, start, end)`) and its output *is* the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). +The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and the durable `compact/summary` event carries `ContentBlock[]`. There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. @@ -30,7 +30,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface, with only `estimateContentTokens()` and `summarize()` abstract. That recouples the contract to one strategy: a backend that wants a different retention policy or a different event-sequencing would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend, where it belongs, and keeps the interface a pure statement of *what*. The backend remains internally factored — `estimateContentTokens()` and `summarize()` are `protected` hooks a sub-backend can override without reimplementing the walk — but that factoring is the backend's private concern, not the contract's. -`compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` takes **required** parameters (not the original all-optional shape). The auto-compaction seam (below) always supplies the agent, lifecycle context, assembled system prompt (counted toward the estimate), and the turn's abort signal, so optionality would only invite a hidden default at the seam. The session being compacted comes from the agent context. `compactRegion(session, start, end, agent, turn, step, signal?)` keeps an optional signal (a manual caller may omit it). Passing lifecycle context rather than a concrete model keeps router agents honest: the backend's summarization request can run through `agent/request`, where model-routing plugins already choose the actual model. +`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required inputs from the auto-compaction seam: the agent, assembled system prompt, composed request prefix, and turn abort signal. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The backend's summarization request is a direct `ctx.llm.stream()` call; the configured summarization model falls back to the agent's model, and adapters can still route through the LLM seam. ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index a06e74b818..c956b1e9de 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -17,7 +17,7 @@ The abstract contract states only WHAT compaction does; this backend owns every - **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface. - **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +The protected `estimateContentTokens()` and `summarize()` methods are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the private retention/pressure accounting and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. ## Config (`BasicCompactConfig`) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 0b0300472c..27e81cd3d9 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -41,12 +41,11 @@ import type { BasicCompactConfig, ResolvedConfig } from './types.ts' import { resolveConfig } from './types.ts' export type { BasicCompactConfig, ResolvedConfig } from './types.ts' -export { resolveConfig } from './types.ts' /** Per-block structural overhead for JSON framing / type tag. */ const BLOCK_OVERHEAD = 4 -/** Role-field framing overhead added per message in {@link BasicCompactService.estimateTokens}. */ +/** Role-field framing overhead added per message in the request estimator. */ const ROLE_OVERHEAD = 4 /** Tags wrapping the structured summary inside the landed checkpoint node. */ @@ -222,7 +221,7 @@ export class BasicCompactService extends CompactService { * their JSON-stringified length. * @returns the estimated token count. */ - estimateContentTokens(blocks: readonly ContentBlock[]): number { + protected estimateContentTokens(blocks: readonly ContentBlock[]): number { const { charsPerToken } = this.config let tokens = 0 for (const block of blocks) { @@ -257,7 +256,8 @@ export class BasicCompactService extends CompactService { * @returns the estimated token count of the event's content, or 0 for a * non-message event. */ - estimateEventTokens(event: SessionEvent): number { + private estimateEventTokens(event: SessionEvent): number { + /* v8 ignore next -- callers traverse surface nodes, whose event types are the five cases below */ switch (event.type) { case 'user/message': case 'assistant/message': @@ -278,7 +278,7 @@ export class BasicCompactService extends CompactService { * @param systemPrompt - counted at chars / `charsPerToken` when provided. * @returns the estimated token footprint of the whole request. */ - estimateTokens(messages: readonly Message[], systemPrompt?: string): number { + private estimateTokens(messages: readonly Message[], systemPrompt?: string): number { let total = 0 for (const msg of messages) { total += this.estimateContentTokens(msg.content) @@ -318,7 +318,7 @@ export class BasicCompactService extends CompactService { * @returns the text-only summary blocks plus the call envelope used * (`model`, and `maxTokens` when the summarizer has a cap). */ - async summarize( + protected async summarize( text: string, agent: Agent, signal?: AbortSignal, ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { const assembler = new BlockAssembler() @@ -417,7 +417,7 @@ export class BasicCompactService extends CompactService { break } - result = await this.compactRegion(session, range.start, range.end, agent, signal) + result = await this.compactRegion(range.start, range.end, agent, signal) } const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix) @@ -439,17 +439,17 @@ export class BasicCompactService extends CompactService { * @param sessionPrefix - the instance's composed session prefix (counts toward pressure). * @returns the estimated token total the next request will carry. */ - estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { + private estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { return this.estimateTokens([...sessionPrefix, ...session.deriveMessages()], fullSystemPrompt) } override async compactRegion( - session: Session, start: number, end: number, agent: Agent, signal?: AbortSignal, ): Promise { + const session = agent.session // Resolve the range by surface POSITION, not numeric seq interval. A prior // replace lands a fresh high-seq summary node AT the shadowed range's // position, so the surface order (head→tail) no longer tracks seq order — @@ -556,13 +556,9 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - const endEvent = session.append('compact/end', { turn: openTurn }) + session.append('compact/end', { turn: openTurn }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 1a30cc9fc9..46bcb9911c 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -5,7 +5,7 @@ import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter, LlmService } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' +import type { SurfaceEvent } from '@deepseek-ai/dsh-session' import * as Invariants from '@deepseek-ai/dsh-invariants' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -68,6 +68,20 @@ class TestCompactService extends BasicCompactService { } } +/** Expose the backend's protected extension hooks for their focused contract tests. */ +class InspectableCompactService extends BasicCompactService { + estimateContent(blocks: readonly ContentBlock[]): number { + return this.estimateContentTokens(blocks) + } + + summarizeForTest( + text: string, + agent: Agent, + ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + return this.summarize(text, agent) + } +} + function isFramedCheckpoint(blocks: readonly ContentBlock[]): boolean { const first = blocks[0] const last = blocks[blocks.length - 1] @@ -333,51 +347,6 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai }) }) -describe('BasicCompactService.estimateEventTokens', () => { - it('returns 0 for non-message events (boundary, chunk, step/end, tool/call)', () => { - const svc = createTestService() - expect(svc.estimateEventTokens({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'tool/call', seq: 4, time: 5, data: { turn: 1, step: 1, callId: CallId('c1'), name: 'read', arguments: '{}' } })).toBe(0) - }) - - it('returns estimate for message-producing events', () => { - const svc = createTestService() - const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } - expect(svc.estimateEventTokens(userEvent)).toBe(10) - - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } - expect(svc.estimateEventTokens(asstEvent)).toBe(20) - - const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } - expect(svc.estimateEventTokens(toolEvent)).toBe(10) - }) -}) - -describe('BasicCompactService.estimateTokens', () => { - it('sums token estimates across messages', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hello' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'hi' }, { type: 'text', text: 'there' }] }, - ] - // 1 block * 10 + 4 (role) + 2 blocks * 10 + 4 (role) = 10 + 4 + 20 + 4 = 38 - expect(svc.estimateTokens(messages)).toBe(38) - }) - - it('includes system prompt in the estimate', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hi' }] }, - ] - const systemPrompt = 'You are a helpful assistant.' - // 1 block * 10 + 4 (role) + ceil(28/4) = 10 + 4 + 7 = 21 - expect(svc.estimateTokens(messages, systemPrompt)).toBe(21) - }) -}) - describe('BasicCompactService.compactRegion', () => { it('shadows surface nodes and inserts a summary via user/message', async () => { const svc = createTestService() @@ -393,7 +362,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) - expect(result.summary).toEqual(svc.mockSummary) + expect(result.shadowedTokenCount).toBe(20) const events = session.events const startEvent = events.findLast(e => e.type === 'compact/start') @@ -405,6 +374,7 @@ describe('BasicCompactService.compactRegion', () => { // The provenance record carries the summarize call's envelope, so "which // model wrote this summary" is answerable from the log alone. expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.model).toBe('test-model') + expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.summary).toEqual(svc.mockSummary) // compact/* events are log-only — no surfaceOp (type system enforces this). const startRaw = startEvent as unknown as { surfaceOp?: unknown } @@ -509,10 +479,9 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(3, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') // Provenance (compact/summary) carries the RAW, unframed summary. - expect(result.summary).toEqual([{ type: 'text', text: 'STRUCTURED SUMMARY' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data).toMatchObject({ summary: [{ type: 'text', text: 'STRUCTURED SUMMARY' }] }) @@ -590,7 +559,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(1) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(70) }) it('walks tail→head and retains nodes within token budget', async () => { @@ -716,7 +684,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(svc.summarizeCalls).toHaveLength(2) expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(2) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(50) }) it('throws after the configured re-compaction attempts still leave the surface above threshold', async () => { @@ -801,53 +768,51 @@ describe('BasicCompactService blocking (compaction in progress)', () => { describe('BasicCompactService token estimation (char/4 heuristic)', () => { it('estimates text blocks with char/4 + overhead', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'this is a somewhat longer text block' = 36 → ceil(36/4)+4 = 13; 'short' = 5 → 2+4 = 6 const blocks: ContentBlock[] = [ { type: 'text', text: 'this is a somewhat longer text block' }, { type: 'text', text: 'short' }, ] - expect(svc.estimateContentTokens(blocks)).toBe(19) + expect(svc.estimateContent(blocks)).toBe(19) }) it('estimates reasoning blocks same as text', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'thinking about this...' = 22 → ceil(22/4)+4 = 10 - expect(svc.estimateContentTokens([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) + expect(svc.estimateContent([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) }) it('estimates tool-call blocks from name + arguments', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'bash' = 4 → 1; '{"command":"ls"}' = 16 → 4; + 4 overhead = 9 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }, ])).toBe(9) }) it('estimates tool-result blocks recursively', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // inner text 5 → 2+4 = 6; outer 6 + 4 overhead = 10 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'hello' }], isError: false }, ])).toBe(10) }) it('returns 0 for empty content blocks', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - expect(svc.estimateContentTokens([])).toBe(0) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) + expect(svc.estimateContent([])).toBe(0) }) it('honors a configured charsPerToken (fractional densities included)', () => { // 'this is a somewhat longer text block' = 36 chars. const blocks: ContentBlock[] = [{ type: 'text', text: 'this is a somewhat longer text block' }] // charsPerToken 2: ceil(36/2)+4 = 22 — a CJK-density config doubles the estimate. - const dense = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) - expect(dense.estimateContentTokens(blocks)).toBe(22) + const dense = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) + expect(dense.estimateContent(blocks)).toBe(22) // Fractional density is legal: ceil(36/1.5)+4 = 28. - const fractional = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) - expect(fractional.estimateContentTokens(blocks)).toBe(28) - // The system-prompt term scales with the same knob: 36-char prompt at density 2 → ceil(36/2) = 18. - expect(dense.estimateTokens([], 'this is a somewhat longer text block')).toBe(18) + const fractional = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) + expect(fractional.estimateContent(blocks)).toBe(28) }) }) @@ -1013,17 +978,17 @@ function compactRegion( model: string, signal?: AbortSignal, ) { - return svc.compactRegion(session, start, end, stubAgent(session, model), signal) + return svc.compactRegion(start, end, stubAgent(session, model), signal) } -function summarize(svc: BasicCompactService, text: string, model: string) { - return svc.summarize(text, stubAgent(new Session(SessionId('summary')), model)) +function summarize(svc: InspectableCompactService, text: string, model: string) { + return svc.summarizeForTest(text, stubAgent(new Session(SessionId('summary')), model)) } describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('summarizes via the registered adapter and returns its content', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) const { summary, model, maxTokens } = await summarize(svc, 'User: hi\n\nAssistant: hello', 'test-model') expect(summary).toEqual([{ type: 'text', text: 'SUMMARY TEXT' }]) @@ -1041,7 +1006,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('uses maxTokens as the summarization provider cap', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 50, })) @@ -1059,7 +1024,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { // synthesized user/message summary as an orphaned call. { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }, ]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const { summary } = await summarize(svc, 'User: hi', 'test-model') @@ -1068,26 +1033,26 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('throws when no text block remains after filtering', async () => { const { ctx } = await ctxWithBlocks([{ type: 'reasoning', text: 'private only' }]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'User: hi', 'test-model')).rejects.toThrow(/no text summary content/) }) it('throws when no model is provided', async () => { const { ctx } = await ctxWithModel('x') - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) }) it('rethrows when the stream ends with a finish-error chunk', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'provider 401', code: 'UNAUTHORIZED' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'provider 401', code: 'UNAUTHORIZED' }) }) it('rethrows a finish-error chunk without a code (code stays undefined)', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'opaque failure' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const error = await summarize(svc, 'text', 'test-model').then(() => null, (e: unknown) => e as Error & { code?: string }) expect(error?.message).toBe('opaque failure') expect(error?.code).toBeUndefined() @@ -1095,13 +1060,13 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('rethrows when the stream ends with a finish-aborted chunk', async () => { const ctx = await ctxWithFinish({ kind: 'aborted' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'summarization stream aborted', code: 'ABORTED' }) }) it('fails closed on a max-tokens finish (an incomplete checkpoint must not commit)', async () => { const ctx = await ctxWithFinish({ kind: 'max-tokens' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ code: 'MAX_TOKENS' }) }) @@ -1129,8 +1094,9 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'CONDENSED' }) }) @@ -1392,10 +1358,10 @@ describe('BasicCompactService edge cases', () => { }) it('estimates unknown block types via JSON length (default branch)', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // A block whose type is none of the known kinds — exercises the default arm. const unknown = { type: 'custom-widget', payload: 'some data' } as unknown as ContentBlock - expect(svc.estimateContentTokens([unknown])).toBeGreaterThan(0) + expect(svc.estimateContent([unknown])).toBeGreaterThan(0) }) it('auto-compaction reports bounded retry exhaustion after committing a smaller summary', async () => { @@ -1604,14 +1570,15 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a // First compaction: shadow the two oldest surface nodes. const nodes0 = session.surface.nodes - const first = await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + const firstSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // The summary node now sits at the head with a seq HIGHER than the // retained older nodes that follow it — the non-monotonic surface. (The // head is the user/message replace node, appended after the compact/summary - // provenance event, so its seq is at least first.summarySeq.) + // provenance event. const nodes1 = session.surface.nodes - expect(nodes1[0]!).toBeGreaterThanOrEqual(first.summarySeq) + expect(nodes1[0]!).toBeGreaterThan(firstSummarySeq) expect(nodes1[0]!).toBeGreaterThan(nodes1[1]!) // Second compaction: shadow [summary(head) … turn-2's step end]. The start @@ -1623,13 +1590,14 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a const endSeq = nodes1[2]! expect(startSeq).toBeGreaterThan(endSeq) const second = await compactRegion(svc, session, startSeq, endSeq, 'm') + const secondSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // Exactly the three nodes at surface positions [0..2] are shadowed, in // surface order — the positional slice, regardless of their seq values. expect(second.shadowedSeqs).toEqual([nodes1[0]!, nodes1[1]!, nodes1[2]!]) // The surface still derives cleanly: a new head replace node + the rest. const finalNodes = session.surface.nodes - expect(finalNodes[0]!).toBeGreaterThanOrEqual(second.summarySeq) + expect(finalNodes[0]!).toBeGreaterThan(secondSummarySeq) expect(session.deriveMessages().length).toBe(finalNodes.length) }) @@ -1679,8 +1647,9 @@ describe('BasicCompactService llm inject (real plugin-load path)', () => { const svc = ctx.compact as BasicCompactService const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // Tear the fiber down so this test owns no leaked registration; the // dedicated cleanup assertion lives in the "HMR safety" suite. diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index e98f00899f..fafcad76b8 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -19,7 +19,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | Member | Semantics | |---|---| | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | -| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +| `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7d1138314c..1eb73c60db 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -14,7 +14,8 @@ * implementation (deferred) / consumer (a `/compact` tool, deferred) — modeled * on the bash trio. Unlike `dsh-bash`, this interface necessarily * depends on `dsh-session` and `dsh-llm`: the contract's verbs are defined over - * a `Session` and its output is the `ContentBlock` vocabulary. That deviation + * an agent-owned `Session` and the durable summary event uses the + * `ContentBlock` vocabulary. That deviation * from the "interface depends only on cordis" guidance is intentional and * recorded in the [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). * @@ -132,10 +133,10 @@ export abstract class CompactService extends Service { * open (unclosed) tail step is invalid — its tool-calls have no results yet. * `dsh-session` exports `isToolPairingBalanced` for this check. * - * @param session - the session whose surface is mutated. * @param start - inclusive seq of the first surface node to compact. * @param end - inclusive seq of the last surface node to compact. - * @param agent - agent context used by router-aware summarizers. + * @param agent - agent context whose session is mutated and whose routing + * options are used by summarizers. * @param signal - optional cancellation signal. A backend that summarizes via * `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal` * so an abort/dispose tears down the in-flight summarization rather than @@ -146,10 +147,10 @@ export abstract class CompactService extends Service { * prior replace can leave the surface non-monotonic in seq order), or if * either boundary is not a balanced tool-pairing cut (would split a step's * tool-call/result pair). - * @returns what the compaction did (the replaced range and its summary node). + * @returns the replaced range and its token accounting. The durable + * `compact/summary` event owns the summary and bookkeeping-event identity. */ abstract compactRegion( - session: Session, start: number, end: number, agent: CompactAgentContext, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index ba9834910f..78e94173a3 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -49,14 +49,6 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..e34c8420d9 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -27,28 +27,24 @@ class StubCompactService extends CompactService { } override async compactRegion( - session: Session, start: number, end: number, - _agent: CompactAgentContext, + agent: CompactAgentContext, signal?: AbortSignal, ): Promise { this.lastSignal = signal + const session = agent.session // Minimal stub honoring the lock + log-only event contract. - const startEvent = session.append('compact/start', { turn: 0 }) - const summaryEvent = session.append('compact/summary', { + session.append('compact/start', { turn: 0 }) + session.append('compact/summary', { summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - const endEvent = session.append('compact/end', { turn: 0 }) + session.append('compact/end', { turn: 0 }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -88,7 +84,7 @@ describe('CompactService seam', () => { const svc = new StubCompactService(ctx) const session = new Session(SessionId('s')) - const result = await svc.compactRegion(session, 0, 0, stubAgent(session, 'm')) + const result = await svc.compactRegion(0, 0, stubAgent(session, 'm')) const startEvent = session.events.find(e => e.type === 'compact/start') expect(startEvent).toBeDefined() @@ -96,8 +92,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() - expect(result.summarySeq).toBeGreaterThan(result.startSeq) - expect(result.endSeq).toBeGreaterThan(result.summarySeq) + expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) + expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) + .toEqual(['compact/start', 'compact/summary', 'compact/end']) }) it('threads the cancellation signal through to the backend', async () => { @@ -106,7 +103,7 @@ describe('CompactService seam', () => { const session = new Session(SessionId('s')) const controller = new AbortController() - await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal) + await svc.compactRegion(0, 0, stubAgent(session, 'm'), controller.signal) expect(svc.lastSignal).toBe(controller.signal) await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b4420e80c7..3d6ade301f 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -109,7 +109,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'Abstract compaction service.', methods: [ 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', - 'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', + 'abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', ], }, { @@ -624,7 +624,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From 7a33ee94be9f4338369f388c5efe3deb4965b50d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:29:16 +0800 Subject: [PATCH 007/140] refactor: remove agent entry mirror --- packages/core/agent/src/index.ts | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 7864f5938c..edb7f59a37 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -202,9 +202,6 @@ interface FactorySlot { */ export class AgentRegistry extends Service { private store = new Map() - // TODO(agent-entry-mirror): derive exact-object checks from store.get(agent.id) - // plus entry.agent identity; this WeakMap mirrors the authoritative id map. - private entries = new WeakMap() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -334,7 +331,7 @@ export class AgentRegistry extends Service { const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. - if (this.entries.has(agent) || this.store.has(id)) throw new Error(`agent "${id}" is already registered`) + if (this.store.has(id)) throw new Error(`agent "${id}" is already registered`) const entry: AgentEntry = { id, agent, @@ -344,7 +341,6 @@ export class AgentRegistry extends Service { detachRequested: false, } this.store.set(id, entry) - this.entries.set(agent, entry) let entered = true const detach = (): void => { if (!entered) return @@ -371,7 +367,6 @@ export class AgentRegistry extends Service { /* v8 ignore next -- enter() rejects replacement while this single-shot detach capability is live. */ if (this.store.get(entry.id) !== entry) return this.store.delete(entry.id) - this.entries.delete(entry.agent) // An insertion rolled back before announce was never externally created, // so emitting disposed would invent an impossible lifecycle edge. Marking // happens before the created emit: if a later created listener throws, @@ -403,8 +398,8 @@ export class AgentRegistry extends Service { * creation listener). */ announce(agent: Agent): void { - const entry = this.entries.get(agent) - if (entry === undefined || this.store.get(entry.id) !== entry) { + const entry = this.store.get(agent.id) + if (entry === undefined || entry.agent !== agent) { throw new Error(`agent "${agent.id}" is not live in this registry`) } if (entry.announced || entry.announcing) { From 709cc7200eb2b3ac64090c67833a25a367a1b3df Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:59:21 +0800 Subject: [PATCH 008/140] refactor: unify agent and session identity --- docs/config-catalog.md | 18 +- docs/cookbook/extension-cookbook.md | 4 +- docs/cordis-catalog/events.md | 34 +-- docs/cordis-catalog/services.md | 12 +- docs/core-data-structures/approval.md | 2 +- docs/core-data-structures/bash.md | 2 +- docs/core-data-structures/core.md | 8 +- docs/core-data-structures/subagent.md | 2 +- docs/event-producer-consumer.md | 34 +-- .../2026-06-11-content-block-vocabulary.md | 2 +- .../2026-06-14-session-persistence.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 10 +- .../2026-06-30-event-domain-semantics.md | 2 +- .../2026-07-08-agent-scope-contexts.md | 3 +- .../feature/2026-07-08-repeat-tool-guard.md | 5 +- ...-20-remove-agent-boundary-mirror-events.md | 8 +- ...claude-code-and-codex-subagent-backends.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 6 +- examples/coding-agent/tests/code-mode.e2e.ts | 7 +- .../coding-agent/tests/coding-task.e2e.ts | 4 +- examples/coding-agent/tests/compaction.e2e.ts | 4 +- examples/coding-agent/tests/full-loop.e2e.ts | 4 +- examples/coding-agent/tests/resume.e2e.ts | 3 - examples/coding-agent/tests/todo-write.e2e.ts | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 8 +- .../bash/tool-bash/tests/integration.spec.ts | 11 +- packages/bash/tool-bash/tests/tools.spec.ts | 2 +- .../tests/compact-loop-repro.spec.ts | 7 +- .../cordis/tool-cordis/src/api-catalog.ts | 16 +- .../tool-cordis/tests/integration.spec.ts | 7 +- packages/core/agent-core/README.md | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 12 +- packages/core/agent-loop/README.md | 10 +- packages/core/agent-loop/src/agent.ts | 8 +- packages/core/agent-loop/src/index.ts | 29 ++- packages/core/agent-loop/tests/agent.spec.ts | 53 +++-- packages/core/agent-loop/tests/cancel.spec.ts | 35 ++-- .../tests/config-session-id.spec.ts | 29 +-- .../agent-loop/tests/coverage-edges.spec.ts | 21 +- .../agent-loop/tests/interception.spec.ts | 62 +++--- packages/core/agent-loop/tests/loop.spec.ts | 85 ++++---- .../core/agent-loop/tests/properties.spec.ts | 11 +- .../agent-loop/tests/request-cache.e2e.ts | 7 +- .../tests/request-reconstruction.spec.ts | 22 +- packages/core/agent-loop/tests/resume.spec.ts | 85 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 83 ++++---- .../agent-loop/tests/scope-lifecycle.spec.ts | 193 ++++++++---------- .../core/agent-loop/tests/tool-order.spec.ts | 9 +- .../core/agent-loop/tests/turn-stop.spec.ts | 19 +- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 28 ++- packages/core/agent/src/types.ts | 20 +- packages/core/agent/tests/agent.spec.ts | 29 +-- packages/core/session/src/index.ts | 7 +- packages/core/tools/tests/code-mode.spec.ts | 3 +- packages/core/tools/tests/scoped.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/guard/repeat-tool-guard/README.md | 4 +- packages/guard/repeat-tool-guard/src/index.ts | 19 +- .../tests/repeat-tool-guard.spec.ts | 39 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 31 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 73 +++---- .../hooks/hooks-codex/tests/bridge.spec.ts | 17 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 73 +++---- packages/subagent/subagent-acp/src/run.ts | 4 +- .../tests/multi-subagent.spec.ts | 7 +- .../subagent-fork/tests/subagent-fork.spec.ts | 7 +- .../subagent/subagent-inprocess/src/index.ts | 7 +- .../tests/structured.spec.ts | 9 +- .../tests/subagent-inprocess.spec.ts | 7 +- .../subagent-spawn/tests/spawn.e2e.ts | 4 +- .../tests/subagent-spawn.spec.ts | 13 +- packages/subagent/subagent/src/index.ts | 7 +- packages/subagent/subagent/src/types.ts | 5 +- .../subagent/subagent/tests/service.spec.ts | 12 +- .../tool-subagent/tests/tool-subagent.spec.ts | 24 ++- packages/support/subagent-mock/src/index.ts | 4 +- .../subagent-mock/tests/subagent-mock.spec.ts | 6 +- .../todo/tool-todo/tests/integration.spec.ts | 9 +- .../todo/tool-todo/tests/tool-todo.spec.ts | 5 +- packages/ui/acp/src/index.ts | 3 - packages/ui/acp/tests/approval.spec.ts | 6 +- packages/ui/acp/tests/bridge.spec.ts | 24 +-- packages/ui/acp/tests/dispose.spec.ts | 43 ++-- packages/ui/acp/tests/edges.spec.ts | 3 +- packages/ui/acp/tests/load.spec.ts | 9 +- packages/ui/acp/tests/multi-session.spec.ts | 6 +- packages/ui/acp/tests/turns.spec.ts | 6 +- packages/ui/jsonrpc/src/server.ts | 2 - packages/ui/jsonrpc/tests/server.spec.ts | 27 +-- packages/ui/stdio-agent/README.md | 8 +- packages/ui/stdio-agent/src/index.ts | 23 +-- packages/ui/stdio-agent/src/stdio-chat.ts | 40 ++-- .../ui/stdio-agent/tests/readline.spec.ts | 2 +- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 16 +- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 60 +++--- packages/util/brand/README.md | 4 +- packages/util/brand/src/index.ts | 8 +- .../tool-workflow/tests/tool-workflow.spec.ts | 6 +- .../workflow-workerthread/src/runtime.ts | 4 +- .../tests/integration.spec.ts | 9 +- .../tests/source-worker.compat.spec.ts | 4 +- .../tests/workflow-workerthread.e2e.ts | 8 +- .../tests/workflow-workerthread.spec.ts | 20 +- packages/workflow/workflow/src/types.ts | 5 +- 105 files changed, 899 insertions(+), 948 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..94d613bc4e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -117,8 +117,8 @@ Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -127,9 +127,9 @@ export interface Config { } ``` -Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) +Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:325`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -611,7 +611,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,7 +620,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -635,7 +635,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -645,7 +645,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index e2677e463a..1db5e85828 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -36,7 +36,7 @@ A UI plugin renders from the `session/event` feed (the assistant token stream as ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -50,7 +50,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5a3398f9a8..a5e018079a 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -317,7 +317,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -327,7 +327,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:66`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:67`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -337,7 +337,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:73`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -347,7 +347,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bfb31749d5..4d162a55f5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -14,12 +14,12 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary Concrete ReactLoopAgent factory and driver service. ```ts cordis-catalog -create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:338`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -32,13 +32,13 @@ async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void enter(agent: Agent): () => void announce(agent: Agent): void -get(id: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined list(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:203`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:592`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:597`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -244,7 +244,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:124`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index c5fa1fe13b..e8820ccfeb 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -6,7 +6,7 @@ Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approv ## Identity and outcome -Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids. +Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call or agent/session ids. ```ts type-equiv type ApprovalRequestId = Branded<'ApprovalRequestId'> diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 51f7cb0696..df6c5ab16b 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -110,7 +110,7 @@ The `owner` token is the isolation key: the executor stores it but never interpr `stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only — because a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so duplicating them as tool params would be redundant. This is NOT a security boundary: the credential scrub in `dsh-bash-local` is what stops the harness's ambient secrets reaching a spawned command, and it works regardless of these fields (a model cannot read a value the scrub removed, and tool-call args are static JSON, never shell-evaluated). A guard test asserts the tool doesn't forward model `env`/`stdin` — to catch a future `...args` spread, not to defend a trust wall. `env` is merged AFTER the scrub so an explicit caller entry (a value it already holds) wins even on a credential-shaped name. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). -Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`/`AgentId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. +Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. ## Foreground runs: `BashRunResult` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 168d727c8d..c6b74ed3c0 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -73,7 +73,7 @@ Two large discriminated unions are the ones consumers `switch` over most: **`Str ## Branded IDs -IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (an `AgentId` can't be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. +IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (a `SessionId` cannot be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. The `Branded` primitive lives in its own type-only package, [dsh-brand](../../packages/util/brand) (no runtime code, no harness-package dependency), so any package can brand the ids it owns without depending on an unrelated capability package (e.g. dsh-bash brands `BashTaskId`/`OwnerToken` via dsh-brand alone, never pulling in dsh-llm). @@ -83,7 +83,7 @@ Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index type Branded = string & { readonly [BRAND]: B } ``` -The three core IDs: `CallId` (correlates a tool call with its result; dsh-llm), `SessionId` (dsh-session), `AgentId` (dsh-agent). Each is `Branded<'CallId'>` etc. plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). +The two core IDs are `CallId` (correlates a tool call with its result; dsh-llm) and `SessionId` (the shared live agent and durable session identity; dsh-session). Each is a `Branded<'…'>` plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). ## Content blocks and messages @@ -254,7 +254,7 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types ```ts type-equiv interface Agent { - readonly id: AgentId + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus @@ -353,7 +353,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `Agent.id` and `Agent.session.id` are the same branded `SessionId`. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 5454f326b3..883c33020a 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -68,7 +68,7 @@ The handle the consumer holds after a provider has established a ready child. Th ```ts type-equiv interface SubagentRun { - readonly id: AgentId + readonly id: SessionId readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index a7e2c8bb37..80389608cc 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | @@ -31,10 +31,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:100`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md index 42efb34774..fb272c5df9 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -21,4 +21,4 @@ In-session context injection (`context/message`, `steering/message`) renders as - Reasoning has a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). Block cache hints likewise have no core field: DeepSeek prompt caching is automatic, so no shipping adapter can transmit a hint; a caching feature adds a `cache` field together with the adapter that honors it — see [the producer-less-variants RFC](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md). Assistant-prefix continuation (prefill) likewise has no request field: DeepSeek's chat-prefix completion is a Beta feature on a base URL neither shipping adapter targets, so a prefill feature adds `GenerateOptions.prefill` together with the adapter that honors it — see [the inert-request-knobs RFC](../simplification/2026-07-04-drop-inert-request-knobs.md). - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. -- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost. +- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md index 03d8a30b37..824e59a172 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md @@ -23,7 +23,7 @@ Key choices recorded here because they are durable, contested, and surprising: - **Append-only; a crashed turn is closed, never truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. **A single turn can be huge in a long-horizon task** (many steps, large tool output spanning a long autonomous run), so discarding the interrupted turn would silently destroy a large amount of real work — truncating a turn is wrong. Instead, on reload `load` PRESERVES those events and CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered, then a `step/end` if a step was still open, then a `turn/end` carrying the merge-extensible `{ kind: 'interrupted' }` reason (a marker that records the turn was cut short by a crash, not completed by the model — no loop ever emits it). The synthetic tool results matter for resume correctness: the loop logs the `assistant/message` (carrying the `tool-call` blocks) BEFORE running the tools, so a crash mid-tool leaves calls without results; `deriveMessages()` would then replay a dangling assistant tool-call, which every provider rejects as an invalid transcript on the next request. Answering each orphaned call with an error result keeps the rehydrated history valid. `load` returns the balanced log, so a resumed session is immediately usable. The ONLY thing discarded is a never-fully-written **torn tail fragment** — a final record whose bytes (JSONL) or row were never completely flushed; that fragment is not a valid event and is dropped before the synthetic closers are written. A parse error or `seq` gap in the COMMITTED region (at or before the last real `turn/end`) is genuine corruption and makes the session unloadable. - **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) -- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. +- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 8171a05d30..5fe8224644 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -4,23 +4,23 @@ Status: implemented ## Problem -The harness already brands three identifiers — `CallId` (`packages/llm/llm/src/brand.ts`), `SessionId` (`packages/core/session/src/types.ts`), and `AgentId` (`packages/core/agent/src/types.ts`) — using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. +The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". -**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId`/`SessionId`/`AgentId` decay back to bare `string` at exactly the places confusion is most likely: the registry/store `Map` key types and most public method params. Representative sites: `SessionStore.store = new Map()` and `create`/`prepare(id?: string)`/`get(id: string)` (`packages/core/session/src/index.ts`); `AgentRegistry.store = new Map()` and `register`/`get(id: string)` (`packages/core/agent/src/index.ts`); `ToolPresenter.pending = new Map()` keyed by call id and `call(callId: string)`/`result(callId: string)` (`packages/ui/acp/src/index.ts`); the ACP session-id surface beyond the store map — `SessionRecord.sessionId: string`, `bySession = new WeakMap()`, `loadingIds = new Set()`, `requireSession(sessionId: string)`, and the exported `streamSessionEventUpdate(sessionId: string, …)` (`packages/ui/acp/src/index.ts`); and the persistence coordinator's `Map` keyed by session id (`packages/session-persistence/session-persistence/src/coordinator.ts`). A brand that is dropped at the `Map` key buys nothing on lookups — the value of the existing brands is partly unrealized. +**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. ## Decision A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId`/`AgentId` already do. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). - **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) -- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `get(id: SessionId)`, `Map`, `Map`, the ACP `SessionRecord.sessionId: SessionId` surface, the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on the struct fields. +- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. Illustrative shape (the factory pattern is identical to the three existing brands): @@ -58,7 +58,7 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o ## Verification -The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`AgentId`/`BashTaskId`) is keyed by bare `string` — `Map` keys, `WeakMap` value slots, `Set` membership (the ACP `bySession`/`loadingIds`), public method params, and exported signatures (`streamSessionEventUpdate`) all take the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. +The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md index f0ab95ca80..f785851237 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -24,7 +24,7 @@ This is the foundational change in a stack that adds a Hooks subsystem; it estab **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. -**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) was migrated to render boundaries from `session/event`, recovering the short agent label from an `agent/created`→id map. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). +**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md index dcff4d3220..15477e023a 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -60,8 +60,7 @@ The ordinary contributor pattern is to register the complete local world during ```js const handle = await ctx.agents.create({ - agentId: AgentId('reviewer'), - sessionId: SessionId('reviewer-session'), + sessionId: SessionId('reviewer'), agentOptions: { model: 'model-name' }, setup(agentCtx) { agentCtx.systemPrompt.section({ diff --git a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md index 9d0446dcad..6961883318 100644 --- a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -12,11 +12,10 @@ The harness already has every seam the pi extension uses, and better ones: [the The guard is a loop-hygiene plugin, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The purpose is to break unproductive loops within a few wasted steps instead of letting them run to the turn's natural end — while leaving the decision (retry differently, gather more evidence, or finish) entirely with the model, so a legitimately repeated call is delayed by nothing and blocked by nothing. -The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers three listeners and holds all state in plugin-local maps keyed by `AgentId` — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish. +The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. - **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, folds a reminder onto the downstream decision's `additionalContext` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking. - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop. -- **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime. ### Detection semantics @@ -25,7 +24,7 @@ The chain key is `(tool name, canonical arguments)`; a call identical to the pre Two deliberate rules, both documented in [the package README](../../../../packages/guard/repeat-tool-guard/README.md) because they are behavior a reader would otherwise guess at: - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful — bookkeeping tools interleaved into a loop must not launder it — and it is the pi extension's (undocumented) semantics, kept on purpose and written down. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no `AgentId` to key on. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no live agent object to key on. ### Reminder delivery diff --git a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index dbef22f3a3..f4b49281ea 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -21,9 +21,9 @@ This duplication is not free. Every lifecycle change had to update the session e Make `session/event` the single live boundary/transcript stream. Consumers that render turns, tool calls, tool results, assistant messages, and durable boundaries subscribe to `session/event` and derive their UI from the same event vocabulary persistence uses. -The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle (or its short id) at a boundary keeps a small map from session id to agent id built from `agent/created`/`agent/disposed`; `dsh-ui-stdio` does exactly this to label its `[ turn N]` header, since the `turn/start` session event carries only the turn number. The canonical record remains the event-sourced session log. +The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle at a boundary retains the live target object from `agent/created`/`agent/disposed` and compares its session directly; `dsh-ui-stdio` uses this to label the app-owned agent's `[main turn N]` header while other sessions render their durable id. The canonical record remains the event-sourced session log. -The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it was migrated to `session/event` + the id map, and the turn mirrors were removed too. +The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. ## Scope: what is and isn't removed @@ -38,8 +38,8 @@ RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: ## Alternatives considered - **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror RFC](2026-07-02-remove-stream-chunk-mirror.md)). -- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` + the id map instead. +- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. ## Consequences -A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It must either subscribe to `session/event` or maintain a session-to-agent association. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. +A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It subscribes to `session/event` and, if it needs the live object, resolves the shared id through `ctx.agents` or retains the object it already owns. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 3de3c7d9be..911d28cf1f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -14,7 +14,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. - `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. -Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = AgentId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. +Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. ## Verified interface facts (pinned versions) diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md index 1a69f9ebe6..6e3eea1515 100644 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,13 +16,13 @@ Session itself repeats the same fact as `Session.id` and `Session.header.id`. Co Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. -The config-driven path must first settle its currently hidden resume-or-create policy. Today it uses a stable agent label and fresh UUID-suffixed session id to avoid colliding with a durable log on the next run. Under unification it must deliberately resume the fixed id, mint a fresh combined id, or expose an explicit policy; implementation must not pick silently. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. ## Alternatives considered -**Keep separate routing and log identities.** The config-driven loop uses a stable configured agent id with a fresh UUID session on each fresh process start. That is a real use of the distinction: a stable routing/display label plus a new durable conversation. Unification can proceed only after choosing whether this path resumes a fixed identity, mints a combined per-run identity, or exposes the policy explicitly. If the stable label is a required product contract, reject this proposal rather than hiding it in another map. +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. ## Acceptance criteria @@ -35,4 +35,4 @@ The config-driven path must first settle its currently hidden resume-or-create p ## Risks -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. The config restart decision is blocking, not mechanical. If separate routing identity is a real requirement, reject this RFC and retain the current caller-supplied pair plus final-entry arbitration. +This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..22446f0dc3 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -4,11 +4,12 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -72,7 +73,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..e1ae9804ac 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -4,8 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The swebench-style smoke test: a real model fixes a real bug in a temp @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-task'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..a0e71aacc4 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The compaction smoke test: a real model runs a multi-step bash task with a @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..9a01713222 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The first place a REAL model meets the REAL bash tool: the cheap canary @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..48e135ad92 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -4,7 +4,6 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -40,7 +39,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // log on disk survives. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const first = (await ctx.agents.create({ - agentId: AgentId('resume-1'), sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent @@ -54,7 +52,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // run 1's exchange as conversation history. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const resumed = (await ctx.agents.resume({ - agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..7f3c3c1e4a 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * A REAL model drives the REAL todo_write tool: verify the WORLD (the session @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..ffe9a290eb 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -1,8 +1,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import type { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId } from '@deepseek-ai/dsh-agent' import { cordisHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the self-referential cordis tools: a REAL model drives @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..3ab3ae6628 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' @@ -74,7 +75,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-fg'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +107,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-exit'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +129,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-bg'), { model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 12b4a53958..c68c445f0a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -57,7 +57,7 @@ async function setup() { const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id) — a config agent has `agentId !== sessionId`. The + // token (session.header.id), which is also the agent's durable id. The // owner token IS the session id, so the notice path must find the agent by // `session.header.id`, NOT the registry key. Using distinct values here makes // the test fail if a regression matched on the wrong field (a same-value fake diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index bb77e44a9c..52a2ecd134 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -3,11 +3,12 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('repro'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 3d6ade301f..5721bd97d9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -56,7 +56,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'agentLoop', summary: 'Concrete ReactLoopAgent factory and driver service.', methods: [ - 'create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], @@ -71,7 +71,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(agent: Agent): () => void', 'enter(agent: Agent): () => void', 'announce(agent: Agent): void', - 'get(id: AgentId): Agent | undefined', + 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', ], }, @@ -488,7 +488,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ export const TYPE_API: readonly TypeApiEntry[] = [ { name: 'Agent', - declaration: 'export interface Agent {\n readonly id: AgentId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', + declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, { name: 'AgentFactory', @@ -498,10 +498,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AgentHandle', declaration: 'export interface AgentHandle {\n agent: Agent;\n dispose(): Promise;\n}', }, - { - name: 'AgentId', - declaration: 'export type AgentId = Branded<\'AgentId\'>;', - }, { name: 'AgentOptions', declaration: 'export interface AgentOptions {\n model?: string;\n}', @@ -644,7 +640,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CreateAgentOptions', - declaration: 'export interface CreateAgentOptions {\n readonly agentId: AgentId;\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'CreateSessionOptions', @@ -756,7 +752,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'ResumeAgentOptions', - declaration: 'export interface ResumeAgentOptions {\n readonly agentId: AgentId;\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface ResumeAgentOptions {\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'SandboxEnforcement', @@ -868,7 +864,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: AgentId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..0d4c6c5c18 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -51,7 +52,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-cordis'), { model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 33cd0faddd..accbf66a7c 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates one under the `main` config label; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..058191c88f 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -6,8 +6,10 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as agentCore from '../src/index.ts' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' async function composePrefix(ctx: Context, cwd: string): Promise { const agent = { session: { header: { cwd } } } as unknown as Agent @@ -102,16 +104,18 @@ describe('dsh-agent-core bundle', () => { it('defaults the agents list to empty (no pre-created agents)', async () => { const ctx = await mount() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.get(SessionId('main'))).toBeUndefined() await ctx.fiber.dispose() }) it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: 'main', model: 'mock' }], persona: 'You are main.', }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) const assembly = await ctx.get('systemPrompt')!.assemble() expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('You are main.') await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..f40577bb95 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -12,14 +12,14 @@ Creation and resume are one rollback-covered transaction: construct a private se The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createAgent(ownerCtx, options)` and `resume(ownerCtx, options)` receive caller ownership explicitly, while the factory keeps its own dependency context for `sessions`/`llm`/`tools`/`systemPrompt`; this lets a caller inject only `agents` without shrinking the new agent's service surface. Caller unload, handle disposal, or provider unload converge on one memoized quiescence boundary. Provider shutdown waits both resource teardown and the public create/resume wrapper that observed deactivation, so no continuation can publish after dependencies disappear. -IDs are caller-chosen and assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same agent or session id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; IDs become reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. +Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: string, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create, used directly by programs and by `cordis.yml`-configured agents. It creates a fresh per-run session id `${id}-session-` with optional metadata; the uuid avoids colliding with a prior durable log. Each call is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): -- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create on a caller-supplied `sessionId`, NOT `${id}-session`. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. -- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. +- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. +- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code. @@ -32,7 +32,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { agents: Array<{ - id: string // required + id: string // required stable label; prefixes fresh combined ids model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index ff66f942be..d54baab597 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -8,11 +8,11 @@ import type { Context } from 'cordis' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -59,7 +59,7 @@ export interface PreparedReactLoopAgent { * @returns the agent and closures bound only to that exact instance. */ export function prepareReactLoopAgent( - ctx: Context, id: AgentId, options: AgentOptions, session: Session, + ctx: Context, id: SessionId, options: AgentOptions, session: Session, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) @@ -163,7 +163,7 @@ export class ReactLoopAgent implements Agent { constructor( private loopCtx: Context, - public readonly id: AgentId, + public readonly id: SessionId, public readonly options: AgentOptions, public readonly session: Session, ) { diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..33276c01f8 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -14,7 +14,6 @@ import { agentEvents } from '@deepseek-ai/dsh-agent' import type { AgentFactory, AgentHandle, - AgentId, AgentOptions, CreateAgentOptions, ResumeAgentOptions, @@ -68,7 +67,7 @@ class FactoryOwnership { } /** Build the public cancellation error while preserving a caller-supplied cause. */ -function signalAbortError(id: AgentId, signal: AbortSignal): Error { +function signalAbortError(id: SessionId, signal: AbortSignal): Error { if (signal.reason instanceof Error) return signal.reason return new Error(`agent "${id}" creation aborted`, { cause: signal.reason }) } @@ -108,7 +107,7 @@ class AgentCreationTransaction { private readonly loopCtx: Context, private readonly ownerCtx: Context, private readonly ownership: FactoryOwnership, - readonly id: AgentId, + readonly id: SessionId, signal?: AbortSignal, ) { ownerCtx.fiber.assertActive() @@ -325,8 +324,8 @@ declare module 'cordis' { export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -363,13 +362,13 @@ export class AgentLoop extends Service implements AgentFactory { for (const { id, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(id, options, cwd === undefined ? {} : { cwd }) + const sessionId = SessionId(`${id}-session-${randomUUID()}`) + this.create(sessionId, options, cwd === undefined ? {} : { cwd }) continue } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { - agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { @@ -382,19 +381,19 @@ export class AgentLoop extends Service implements AgentFactory { } /** - * Create an agent on a fresh per-run session, owned by the accessing fiber. - * Constructor-driven config calls use the loop fiber itself. - * @param id - agent registry id. + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. * @param options - concrete loop options. * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - const session = loopCtx.sessions.prepare(sessionId, { meta }) + const session = loopCtx.sessions.prepare(id, { meta }) const agent = transaction.prepare(options, session) transaction.publish('startup') return agent @@ -417,7 +416,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.sessionId, options.signal, ) try { @@ -461,7 +460,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.resumeSessionId, options.signal, ) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..56d6489fbe 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -1,6 +1,5 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -53,10 +52,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('first-driver'), { model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, SessionId('second-driver'), { model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -66,11 +65,11 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) const options = { model: 'mock' } - const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) + const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options) expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') - expect(agent.session.id).toMatch(/^owned-bindings-session-/) + expect(agent.session.id).toBe(agent.id) expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() @@ -81,7 +80,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +95,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +110,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +123,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +149,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +162,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +182,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +205,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +224,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +239,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +257,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +279,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('pre-start-dispose'), { model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +293,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +312,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +323,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +341,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +378,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +403,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +424,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +445,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +463,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..82b1f6c58c 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,7 +16,8 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +75,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +94,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +115,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +132,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +148,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +170,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -203,7 +204,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -334,7 +334,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) @@ -366,7 +365,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +397,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +427,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +457,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +477,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..134ea68c32 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,7 +7,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -32,7 +33,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,11 +54,13 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as ReactLoopAgent + expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) + expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -70,10 +73,11 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as ReactLoopAgent + expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) @@ -96,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -110,7 +114,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -118,11 +122,12 @@ describe('config-driven session id', () => { let resumed: ReactLoopAgent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), // and the prior turn's user message is in the derived history. + expect(resumed!.id).toBe(SessionId('sticky-1')) expect(resumed!.session.id).toBe('sticky-1') const derived = resumed!.session.deriveMessages() expect(JSON.stringify(derived)).toContain('remember me') @@ -138,16 +143,16 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')])) // The deferred resume fails (no such session on disk). It must be contained: - // a warning is logged, no 'main' agent is registered, and the app stays up. + // a warning is logged, no agent is registered, and the app stays up. await new Promise(r => setTimeout(r, 200)) - expect(ctx.agents.get(AgentId('main'))).toBeUndefined() + expect(ctx.agents.list()).toEqual([]) expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed')) warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..4e82e398f1 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -40,7 +41,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +81,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +114,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +127,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +153,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +181,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +215,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +243,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 1ec48e553f..8c95be0d82 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -1,15 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { - AgentId, - type ContinuationDecision, - type PromptDecision, - type SessionStartSource, -} from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -57,7 +53,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +72,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +90,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +123,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +153,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +190,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +226,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +259,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +278,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,8 +296,8 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - expect(agent.id).toBe(AgentId('a1')) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + expect(agent.id).toBe(SessionId('a1')) // and the agent still runs send(agent, 'go') @@ -314,8 +310,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { model: 'mock' }) + const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +348,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +381,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +408,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +430,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +446,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +475,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +496,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +529,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +559,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +595,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +659,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +682,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +701,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a3'), { model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..c4e49e0fa5 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -44,7 +45,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +93,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +132,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +156,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -169,7 +170,6 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'Working in {{cwd}}.') const handle = await ctx.agents.create({ - agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, agentOptions: { model: 'mock' }, @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('agent loop', () => { ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } }) - const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) + const agent = ctx.agentLoop.create(SessionId('a-late-model'), {}) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -259,7 +259,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +288,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-no-system'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +324,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +356,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +366,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +393,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +427,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +453,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -469,7 +469,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,10 +913,10 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) - expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) + expect(ctx.agents.get(SessionId('scoped'))).toBe(agent) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -925,7 +925,7 @@ describe('agent loop', () => { await agent.done expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() expect(() => { send(agent, 'too late') }).toThrow('disposed') }) @@ -938,13 +938,14 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: 'config-agent', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent).toBeDefined() - expect(agent.id).toBe('config-agent') + expect(agent.id).toBe(agent.session.id) + expect(agent.id).toMatch(/^config-agent-session-/) expect(agent.options.model).toBe('mock') // the agent is alive: send triggers a turn @@ -961,10 +962,10 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent.session.header.cwd).toBe('/work/project') }) @@ -982,7 +983,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..b3653d6540 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -14,10 +14,11 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -95,7 +96,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +121,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +146,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..7eddb6be39 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -71,7 +72,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 7054b683cb..202a8f6795 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,7 +15,8 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -74,7 +75,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +96,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +110,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -194,7 +195,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -215,7 +216,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('gen1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -224,7 +225,6 @@ describe('request stability across the loop', () => { const adapter2 = new MockAdapter([textResponse('two')]) const ctx2 = await harness(adapter2) const handle = await ctx2.agents.create({ - agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], agentOptions: { model: 'mock' }, @@ -244,7 +244,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -278,7 +278,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..f5809575ab 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,7 +8,8 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -83,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => throwUnknown(failure)) await expect(ctx.agents.resume({ - agentId: AgentId('unknown-resume-failure'), resumeSessionId: sessionId, })).rejects.toBe(failure) - expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() await ctx.fiber.dispose() }) @@ -95,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) expect(agent.session.id).toBe('custom-session') expect(agent.session.header.cwd).toBe('/w') await ctx.fiber.dispose() }) - it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => { + it('createAgent rejects a duplicate identity without orphaning a session', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') }) - // A second create with the SAME agent id but a fresh session id must reject - // up front — and must NOT leave an orphaned 'sess-b' session behind. - await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/) - expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined() + const sessionId = SessionId('sess-a') + await ctx.agents.create({ sessionId }) + await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/) + expect(ctx.sessions.list()).toHaveLength(1) await ctx.fiber.dispose() }) it('createAgent works without meta (no cwd)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') }) expect(agent.session.id).toBe('nometa-session') expect(agent.session.header.cwd).toBeUndefined() await ctx.fiber.dispose() @@ -125,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -141,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -152,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -171,7 +170,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx2.llm.registerAdapter(['mock'], adapter2) const sources2: string[] = [] ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source)) - await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') }) + await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') }) expect(sources2).toEqual(['resume']) await ctx2.fiber.dispose() }) @@ -186,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session) + expect(ctx.agents.get(sessionId)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', (agent) => { @@ -199,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) const resuming = ctx.agents.resume({ - agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) + expect(agentCtx.agent?.id).toBe(sessionId) expect(agentCtx.agent?.session.events).toHaveLength(2) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) @@ -215,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) await setupStarted.promise - expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() expect(order).toEqual(['setup:start']) @@ -236,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('successful resume disposal retires its caller-owned transaction effects', async () => { const sessionId = SessionId('resume-retired-effects-s') - const agentId = AgentId('resume-retired-effects') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const handle = await ctx.agents.resume({ - agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) const transactionLabels = [ - `agentLoop.owner(${agentId})`, - `agentLoop.lifecycle(${agentId})`, + `agentLoop.owner(${sessionId})`, + `agentLoop.lifecycle(${sessionId})`, ] expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels)) @@ -255,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => { + it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => { const sessionId = SessionId('resume-setup-reject') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) @@ -265,7 +261,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -275,10 +270,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { })).rejects.toThrow('resume setup failed') expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() const retry = await ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) @@ -299,7 +293,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { resuming = inner.agents.resume({ - agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -313,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await owner.dispose() await expect(resuming).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() gate.resolve(undefined) @@ -322,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => { + it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => { const sessionId = SessionId('resume-load-owner-unload') - const agentId = AgentId('resume-load-race') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const snapshot = await ctx.sessionPersistence.load(sessionId) @@ -348,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/) await promptly(owner.dispose()) expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - // owner.dispose() awaited transaction settlement, so the same identities - // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + // owner.dispose() awaited transaction settlement, so the identity can be + // reused before awaiting the public rejection. + const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -370,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() await Promise.resolve() - expect(ctx.agents.get(agentId)).toBe(retry.agent) + expect(ctx.agents.get(sessionId)).toBe(retry.agent) expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -380,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => { const sessionId = SessionId('resume-load-factory-unload') - const agentId = AgentId('resume-load-factory-race') const root = await persistSession(sessionId) const ctx = new Context() await ctx.plugin(LlmService) @@ -404,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) await rejection expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() @@ -452,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -466,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -491,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -509,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -519,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -539,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) @@ -567,7 +558,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') })) + await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') })) .rejects.toThrow(/session persistence is not configured/) await ctx.fiber.dispose() }) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..942199e9eb 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -53,7 +54,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -104,7 +105,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +149,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +189,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +219,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +245,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +268,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +296,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +326,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +349,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -361,7 +362,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { await agent.done // must not hang expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw }) }) @@ -380,7 +381,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { const adapter = new MockAdapter([textResponse('never')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -395,7 +396,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('the agent/request waterfall can supply the model for a model-less agent', async () => { const adapter = new MockAdapter([textResponse('routed')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } @@ -410,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +439,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-send'), { model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +475,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-steer'), { model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +529,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +545,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, SessionId('forked-agent'), { model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +592,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +617,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +635,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +651,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-step-order'), { model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +712,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +741,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +772,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +806,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +840,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +873,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +902,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +936,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-preturn'), { model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +967,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1009,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1039,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1086,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-callid'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1121,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1172,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1228,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1283,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1335,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1385,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..c68d96e525 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -4,7 +4,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' + import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' @@ -57,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void { } describe('agent scope lifecycle', () => { - it('rejects an already-aborted creation signal before publishing either identity', async () => { + it('rejects an already-aborted creation signal before publishing either object', async () => { const ctx = await harness() const reason = new Error('cancelled before creation') const controller = new AbortController() controller.abort(reason) await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted'), sessionId: SessionId('pre-aborted-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined() const valueController = new AbortController() valueController.abort('plain cancellation reason') await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted-value'), sessionId: SessionId('pre-aborted-value-s'), signal: valueController.signal, })).rejects.toMatchObject({ - message: 'agent "pre-aborted-value" creation aborted', + message: 'agent "pre-aborted-value-s" creation aborted', cause: 'plain cancellation reason', }) - expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -100,12 +99,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('prepare-abort'), sessionId: SessionId('prepare-abort-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined() + expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -124,7 +122,7 @@ describe('agent scope lifecycle', () => { thrown = createFailure let createCaught: unknown try { - ctx.agentLoop.create(AgentId('unknown-create')) + ctx.agentLoop.create(SessionId('unknown-create')) } catch (error: unknown) { createCaught = error } @@ -133,28 +131,27 @@ describe('agent scope lifecycle', () => { const ownedFailure = { source: 'createAgent' } thrown = ownedFailure await expect(ctx.agents.create({ - agentId: AgentId('unknown-owned-create'), sessionId: SessionId('unknown-owned-create-s'), })).rejects.toBe(ownedFailure) - expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined() - expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined() await ctx.fiber.dispose() }) it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. expect(ctx.agent).toBeUndefined() - await ctx.agents.get(AgentId('a1'))?.whenIdle() + await ctx.agents.get(SessionId('a1'))?.whenIdle() }) it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +176,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) + const b = ctx.agentLoop.create(SessionId('b'), { model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -210,7 +207,6 @@ describe('agent scope lifecycle', () => { }) const handle = await ctx.agents.create({ - agentId: AgentId('child'), sessionId: SessionId('child-s'), agentOptions: { model: 'mock' }, setup: async (agentCtx) => { @@ -224,14 +220,14 @@ describe('agent scope lifecycle', () => { await handle.dispose() }) - it('keeps both identities unpublished until async setup completes, then announces in order', async () => { + it('keeps both objects unpublished until async setup completes, then announces in order', async () => { const ctx = await harness() const gate = Promise.withResolvers() const setupStarted = Promise.withResolvers() const order: string[] = [] ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session) + expect(ctx.agents.get(session.id)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', () => void order.push('agent/created')) @@ -239,11 +235,10 @@ describe('agent scope lifecycle', () => { const acceptedOptions = { model: 'mock' } const creating = ctx.agents.create({ - agentId: AgentId('atomic'), - sessionId: SessionId('atomic-s'), + sessionId: SessionId('atomic'), agentOptions: acceptedOptions, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('atomic')) + expect(agentCtx.agent?.id).toBe(SessionId('atomic')) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) order.push('setup:start') @@ -253,7 +248,7 @@ describe('agent scope lifecycle', () => { }, }) await setupStarted.promise - expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined() + expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) @@ -281,16 +276,14 @@ describe('agent scope lifecycle', () => { if (started === 2) bothStarted.resolve(undefined) await gate.promise } - const agentId = AgentId('concurrent-final-enter') + const sessionId = SessionId('concurrent-final-enter') const first = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-a'), + sessionId, agentOptions: { model: 'mock' }, setup, }) const second = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-b'), + sessionId, agentOptions: { model: 'mock' }, setup, }) @@ -304,7 +297,7 @@ describe('agent scope lifecycle', () => { const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected') expect(fulfilled).toHaveLength(1) expect(rejected).toHaveLength(1) - expect(String(rejected[0]!.reason)).toMatch(/already registered/) + expect(String(rejected[0]!.reason)).toMatch(/already exists/) expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent]) expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session]) @@ -318,7 +311,6 @@ describe('agent scope lifecycle', () => { const pendingController = new AbortController() const setupStarted = Promise.withResolvers() const pending = ctx.agents.create({ - agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), agentOptions: { model: 'mock' }, signal: pendingController.signal, @@ -330,12 +322,11 @@ describe('agent scope lifecycle', () => { await setupStarted.promise pendingController.abort(new Error('cancel pending creation')) await expect(pending).rejects.toThrow('cancel pending creation') - expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined() + expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined() const liveController = new AbortController() const live = await ctx.agents.create({ - agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), agentOptions: { model: 'mock' }, signal: liveController.signal, @@ -358,7 +349,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -372,7 +362,7 @@ describe('agent scope lifecycle', () => { await owner.dispose() await expect(creating).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined() // Let the losing callback settle; Promise.race already observes it. gate.resolve(undefined) @@ -386,7 +376,6 @@ describe('agent scope lifecycle', () => { let creating2!: ReturnType const owner2 = await ctx.plugin(Object.assign((inner: Context) => { creating2 = inner.agents.create({ - agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), agentOptions: { model: 'mock' }, setup: async () => { @@ -400,7 +389,7 @@ describe('agent scope lifecycle', () => { const unload2 = owner2.dispose() await expect(creating2).rejects.toThrow(/owner disposed during setup/) await unload2 - expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined() }) @@ -413,7 +402,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) const creating = ctx.agents.create({ - agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -426,7 +414,7 @@ describe('agent scope lifecycle', () => { await loopFiber.dispose() await expect(creating).rejects.toThrow(/agent loop is not active/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined() gate.resolve(undefined) @@ -444,7 +432,6 @@ describe('agent scope lifecycle', () => { }) const creating = ctx.agents.create({ - agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), agentOptions: { model: 'mock' }, setup: () => { setupCalls += 1 }, @@ -452,7 +439,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/agent loop is not active/) await loopFiber.dispose() expect(setupCalls).toBe(0) - expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -479,7 +466,6 @@ describe('agent scope lifecycle', () => { const owner = ctx.plugin(Object.assign((inner: Context) => { ownerFiber = inner.fiber creating = inner.agents.create({ - agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), agentOptions: { model: 'mock' }, }) @@ -495,7 +481,7 @@ describe('agent scope lifecycle', () => { await ownerDisposal await owner expect(scopeFiber?.uid).toBeNull() - expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined() await owner.dispose() await ctx.fiber.dispose() @@ -511,17 +497,17 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() - expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) await ctx.fiber.dispose() }) it('synchronous create leaves no lifecycle state when session preparation fails', async () => { const ctx = await harness() - const id = AgentId('config-prepare-failure') + const id = SessionId('config-prepare-failure') expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) @@ -542,12 +528,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() - expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -556,23 +541,21 @@ describe('agent scope lifecycle', () => { it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => { const { ctx, loopFiber } = await harnessWithLoop() const loop = ctx.agentLoop - const agentId = AgentId('factory-live') + const sessionId = SessionId('factory-live') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('factory-live-s'), + sessionId, agentOptions: { model: 'mock' }, }) await loopFiber.dispose() expect(handle.agent.status).toBe('disposed') - expect(ctx.agents.get(agentId)).toBeUndefined() - expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.agents.get(sessionId)).toBeUndefined() + expect(ctx.sessions.get(sessionId)).toBeUndefined() + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) // The consumer handle shares the provider's completed quiescence boundary. await handle.dispose() await expect(loop.createAgent(ctx, { - agentId: AgentId('factory-inactive'), sessionId: SessionId('factory-inactive-s'), })).rejects.toThrow('agent loop is not active') await ctx.fiber.dispose() @@ -583,7 +566,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), agentOptions: { model: 'mock' }, setup: (agentCtx) => { @@ -623,7 +605,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('session/created', (session) => { if (session.id !== SessionId('session-created-barrier-s')) return - const agent = ctx.agents.get(AgentId('session-created-barrier'))! + const agent = ctx.agents.get(SessionId('session-created-barrier-s'))! expect(ctx.sessions.get(session.id)).toBe(session) expect(agent.session).toBe(session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) @@ -638,7 +620,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -652,7 +633,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -666,19 +647,19 @@ describe('agent scope lifecycle', () => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created') }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return lifecycle.push('agent-created:dispose') disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) lifecycle.push('agent-created:observer') }) ctx.on('agent/disposed', (agent) => { - if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed') + if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed') }) ctx.on('session/disposed', (session) => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed') @@ -687,7 +668,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -703,7 +683,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -715,13 +695,12 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType ctx.on('agent/session-start', agent => void starts.push(agent.id)) ctx.on('agent/created', (agent) => { - if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose() + if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose() }) const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -730,7 +709,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/owner disposed during setup/) await owner.dispose() expect(starts).toEqual([]) - expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -744,15 +723,15 @@ describe('agent scope lifecycle', () => { let scopeDisposed = false let observerSawLive = false ctx.on('agent/status', (agent, status) => { - if (agent.id === AgentId('session-start-dispose')) statuses.push(status) + if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return announced = agent as ReactLoopAgent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { scopeDisposed = true }) @@ -762,7 +741,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -775,7 +753,7 @@ describe('agent scope lifecycle', () => { expect(observerSawLive).toBe(true) expect(scopeDisposed).toBe(true) expect(announced.session.events).toEqual([]) - expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -787,7 +765,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -798,13 +775,13 @@ describe('agent scope lifecycle', () => { // Nothing leaked: no agent, no session, and the ids are reusable. expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) await retry.dispose() }) - it('rejects an exotic durable seed before publishing either identity', async () => { + it('rejects an exotic durable seed before publishing either object', async () => { const ctx = await harness() const published: string[] = [] ctx.on('session/created', () => { published.push('session') }) @@ -817,17 +794,15 @@ describe('agent scope lifecycle', () => { }] as unknown as SessionEvent[] await expect(ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined() const retry = await ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, }) @@ -843,13 +818,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('boom created') - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -866,18 +841,17 @@ describe('agent scope lifecycle', () => { ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) }) await expect(ctx.agents.create({ - agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), agentOptions: { model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ 'session-created:partial-session', - 'agent-created:partial-agent', - 'agent-disposed:partial-agent', + 'agent-created:partial-session', + 'agent-disposed:partial-session', 'session-disposed:partial-session', ]) - expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined() + expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined() }) @@ -892,23 +866,23 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-bad'), { model: 'mock' })) .toThrow('config publish failed') - expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) }) it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +895,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -930,7 +904,7 @@ describe('agent scope lifecycle', () => { if (event.type === 'turn/end') order.push('turn-end') }) ctx.on('agent/disposed', () => { - order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`) + order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`) order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`) }) @@ -955,7 +929,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -967,23 +941,22 @@ describe('agent scope lifecycle', () => { // actually finished (the raw wrapper returns undefined on a repeat call). await handle.dispose() expect(teardownDone).toContain('unregistered') - expect(ctx.agents.get(AgentId('h1'))).toBeUndefined() + expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined() await unload }) it('successful handle disposal retires its caller ownership effect', async () => { const ctx = await harness() - const agentId = AgentId('retired-owner-effect') + const sessionId = SessionId('retired-owner-effect') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('retired-owner-effect-s'), + sessionId, agentOptions: { model: 'mock' }, }) - expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) + expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`) await handle.dispose() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) await ctx.fiber.dispose() }) @@ -994,7 +967,6 @@ describe('agent scope lifecycle', () => { let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { handle = await inner.agents.create({ - agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1014,7 +986,7 @@ describe('agent scope lifecycle', () => { expect(ownerSettled).toBe(false) gate.resolve(undefined) await Promise.all([disposing, unloading]) - expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined() + expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -1024,13 +996,11 @@ describe('agent scope lifecycle', () => { const gate = Promise.withResolvers() const cleanupStarted = Promise.withResolvers() const sessionDisposed = Promise.withResolvers() - const agentId = AgentId('quiescent-reuse') - const sessionId = SessionId('quiescent-reuse-s') + const sessionId = SessionId('quiescent-reuse') ctx.on('session/disposed', (session) => { if (session.id === sessionId) sessionDisposed.resolve(undefined) }) const first = await ctx.agents.create({ - agentId, sessionId, agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1043,10 +1013,10 @@ describe('agent scope lifecycle', () => { const disposing = first.dispose() await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) - expect(ctx.agents.get(agentId)).toBe(replacement.agent) + const replacement = await ctx.agents.create({ sessionId, agentOptions: { model: 'mock' } }) + expect(ctx.agents.get(sessionId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) gate.resolve(undefined) @@ -1058,7 +1028,6 @@ describe('agent scope lifecycle', () => { it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => { const ctx = await harness() const handle = await ctx.agents.create({ - agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), agentOptions: { model: 'mock' }, }) @@ -1077,12 +1046,12 @@ describe('agent scope lifecycle', () => { const disposal = handle.dispose().then(() => { disposed = true }) await new Promise(resolve => setTimeout(resolve, 0)) expect(disposed).toBe(false) - expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent) + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent) expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session) gate.resolve(undefined) await disposal - expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined() + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined() }) }) diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..1085f01a4c 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -10,11 +10,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +104,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..c7823a2aa5 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -45,7 +46,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +73,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +99,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +125,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(SessionId('stopped'), { model: 'mock' }) + const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +146,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-listener'), { model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +163,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-policy'), { model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 9ee324b0c3..4eddb050d5 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -12,7 +12,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. -- `ctx.agents.get(id: AgentId): Agent | undefined` +- `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index edb7f59a37..1306e8004d 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -9,7 +9,7 @@ import { Context, getTraceable, Service, symbols } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { Agent, AgentId, AgentOptions } from './types.ts' +import type { Agent, AgentOptions } from './types.ts' export * from './types.ts' export { agentEvents, assembleContextFor } from './dispatch.ts' @@ -33,15 +33,13 @@ declare module 'cordis' { /** * Options for programmatically creating an agent through the registry factory - * ({@link AgentRegistry.create}). The caller supplies the live `sessionId` - * (e.g. an ACP-generated id) and optional session metadata (the validated - * `cwd`, fork lineage); the factory creates the session, the agent, and wires - * them together. + * ({@link AgentRegistry.create}). The caller supplies the single live + * `sessionId` shared by the agent registry and session log (e.g. an + * ACP-generated id), plus optional session metadata (the validated `cwd`, fork + * lineage); the factory creates the session and agent under that identity. */ export interface CreateAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The live session's id (NOT derived from agentId). */ + /** The live agent/session identity. */ readonly sessionId: SessionId /** * Session creation metadata: validated absolute `cwd`, `parentSession` @@ -93,9 +91,7 @@ export interface CreateAgentOptions { * ({@link AgentRegistry.resume}). */ export interface ResumeAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The persisted session id to load and resume on. */ + /** The persisted session id to load and use as the live agent/session identity. */ readonly resumeSessionId: SessionId /** Per-agent options (model, …). */ readonly agentOptions?: AgentOptions @@ -180,7 +176,7 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug /** All mutable lifecycle state for one exact registry entry. */ interface AgentEntry { - readonly id: AgentId + readonly id: SessionId readonly agent: Agent readonly carrier: Scoped announced: boolean @@ -201,7 +197,7 @@ interface FactorySlot { * {@link setFactory}. */ export class AgentRegistry extends Service { - private store = new Map() + private store = new Map() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -257,7 +253,7 @@ export class AgentRegistry extends Service { * agent): this constructs the agent and its session. Rejects if no factory is * registered or creation/setup fails. The resolved {@link AgentHandle} lets * the owner tear down exactly this agent. - * @param options - agent id, session id/seed/metadata, and agent options. + * @param options - shared identity, session seed/metadata, and agent options. * @returns the handle after setup, rollback-covered publication, and loop start complete. */ async create(options: CreateAgentOptions): Promise { @@ -428,10 +424,10 @@ export class AgentRegistry extends Service { /** * Look up a live agent. - * @param id - the agent id to look up. + * @param id - the shared agent/session id to look up. * @returns the agent, or undefined when no live agent has that id. */ - get(id: AgentId): Agent | undefined { + get(id: SessionId): Agent | undefined { return this.store.get(id)?.agent } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index a990f0d67d..b0fb78ad66 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -32,7 +32,7 @@ * event. A turn/step boundary is a durable fact: it lives in the session log * and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` * emit. A consumer that needs the `Agent` handle (or its short id) at a boundary - * keeps a session-id→agent map from `agent/created`/`agent/disposed`. + * looks up the agent directly by the event's session id. * See `docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md` * and `docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md`. * @@ -45,25 +45,12 @@ * @module @deepseek-ai/dsh-agent/types */ -import type { Branded } from '@deepseek-ai/dsh-brand' import type { Context } from 'cordis' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm' +import type { Session, SessionId } from '@deepseek-ai/dsh-session' import type {} from '@deepseek-ai/dsh-system-prompt' -/** Identifies one live agent in the registry. */ -export type AgentId = Branded<'AgentId'> - -/** - * Brand a string as an {@link AgentId}. - * @param id - the raw agent id string. - * @returns the same string, branded (a compile-time cast — no runtime cost). - */ -export function AgentId(id: string): AgentId { - return id as AgentId -} -import type { Session } from '@deepseek-ai/dsh-session' - declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { /** @@ -186,7 +173,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' * package should depend on the implementation. */ export interface Agent { - readonly id: AgentId + /** The single identity shared with {@link session}. */ + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5d541d56a8..cba833b212 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,11 +2,12 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' + import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' function stubAgent(rawId: string): Agent { - const id = AgentId(rawId) + const id = SessionId(rawId) return { id, options: {}, @@ -57,7 +58,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) expect(() => ctx.agents.register(stubAgent('vetoed'))).toThrow('creation veto') - expect(ctx.agents.get(AgentId('vetoed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('vetoed'))).toBeUndefined() expect(lifecycle).toEqual(['created:vetoed', 'disposed:vetoed']) }) @@ -158,11 +159,11 @@ describe('AgentRegistry factory seam', () => { const factory: AgentFactory = { async createAgent(ownerCtx, options) { calls.create.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } }, async resume(ownerCtx, options) { calls.resume.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } }, } return { factory, calls } @@ -171,15 +172,15 @@ describe('AgentRegistry factory seam', () => { it('requires a factory and delegates through the calling context', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) - await expect(ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) const { factory, calls } = stubFactory() ctx.agents.setFactory(factory) let callerFiber: Context['fiber'] | undefined await ctx.plugin(Object.assign(async (inner: Context) => { callerFiber = inner.fiber - await inner.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await inner.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await inner.agents.create({ sessionId: SessionId('create-s') }) + await inner.agents.resume({ resumeSessionId: SessionId('resume-s') }) }, { inject: ['agents'] })) expect(calls.create[0]?.ownerCtx.fiber).toBe(callerFiber) expect(calls.resume[0]?.ownerCtx.fiber).toBe(callerFiber) @@ -192,9 +193,9 @@ describe('AgentRegistry factory seam', () => { inner.agents.setFactory(stubFactory().factory) expect(() => inner.agents.setFactory(stubFactory().factory)).toThrow(/already registered/) }, { inject: ['agents'] })) - await expect(ctx.agents.create({ agentId: AgentId('before'), sessionId: SessionId('before-s') })).resolves.toBeDefined() + await expect(ctx.agents.create({ sessionId: SessionId('before-s') })).resolves.toBeDefined() await owner.dispose() - await expect(ctx.agents.create({ agentId: AgentId('after'), sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) }) it('canonicalizes an already traced Service before tracing it for the caller', async () => { @@ -214,18 +215,18 @@ describe('AgentRegistry factory seam', () => { } async createAgent(_ownerCtx: Context, options: CreateAgentOptions) { this.calls().push('create') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } } async resume(_ownerCtx: Context, options: ResumeAgentOptions) { this.calls().push('resume') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } } } await ctx.plugin(TracedFactory) const traced = (ctx as Context & { tracedFactory: TracedFactory }).tracedFactory ctx.agents.setFactory(traced) - await ctx.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await ctx.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await ctx.agents.create({ sessionId: SessionId('create-s') }) + await ctx.agents.resume({ resumeSessionId: SessionId('resume-s') }) const raw = (traced as unknown as { [symbols.original]?: TracedFactory })[symbols.original] expect(states.get(raw!)).toEqual(['create', 'resume']) }) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 06669ca85c..cb6e1304c3 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -288,7 +288,12 @@ export class Session { */ readonly header: SessionHeader - constructor(public readonly id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId { + return this.header.id + } + + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { if (seed) { // Validate the seed to the SAME invariants `append` enforces, so a // replay/fork (`ctx.sessions.create(id, { seed })`) cannot construct a diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index f9d84aadbf..2339657ec8 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -8,7 +8,6 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime' import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime' import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools' import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventMap } from '@deepseek-ai/dsh-session' @@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) { /** Mint one production-shaped agent scope that can register scoped tool policy. */ async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> { - const agent = { id: AgentId(name) } as Agent + const agent = { id: SessionId(name) } as Agent let scope!: Scope await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) }, { inject: ['tools', 'systemPrompt'] })) diff --git a/packages/core/tools/tests/scoped.spec.ts b/packages/core/tools/tests/scoped.spec.ts index 6599112c2a..8b8e1cfead 100644 --- a/packages/core/tools/tests/scoped.spec.ts +++ b/packages/core/tools/tests/scoped.spec.ts @@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' + import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Mount the registry (with its systemPrompt dependency) on a fresh context. */ async function mount(): Promise { @@ -20,7 +22,7 @@ async function mount(): Promise { /** Mint a scope whose key doubles as a minimal Agent-like object. */ async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> { - const key = { id: name as AgentId } as Agent + const key = { id: name as SessionId } as Agent let scope!: Scope // The scoped context resolves services through the MINTING plugin's // dependency chain — the minter must inject what scope holders will reach @@ -62,7 +64,7 @@ describe('scoped tool registration', () => { it('files a scoped tool in its layer: visible/executable for that scope only', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('shared')) scope.ctx.tools.register(tool('mine')) @@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => { it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('t')) const seen: (string | undefined)[] = [] @@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => { it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent let bodyCalls = 0 ctx.tools.register({ ...tool('t'), @@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => { it('uses one input snapshot for the normalized error shell', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'accepted') - const driftAgent = { id: 'drift' as AgentId } as Agent + const driftAgent = { id: 'drift' as SessionId } as Agent ctx.tools.register(tool('parent')) ctx.tools.register(tool('t')) let parent!: ToolExecutionToken diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..dca48d65ab 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { fsHarness, waitForIdle } from './harness.ts' @@ -35,7 +34,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -65,7 +64,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => try { ctx = await fsHarness(configDir, SYSTEM) const handle = await ctx.agents.create({ - agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, agentOptions: { model: 'deepseek-v4-flash' }, diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index dc385bc033..e46f113301 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -24,8 +24,8 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful: bookkeeping tools interleaved into a loop must not launder it. - **Denied calls count.** Detection sits on `tools/post-execute`, which also runs for calls a `tools/pre-execute` listener denied — a model hammering a denied call is exactly the loop worth breaking. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no `AgentId` to key on. -- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so chains are keyed by `AgentId`; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain; agent disposal drops its state. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no live agent object to key on. +- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener. - **In-memory only.** A session resumed from persistence starts with a fresh chain — the guard is a heuristic nudge, not a logged invariant, later reminders are the accepted cost. ## Reminder delivery diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index 6a5662d693..d51df1d829 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -22,7 +22,7 @@ * exclude: [todo_write] # tool-name patterns transparent to the chain * ``` * - * Chain state is keyed per {@link AgentId} — the tool registry is a + * Chain state is keyed by the live agent object — the tool registry is a * context-level singleton whose waterfalls interleave every agent's calls, so * a shared counter would let one agent's repetition trip another's reminder. * State is in-memory only: a session resumed from persistence starts with a @@ -37,7 +37,7 @@ import type { Context } from 'cordis' import z from 'schemastery' -import type { AgentId, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { Agent, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { MessageSource } from '@deepseek-ai/dsh-llm' import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools' @@ -202,9 +202,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`) } - // TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that - // removes the disposal-only status listener and cannot collide on id reuse. - const chains = new Map() + const chains = new WeakMap() /** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */ function tracked(toolName: string): boolean { @@ -227,9 +225,9 @@ export function apply(ctx: Context, config: Config): void { if (!tracked(exec.name)) return undefined const canonical = canonicalize(exec.arguments) const key = JSON.stringify([exec.name, canonical]) - const chain = chains.get(exec.agent.id) + const chain = chains.get(exec.agent) const count = chain !== undefined && chain.key === key ? chain.count + 1 : 1 - chains.set(exec.agent.id, { key, count }) + chains.set(exec.agent, { key, count }) if (!thresholdSet.has(count)) return undefined const text = count === thresholds[0] ? GENTLE_REMINDER @@ -259,12 +257,7 @@ export function apply(ctx: Context, config: Config): void { // loop. Pure reset hook: always delegates (attaching nothing, vetoing // nothing). ctx.on('agent/prompt-submit', (agent, _content, _source, next): Promise => { - chains.delete(agent.id) + chains.delete(agent) return next() }) - - // Drop state when an agent goes away, bounding the map over harness lifetime. - ctx.on('agent/status', (agent, status) => { - if (status === 'disposed') chains.delete(agent.id) - }) } diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..9538166fc4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' @@ -57,7 +58,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +79,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +101,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +164,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +180,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +196,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +216,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' }) + const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +236,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +257,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +280,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +296,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +318,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +349,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..2f0a2666c9 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -95,7 +96,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +119,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +144,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +189,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +210,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +234,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +258,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -294,8 +295,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: AgentId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -330,7 +331,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() @@ -359,7 +360,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +386,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..16c48aa149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -72,7 +73,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +89,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +105,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +135,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +160,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +176,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +193,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -208,9 +209,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -224,9 +225,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -240,7 +241,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +255,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -270,7 +271,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -283,7 +284,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +299,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +314,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +343,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +358,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +373,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +394,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +411,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +431,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +449,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -466,7 +467,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(path, adapter) // A later listener that blocks every prompt (registered AFTER the bridge). - const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') + const { SessionId: AId } = await import('@deepseek-ai/dsh-session') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) @@ -492,7 +493,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +515,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +534,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +558,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +574,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +614,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +650,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +671,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +692,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..4aa678c36e 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -82,7 +83,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +108,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +136,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +162,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +191,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..75b04d4c57 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -52,7 +53,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +65,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +79,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +97,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +112,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +126,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +139,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +152,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +165,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +177,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +188,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +201,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +224,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +247,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +260,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +274,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +286,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +299,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +312,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +328,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +341,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +353,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +370,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +406,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +420,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +433,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +449,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +463,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +474,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +488,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +503,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +519,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +531,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +554,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 5222906a2d..1e82ef85b0 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -37,8 +37,8 @@ import { type SessionNotification, type StopReason, } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent' import { buildChildEnv, disposeChildProcess, spawnFailure } from '@deepseek-ai/dsh-subagent-subprocess' @@ -190,7 +190,7 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = AgentId(randomUUID()) + const id = SessionId(randomUUID()) if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..d1b9065c60 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(Spawn, { providerName: 'spawn' }) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index e089cebe5f..360098e369 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -2,10 +2,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -43,7 +44,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index f6de7200cf..965d9c8e78 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -9,7 +9,7 @@ import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' -import { AgentId, type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' @@ -104,7 +104,7 @@ export async function startInProcessRun( throw new SubagentDepthError(childDepth, request.maxDepth) } - const childId = AgentId(randomUUID()) + const childId = SessionId(randomUUID()) const seedLength = options.seed?.length ?? 0 const parentHeader = parent.session.header const parentModel = parent.options.model @@ -127,8 +127,7 @@ export async function startInProcessRun( const flags = { cancelled: false } const handle = await parent.ctx.agents.create({ - agentId: childId, - sessionId: SessionId(randomUUID()), + sessionId: childId, meta: { ...parentHeader.cwd !== undefined ? { cwd: parentHeader.cwd } : {}, parentSession: parentHeader.id, diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index 3e23123622..93da5b1d51 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type ContentBlock, type GenerateOptions } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -68,7 +69,7 @@ async function setup(script: Script, options: SetupOptions = {}) { start: (request: SubagentStartRequest) => startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } @@ -333,7 +334,7 @@ describe('in-process structured output', () => { await expect(ctx.subagents.start('spawn', structuredRequest(parent, { outputSchema: { type: 'object', oneOf: [] } as unknown as StructuredOutputSchema, }))).rejects.toThrow(/unsupported output schema/) - expect(ctx.agents.get(AgentId('parent'))).toBeDefined() + expect(ctx.agents.get(SessionId('parent'))).toBeDefined() }) it('a schema carrying non-JSON values fails as OutputSchemaError at the validation boundary', async () => { diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..aa0f946c89 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -24,7 +25,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..b156f951ed 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { spawnHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the in-process spawn backend: a REAL parent agent delegates @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..06aa40ca9f 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -5,7 +5,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -36,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -237,7 +238,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('x')]) // A parent WITH a cwd (config agents have none, so create one explicitly). const parentHandle = await ctx.agents.create({ - agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, agentOptions: { model: 'mock' }, @@ -254,7 +254,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('explicit model child')]) // A parent with NO model (its own turns would need one supplied per-request). const parentHandle = await ctx.agents.create({ - agentId: AgentId('modelless-parent'), sessionId: SessionId('modelless-parent-session'), agentOptions: {}, }) @@ -318,7 +317,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +348,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -442,7 +441,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([]) // A handle-owned parent we can dispose (config agents dispose with the loop fiber). const parentHandle = await ctx.agents.create({ - agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), agentOptions: { model: 'mock' }, }) @@ -465,7 +463,6 @@ describe('dsh-subagent-spawn', () => { it('parent disposal during the child setup transaction prevents every publication notification', async () => { const { ctx } = await setup([]) const parentHandle = await ctx.agents.create({ - agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), agentOptions: { model: 'mock' }, }) diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 4635de9697..e885c16469 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -18,7 +18,8 @@ import type { Scoped } from '@deepseek-ai/dsh-scope' import { assertSupportedOutputSchema } from '@deepseek-ai/dsh-tools' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -96,7 +97,7 @@ export interface SubagentRunInfo { /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId } /** Observe-only outcome detail for a settled subagent run. */ @@ -104,7 +105,7 @@ export interface SubagentRunEndInfo { /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 3bdc78569a..8d360b1182 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -6,8 +6,9 @@ * @module @deepseek-ai/dsh-subagent/types */ -import type { Agent, AgentId, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' /** @@ -147,7 +148,7 @@ export interface SubagentResult { */ export interface SubagentRun { /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ - readonly id: AgentId + readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index 3d10b425ed..ad7dbaafff 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import { HarnessError } from '@deepseek-ai/dsh-llm' import { carrierKeyOf } from '@deepseek-ai/dsh-scope' import SubagentService, { @@ -12,9 +13,10 @@ import SubagentService, { type SubagentRun, type SubagentStartRequest, } from '@deepseek-ai/dsh-subagent' +import { SessionId } from '@deepseek-ai/dsh-session' function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } const ALL_CAPS: SubagentCapabilities = { outputSchema: true, depthLimit: true, toolFilter: true, persona: true } @@ -45,7 +47,7 @@ class StubProvider implements SubagentProvider { async start(request: SubagentStartRequest): Promise { this.startCount += 1 return { - id: AgentId(`child:${this.name}:${request.parent.id}`), + id: SessionId(`child:${this.name}:${request.parent.id}`), result: Promise.resolve(this.outcome), async dispose() {}, } @@ -141,7 +143,7 @@ describe('SubagentService', () => { const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: AgentId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -190,7 +192,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: AgentId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 5830513cf4..79df080657 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -4,10 +4,12 @@ import Loader from '@cordisjs/plugin-loader' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService from '@deepseek-ai/dsh-subagent' import * as mock from '@deepseek-ai/dsh-subagent-mock' import * as tool from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real @@ -20,7 +22,7 @@ import * as tool from '../src/index.ts' /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ function fakeAgent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } async function setup(toolConfig: tool.Config, mockConfig: Partial = {}) { @@ -114,7 +116,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('weird-child'), + id: SessionId('weird-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -141,7 +143,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture-child'), + id: SessionId('capture-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -170,7 +172,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('bare-child'), + id: SessionId('bare-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -297,7 +299,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -319,7 +321,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -350,7 +352,7 @@ describe('dsh-tool-subagent', () => { resolveResult({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('spy-child'), + id: SessionId('spy-child'), result, dispose: async () => {}, } @@ -442,7 +444,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture2-child'), + id: SessionId('capture2-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -499,7 +501,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture3-child'), + id: SessionId('capture3-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -528,7 +530,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture4-child'), + id: SessionId('capture4-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index abc1a6c5e9..bf7bcbe2fb 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -13,8 +13,8 @@ import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -65,7 +65,7 @@ class MockSubagentProvider implements SubagentProvider { // A deterministic child id derived from the parent — no clock/random (both // banned in deterministic paths here, and unnecessary for a scripted run). - const id = AgentId(`mock-subagent:${this.name}:${request.parent.id}`) + const id = SessionId(`mock-subagent:${this.name}:${request.parent.id}`) const resultFor = (): SubagentResult => ({ output, diff --git a/packages/support/subagent-mock/tests/subagent-mock.spec.ts b/packages/support/subagent-mock/tests/subagent-mock.spec.ts index 7fd93c62bc..b5e7180782 100644 --- a/packages/support/subagent-mock/tests/subagent-mock.spec.ts +++ b/packages/support/subagent-mock/tests/subagent-mock.spec.ts @@ -1,13 +1,15 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import * as mock from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent — the mock provider only reads `parent.id`. */ function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } function baseRequest(over: Partial = {}): SubagentStartRequest { diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..8376a70425 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -64,7 +65,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +93,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/todo/tool-todo/tests/tool-todo.spec.ts b/packages/todo/tool-todo/tests/tool-todo.spec.ts index 86e8814633..b426b6760c 100644 --- a/packages/todo/tool-todo/tests/tool-todo.spec.ts +++ b/packages/todo/tool-todo/tests/tool-todo.spec.ts @@ -6,7 +6,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { TodoItem } from '@deepseek-ai/dsh-session' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import * as tool from '../src/index.ts' /** @@ -20,7 +21,7 @@ import * as tool from '../src/index.ts' /** A parent Agent backed by a real Session — the tool reads `agent.session`. */ function agentWithSession(id = 'parent-1'): Agent & { session: Session } { const session = new Session(SessionId(id)) - return { id: AgentId(id), session } as unknown as Agent & { session: Session } + return { id: SessionId(id), session } as unknown as Agent & { session: Session } } async function setup(): Promise { diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..e795c7e177 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -72,7 +72,6 @@ import { import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' @@ -686,7 +685,6 @@ export function apply(ctx: Context, config: AcpConfig): void { validateMcpServers(params) const sessionId = SessionId(randomUUID()) const handle = await agents.create({ - agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), @@ -757,7 +755,6 @@ export function apply(ctx: Context, config: AcpConfig): void { } } const handle = await agents.resume({ - agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), }) diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index ed035aaf80..36846ac728 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -4,9 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import ApprovalService, { type ApprovalRequest } from '@deepseek-ai/dsh-user-approval' import { makeBridgeHarness, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The bridge's `approval/request` answerer: an ask for an agent the bridge @@ -31,7 +33,7 @@ describe('acp bridge — approval answerer', () => { ): Promise<{ agent: Agent; request: ApprovalRequest }> { await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = h.ctx.agents.get(AgentId(sessionId)) + const agent = h.ctx.agents.get(SessionId(sessionId)) if (agent === undefined) throw new Error('newSession created no agent') // In production an ask always fires mid-turn (tool execution); open one so // request()'s turn-enclosure precondition holds for the direct drive below. diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index be05a09644..7e780348ba 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * End-to-end bridge specs over an in-memory transport: a real @@ -98,7 +98,7 @@ describe('acp bridge', () => { required: [], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') const toolResultBlock = toolResult?.type === 'tool/result' ? toolResult.data.content[0] : undefined const toolResultText = toolResultBlock?.type === 'text' ? toolResultBlock.text : undefined expect(toolResultText).toBe('{"answers":[{"id":"language","selected":["Python"]}]}') @@ -127,7 +127,7 @@ describe('acp bridge', () => { required: ['custom'], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') expect(JSON.stringify(toolResult)).toContain('apollo') }) @@ -136,7 +136,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const result = await harness.ctx.userInteraction.ask({ agent, @@ -167,7 +167,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: 'TypeScript', custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -184,7 +184,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: ['Tests', 'Docs'] } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -201,7 +201,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) @@ -225,7 +225,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const alreadyAborted = new AbortController() alreadyAborted.abort() @@ -265,8 +265,8 @@ describe('acp bridge', () => { expect(b.sessionId).toBeTruthy() expect(a.sessionId).not.toBe(b.sessionId) // Both agents are live and independently registered. - expect(harness.ctx.agents.get(AgentId(a.sessionId))).toBeDefined() - expect(harness.ctx.agents.get(AgentId(b.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(a.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(b.sessionId))).toBeDefined() }) it('rejects a non-absolute cwd but accepts any absolute cwd (per-session workspace)', async () => { @@ -281,7 +281,7 @@ describe('acp bridge', () => { const res = await harness.client.newSession({ cwd: '/tmp', mcpServers: [] }) expect(res.sessionId).toBeTruthy() // The session header records that cwd, so its bash tools run there. - expect(harness.ctx.agents.get(AgentId(res.sessionId))!.session.header.cwd).toBe('/tmp') + expect(harness.ctx.agents.get(SessionId(res.sessionId))!.session.header.cwd).toBe('/tmp') }) it('rejects non-empty additionalDirectories', async () => { @@ -321,7 +321,7 @@ describe('acp bridge', () => { ], }) expect(result.stopReason).toBe('end_turn') - const user = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'user/message') + const user = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'user/message') expect(JSON.stringify(user)).toContain('resource_link') }) diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..b5d98c0881 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse } from './harness.ts' describe('acp bridge — disposal & HMR safety', () => { @@ -17,7 +16,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) @@ -62,10 +61,10 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeDefined() await harness.acpFiber.dispose() // tear down ONLY the bridge - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -92,7 +91,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. The prompt RPC will never // return (its transport is severed), so do not await it. void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) @@ -115,7 +114,7 @@ describe('acp bridge — disposal & HMR safety', () => { // and its session removed from the store, not merely idled (the old // behavior). The services live on the root ctx, so they survive this. await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -128,7 +127,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -145,7 +144,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const session = harness.ctx.agents.get(AgentId(sessionId))!.session + const session = harness.ctx.agents.get(SessionId(sessionId))!.session await harness.ctx.fiber.dispose() const before = harness.updates.length @@ -169,12 +168,12 @@ describe('acp bridge — disposal & HMR safety', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) - const liveEvents = harness.ctx.agents.get(AgentId(sessionId))!.session.events.length + const liveEvents = harness.ctx.agents.get(SessionId(sessionId))!.session.events.length expect(liveEvents).toBeGreaterThan(0) // Tear down JUST the bridge (the AgentHandle dispose runs to quiescence). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // Re-load the session from disk: every live event (incl. the closing // turn/end) was flushed before the session was detached. @@ -201,7 +200,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -211,7 +210,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose JUST the bridge: a fiber unload that must STILL honor the ordered // teardown (the composite effect runs its disposer chain as a unit). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // The loop's own `turn/end {disposed}` is on disk (re-load: the world, not // self-report) — NOT a crash-recovery `interrupted` substitute. @@ -230,21 +229,21 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, }) - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBe(handleA.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) await handleA.dispose() // A is gone — unregistered AND its session removed from the store. - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined() expect(handleA.agent.status).toBe('disposed') // B is wholly unaffected. - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) expect(harness.ctx.sessions.get(SessionId('sib-b'))).toBeDefined() expect(handleB.agent.status).not.toBe('disposed') await harness.dispose() @@ -262,7 +261,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -270,7 +269,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose: the throwing listener must NOT break the chain before detach. await handle.dispose() - expect(harness.ctx.agents.get(AgentId('guard-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('guard-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeUndefined() // detach still ran await harness.dispose() }) @@ -283,7 +282,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the @@ -313,7 +312,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Release the flush; both resolve together and the session is gone. releaseFlush() await Promise.all([first, second]) - expect(harness.ctx.agents.get(AgentId('conc-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('conc-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('conc-a'))).toBeUndefined() await harness.dispose() }) diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..329016a69e 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts' @@ -27,7 +26,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index 2fbc95b3d9..efc9399c75 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' /** Concatenate the text of all agent_message_chunk updates. */ @@ -194,7 +193,7 @@ describe('acp bridge — session/load replay', () => { release() // resume() finishes AFTER teardown expect(await loadResult).toBe('rejected') // No live agent was installed for the closed connection. - expect(loader.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId(sessionId))).toBeUndefined() }) it('rejects load when the requested cwd does not match the persisted session cwd', async () => { @@ -215,11 +214,11 @@ describe('acp bridge — session/load replay', () => { await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) await expect(loader.client.loadSession({ sessionId: 'elsewhere', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/cwd mismatch/) - expect(loader.ctx.agents.get(AgentId('elsewhere'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('elsewhere'))).toBeUndefined() const res = await loader.client.loadSession({ sessionId: 'elsewhere', cwd: `${otherCwd}/.`, mcpServers: [] }) expect(res).toBeDefined() - expect(loader.ctx.agents.get(AgentId('elsewhere'))!.session.header.cwd).toBe(otherCwd) + expect(loader.ctx.agents.get(SessionId('elsewhere'))!.session.header.cwd).toBe(otherCwd) }) it('rejects load for a non-absolute cwd (still required to be absolute)', async () => { @@ -254,7 +253,7 @@ describe('acp bridge — session/load replay', () => { // Rejected BEFORE resume (metadata-only check) — no agent was registered, so // the id is not wedged: a later attempt hits the same clean rejection, not a // duplicate-registration error. - expect(loader.ctx.agents.get(AgentId('legacy'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('legacy'))).toBeUndefined() await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/no absolute persisted cwd/) }) diff --git a/packages/ui/acp/tests/multi-session.spec.ts b/packages/ui/acp/tests/multi-session.spec.ts index ca11934046..0881fe4199 100644 --- a/packages/ui/acp/tests/multi-session.spec.ts +++ b/packages/ui/acp/tests/multi-session.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Text of the agent_message_chunk updates scoped to one session id. */ function messageTextFor(updates: { sessionId?: string; update: CapturedUpdate }[], sessionId: string): string { @@ -102,8 +102,8 @@ describe('acp bridge — RFC 011 multi-session isolation', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId - const agentA = harness.ctx.agents.get(AgentId(a))! - const agentB = harness.ctx.agents.get(AgentId(b))! + const agentA = harness.ctx.agents.get(SessionId(a))! + const agentB = harness.ctx.agents.get(SessionId(b))! // Wait deterministically for BOTH agents to enter `running` (not a fixed // sleep — agent startup latency is unbounded on a loaded worker). diff --git a/packages/ui/acp/tests/turns.spec.ts b/packages/ui/acp/tests/turns.spec.ts index f559ca36d9..000b80336d 100644 --- a/packages/ui/acp/tests/turns.spec.ts +++ b/packages/ui/acp/tests/turns.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { errorResponse, @@ -13,6 +12,7 @@ import { toolCallResponse, type BridgeHarness, } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Boilerplate: initialize + create one session, returning its id. */ async function newSession(h: BridgeHarness, clientCapabilities: Record = {}): Promise { @@ -279,7 +279,7 @@ describe('acp bridge — turn outcomes', () => { // OWN turn with the real model answer. harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] }) const sessionId = await newSession(harness) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // On the queued prompt, synchronously inject a one-shot context turn (idle // inject writes turn/start{injection} → context/message → turn/end). Fire // once so it lands between install and the prompt turn. @@ -335,7 +335,7 @@ describe('acp bridge — turn outcomes', () => { await harness.client.cancel({ sessionId }) const res = await promptDone expect(res.stopReason).toBe('cancelled') - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await agent.whenIdle() // At most ONE turn ran (the cancelled one) — the cancel cleared the queue, so // no second turn was batched or leaked. (A best-effort abort that left queued diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..4dbfeb0fa2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -16,7 +16,6 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -255,7 +254,6 @@ export class HarnessSdkServer { private async createSession(sessionId: string): Promise { const handle = await this.ctx.agents.create({ - agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, agentOptions: { model: this.model }, diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..9260a59aae 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -5,7 +5,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' +import { type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -135,7 +136,6 @@ describe('HarnessSdkServer', () => { expect(llmServer.requests).toHaveLength(2) const orphanHandle = await ctx.agents.create({ - agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, agentOptions: { model: 'dsagent-model' }, @@ -170,8 +170,8 @@ describe('HarnessSdkServer', () => { } as unknown as Agent const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) } const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) } - const create = vi.fn(async (options: { agentId: AgentId }) => - String(options.agentId) === 'main' ? mainHandle : otherHandle) + const create = vi.fn(async (options: { sessionId: SessionId }) => + String(options.sessionId) === 'main' ? mainHandle : otherHandle) const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, @@ -263,20 +263,18 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, transport) const parentHandle = await ctx.agents.create({ - agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) const handle = await ctx.agents.create({ - agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', - id: AgentId('child-agent'), + id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) @@ -285,7 +283,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'spawn', - agentId: 'child-agent', + agentId: 'child-session', parentSessionId: 'main', childSessionId: 'child-session', status: 'ok', @@ -311,19 +309,16 @@ describe('HarnessSdkServer', () => { let failedHandle: AgentHandle | undefined try { parentHandle = await ctx.agents.create({ - agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) handle = await ctx.agents.create({ - agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ - agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -333,18 +328,18 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('fallback-child-agent'), + id: SessionId('fallback-child-session'), stopReason: 'max-tokens', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('failed-child-agent'), + id: SessionId('failed-child-session'), stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('missing-child-agent'), + id: SessionId('missing-child-agent'), stopReason: 'error', }) @@ -352,7 +347,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'fallback-child-agent', + agentId: 'fallback-child-session', parentSessionId: 'fallback-parent', childSessionId: 'fallback-child-session', status: 'error', @@ -364,7 +359,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'failed-child-agent', + agentId: 'failed-child-session', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..82da64cd81 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,11 +11,11 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating one agent under the `main` config label from this app's `model`, with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | -| `stdio-chat` (in-package module) | the readline UI, bound to the `main` agent | +| `stdio-chat` (in-package module) | the readline UI, holding the app-owned agent object directly and rendering it as `main` | `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. @@ -25,14 +25,14 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| -| `model` | (required) | the pre-created `main` agent's model | +| `model` | (required) | the pre-created agent's model | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-agent` was started. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..f01c48a615 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -3,11 +3,11 @@ * @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster a terminal * chat needs — a console logger, the readline UI (the in-package `stdio-chat` * module), JSONL session - * persistence, and a pre-created `main` agent the UI drives. + * persistence, and one pre-created agent the UI drives under its `main` label. * * The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the - * console (stdout is just the terminal) and always pre-creates the `main` agent - * the readline UI sends to. The leaf supplies the swappable backends (the LLM + * console (stdout is just the terminal) and always pre-creates one agent the + * readline UI labels `main`. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence * root, welcome banner). @@ -41,7 +41,6 @@ import type { Context } from 'cordis' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import * as agentCore from '@deepseek-ai/dsh-agent-core' @@ -54,7 +53,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,7 +62,7 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -78,7 +77,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -103,9 +102,9 @@ export const Config: z = z.object({ /** * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating the `main` agent from this - * app's `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI bound to `main`. The `hmr` dev-reload plugin is + * (infra), then the agent-core bundle pre-creating one agent from this app's + * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL + * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { @@ -115,7 +114,7 @@ export function apply(ctx: Context, config: Config): void { ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ - id: AgentId('main'), + id: 'main', model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, @@ -125,5 +124,5 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 8e3c1f467b..cb9ce0bc10 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -19,7 +19,7 @@ import { createInterface } from 'node:readline' import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import { UserInteractionError, type AskUserQuestionAnswer, @@ -36,15 +36,10 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - // TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the - // precreated `main` agent; remove configurability and its config-only test. - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - agent: z.string().default('main'), }) /** @@ -98,23 +93,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Loader validation, so it must be self-contained rather than trusting the // cast — `config.welcome as string` would otherwise be `undefined` on `{}`. const welcome = config.welcome ?? 'ready.' - const agentId = AgentId(config.agent ?? 'main') const { input, output, exit } = runtime - // Render label lookup: the `turn/start` session event carries only the turn - // number, so to print the short agent id (`[main turn 1]`) we map the - // session's id to its agent's id. The session id is not reliably the agent id - // (a session can be created with an explicit/client-supplied id), so build the - // map from `agent/created` rather than parsing the id string. Seed from the - // registry's current agents first: an agent registered before this plugin - // installed (e.g. the pre-created `main` agent, or any agent surviving an HMR - // reload of just this fiber) already fired its `agent/created`, so the live - // listener alone would miss it and its turns would fall back to the raw - // session id. - const labelBySession = new Map() - for (const agent of ctx.agents.list()) labelBySession.set(agent.session.header.id, agent.id) - ctx.on('agent/created', (agent) => { labelBySession.set(agent.session.header.id, agent.id) }) - ctx.on('agent/disposed', (agent) => { labelBySession.delete(agent.session.header.id) }) + // This app owns exactly one pre-created agent. Hold the live object directly: + // its per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) + ctx.on('agent/disposed', (agent) => { + if (target === agent) target = undefined + }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -136,7 +124,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt output.write(chunk.text) } } else if (event.type === 'turn/start') { - const label = labelBySession.get(session.header.id) ?? session.header.id + const label = target?.session === session ? 'main' : session.id output.write(`\n[${label} turn ${event.data.turn}] `) } else if (event.type === 'turn/end') { if (inReasoning) output.write('\x1B[0m') @@ -187,7 +175,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Work submitted: wait until a turn has run and the agent is idle. if (submittedWork) { if (!sawRunning) return - const agent = ctx.agents.get(agentId) + const agent = target if (agent && agent.status !== 'idle') return // a turn is still running } // Let any final output flush, then exit. The handle is tracked so the @@ -201,7 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const disposeStatusListener = ctx.on('agent/status', (subject, status) => { - if (subject.id !== agentId) return + if (subject !== target) return if (status === 'running') sawRunning = true if (status === 'idle') maybeExit() }) @@ -354,9 +342,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return - const agent = ctx.agents.get(agentId) + const agent = target if (!agent) { - ctx.logger.error('ui-stdio: agent "%s" is not running', agentId) + ctx.logger.error('ui-stdio: main agent is not running') return } submittedWork = true diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index a958c435c1..6116aa356f 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,7 +16,7 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its label map from the registry at install; this suite only + // The UI seeds its target object from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. agents: { list: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..5c5c0d2667 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -4,7 +4,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as stdioAgent from '../src/index.ts' @@ -82,9 +83,12 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() - // The pre-created `main` agent the UI drives. - const agent = ctx.get('agents')?.get(AgentId('main')) + // The sole pre-created agent the UI drives. `main` is its stable config + // label; each fresh process mints a durable combined agent/session id. + const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) await ctx.fiber.dispose() }) @@ -99,7 +103,7 @@ describe('dsh-stdio-agent app', () => { stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) @@ -116,7 +120,7 @@ describe('dsh-stdio-agent app', () => { it('forwards resumeSessionId onto the pre-created agent when set', async () => { // A resume id defers agent creation until persistence loads; with no backing - // session the resume is contained + logged, so no `main` agent registers — + // session the resume is contained + logged, so no agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ model: 'mock', @@ -125,7 +129,7 @@ describe('dsh-stdio-agent app', () => { resumeSessionId: 'no-such-session', skills: await isolatedSkillsConfig(), }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.list()).toEqual([]) await ctx.fiber.dispose() }) diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 93683d0768..69ca5f8837 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -57,17 +57,16 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { status, sent, steered, - // A minimal session stub: the UI reads only `session.header.id` (to map the - // session back to its agent id for the turn-boundary label). - session: { header: { id: `${id}-session` } }, + // A minimal session stub with the agent's shared durable identity. + session: { id, header: { id } }, send: (content: ContentBlock[]) => void sent.push(content), steer: (content: ContentBlock[]) => void steered.push(content), } as never } /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ -function makeSession(agentId: string): Session { - return { header: { id: `${agentId}-session` } } as Session +function makeSession(id: string): Session { + return { id, header: { id } } as Session } /** An `assistant/chunk` session event carrying one raw stream chunk. */ @@ -75,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', agent: 'main' } +const CONFIG: Config = { welcome: 'hi there' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -99,12 +98,11 @@ describe('createStdioChat rendering', () => { expect(out.text()).toBe('hi there\n> ') }) - it('falls back to default welcome/agent when called with empty config', async () => { + it('falls back to the default welcome when called with empty config', async () => { // createStdioChat is exported and may be driven directly (bypassing the - // Loader's schemastery validation), so it must default welcome/agent itself. + // Loader's schemastery validation), so it must default the welcome itself. const { out } = await setup({}) expect(out.text()).toBe('ready.\n> ') - // And it drives the default agent id 'main'. }) it('detects readline terminal mode from both stream TTY flags', async () => { @@ -156,9 +154,9 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created populates the session-id → agent-id label map. + // agent/created supplies the app-owned target object. ctx.emit('agent/created', agent) - const session = makeSession('main') + const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, } as SessionEvent) @@ -169,21 +167,20 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\n> ') }) - it('falls back to the session id as the label when no agent is mapped', async () => { + it('uses the session id as the label for a non-target session', async () => { const { ctx, out } = await setup() - // No agent/created emitted, so the label map is empty — the header id shows. + // No target exists, so the event's durable identity is the label. ctx.emit('session/event', makeSession('orphan'), { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[orphan-session turn 1] ') + expect(out.text()).toContain('[orphan turn 1] ') }) - it('seeds labels for agents already registered before the UI installs', async () => { + it('uses an agent already registered before the UI installs as its target', async () => { // The pre-created `main` agent (and any agent surviving an HMR reload of just // this fiber) fired its `agent/created` before the UI's listener existed, so // the live listener alone would miss it. Seeding from `ctx.agents.list()` at - // install time is what keeps its turn header showing `[main turn N]` instead - // of the raw session id. + // install time preserves the terminal's fixed `[main turn N]` label. const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -193,7 +190,7 @@ describe('createStdioChat rendering', () => { await ctx.plugin(Object.assign((inner: Context) => { createStdioChat(inner, CONFIG, runtime) }, { inject: ['agents', 'userInteraction'] })) - ctx.emit('session/event', makeSession('main'), { + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 5, trigger: { kind: 'message' } }, } as SessionEvent) expect(out.text()).toContain('[main turn 5] ') @@ -209,17 +206,28 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\x1B[2mmid\x1B[0m') }) - it('drops the label mapping on agent/disposed', async () => { + it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') ctx.emit('agent/created', agent) ctx.emit('agent/disposed', agent) - // After disposal the map no longer resolves the agent id — fall back to the - // session header id. - ctx.emit('session/event', makeSession('main'), { + // After disposal the event belongs to a non-target session, so its durable + // identity is rendered directly. + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[main-session turn 1] ') + expect(out.text()).toContain('[main turn 1] ') + }) + + it('keeps the target when a different agent is disposed', async () => { + const { ctx, out } = await setup() + const target = makeAgent('target') + ctx.emit('agent/created', target) + ctx.emit('agent/disposed', makeAgent('other')) + ctx.emit('session/event', target.session, { + type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, + } as SessionEvent) + expect(out.text()).toContain('[main turn 1] ') }) it('renders tool/call and tool/result session events', async () => { @@ -666,11 +674,11 @@ describe('createStdioChat input', () => { const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: agent "%s" is not running', 'main') + expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the agent named in config, not a hardcoded id', async () => { - const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' }) + it('drives the app-owned agent without a duplicate id config', async () => { + const { ctx, input } = await setup({ welcome: 'w' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') diff --git a/packages/util/brand/README.md b/packages/util/brand/README.md index 8f7943def7..be25edd55e 100644 --- a/packages/util/brand/README.md +++ b/packages/util/brand/README.md @@ -4,7 +4,7 @@ The `Branded` nominal-typing primitive — a tiny, **type-only** package (no ## What `Branded` is -A brand makes structurally-identical strings non-interchangeable at the type level: an `AgentId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. +A brand makes structurally-identical strings non-interchangeable at the type level: a `SessionId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -21,6 +21,6 @@ Construction goes through the per-id factory in the OWNING package (a plain cast ## Policy: brand ids that cross package boundaries -A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), `SessionId` in `dsh-session`, `AgentId` in `dsh-agent`, `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** +A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), the shared agent/session `SessionId` in `dsh-session`, and `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** This package owns ONLY the primitive — no concrete id, no runtime code beyond the (erased) type. Keeping the primitive dependency-free is the point: a capability package can brand its ids without depending on an unrelated package. `dsh-bash`, for example, brands `BashTaskId`/`OwnerToken` by depending on `dsh-brand` alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. diff --git a/packages/util/brand/src/index.ts b/packages/util/brand/src/index.ts index 051ced94b7..d8c28846b3 100644 --- a/packages/util/brand/src/index.ts +++ b/packages/util/brand/src/index.ts @@ -4,15 +4,15 @@ * cross-boundary id. * * A brand makes structurally-identical strings non-interchangeable at the type - * level: an `AgentId` cannot be passed where a `CallId` is expected, even + * level: a `SessionId` cannot be passed where a `CallId` is expected, even * though both are plain strings at runtime. Construction goes through a per-id * factory in the OWNING package (a plain cast inside — zero runtime cost); * comparison, logging, and serialization all behave as ordinary strings. * * Policy: a package brands the ids it owns — `CallId` in dsh-llm (tool-call - * correlation), `SessionId` in dsh-session, `AgentId` in dsh-agent, - * `BashTaskId`/`OwnerToken` in dsh-bash. Branding is for ids that cross package - * boundaries and could plausibly be confused; not every string needs a brand. + * correlation), and `SessionId` in dsh-session; `BashTaskId`/`OwnerToken` live + * in dsh-bash. Branding is for ids that cross package boundaries and could + * plausibly be confused; not every string needs a brand. * This package owns ONLY the primitive — no concrete id, no runtime code beyond * the (erased) type — so the brand vocabulary stays dependency-free and a * package can brand its ids without depending on an unrelated capability diff --git a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts index 0585889617..ac7112a0f0 100644 --- a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts +++ b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts @@ -4,7 +4,6 @@ import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { WorkflowRunId, WorkflowService } from '@deepseek-ai/dsh-workflow' import type { WorkflowResult, WorkflowRun, WorkflowStartRequest } from '@deepseek-ai/dsh-workflow' @@ -12,6 +11,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import * as toolWorkflow from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A controllable engine standing in behind ctx.workflows (the tool's only seam). */ class StubEngine extends WorkflowService { @@ -51,7 +51,7 @@ async function setup(config?: { toolName?: string; maxResultChars?: number }) { await ctx.plugin(StubEngine) await ctx.plugin(toolWorkflow, config ?? {}) const engine = ctx.workflows as StubEngine - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent return { ctx, engine, parent } } @@ -237,7 +237,7 @@ describe('dsh-tool-workflow', () => { await ctx.plugin(SubagentService) await ctx.plugin(WorkerWorkflowEngine, { disposeGraceMs: 30 }) await ctx.plugin(toolWorkflow, {}) - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent const controller = new AbortController() const pending = execute(ctx, { script: 'await new Promise(() => {})\nreturn 1', diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..7dbdccbb43 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -38,8 +38,8 @@ */ import * as vm from 'node:vm' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import { assertSupportedOutputSchema, OutputSchemaError } from '@deepseek-ai/dsh-tools' import type { StructuredOutputSchema } from '@deepseek-ai/dsh-tools' import { isFatalWorkflowError, WorkflowError } from '@deepseek-ai/dsh-workflow' @@ -319,7 +319,7 @@ export class WorkflowExecution { await run.dispose() throw this.cancelledError() } - const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: AgentId(run.id) } + const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: SessionId(run.id) } this.observer.agentStart(info) try { let result diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..2e13ddcb8b 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -73,7 +74,7 @@ return { prose, verdict: judged.verdict, confidence: judged.confidence }`, // Both children were disposed to quiescence — no live child agents remain. expect(childIds.length).toBe(2) for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } }) diff --git a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts index 7f34396d52..673a43ee0a 100644 --- a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts @@ -6,10 +6,10 @@ import { expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' // A fresh thread compiles the source runtime. Leave contention headroom on // shared CI runners without weakening any engine-level timeout assertion. @@ -19,7 +19,7 @@ it('runs the default config through the source worker', async () => { const ctx = new Context() const subagents = await ctx.plugin(SubagentService) const engine = await ctx.plugin(WorkerWorkflowEngine, {}) - const parent = { id: AgentId('workflow-compat-parent'), options: {} } as unknown as Agent + const parent = { id: SessionId('workflow-compat-parent'), options: {} } as unknown as Agent try { const run = ctx.workflows.start({ script: 'return 6 * 7', diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..169d80cda7 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -62,7 +63,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key it('runs a two-phase script in a worker thread over real children, one through the structured runtime', async () => { ctx = await harness() const parentHandle = await ctx.agents.create({ - agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, agentOptions: { model: 'deepseek-v4-flash' }, }) @@ -95,7 +95,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key expect(childIds.length).toBe(2) // The children were disposed to quiescence after collection. for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } await parentHandle.dispose() }, 240_000) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..09fb606d69 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -3,17 +3,17 @@ import { fileURLToPath } from 'node:url' import type { Worker } from 'node:worker_threads' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentCapabilities, SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo } from '@deepseek-ai/dsh-workflow' import * as workerEngineModule from '../src/index.ts' import WorkerWorkflowEngine, { HostToWorkerType, WorkerToHostType, type Config } from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent stand-in: the engine only threads it through to the provider. */ function fakeParent(): Agent { - return { id: AgentId('workflow-parent'), options: {} } as unknown as Agent + return { id: SessionId('workflow-parent'), options: {} } as unknown as Agent } // Worker-thread startup is CPU-bound (a fresh thread compiles the runtime on @@ -117,7 +117,7 @@ class StubProvider implements SubagentProvider { } if (request.signal.aborted) throw new Error('child start aborted before publication') return { - id: AgentId(`stub-child-${index}`), + id: SessionId(`stub-child-${index}`), result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -366,7 +366,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('reject-child'), + id: SessionId('reject-child'), result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -400,7 +400,7 @@ describe('dsh-workflow-workerthread', () => { stopReason: 'completed', } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ - id: AgentId('raw-invalid-child'), + id: SessionId('raw-invalid-child'), result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -423,7 +423,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('bad-dispose-child'), + id: SessionId('bad-dispose-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -444,7 +444,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('trap-child'), + id: SessionId('trap-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -771,7 +771,7 @@ describe('dsh-workflow-workerthread', () => { settle({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('signal-only-child'), + id: SessionId('signal-only-child'), result, dispose: () => Promise.resolve(), } @@ -1092,7 +1092,7 @@ describe('dsh-workflow-workerthread', () => { expect(request.signal.reason).toBe('workflow worker gone') ready.resolve({ - id: AgentId('late-ready-child'), + id: SessionId('late-ready-child'), result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1128,7 +1128,7 @@ describe('dsh-workflow-workerthread', () => { handle.cancel('reentered from worker-death signal cleanup') }, { once: true }) return { - id: AgentId('doomed-child'), + id: SessionId('doomed-child'), result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..35ea4fb053 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -7,7 +7,8 @@ */ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Identifies one workflow run. */ export type WorkflowRunId = Branded<'WorkflowRunId'> @@ -145,7 +146,7 @@ export interface WorkflowAgentInfo { /** The phase this agent belongs to (the `phase` option, else the current `phase()` title). */ phase?: string /** The child agent's id on the subagent seam. */ - childId: AgentId + childId: SessionId } /** How one `agent()` call settled: clean result, child failure (script sees `null`), or run cancellation. */ From 61136b22bbfabae49227843f924cc4832a07fe51 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:09:09 +0800 Subject: [PATCH 009/140] refactor: remove UI identity translations --- docs/config-catalog.md | 4 +- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 ++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 -------------- packages/ui/acp/README.md | 4 +- packages/ui/acp/src/index.ts | 52 ++++++++----------- packages/ui/acp/tests/approval.spec.ts | 9 ++-- packages/ui/acp/tests/bridge.spec.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 ++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 20 ++++--- 12 files changed, 100 insertions(+), 110 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..4ae020f0be 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml` ## `@deepseek-ai/dsh-acp` -Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` +Requires: `agents` · `sessionPersistence` · `tools` · `userInteraction` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:246`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..79d7332553 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; subagent creation mints one combined id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. ACP verifies exact `Agent` ownership from the forward session map; JSON-RPC caches only disposable-child parent lineage. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..31a865c068 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -`inject: ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. +`inject: ['agents', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` (forward) with a `WeakMap` reverse map so agent-scoped approval events demultiplex in O(1). Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership: the `approval/request` answerer resolves the owning session through the reverse map and prompts only there. +The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` keyed by the shared agent/session id. Agent-scoped events derive that id from `agent.session.id` and verify the record owns the exact agent object, so a foreign same-id object cannot claim the bridge's session. Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership and prompt only the matching session. ## Session config options diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index e795c7e177..369c8ae166 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,12 +18,11 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by id in `sessions` (forward) with an - * `agent→sessionId` reverse map for O(1) demux of `agent/*` events; every - * `session/event` and `agent/*` event is routed strictly to its owning session - * record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts ride the same ownership - * map: the bridge answers `approval/request` for its own agents over + * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * every `session/event` and `agent/*` event is routed strictly to its owning + * session record, so two sessions streaming at once never interleave their + * `session/update` notifications. Permission prompts use the same identity: the + * bridge answers `approval/request` for its own agents over * `session/request_permission` (see the approval answerer below) — whether a * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. * @@ -106,9 +105,7 @@ export const name = 'acp' // because `initialize` advertises `loadSession: true`. `tools` lets a tool own // how its calls render (`presentCall`/`presentResult`); the bridge looks up the // definition by name and falls back to a generic presentation when absent. -// TODO(acp-session-inject): drop `sessions`; this bridge never reads -// ctx.sessions, and agent/session ownership is already behind ctx.agents. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction'] /** * Build an ACP "invalid params" error whose human detail rides in the message. @@ -268,7 +265,6 @@ export const Config: Schema = Schema.object({ * map keyed by id (RFC 011 multi-session). */ interface SessionRecord { - sessionId: SessionId agent: Agent /** * The owned-agent disposer (from the {@link AgentHandle} the factory returned). @@ -353,15 +349,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // this warn sink so a throwing tool presenter is logged, not propagated. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) - // TODO(derive-acp-session-id): derive an event's id from agent.session and - // verify sessions.get(id)?.agent === agent; then remove this reverse map and - // SessionRecord.sessionId, whose sole read duplicates the same identity. - // Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId - // reverse map so `agent/*` events (which carry only the Agent) demux in O(1). - // The forward record and weak reverse entry are installed together; removing - // the record releases its strong Agent reference, so the WeakMap entry expires. + // Live sessions keyed by their shared agent/session id (RFC 011 multi-session). const sessions = new Map() - const bySession = new WeakMap() // Session ids whose `session/load` is mid-`resume()` (the slot is reserved // before the async resume so a pipelined load/new for the SAME id can't create // two agents). Distinct ids load concurrently; a given id loads once at a time. @@ -382,20 +371,26 @@ export function apply(ctx: Context, config: AcpConfig): void { // `notify` never observes it unset — no undefined guard needed. let conn: AgentSideConnection + /** Return the bridge-owned record for an agent, rejecting same-id impostors. */ + const ownedRecord = (agent: Agent): SessionRecord | undefined => { + const rec = sessions.get(agent.session.id) + return rec?.agent === agent ? rec : undefined + } + userInteraction.registerProvider({ async ask(request: AskUserQuestionRequest): Promise { if (request.agent === undefined) { throw new UserInteractionError('ACP user questions must come from an agent-owned request', 'NO_AGENT') } - const sessionId = bySession.get(request.agent) - if (sessionId === undefined) { + const rec = ownedRecord(request.agent) + if (rec === undefined) { throw new UserInteractionError('ACP user question has no matching session', 'NO_SESSION') } const answers: AskUserQuestionAnswerItem[] = [] for (const question of request.questions) { const options = question.options ?? [] const response = await withAbort(conn.unstable_createElicitation( - elicitationForQuestion(sessionId, question, options), + elicitationForQuestion(rec.agent.session.id, question, options), ), request.signal).catch((error: unknown) => { if (error instanceof UserInteractionError) throw error throw new UserInteractionError('ACP elicitation request failed', 'ASK_FAILED', { cause: error }) @@ -496,7 +491,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const rec = sessions.get(session.header.id) if (rec === undefined) return try { - streamSessionEventUpdate(rec.sessionId, event, notify, rec.presenter, { + streamSessionEventUpdate(rec.agent.session.id, event, notify, rec.presenter, { enabled: rec.terminalEnabled, cwd: session.header.cwd, }, { includeUserMessages: false }) @@ -527,12 +522,12 @@ export function apply(ctx: Context, config: AcpConfig): void { // allow_always is a grant-storage design the approval RFC defers, so the // prompt never offers a durable grant the harness could not honor. ctx.on('approval/request', (req, next) => { - const sessionId = bySession.get(req.agent) + const rec = ownedRecord(req.agent) // The protocol requires `toolCall` (the prompt renders attached to it), so // a request without a callId has nothing to attach to — delegate. - if (sessionId === undefined || req.callId === undefined) return next() + if (rec === undefined || req.callId === undefined) return next() return conn.requestPermission({ - sessionId, + sessionId: rec.agent.session.id, toolCall: { toolCallId: req.callId }, options: [ { optionId: 'allow-once', name: 'Allow once', kind: 'allow_once' }, @@ -639,8 +634,7 @@ export function apply(ctx: Context, config: AcpConfig): void { // turn) leaves the switch pending — it runs no step, so nothing executes // or assembles under a stale value. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { - const sessionId = bySession.get(agent) - const rec = sessionId === undefined ? undefined : sessions.get(sessionId) + const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) return next() }) @@ -699,9 +693,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw internalError('connection closed during session/new') } - bySession.set(handle.agent, sessionId) sessions.set(sessionId, { - sessionId, agent: handle.agent, dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), @@ -773,13 +765,11 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams('connection closed during session/load') } const agent = handle.agent - bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both // the replay below and the post-load live stream) so a later // `initialize` can't desync the call/result of a tool card. const terminalEnabled = terminalOutputCap const record: SessionRecord = { - sessionId, agent, dispose: () => handle.dispose(), presenter: makePresenter(agent), diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index 36846ac728..65679cd905 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -90,9 +90,12 @@ describe('acp bridge — approval answerer', () => { await harness.ctx.plugin(ApprovalService) harness.onPermission = () => ({ outcome: { outcome: 'selected', optionId: 'allow-once' } }) - // Not created through the bridge: no bySession entry, so the answerer must - // call next() — nobody else answers, so the seam fails closed. - const foreign = { session: { events: [{ type: 'turn/start' }], append: () => ({}) } } as unknown as Agent + const { agent } = await ownedAgentRequest(harness) + // Even an impostor that claims the bridge-owned session id must delegate: + // ownership requires the exact Agent object stored in the session record. + const foreign = { + session: { id: agent.session.id, events: [{ type: 'turn/start' }], append: () => ({}) }, + } as unknown as Agent await expect(harness.ctx.approval.request({ agent: foreign, toolName: 'echo', callId: CallId('c') })) .resolves.toBe('unavailable') expect(harness.permissionRequests).toHaveLength(0) diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index 7e780348ba..e7170c380f 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -205,7 +205,8 @@ describe('acp bridge', () => { await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) - await expect(harness.ctx.userInteraction.ask({ agent: { id: 'other' } as typeof agent, questions: [{ id: 'x', question: 'No session?' }] })) + const impostor = { session: { id: agent.session.id } } as typeof agent + await expect(harness.ctx.userInteraction.ask({ agent: impostor, questions: [{ id: 'x', question: 'No session?' }] })) .rejects.toMatchObject({ code: 'NO_SESSION' }) harness.onElicitation = () => ({ action: 'cancel' }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..933023a2d9 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 4dbfeb0fa2..cfa083c394 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,11 +58,6 @@ interface SessionRecord { activePrompt: boolean } -interface SubagentRecord { - childSessionId: string - parentSessionId: string | undefined -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -76,7 +71,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentSessions = new Map() + private readonly subagentParents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,29 +95,22 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache agent → session lineage on creation: by the time `subagent/end` - // fires the child agent may already be disposed and gone from the registry. + // Cache parent lineage on creation: by the time `subagent/end` fires the + // child agent may already be disposed and gone from the registry. The child + // session id needs no cache because it is the shared agent/session id. this.disposers.push(ctx.on('agent/created', (agent) => { - this.subagentSessions.set(String(agent.id), { - childSessionId: String(agent.session.id), - parentSessionId: agent.session.header.parentSession === undefined - ? undefined - : String(agent.session.header.parentSession), - }) + const parentSessionId = agent.session.header.parentSession + if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const rec = this.subagentSessions.get(String(info.id)) const agent = this.ctx.agents.get(info.id) - const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id)) - const parentSessionId = rec?.parentSessionId ?? ( - agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession) - ) - if (childSessionId === undefined) return + const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + this.subagentParents.delete(info.id) this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId }), - childSessionId, + ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }), @@ -195,7 +183,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentSessions.clear() + this.subagentParents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 9260a59aae..433119e046 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,6 +272,9 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + // The backend may dispose the child before publishing its run outcome; + // only the cached parent lineage should be needed at this point. + await handle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), @@ -292,7 +295,6 @@ describe('HarnessSdkServer', () => { }, }) - await handle.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -301,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live agent lineage for uncached subagent end events', async () => { + it('falls back to live lineage and treats the shared id as the child session id', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -365,10 +367,16 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications.some(n => - n.method === 'subagent.finished' - && n.params?.agentId === 'missing-child-agent', - )).toBe(false) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'fork', + agentId: 'missing-child-agent', + childSessionId: 'missing-child-agent', + status: 'error', + stopReason: 'error', + }, + }) await server.shutdown() } finally { From 17c99efcc14c76bbc548f64ec536d95a2dbb25c5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:22:20 +0800 Subject: [PATCH 010/140] fix: complete unified subagent identity --- docs/module-graph.md | 12 ++++-- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 +++++++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 ------------------- packages/subagent/subagent-acp/package.json | 2 + packages/subagent/subagent-acp/src/run.ts | 16 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- packages/subagent/subagent/package.json | 2 + packages/support/subagent-mock/package.json | 2 + packages/workflow/workflow/package.json | 1 + pnpm-lock.yaml | 9 +++++ 13 files changed, 77 insertions(+), 54 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/module-graph.md b/docs/module-graph.md index e4d0b3367d..8ac71b11cc 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -179,6 +179,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -215,6 +216,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -265,6 +267,7 @@ flowchart TD pkg_agent_core --> pkg_tools pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -285,6 +288,7 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm @@ -362,14 +366,14 @@ flowchart TD | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -380,11 +384,11 @@ flowchart TD | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..be1052830a --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/subagent/subagent-acp/package.json b/packages/subagent/subagent-acp/package.json index e73d861a79..4c34ebe3fc 100644 --- a/packages/subagent/subagent-acp/package.json +++ b/packages/subagent/subagent-acp/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-subagent-subprocess": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -35,6 +36,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-subprocess": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1e82ef85b0..1cc220204f 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,7 +23,6 @@ */ import { spawn } from 'node:child_process' -import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,8 +189,6 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = SessionId(randomUUID()) - if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP @@ -260,7 +257,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: string | undefined + let sessionId: SessionId | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -309,7 +306,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + sessionId = SessionId(session.sessionId) if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -321,6 +318,11 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } + // The startup race can fulfill only after newSession assigned the id; this + // guard keeps that cross-closure invariant explicit for TypeScript. + /* v8 ignore next */ + if (sessionId === undefined) throw new Error('ACP child published without a session id') + const runId = sessionId const result: Promise = (async (): Promise => { try { @@ -332,7 +334,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: sessionId as string, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -366,7 +368,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id, + id: runId, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index fb200f3505..5145941526 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -99,7 +99,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } - return { sessionId: randomUUID() } + return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { // No auth methods advertised; nothing to do. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index eed3cfe1ed..115d5c3e97 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -122,8 +122,9 @@ describe('buildChildEnv', () => { describe('dsh-subagent-acp', () => { it('drives a child process to completion and returns its streamed output', async () => { - const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn' }) + const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) + expect(run.id).toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index eb0dbf8da0..cf1ebf9485 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -32,6 +33,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json index 8980cc35d2..528691daef 100644 --- a/packages/support/subagent-mock/package.json +++ b/packages/support/subagent-mock/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -33,6 +34,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", "cordis": "^4.0.0-rc.6" diff --git a/packages/workflow/workflow/package.json b/packages/workflow/workflow/package.json index a6c004d6d0..4d79d672a1 100644 --- a/packages/workflow/workflow/package.json +++ b/packages/workflow/workflow/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d02b4a9ca6..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -827,6 +827,9 @@ importers: '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -852,6 +855,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent @@ -1085,6 +1091,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent From 9ebb40b84b404b3568a53cd6fab1b966e2c82c74 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:28:04 +0800 Subject: [PATCH 011/140] fix: keep SDK subagent notifications local --- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 8 +++++++- packages/ui/jsonrpc/tests/server.spec.ts | 16 +++++----------- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 10521447e0..bb77717e3b 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only disposable-child parent lineage. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 933023a2d9..2324227ff7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index cfa083c394..3c803a6c8c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -104,8 +104,14 @@ export class HarnessSdkServer { })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + const cachedParentSessionId = this.subagentParents.get(info.id) this.subagentParents.delete(info.id) + // This protocol reports LOCAL child sessions, paired with the + // session/created-driven subagent.started notification above. A remote + // provider may use a real remote SessionId for its run, but that session + // does not exist in this harness and therefore has no paired start event. + if (cachedParentSessionId === undefined && agent === undefined) return + const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 433119e046..e7f591b88f 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -303,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and treats the shared id as the child session id', async () => { + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -367,16 +367,10 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications).toContainEqual({ - method: 'subagent.finished', - params: { - provider: 'fork', - agentId: 'missing-child-agent', - childSessionId: 'missing-child-agent', - status: 'error', - stopReason: 'error', - }, - }) + expect(transport.notifications.some(n => + n.method === 'subagent.finished' + && n.params?.agentId === 'missing-child-agent', + )).toBe(false) await server.shutdown() } finally { From 225796c90dc5a6ea9b4afa2a9f4081f9d48606ae Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:32:35 +0800 Subject: [PATCH 012/140] refactor: hide the concrete agent loop --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 26 ++++----- docs/cordis-catalog/services.md | 8 ++- docs/core-data-structures/core.md | 2 +- docs/event-producer-consumer.md | 26 ++++----- .../2026-06-21-subagent-capability-seam.md | 2 +- examples/coding-agent/tests/code-mode.e2e.ts | 6 +- examples/coding-agent/tests/harness.ts | 6 +- examples/coding-agent/tests/resume.e2e.ts | 5 +- examples/cordis-agent/tests/harness.ts | 6 +- .../bash/tool-bash/tests/integration.spec.ts | 8 +-- .../tests/compact-loop-repro.spec.ts | 6 +- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- .../tool-cordis/tests/integration.spec.ts | 6 +- packages/core/README.md | 2 +- packages/core/agent-loop/README.md | 10 ++-- packages/core/agent-loop/src/index.ts | 7 +-- packages/core/agent-loop/tests/agent.spec.ts | 42 +++++++------- packages/core/agent-loop/tests/cancel.spec.ts | 22 +++++--- .../tests/config-session-id.spec.ts | 16 +++--- .../agent-loop/tests/coverage-edges.spec.ts | 16 ++++-- .../agent-loop/tests/interception.spec.ts | 10 ++-- packages/core/agent-loop/tests/loop.spec.ts | 22 +++++--- .../core/agent-loop/tests/properties.spec.ts | 12 ++-- .../tests/request-reconstruction.spec.ts | 10 ++-- packages/core/agent-loop/tests/resume.spec.ts | 24 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 56 ++++++++++--------- .../agent-loop/tests/scope-lifecycle.spec.ts | 8 +-- .../core/agent-loop/tests/tool-order.spec.ts | 6 +- .../core/agent-loop/tests/turn-stop.spec.ts | 6 +- packages/core/agent/src/types.ts | 5 +- .../tests/repeat-tool-guard.spec.ts | 12 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 14 ++--- .../hooks/hooks-codex/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-codex/tests/coverage.spec.ts | 10 ++-- .../todo/tool-todo/tests/integration.spec.ts | 6 +- packages/ui/acp/README.md | 2 +- packages/ui/acp/src/index.ts | 2 +- 40 files changed, 234 insertions(+), 217 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..272191c9c6 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped `ReactLoopAgent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | ### Capability Services diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4ae020f0be..20d90d1e8b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -129,7 +129,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:323`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..32d697f1eb 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:303`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:318`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:592`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:425`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:443`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:347`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:472`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:524`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:368`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:332`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:539`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:557`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:575`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..89a8dc4edb 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -11,15 +11,17 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary ## `ctx.agentLoop` — `AgentLoop` -Concrete ReactLoopAgent factory and driver service. +Concrete agent factory and driver service. ```ts cordis-catalog -create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:336`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index c6b74ed3c0..897b04240b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -248,7 +248,7 @@ The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, ## The agent handle -`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is `ReactLoopAgent` in dsh-agent-loop; nothing outside the loop depends on the implementation. +`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is package-internal to dsh-agent-loop; nothing outside the loop depends on it. Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..ba0d9722b2 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:303`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:318`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:592`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:425`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:443`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:347`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:472`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:524`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:368`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:332`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:539`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:557`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:575`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md index 652eac5522..3c42e83691 100644 --- a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -10,7 +10,7 @@ The harness has a long-deferred seam for **subagents** — an agent delegating w The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee: -- **in-process** — a child `ReactLoopAgent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); +- **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); - **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves); - later: **A2A**, the **Codex app-server**, and the **Claude Code Agent SDK** — each the same out-of-process "start a child, prompt it, stream updates, cancel" shape as the ACP backend. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 22446f0dc3..176b2898d6 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -8,9 +8,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -58,7 +58,7 @@ async function codeModeHarness(cwd: string): Promise { return harness } -function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(harness: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = harness.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..6535e30ac3 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -4,8 +4,8 @@ import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' @@ -70,7 +70,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 48e135ad92..486e32608c 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -41,7 +40,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const first = (await ctx.agents.create({ sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) await ctx.fiber.dispose() @@ -54,7 +53,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const resumed = (await ctx.agents.resume({ resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent expect(resumed.session.id).toBe(SESSION_ID) // The prior user turn is in the rehydrated log before the model is asked. expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET) diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..c9ccd59767 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -3,8 +3,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' @@ -34,7 +34,7 @@ export async function cordisHarness(): Promise { return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 3ab3ae6628..b8275fedba 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 52a2ecd134..c9d9e34b26 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -7,9 +7,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { SurfaceEvent } from '@deepseek-ai/dsh-session' @@ -105,7 +105,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr return { ctx, compact } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..23a8c8e1d0 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -54,9 +54,9 @@ export interface TypeApiEntry { export const SERVICE_API: readonly ServiceApiEntry[] = [ { key: 'agentLoop', - summary: 'Concrete ReactLoopAgent factory and driver service.', + summary: 'Concrete agent factory and driver service.', methods: [ - 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 0d4c6c5c18..25adece9bc 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import { REVERSE_TOOL_CODE } from './helpers.ts' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/README.md b/packages/core/README.md index b132b04d49..d822627136 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | The concrete `Agent` plugin and loop driver | `ctx.agentLoop` | | `agent-core/` | Bundle plugin: the default executor-less/UI-less spine as code | (loads the spine) | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..f5b25c0e25 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -1,6 +1,6 @@ # dsh-agent-loop -THE concrete agent plugin: `ReactLoopAgent` and the loop driver. Implements the `Agent` interface and drives the session/turn/step lifecycle. +THE concrete agent plugin and loop driver. Its package-internal implementation satisfies the `Agent` interface and drives the session/turn/step lifecycle. This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here. @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): Agent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -42,11 +42,9 @@ interface Config { Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. -### Exported concrete class +### Internal concrete driver -- `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. - -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. +The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. The concrete `send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..c9c97fb206 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -12,6 +12,7 @@ import { createScope } from '@deepseek-ai/dsh-scope' import type { Scope } from '@deepseek-ai/dsh-scope' import { agentEvents } from '@deepseek-ai/dsh-agent' import type { + Agent, AgentFactory, AgentHandle, AgentOptions, @@ -32,8 +33,6 @@ import { } from './agent.ts' import type { PreparedReactLoopAgent } from './agent.ts' -export { ReactLoopAgent } from './agent.ts' - /** Fiber states that cannot own or serve a new lifecycle. */ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.UNLOADING, @@ -333,7 +332,7 @@ export interface Config { })[] } -/** Concrete ReactLoopAgent factory and driver service. */ +/** Concrete agent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -389,7 +388,7 @@ export class AgentLoop extends Service implements AgentFactory { * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 56d6489fbe..7969d18200 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -4,11 +4,15 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -21,7 +25,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -32,7 +36,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopAgent['status']): Promise { +function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === expected) { @@ -43,11 +47,11 @@ function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopA }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('ReactLoopAgent', () => { +describe('Agent', () => { it('rejects access before context binding and a second driver for one session', async () => { const ctx = new Context() await ctx.plugin(SessionStore) @@ -70,7 +74,7 @@ describe('ReactLoopAgent', () => { expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') expect(agent.session.id).toBe(agent.id) - expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) + expect(() => { bindReactLoopAgentContext(agent as ReactLoopAgent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() }) @@ -78,14 +82,14 @@ describe('ReactLoopAgent', () => { it('send() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -93,14 +97,14 @@ describe('ReactLoopAgent', () => { it('steer() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.steer([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -108,14 +112,14 @@ describe('ReactLoopAgent', () => { it('inject() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.inject([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -251,7 +255,7 @@ describe('ReactLoopAgent', () => { }) it('disposer is idempotent (double-stop)', async () => { - // Create a bare ReactLoopAgent and start it through the package-internal + // Create a bare Agent and start it through the package-internal // test seam. Then call its disposer twice — the second call hits the // early-return branch. const ctx = new Context() @@ -367,7 +371,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() subscribed while running resolves via done when the agent is then disposed', async () => { // Covers the waiter's disposed arm: whenIdle() queues an internal waiter // while running (not the fast path), then the disposer settles it and chains - // `done` (loop exit), not an eager resolve. A bare ReactLoopAgent + direct + // `done` (loop exit), not an eager resolve. A bare Agent + direct // internal driver disposer keeps the emit synchronous. const ctx = new Context() await ctx.plugin(LlmService) @@ -401,7 +405,7 @@ describe('ReactLoopAgent', () => { // it. Regression for the round-3 whenIdle finding. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -422,7 +426,7 @@ describe('ReactLoopAgent', () => { // only after `done` — i.e. the loop has actually exited. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -430,7 +434,7 @@ describe('ReactLoopAgent', () => { await new Promise(r => setTimeout(r, 30)) let doneResolved = false - void agent.done.then(() => { doneResolved = true }) + void driverDone(agent).then(() => { doneResolved = true }) await fiber.dispose() // sets status disposed, aborts, drains the loop expect(agent.status).toBe('disposed') diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 82b1f6c58c..d88d58a340 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,11 +16,15 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -33,12 +37,12 @@ async function harness(adapter: MockAdapter) { return ctx } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } /** Resolve on the agent's next idle transition (event-based, not status poll). */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -47,7 +51,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { } /** All user-message texts recorded in the log (to assert what actually ran). */ -function userTexts(agent: ReactLoopAgent): string[] { +function userTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .flatMap(e => e.type === 'user/message' ? e.data.content : []) @@ -207,7 +211,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -220,7 +224,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await new Promise(resolve => setTimeout(resolve, 0)) await disposalDone - await agent.done + await driverDone(agent) // No step opened, no model call ran, and the turn closed disposed. expect(streamed).toBe(false) @@ -337,7 +341,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -348,7 +352,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await disposalDone - await agent.done + await driverDone(agent) expect(streamed).toBe(false) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..428581bb58 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,16 +7,16 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) }) -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -57,7 +57,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.list()[0] as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as Agent expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() @@ -76,7 +76,7 @@ describe('config-driven session id', () => { await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.list()[0] as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as Agent expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) @@ -100,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -119,10 +119,10 @@ describe('config-driven session id', () => { ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) // The deferred resume runs on a microtask after the backend is available. - let resumed: ReactLoopAgent | undefined + let resumed: Agent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 4e82e398f1..708cff504b 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -5,11 +5,15 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -22,7 +26,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -33,7 +37,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -213,7 +217,7 @@ describe('disposed vs aborted branching', () => { it('handles dispose during model streaming producing reason "disposed"', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -224,7 +228,7 @@ describe('disposed vs aborted branching', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during hang - await agent.done + await driverDone(agent) // The review-fixes test for 'HIGH: disposed status' already covers // this assertion path. The reason is 'disposed' because isDisposed() is diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 8c95be0d82..bbae57d7f9 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' /** @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -41,11 +41,11 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index c4e49e0fa5..49a7c6a328 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,11 +4,15 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter, persona = '') { const ctx = new Context() await ctx.plugin(LlmService) @@ -26,7 +30,7 @@ async function harness(adapter: MockAdapter, persona = '') { * invoke this right after send(), when the loop hasn't woken yet (status is * still 'idle' synchronously), so polling the current status would lie. */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -37,7 +41,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -175,7 +179,7 @@ describe('agent loop', () => { agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent send(agent, 'hi') await waitForIdle(ctx, agent) @@ -911,7 +915,7 @@ describe('agent loop', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -922,7 +926,7 @@ describe('agent loop', () => { expect(agent.status).toBe('running') await fiber.dispose() - await agent.done + await driverDone(agent) expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() @@ -942,7 +946,7 @@ describe('agent loop', () => { }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent).toBeDefined() expect(agent.id).toBe(agent.session.id) expect(agent.id).toMatch(/^config-agent-session-/) @@ -965,7 +969,7 @@ describe('agent loop', () => { agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent.session.header.cwd).toBe('/work/project') }) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index b3653d6540..a4539587d5 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -17,9 +17,9 @@ import { LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' /** A never-exhausting adapter: every model call returns the same short reply. */ @@ -48,7 +48,7 @@ async function harness() { } /** Resolve on the agent's next transition to idle (event-based, not polled). */ -function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function nextIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -61,7 +61,7 @@ function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { /** Record every status transition for the legal-machine assertion. Returns * the seen list plus a disposer for the listener (per the registry convention). */ -function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; dispose: () => void } { +function recordStatus(ctx: Context, agent: Agent): { seen: string[]; dispose: () => void } { const seen: string[] = [] const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent) seen.push(status) @@ -69,13 +69,13 @@ function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; di return { seen, dispose } } -function userMessageTexts(agent: ReactLoopAgent): string[] { +function userMessageTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .map(e => (e.data as { content: { type: string; text?: string }[] }).content.map(b => b.text ?? '').join('')) } -function turnNumbers(agent: ReactLoopAgent): number[] { +function turnNumbers(agent: Agent): number[] { return agent.session.events .filter(e => e.type === 'turn/start') .map(e => (e.data as { turn: number }).turn) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 202a8f6795..03b9a058ea 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,9 +15,9 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, persona = 'stable base') { @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -229,7 +229,7 @@ describe('request stability across the loop', () => { seed: [...agent.session.events], agentOptions: { model: 'mock' }, }) - const agent2 = handle.agent as ReactLoopAgent + const agent2 = handle.agent send(agent2, 'second') await waitForIdle(ctx2, agent2) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index f5809575ab..630331c39c 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,10 +8,10 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] @@ -51,7 +51,7 @@ async function persistSession(sessionId: SessionId): Promise { return root } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -124,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -140,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -151,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -443,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -457,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -482,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -500,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -510,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -530,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 942199e9eb..2664e38c04 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,13 +4,17 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */ async function harness(adapter: MockAdapter) { @@ -25,7 +29,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -36,7 +40,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -324,7 +328,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -337,7 +341,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(statuses).toEqual(['running', 'disposed']) expect(reasons).toEqual([{ kind: 'disposed' }]) @@ -347,7 +351,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -359,7 +363,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done // must not hang + await driverDone(agent) // must not hang expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw @@ -697,7 +701,7 @@ describe('turn and step boundary recovery', () => { } /** Count turn/step boundary events for balance assertions. */ - function boundaryCounts(agent: ReactLoopAgent) { + function boundaryCounts(agent: Agent) { const e = [...agent.session.events] return { turnStart: e.filter(x => x.type === 'turn/start').length, @@ -871,7 +875,7 @@ describe('turn and step boundary recovery', () => { // balanced with reason disposed (no error event for a disposal). const adapter = new MockAdapter(['hang']) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -882,7 +886,7 @@ describe('turn and step boundary recovery', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during the hanging step - await agent.done + await driverDone(agent) const e = [...agent.session.events] const turnStarts = e.filter(x => x.type === 'turn/start').length @@ -900,7 +904,7 @@ describe('turn and step boundary recovery', () => { // and must preserve reason=disposed rather than rewrite it as a plugin error. const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -919,7 +923,7 @@ describe('turn and step boundary recovery', () => { ctx.on('agent/error', (_a, _t, _s, error) => void errorEmits.push(error)) send(agent, 'go') - await agent.done + await driverDone(agent) const e = [...agent.session.events] // Balanced: one turn/start, one turn/end carrying disposed (NOT error). @@ -1148,7 +1152,7 @@ describe('disposal and cancellation during pre-step assembly', () => { // calls stop() synchronously, setting status=disposed), then release the // block. The loop must check isDisposed() after assembly and end the turn // `disposed` — no LLM call. Don't await fiber.dispose() before releasing - // the blocker: the dispose chain awaits agent.done, which hangs until the + // the blocker: the dispose chain awaits driverDone(agent), which hangs until the // loop unblocks. const adapter = new MockAdapter(['hang']) let releaseAssemble!: () => void @@ -1170,7 +1174,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1183,15 +1187,15 @@ describe('disposal and cancellation during pre-step assembly', () => { await new Promise(r => setTimeout(r, 50)) // Start disposal — stop() sets status=disposed synchronously, then the - // disposer's await agent.done hangs because the loop is blocked in the + // disposer's await driverDone(agent) hangs because the loop is blocked in the // waterfall. Do NOT await yet; release the blocker first. const disposalDone = fiber.dispose() // Now release the blocked waterfall — the loop unblocks, checks - // isDisposed(), and exits, which resolves agent.done and disposalDone. + // isDisposed(), and exits, which resolves driverDone(agent) and disposalDone. releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1226,7 +1230,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1241,7 +1245,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releaseAssemble() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1281,7 +1285,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1296,7 +1300,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releasePreStep() await disposalDone - await agent.done + await driverDone(agent) // After the pre-step seam finishes, the post-seam cancel/dispose check // catches disposal. The step was never opened, no LLM call was made. @@ -1333,7 +1337,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1348,7 +1352,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releasePreStep() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) @@ -1383,7 +1387,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1394,7 +1398,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..57dae254c8 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -8,7 +8,7 @@ import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -28,7 +28,7 @@ async function harness(adapter: MockAdapter = new MockAdapter([textResponse('ok' return (await harnessWithLoop(adapter)).ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -718,7 +718,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let ownerCtx!: Context let creating!: ReturnType - let announced!: ReactLoopAgent + let announced!: Agent const statuses: string[] = [] let scopeDisposed = false let observerSawLive = false @@ -727,7 +727,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('agent/session-start', (agent) => { if (agent.id !== SessionId('session-start-dispose-s')) return - announced = agent as ReactLoopAgent + announced = agent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 1085f01a4c..3b7df63965 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,9 +14,9 @@ import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-ses import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) { @@ -31,7 +31,7 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c7823a2aa5..90bc0f9558 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -23,7 +23,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function send(agent: ReactLoopAgent, text = 'go'): Promise { +function send(agent: Agent, text = 'go'): Promise { agent.send([{ type: 'text', text }]) return agent.whenIdle() } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index b0fb78ad66..edd38e31b6 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -168,9 +168,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' /** * The agent handle — the surface every plugin (UI, hooks, orchestrators) - * programs against. The concrete implementation lives in - * `@deepseek-ai/dsh-agent-loop` (class `ReactLoopAgent`); nothing outside the loop - * package should depend on the implementation. + * programs against. The concrete implementation is package-internal to + * `@deepseek-ai/dsh-agent-loop`; nothing outside that package depends on it. */ export interface Agent { /** The single identity shared with {@link session}. */ diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 9538166fc4..4f7015d8c4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -34,12 +34,12 @@ async function harness(config: Config = {}): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } /** Every `context/message` in the agent's log, flattened to joined text + source for terse assertions. */ -function reminders(agent: ReactLoopAgent): { text: string; source: unknown }[] { +function reminders(agent: Agent): { text: string; source: unknown }[] { return [...agent.session.events] .filter((e): e is SessionEvent<'context/message'> => e.type === 'context/message') .map(e => ({ @@ -255,14 +255,14 @@ describe('chain semantics', () => { ])) // Loop agents are torn down by disposing the scope that created them // (the loop.spec pattern): a child plugin fiber owns `first`. - let first!: ReactLoopAgent + let first!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() - await first.done + await first.whenIdle() const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2f0a2666c9..2c26d64f5a 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -58,7 +58,7 @@ async function harnessWithFiber(configDir: string, adapter: MockAdapter): Promis return { ctx, hooks } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -66,7 +66,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..7997e0fd87 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -42,10 +42,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOp ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -451,8 +451,8 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' + await waitForIdle(ctx, handle.agent) + expect(events(handle.agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) await handle.dispose() }) @@ -616,7 +616,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir const { readFileSync } = await import('node:fs') diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index 4aa678c36e..84e877af97 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -54,14 +54,14 @@ async function harness(dir: string, adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll `predicate` until true or the deadline passes (detached hook effects can't be awaited directly). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 75b04d4c57..018f109a83 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -33,10 +33,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: { stderrS ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -556,7 +556,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) await handle.dispose() diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 8376a70425..ba2df4f6ea 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..9f4e8b7c0b 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-acp -The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own `ReactLoopAgent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. +The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own concrete `Agent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. It is a **client-driver / UI plugin**, the structured analogue of the readline `stdio-chat` plugin — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 369c8ae166..7c97ad715c 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,7 +18,7 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * its own concrete `Agent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning * session record, so two sessions streaming at once never interleave their * `session/update` notifications. Permission prompts use the same identity: the From f85b831bd2cd0d37ca814473abc17ccfb2a6c287 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:41:23 +0800 Subject: [PATCH 013/140] refactor: hide subagent implementation helpers --- ...claude-code-and-codex-subagent-backends.md | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- .../subagent/subagent-inprocess/README.md | 2 +- .../subagent/subagent-inprocess/src/index.ts | 4 +- .../tests/subagent-inprocess.spec.ts | 24 ++---- .../tests/subagent-spawn.spec.ts | 8 +- .../subagent/subagent-subprocess/README.md | 8 +- .../subagent/subagent-subprocess/src/index.ts | 6 +- .../tests/subagent-subprocess.spec.ts | 84 +++++++------------ 9 files changed, 54 insertions(+), 87 deletions(-) diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 911d28cf1f..c05ae8d67f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -12,7 +12,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-claude-code` — drives a Claude Code child through `@anthropic-ai/claude-agent-sdk`'s `query()` (the SDK runs in the parent process and spawns its bundled `claude` CLI as the subprocess). Provider name `claude-code`: the child is the Claude Code *product*, not an Anthropic model adapter — "claude" stays reserved for a future `dsh-llm` adapter. - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. -- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. +- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..cc4d8307f8 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -6,7 +6,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import SubagentService from '@deepseek-ai/dsh-subagent' -import { buildChildEnv, SENSITIVE_ENV_PATTERN } from '@deepseek-ai/dsh-subagent-subprocess' +import { buildChildEnv } from '@deepseek-ai/dsh-subagent-subprocess' import type { Agent } from '@deepseek-ai/dsh-agent' import * as acp from '../src/index.ts' import { acpStopReason, acpContentText, DEFAULT_DISPOSE_EOF_GRACE_MS, DEFAULT_DISPOSE_GRACE_MS, startAcpRun, toAcpPrompt, type AcpRunSpec } from '../src/run.ts' @@ -112,7 +112,6 @@ describe('buildChildEnv', () => { // The explicitly-supplied key survives (an opt-in for the child's creds). expect(env.DEEPSEEK_API_KEY).toBe('explicit') // A normal ambient var is forwarded. - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(env.PATH).toBe(process.env.PATH) } finally { delete process.env.DSH_ACP_TEST_SECRET_TOKEN diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index 48fd0a201d..83c2ba3500 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -26,7 +26,7 @@ After fulfillment, the caller owns the run. Provider-plugin unload does not revo `InProcessRunOptions` is `{ seed?: SessionEvent[] }`. Spawn omits it. Fork supplies a balanced completed-turn prefix and records its length so the result reader never mistakes a seeded parent message for child output. -`depthOf(agent)` reads `AgentOptions.subagentDepth`, treating absence as top-level depth zero and rejecting malformed stored values. `SubagentDepthError` reports an attempted child depth above `maxDepth`; an unrepresentable depth above the safe-integer domain is a `RangeError`. +Depth enforcement is internal to `startInProcessRun`: it reads `AgentOptions.subagentDepth`, treats absence as top-level depth zero, rejects malformed stored values, and reports an attempted child depth above `maxDepth`. An unrepresentable depth above the safe-integer domain is a `RangeError`. ## Structured output diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 965d9c8e78..9676c74b5b 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -36,7 +36,7 @@ declare module '@deepseek-ai/dsh-agent' { * @param agent - the agent whose options carry the depth. * @returns its non-negative safe-integer depth. */ -export function depthOf(agent: Agent): number { +function depthOf(agent: Agent): number { const depth = agent.options.subagentDepth if (depth === undefined) return 0 if (!Number.isSafeInteger(depth) || depth < 0 || Object.is(depth, -0)) { @@ -46,7 +46,7 @@ export function depthOf(agent: Agent): number { } /** Thrown when starting a child would exceed the requested depth cap. */ -export class SubagentDepthError extends Error { +class SubagentDepthError extends Error { constructor(public readonly attemptedDepth: number, public readonly maxDepth: number) { super(`subagent depth ${attemptedDepth} exceeds maxDepth ${maxDepth}`) this.name = 'SubagentDepthError' diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index aa0f946c89..c594e27fa8 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -10,7 +10,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' -import { depthOf, SubagentDepthError, startInProcessRun } from '../src/index.ts' +import { startInProcessRun } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -37,19 +37,6 @@ function text(blocks: readonly { type: string; text?: string }[]): string { return blocks.filter(block => block.type === 'text').map(block => block.text).join('') } -describe('depthOf', () => { - it('reads zero for a top-level agent and an explicit child depth', async () => { - const { parent } = await setup([]) - expect(depthOf(parent)).toBe(0) - expect(depthOf({ options: { subagentDepth: 3 } } as unknown as Agent)).toBe(3) - }) - - it.each([Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1])('rejects malformed depth %s', (value) => { - expect(() => depthOf({ options: { subagentDepth: value } } as unknown as Agent)) - .toThrow('non-negative safe integer') - }) -}) - describe('startInProcessRun', () => { it('returns only after publication, drives a fresh child, and disposes it', async () => { const { ctx, parent } = await setup([textResponse('driver answer')]) @@ -58,7 +45,7 @@ describe('startInProcessRun', () => { const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('driver answer') - expect(depthOf(ctx.agents.get(run.id)!)).toBe(1) + expect(ctx.agents.get(run.id)!.options.subagentDepth).toBe(1) await run.dispose() await run.dispose() expect(ctx.agents.get(run.id)).toBeUndefined() @@ -83,7 +70,12 @@ describe('startInProcessRun', () => { await expect(startInProcessRun({ ...request(parent), maxDepth: -1 }, {})) .rejects.toThrow('non-negative safe integer') await expect(startInProcessRun({ ...request(parent), maxDepth: 0 }, {})) - .rejects.toBeInstanceOf(SubagentDepthError) + .rejects.toMatchObject({ name: 'SubagentDepthError' }) + for (const value of [Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1]) { + const malformed = { options: { subagentDepth: value } } as unknown as Agent + await expect(startInProcessRun(request(malformed), {})) + .rejects.toThrow('agent subagentDepth must be a non-negative safe integer') + } const maxParent = { options: { subagentDepth: Number.MAX_SAFE_INTEGER } } as unknown as Agent await expect(startInProcessRun(request(maxParent), {})).rejects.toBeInstanceOf(RangeError) }) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 06aa40ca9f..9b9e2a8fd2 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -13,7 +13,7 @@ import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import * as spawn from '../src/index.ts' -import { depthOf, STRUCTURED_OUTPUT_TOOL, SubagentDepthError } from '@deepseek-ai/dsh-subagent-inprocess' +import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' type Script = ConstructorParameters[0] @@ -118,11 +118,11 @@ describe('dsh-subagent-spawn', () => { it('stamps child depth = parent depth + 1 (via the merged AgentOptions field)', async () => { const { ctx, parent } = await setup([textResponse('x')]) - expect(depthOf(parent)).toBe(0) + expect(parent.options.subagentDepth).toBeUndefined() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent }) await run.result const child = ctx.agents.get(run.id)! - expect(depthOf(child)).toBe(1) + expect(child.options.subagentDepth).toBe(1) await run.dispose() }) @@ -130,7 +130,7 @@ describe('dsh-subagent-spawn', () => { const { ctx, parent } = await setup([]) // parent is depth 0, child would be depth 1 — cap at 0 forbids any child. await expect(start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent, maxDepth: 0 })) - .rejects.toThrow(SubagentDepthError) + .rejects.toThrow('subagent depth 1 exceeds maxDepth 0') }) it('maps a child that hit its token ceiling to stopReason "max-tokens"', async () => { diff --git a/packages/subagent/subagent-subprocess/README.md b/packages/subagent/subagent-subprocess/README.md index ccc68bf31b..c8b8a06437 100644 --- a/packages/subagent/subagent-subprocess/README.md +++ b/packages/subagent/subagent-subprocess/README.md @@ -6,7 +6,7 @@ Every tunable is a **parameter**: the dispose ladder takes its grace periods per ## What it exports -### `SENSITIVE_ENV_PATTERN` / `buildChildEnv(extra)` +### `buildChildEnv(extra)` The credential env scrub (same pattern as the [bash executor](../../bash/bash-local/README.md)): the child env is the ambient env minus credential-shaped vars (`/KEY|SECRET|TOKEN/i`), with `extra` layered on top AFTER the scrub. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive, so the child CLI runs normally; the parent's own secrets never leak implicitly, while an explicitly supplied credential (the child's OWN key in a backend's `env` config) still reaches the child. @@ -14,10 +14,6 @@ The credential env scrub (same pattern as the [bash executor](../../bash/bash-lo Spawn-failure capture: a promise that resolves (never rejects) with the child's first `error` event. A spawn failure such as `ENOENT` is an event, not a thrown exception — without a listener Node crashes the parent process — so call this in the same tick as `spawn()` and race it in the run's result path; a bad command then settles as an ordinary child-level failure. For a child that spawns cleanly the promise never settles. -### `waitForExit(child)` / `exitsWithin(child, ms)` - -Exit waits over a `ChildProcess`: resolve once the child exits by any code or signal (immediately if it is already gone), or race that against a timer (`true` = exited in time). The race cleans up after itself on both outcomes — the pending timer is `unref()`ed and cleared on exit, the exit listener removed on timeout — so repeated calls (the dispose ladder's tiers, a poll loop) never accumulate listeners on the child. - ### `disposeChildProcess(child, graces)` The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited — quiescence reached, not merely requested (see [defensive patterns](../../../docs/defensive-patterns.md)): @@ -28,6 +24,8 @@ The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited The two graces (`DisposeLadderGraces`) come from the consuming plugin's `disposeEofGraceMs`/`disposeGraceMs` Config fields; the EOF window is deliberately a separate — usually wider — grace than the signal tier, since a cooperative child's EOF teardown may itself await a signal-trapping grandchild plus a final flush. +The exit waits are internal to this ladder. They clean up their timer and listener on either outcome, so escalation never accumulates listeners on the child. + ### `createIsolatedConfigDir(prefix, pinnedPath?)` A per-run isolated config directory for an external CLI child (the target of `CLAUDE_CONFIG_DIR` / `CODEX_HOME`-style redirection), so child behavior is a function of deployment config alone — never of whatever `~/.claude` / `~/.codex`-style state exists on the host. Returns an `IsolatedConfigDir` handle: `path` goes into the child env, `remove()` runs on dispose. diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 35d7383456..2ee2745985 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -32,7 +32,7 @@ import { join } from 'node:path' * the scrub, so an intended `DEEPSEEK_API_KEY` survives while an incidental * `AWS_SECRET_ACCESS_KEY` does not. */ -export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i +const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit @@ -72,7 +72,7 @@ export function spawnFailure(child: ChildProcess): Promise { * already gone. * @param child - the child process to await. */ -export function waitForExit(child: ChildProcess): Promise { +function waitForExit(child: ChildProcess): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() return new Promise(resolve => child.once('exit', () => { resolve() })) } @@ -87,7 +87,7 @@ export function waitForExit(child: ChildProcess): Promise { * @returns `true` if the child exits within `ms` (immediately if it is * already gone), `false` on timeout. */ -export function exitsWithin(child: ChildProcess, ms: number): Promise { +function exitsWithin(child: ChildProcess, ms: number): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve(true) return new Promise((resolve) => { const onExit = (): void => { diff --git a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts index 2766ed0a41..8e19a8a4a1 100644 --- a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts +++ b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts @@ -9,10 +9,7 @@ import { buildChildEnv, createIsolatedConfigDir, disposeChildProcess, - exitsWithin, - SENSITIVE_ENV_PATTERN, spawnFailure, - waitForExit, } from '../src/index.ts' // `rm` is wrapped (real-passthrough by default) so ONE test can inject a @@ -47,6 +44,8 @@ interface FakeChildScript { diesOn?: LethalTrigger /** Delay (ms) between the lethal trigger and the exit event. */ delayMs?: number + /** Complete the scripted exit inside the triggering call. */ + synchronousExit?: boolean /** `false` models a child spawned without a stdin pipe. */ stdin?: boolean } @@ -80,11 +79,13 @@ class FakeChild extends EventEmitter { // SIGKILL is uncatchable — it always fells the child; any other trigger // only when the scenario scripts it as the lethal one. if (trigger !== 'SIGKILL' && this.script.diesOn !== trigger) return - setTimeout(() => { + const exit = (): void => { if (trigger === 'eof') this.exitCode = 0 else this.signalCode = trigger this.emit('exit', this.exitCode, this.signalCode) - }, this.script.delayMs ?? 0) + } + if (this.script.synchronousExit === true) exit() + else setTimeout(exit, this.script.delayMs ?? 0) } } @@ -93,7 +94,7 @@ function asChild(fake: FakeChild): ChildProcess { return fake as unknown as ChildProcess } -describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { +describe('buildChildEnv', () => { it('drops credential-shaped ambient vars (KEY/SECRET/TOKEN, case-insensitive)', () => { process.env.DSH_PROC_TEST_API_KEY = 'leak' process.env.dsh_proc_test_secret = 'leak' @@ -111,7 +112,6 @@ describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { }) it('forwards normal ambient vars', () => { - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(buildChildEnv({}).PATH).toBe(process.env.PATH) }) @@ -149,7 +149,7 @@ describe('spawnFailure', () => { const fake = new FakeChild({ diesOn: 'SIGTERM' }) const failure = spawnFailure(asChild(fake)) fake.kill('SIGTERM') - await waitForExit(asChild(fake)) + await new Promise(resolve => fake.once('exit', () => { resolve() })) // A clean lifecycle emits `exit`, never `error` — the capture stays // pending forever, so a race against it is decided by the other arms. const settled = await Promise.race([ @@ -160,51 +160,6 @@ describe('spawnFailure', () => { }) }) -describe('waitForExit / exitsWithin', () => { - it('resolves immediately for a child that already exited by code', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves immediately for a child that already died by signal', async () => { - const fake = new FakeChild() - fake.signalCode = 'SIGTERM' - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves on the exit event of a live child', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - const exited = waitForExit(asChild(fake)) - fake.kill('SIGTERM') - await expect(exited).resolves.toBeUndefined() - expect(fake.signalCode).toBe('SIGTERM') - }) - - it('exitsWithin resolves true immediately for an already-exited child (no listener attached)', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves true when the child exits inside the window', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - fake.kill('SIGTERM') - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - // The once-listener fired and the grace timer was cleared — nothing lingers. - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves false on timeout for a child that never exits', async () => { - const fake = new FakeChild() // nothing short of SIGKILL fells it; no signal sent - await expect(exitsWithin(asChild(fake), 20)).resolves.toBe(false) - // The timeout arm removed its exit listener: repeated waits (a poll loop, - // the ladder's tiers) never accumulate listeners on the same child. - expect(fake.listenerCount('exit')).toBe(0) - }) -}) - describe('disposeChildProcess', () => { it('returns immediately for an already-exited child (no EOF, no signals)', async () => { const fake = new FakeChild() @@ -230,12 +185,28 @@ describe('disposeChildProcess', () => { expect(fake.exitCode).toBe(0) }) + it('recognizes a child that exits synchronously on stdin EOF', async () => { + const fake = new FakeChild({ diesOn: 'eof', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 1000, disposeGraceMs: 1000 }) + expect(fake.exitCode).toBe(0) + expect(fake.listenerCount('exit')).toBe(0) + }) + it('tier 2: a child that ignores EOF but honors SIGTERM dies on the middle rung', async () => { const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) expect(fake.stdinEnded).toBe(true) expect(fake.kills).toEqual(['SIGTERM']) expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) + }) + + it('recognizes a child that exits synchronously on SIGTERM', async () => { + const fake = new FakeChild({ diesOn: 'SIGTERM', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) + expect(fake.kills).toEqual(['SIGTERM']) + expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) }) it('tier 3: a SIGTERM-trapping child is SIGKILLed, and dispose resolves only after the exit', async () => { @@ -247,6 +218,13 @@ describe('disposeChildProcess', () => { expect(fake.signalCode).toBe('SIGKILL') }) + it('recognizes a child already gone when the final exit wait begins', async () => { + const fake = new FakeChild({ synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 20 }) + expect(fake.kills).toEqual(['SIGTERM', 'SIGKILL']) + expect(fake.signalCode).toBe('SIGKILL') + }) + it('walks the ladder for a child spawned without a stdin pipe', async () => { const fake = new FakeChild({ stdin: false, diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) From 65521b589f3ffa1a912bb3d8db05a6e2ce204a85 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:45:34 +0800 Subject: [PATCH 014/140] refactor: hide remaining subagent helpers --- ...t-variables-and-tool-guidance-ownership.md | 2 +- ...7-05-subagent-provider-lifecycle-events.md | 2 +- .../2026-06-22-fork-snapshot-scenarios.md | 2 +- packages/subagent/subagent-fork/README.md | 2 +- packages/subagent/subagent-fork/src/index.ts | 2 +- .../subagent-fork/tests/subagent-fork.spec.ts | 42 ++++++++----------- packages/subagent/tool-subagent/src/index.ts | 4 +- 7 files changed, 25 insertions(+), 31 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 0961830c1a..aae4564513 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -38,7 +38,7 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag (`providerWording`): the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index 46e7ea4e71..4a96ef7419 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description (`providerWording`), so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. +[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. The first implementation resolved the provider at the tool plugin's `apply` time and threw when it was absent — an implicit load-order requirement ("list the backend before the tool in cordis.yml"). Review reproduced the failure that requirement hides: the cordis Loader starts sibling entries CONCURRENTLY (`Promise.all` over the group) and `Entry.init()` does not await activation, so a backend whose activation is delayed leaves the tool's fiber permanently failed even when "listed first". The ordering the requirement leaned on is not a contract the Loader offers — "async state is not synchronous state" ([defensive patterns](../../../defensive-patterns.md)). diff --git a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md index b2c39047b9..34bebd1194 100644 --- a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md +++ b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md @@ -17,7 +17,7 @@ Record two scenarios against the real API, both replayed keyless in the default ### Why a completed turn-1 is required -The fork backend seeds the child with the parent's **balanced completed-turn prefix** ([`completedTurnPrefix`](../../../../packages/subagent/subagent-fork)). A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. +The fork backend seeds the child with the parent's **balanced completed-turn prefix**. A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. ## Consequences diff --git a/packages/subagent/subagent-fork/README.md b/packages/subagent/subagent-fork/README.md index bf90ecdf52..0909dc0bf1 100644 --- a/packages/subagent/subagent-fork/README.md +++ b/packages/subagent/subagent-fork/README.md @@ -6,7 +6,7 @@ The fork provider creates an in-process child seeded with the parent's completed The parent's current tool-calling turn is still open when a subagent starts: its log contains the assistant tool call but not the matching tool result or `turn/end`. Copying that raw log would give the child an invalid, unbalanced session. -Fork therefore uses `completedTurnPrefix(parent.session.events)`: the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. +Fork therefore computes the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. The seed transfers conversation history only. The child still receives a fresh flat registration scope; it does not inherit the parent's tool restrictions or authority. diff --git a/packages/subagent/subagent-fork/src/index.ts b/packages/subagent/subagent-fork/src/index.ts index ebf64e7b70..22be47cc56 100644 --- a/packages/subagent/subagent-fork/src/index.ts +++ b/packages/subagent/subagent-fork/src/index.ts @@ -54,7 +54,7 @@ export const Config: z = z.object({ * @param parent - the agent whose session log to slice. * @returns the seed events, contiguous from seq 0; empty when no turn has completed. */ -export function completedTurnPrefix(parent: Agent): SessionEvent[] { +function completedTurnPrefix(parent: Agent): SessionEvent[] { const events = parent.session.events const lastEnd = events.findLast(e => e.type === 'turn/end') if (lastEnd === undefined) return [] diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index 360098e369..bfb0bedac7 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -14,7 +14,6 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent import type { StreamChunk } from '@deepseek-ai/dsh-llm' import * as fork from '../src/index.ts' import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' -import { completedTurnPrefix } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -52,28 +51,6 @@ function text(blocks: { type: string; text?: string }[]): string { return blocks.filter(b => b.type === 'text').map(b => b.text).join('') } -describe('completedTurnPrefix', () => { - it('returns an empty prefix for a parent that has never completed a turn', async () => { - const { parent } = await setup([]) - expect(completedTurnPrefix(parent)).toEqual([]) - }) - - it('returns the balanced prefix up to and including the last turn/end', async () => { - const { parent } = await setup([textResponse('first'), textResponse('second')]) - parent.send([{ type: 'text', text: 'q1' }]) - await parent.whenIdle() - parent.send([{ type: 'text', text: 'q2' }]) - await parent.whenIdle() - - const prefix = completedTurnPrefix(parent) - // Ends exactly at the last turn/end; seq is contiguous from 0. - expect(prefix.at(-1)?.type).toBe('turn/end') - expect(prefix.map(e => e.seq)).toEqual(prefix.map((_, i) => i)) - // Both completed turns are present. - expect(prefix.filter(e => e.type === 'turn/end')).toHaveLength(2) - }) -}) - describe('dsh-subagent-fork', () => { it('emits subagent/start only after the seeded child is published', async () => { const { ctx, parent } = await setup([textResponse('child answer')]) @@ -96,7 +73,6 @@ describe('dsh-subagent-fork', () => { // The parent has never completed a turn → empty prefix → the provider omits // the seed → the child runs fresh. Exercises the `seed.length > 0` false arm. const { ctx, parent } = await setup([textResponse('fresh child')]) - expect(completedTurnPrefix(parent)).toEqual([]) const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) const result = await run.result expect(result.stopReason).toBe('completed') @@ -104,6 +80,24 @@ describe('dsh-subagent-fork', () => { const child = ctx.agents.get(run.id)! // Only the child's own turn — no seeded parent turns. expect(child.session.events.filter(e => e.type === 'turn/end')).toHaveLength(1) + expect(child.session.header.seedLength).toBeUndefined() + await run.dispose() + }) + + it('seeds every completed parent turn through the last turn/end', async () => { + const { ctx, parent } = await setup([textResponse('first'), textResponse('second'), textResponse('child')]) + parent.send([{ type: 'text', text: 'q1' }]) + await parent.whenIdle() + parent.send([{ type: 'text', text: 'q2' }]) + await parent.whenIdle() + const parentPrefixLen = parent.session.events.length + + const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) + await run.result + const child = ctx.agents.get(run.id)! + expect(child.session.header.seedLength).toBe(parentPrefixLen) + expect(child.session.events.slice(0, parentPrefixLen).at(-1)?.type).toBe('turn/end') + expect(child.session.events.slice(0, parentPrefixLen).filter(e => e.type === 'turn/end')).toHaveLength(2) await run.dispose() }) diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index d07e6726dd..426753dbb9 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -161,13 +161,13 @@ function stopReasonError(result: SubagentResult): string | undefined { * A fresh child needs a standalone prompt; a forked child already sees the * conversation's completed turns — telling the model to restate everything * (or, worse, that the child "does not see this conversation") would be false - * for a fork. Exported for tests. + * for a fork. * @param inheritsConversation - whether the child's conversation is seeded * with the parent's completed turns; this says nothing about tool, service, * scope, or authority inheritance. * @returns the tool `description` and the `prompt` parameter description. */ -export function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { +function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { if (inheritsConversation) { return { description: From 5c82310f47a57f5031e3301042a53a0768a53b30 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 03:58:34 +0800 Subject: [PATCH 015/140] refactor: prune unused llm contract fields --- docs/cordis-catalog/services.md | 2 +- .../testing/2026-06-19-acp-snapshot-tests.md | 2 +- ...0-remove-redundant-snapshot-log-goldens.md | 2 +- .../error-finish/replay.override.json | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 8 ++-- .../llm/llm-deepseek/tests/adapter.spec.ts | 7 +-- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/assembler.ts | 8 ++-- packages/llm/llm/src/index.ts | 6 +-- packages/llm/llm/tests/assembler.spec.ts | 43 ++++++------------- packages/llm/llm/tests/service.spec.ts | 5 ++- packages/support/llm-replay/src/index.ts | 4 +- .../llm-replay/tests/llm-replay.spec.ts | 10 ++--- 13 files changed, 37 insertions(+), 64 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 0aea3f1589..95df09d45e 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -159,7 +159,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:86`](../../packages/llm/llm/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) diff --git a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md index b424a253bd..4bfa3660bf 100644 --- a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -30,7 +30,7 @@ The replay seam is the provider-agnostic `llm/stream` waterfall ([packages/llm/l ``` { kind: 'chunks', chunks: StreamChunk[] } -| { kind: 'throw', chunks: StreamChunk[], message: string, code: string, status?: number } +| { kind: 'throw', chunks: StreamChunk[], message: string, code: string } | { kind: 'hang' } ``` diff --git a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md index 2a6f8b7ae3..a7c56af2bd 100644 --- a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md +++ b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md @@ -6,7 +6,7 @@ Status: implemented Model-driving ACP snapshot scenarios ship both `session.jsonl` and `session.golden.jsonl`. For normal recorded scenarios, `session.jsonl` is the replay fixture harvested from a real run, and the replay test normalizes the newly persisted log and compares it to `session.golden.jsonl`. In the current fixtures, the normalized recorded log and normalized golden are identical for the ordinary recorded scenarios. -Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string, "status"?: number }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. +Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. ## Decision diff --git a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json index eea32f25ca..cfa0d84227 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json +++ b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json @@ -1,3 +1,3 @@ [ - { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH", "status": 401 } + { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH" } ] diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index e0627c5695..c90404720b 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -79,9 +79,9 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Paranoid by design: `code` and the HTTP status are ALREADY captured - // above (and passed to LlmError below), so the only thing this `try` - // can add is a richer provider-supplied message. A malformed, empty, + // Paranoid by design: the stable `code` and status-line message are + // already captured above, so the only thing this `try` can add is a + // richer provider-supplied message. A malformed, empty, // or non-JSON error body is a normal thing for gateways/proxies to // return on a 5xx/429 — swallowing the parse failure keeps the usable // status-line message instead of letting a JSON.parse throw mask the @@ -89,7 +89,7 @@ export class DeepSeekAdapter extends LlmAdapter { // is the sole statement, and any non-parse failure (e.g. body already // consumed) is equally non-actionable here. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 42694ba5ea..7c847447b8 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter must identify the application on every provider HTTP reque - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 1b8ba6e60c..fb34afe0b9 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -38,12 +38,10 @@ export class BlockAssembler { private _finish: FinishReason | undefined /** - * Feed one chunk. Returns the completed block when the chunk closes one - * (an explicit `block-end`), otherwise undefined. + * Feed one chunk into the assembly state. * @param chunk - the next raw chunk, in stream order. - * @returns the authoritative block from the first `block-end` at its index; undefined for every other chunk. */ - push(chunk: StreamChunk): ContentBlock | undefined { + push(chunk: StreamChunk): void { switch (chunk.type) { case 'block-start': { if (!this.partials.has(chunk.index)) { @@ -79,7 +77,7 @@ export class BlockAssembler { // re-close could rewrite a block already flushed downstream. if (partial.block) return partial.block = chunk.block - return chunk.block + return } case 'usage': { this._usage = chunk.usage diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 667e9bca78..e32894efdd 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/assembler.spec.ts b/packages/llm/llm/tests/assembler.spec.ts index d9a4fe33f3..0674c55fb8 100644 --- a/packages/llm/llm/tests/assembler.spec.ts +++ b/packages/llm/llm/tests/assembler.spec.ts @@ -29,12 +29,12 @@ describe('BlockAssembler', () => { expect(assembler.message().role).toBe('assistant') }) - it('returns the completed block from push() on block-end', () => { + it('records the completed block from block-end', () => { const assembler = new BlockAssembler() - expect(assembler.push({ type: 'block-start', index: 0, blockType: 'text' })).toBeUndefined() - expect(assembler.push({ type: 'text-delta', index: 0, text: 'hi' })).toBeUndefined() - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-start', index: 0, blockType: 'text' }) + assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('tolerates deltas without explicit block-start/end', () => { @@ -57,8 +57,8 @@ describe('BlockAssembler', () => { // push a delta first to guarantee the partial exists assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) // block-end's ensure() must find the existing partial (the second branch path) - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('throws from assemble() when a partial has an unhandled blockType', () => { @@ -130,7 +130,7 @@ describe('assertNever', () => { it('BlockAssembler.push rejects chunks outside the closed StreamChunk union', () => { const assembler = new BlockAssembler() - expect(() => assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk)) + expect(() => { assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk) }) .toThrow('unreachable variant in BlockAssembler.push') }) }) @@ -140,32 +140,13 @@ describe('BlockAssembler regressions (property-test findings)', () => { // Found by fast-check (the property-testing RFC): two block-ends at the same index made the // streamed prefix (first block) disagree with final blocks() (second // block). The first close must win — same straggler rule as post-close - // deltas — so the prefix returned incrementally by push() and the final - // blocks() stay identical. + // deltas — so later chunks cannot rewrite the completed block. const chunks: StreamChunk[] = [ { type: 'block-end', index: 0, block: { type: 'reasoning', text: 'first' } }, { type: 'block-end', index: 0, block: { type: 'text', text: 'second' } }, ] - const streaming = new BlockAssembler() - const closed = [] - for (const chunk of chunks) { - const block = streaming.push(chunk) - if (block) closed.push(block) - } - - const oneShot = new BlockAssembler() - for (const chunk of chunks) oneShot.push(chunk) - - expect(closed).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(oneShot.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(closed).toEqual(oneShot.blocks()) - }) - - it('push returns undefined for a duplicate block-end (it closed nothing)', () => { - const a = new BlockAssembler() - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'x' } })) - .toEqual({ type: 'text', text: 'x' }) - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'y' } })) - .toBeUndefined() + const assembler = new BlockAssembler() + for (const chunk of chunks) assembler.push(chunk) + expect(assembler.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) }) }) diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 94bd0cdd7e..b919c21176 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -74,7 +74,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -324,7 +324,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 3b4e8c5fee..f7e85a74bf 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From 91075e010ab641a3cc236881d0713f68b27e8191 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:03:44 +0800 Subject: [PATCH 016/140] refactor: hide llm adapter helpers --- docs/config-catalog.md | 4 ++-- packages/llm/llm-deepseek/README.md | 2 ++ packages/llm/llm-deepseek/src/index.ts | 5 +---- packages/llm/llm-deepseek/tests/adapter.spec.ts | 16 +++++++++++++++- .../llm/llm-deepseek/tests/serialize.spec.ts | 2 +- packages/llm/llm-deepseek/tests/sse.spec.ts | 2 +- .../llm/llm-deepseek/tests/translate.spec.ts | 3 ++- packages/llm/llm-pi-ai/README.md | 2 ++ packages/llm/llm-pi-ai/src/index.ts | 3 +-- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 9 ++++++++- packages/llm/llm-pi-ai/tests/convert.spec.ts | 2 +- 11 files changed, 36 insertions(+), 14 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..9db148cbae 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -389,7 +389,7 @@ export interface Config { } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:43`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:40`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -420,7 +420,7 @@ export interface Config { export type PiAiReasoning = 'off' | 'high' | 'xhigh' ``` -Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts) +Source: [`packages/llm/llm-pi-ai/src/index.ts:36`](../packages/llm/llm-pi-ai/src/index.ts) ## `@deepseek-ai/dsh-llm-replay` diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 15fad9f881..4d9ff8fcae 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -4,6 +4,8 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch` A second, independent implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai` (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design). +The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire serialization, SSE parsing, and chunk translation helpers are not part of that root contract. + ## Config ```yaml diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3a3d7bb4a1..3b8013de5c 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -23,12 +23,9 @@ import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { DeepSeekAdapter } from './adapter.ts' -export { DeepSeekAdapter, httpErrorCode } from './adapter.ts' +export { DeepSeekAdapter } from './adapter.ts' export type { DeepSeekAdapterOptions } from './adapter.ts' -export { serializeMessages, serializeRequest } from './serialize.ts' export type { RequestDefaults } from './serialize.ts' -export { DONE, parseSse } from './sse.ts' -export { mapFinishReason, mapUsage, translate } from './translate.ts' export type * from './types.ts' export const name = 'llm-deepseek' diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..ca9c6b7097 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' +import { DeepSeekAdapter } from '@deepseek-ai/dsh-llm-deepseek' +import { httpErrorCode } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** One scripted behavior for the next request the mock server receives. */ @@ -234,6 +235,19 @@ describe('DeepSeekAdapter against a mock server', () => { }) describe('plugin registration and config', () => { + it('keeps wire helpers off the package root', () => { + for (const helper of [ + 'httpErrorCode', + 'serializeMessages', + 'serializeRequest', + 'DONE', + 'parseSse', + 'mapFinishReason', + 'mapUsage', + 'translate', + ]) expect(LlmDeepSeek).not.toHaveProperty(helper) + }) + it('registers the configured models and unregisters on dispose (HMR safety)', async () => { const server = await mockServer([]) const ctx = new Context() diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index 3e533f8e7c..a1d7d8b4a7 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm' -import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek' +import { serializeMessages, serializeRequest } from '../src/serialize.ts' function request(overrides: Partial = {}): GenerateOptions { return { model: 'deepseek-v4-flash', messages: [], ...overrides } diff --git a/packages/llm/llm-deepseek/tests/sse.spec.ts b/packages/llm/llm-deepseek/tests/sse.spec.ts index 2fc297bbec..b18862e4f3 100644 --- a/packages/llm/llm-deepseek/tests/sse.spec.ts +++ b/packages/llm/llm-deepseek/tests/sse.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { LlmError } from '@deepseek-ai/dsh-llm' -import { DONE, parseSse } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE, parseSse } from '../src/sse.ts' /** Build a byte stream from string fragments (fragments = network reads). */ async function* bytes(...fragments: (string | Uint8Array)[]): AsyncGenerator { diff --git a/packages/llm/llm-deepseek/tests/translate.spec.ts b/packages/llm/llm-deepseek/tests/translate.spec.ts index d6968faed5..e62cebc4af 100644 --- a/packages/llm/llm-deepseek/tests/translate.spec.ts +++ b/packages/llm/llm-deepseek/tests/translate.spec.ts @@ -1,7 +1,8 @@ import { describe, expect, it } from 'vitest' import { BlockAssembler, LlmError } from '@deepseek-ai/dsh-llm' import type { StreamChunk } from '@deepseek-ai/dsh-llm' -import { DONE, mapFinishReason, mapUsage, translate } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE } from '../src/sse.ts' +import { mapFinishReason, mapUsage, translate } from '../src/translate.ts' async function* feed(...payloads: (string | object)[]): AsyncGenerator { for (const payload of payloads) { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index f74ccd2246..adb22c585c 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -2,6 +2,8 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai) (the LLM library behind the pi agent). +The package root exposes the Cordis plugin contract and `PiAiAdapter`; model construction and event-conversion helpers are not part of that root contract. + ## Why a second adapter exists `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: diff --git a/packages/llm/llm-pi-ai/src/index.ts b/packages/llm/llm-pi-ai/src/index.ts index 43468ba507..fd81b77b56 100644 --- a/packages/llm/llm-pi-ai/src/index.ts +++ b/packages/llm/llm-pi-ai/src/index.ts @@ -22,9 +22,8 @@ import type {} from '@deepseek-ai/dsh-llm' import { PiAiAdapter } from './adapter.ts' import type { PiAiReasoning } from './adapter.ts' -export { buildModel, PiAiAdapter } from './adapter.ts' +export { PiAiAdapter } from './adapter.ts' export type { PiAiAdapterOptions, PiAiReasoning } from './adapter.ts' -export { mapStopReason, mapUsage, toPiContext, toStreamChunks } from './convert.ts' export const name = 'llm-pi-ai' export const inject = ['llm'] diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index cefaa9f745..cc4f129b72 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import { buildModel, PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { buildModel } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** Scripted SSE responses, one per request (OpenAI chat-completions shape). */ @@ -245,6 +246,12 @@ describe('PiAiAdapter against a mock server', () => { }) describe('option spreads and env fallbacks', () => { + it('keeps adapter conversion helpers off the package root', () => { + for (const helper of ['buildModel', 'mapStopReason', 'mapUsage', 'toPiContext', 'toStreamChunks']) { + expect(LlmPiAi).not.toHaveProperty(helper) + } + }) + it('forwards temperature, maxTokens, and signal', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url) diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..3dc4709603 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' -import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' +import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '../src/convert.ts' function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage { return { From f1373cd7abc479ae89a219e6a3fad6023f66aa64 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:15:17 +0800 Subject: [PATCH 017/140] refactor: drop unused tool schema defaults --- docs/core-data-structures/tools.md | 2 -- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 10 ------- packages/core/tools/tests/tools.spec.ts | 37 ++----------------------- 4 files changed, 3 insertions(+), 48 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 36c59aea17..1d59542404 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,8 +57,6 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** Default value. */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index d57aeba10b..5f06154ec4 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index d3a2d32e18..ad7c28760e 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,15 +39,6 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** - * Default value, emitted into the JSON Schema only (validation never applies - * it — see the validator note below). - * - * XXX(unused-default): no tool definition in the repo sets `default`; it rides - * into the wire schema for a model that no tool surfaces it to. Drop the field - * and its converter line unless a real tool needs a model-visible default. - */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -123,7 +114,6 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum - if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index a2dff84287..2bca8e05fc 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,17 +904,6 @@ describe('schema DSL edge cases', () => { }) }) - it('emits default value in JSON Schema property', () => { - const spec = { - limit: { type: 'number', default: 25 }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['limit']).toMatchObject({ - type: 'number', - default: 25, - }) - }) - it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -926,28 +915,12 @@ describe('schema DSL edge cases', () => { }) }) - it('handles enum and default together in one property', () => { - const spec = { - level: { type: 'string', enum: ['low', 'high'], default: 'low' }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['level']).toMatchObject({ - type: 'string', - enum: ['low', 'high'], - default: 'low', - }) - }) - - it('omits description, enum, default keys when not specified', () => { + it('emits only the type when optional fields are omitted', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - const prop = jsonSchema.properties['bare'] as Record - expect(prop).toEqual({ type: 'string' }) - expect('description' in prop).toBe(false) - expect('enum' in prop).toBe(false) - expect('default' in prop).toBe(false) + expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) }) it('handles array with no items (items omitted)', () => { @@ -1137,12 +1110,6 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) - it('does not apply defaults (validation only)', () => { - const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec - // absent optional is valid, and validation does not synthesize the default - expect(validateArgs(spec, {})).toEqual([]) - }) - it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 863116daaf406d3fc6485be819bcba0fc3d275f1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:23:17 +0800 Subject: [PATCH 018/140] fix: retain dynamic tool schema defaults --- docs/core-data-structures/tools.md | 2 + .../cordis/tool-cordis/tests/mount.spec.ts | 6 ++- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 6 +++ packages/core/tools/tests/tools.spec.ts | 37 ++++++++++++++++++- 5 files changed, 49 insertions(+), 4 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 1d59542404..36c59aea17 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,6 +57,8 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** Default value. */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/cordis/tool-cordis/tests/mount.spec.ts b/packages/cordis/tool-cordis/tests/mount.spec.ts index fc29eeb2a0..bf2e57c13e 100644 --- a/packages/cordis/tool-cordis/tests/mount.spec.ts +++ b/packages/cordis/tool-cordis/tests/mount.spec.ts @@ -185,9 +185,13 @@ describe('cordis_mount', () => { // The registered schema is canonical JSON Schema derived from the DSL: // the required array survived, integer became number, extra is optional. const schema = ctx.tools.schemas().find(s => s.name === 'json_schema_tool')! - const parameters = schema.parameters as { properties: Record; required?: string[] } + const parameters = schema.parameters as { + properties: Record + required?: string[] + } expect(parameters.required).toEqual(['text']) expect(parameters.properties.count!.type).toBe('number') + expect(parameters.properties.count!.default).toBe(1) expect(parameters.properties.mode!.enum).toEqual(['fast', 'slow']) // Arg validation enforces the normalized spec: text required, extra not. expect((await call(ctx, 'json_schema_tool', { count: 2 })).isError).toBe(true) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 5f06154ec4..d57aeba10b 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index ad7c28760e..e912252b18 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,6 +39,11 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** + * Model-visible JSON Schema default annotation. Validation does not apply it; + * dynamic tool mounts may supply it even though first-party definitions do not. + */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -114,6 +119,7 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum + if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index 2bca8e05fc..a2dff84287 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,6 +904,17 @@ describe('schema DSL edge cases', () => { }) }) + it('emits default value in JSON Schema property', () => { + const spec = { + limit: { type: 'number', default: 25 }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['limit']).toMatchObject({ + type: 'number', + default: 25, + }) + }) + it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -915,12 +926,28 @@ describe('schema DSL edge cases', () => { }) }) - it('emits only the type when optional fields are omitted', () => { + it('handles enum and default together in one property', () => { + const spec = { + level: { type: 'string', enum: ['low', 'high'], default: 'low' }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['level']).toMatchObject({ + type: 'string', + enum: ['low', 'high'], + default: 'low', + }) + }) + + it('omits description, enum, default keys when not specified', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) + const prop = jsonSchema.properties['bare'] as Record + expect(prop).toEqual({ type: 'string' }) + expect('description' in prop).toBe(false) + expect('enum' in prop).toBe(false) + expect('default' in prop).toBe(false) }) it('handles array with no items (items omitted)', () => { @@ -1110,6 +1137,12 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) + it('does not apply defaults (validation only)', () => { + const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec + // absent optional is valid, and validation does not synthesize the default + expect(validateArgs(spec, {})).toEqual([]) + }) + it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 9028c9b63b6c3ed1737c168ae5e1548bab064668 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:35:34 +0800 Subject: [PATCH 019/140] fix: contain ACP update predicate failures --- packages/support/acp-snapshot/src/launcher.ts | 13 +++++++++++-- packages/support/acp-snapshot/tests/harness.spec.ts | 4 ++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 635a02ca35..975b1bb852 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -107,6 +107,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void + reject: (reason: unknown) => void }[] = [] const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -119,7 +120,15 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const waiter = updateWaiters[index] /* v8 ignore next 1 -- index is bounded by the array length */ if (waiter === undefined) continue - if (!waiter.match(params.update)) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) waiter.resolve(params.update) } @@ -136,7 +145,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ec1ed5cf6f..db715db90c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -57,7 +57,11 @@ describe('runScenario', () => { await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + const predicateFailure = new Error('predicate failed') + const failedPredicate = launched.waitForUpdate(() => { throw predicateFailure }) + .catch((error: unknown): unknown => error) await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect(await failedPredicate).toBe(predicateFailure) expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') From 7d711c44a8a6202680f2801ba16b391858715163 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:41:01 +0800 Subject: [PATCH 020/140] fix: keep remote subagent ids parent-scoped --- .../2026-06-20-unify-agent-and-session-id.md | 4 ++-- .../core/agent-loop/tests/scope-lifecycle.spec.ts | 2 +- packages/subagent/subagent-acp/README.md | 2 ++ packages/subagent/subagent-acp/src/run.ts | 15 ++++++++++----- .../subagent-acp/tests/subagent-acp.spec.ts | 10 ++++++++-- packages/subagent/subagent/src/types.ts | 2 +- 6 files changed, 24 insertions(+), 11 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index be1052830a..032eae4f7d 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -14,7 +14,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C ## Decision -An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..e29e73c393 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -249,7 +249,7 @@ describe('agent scope lifecycle', () => { }) await setupStarted.promise expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() - expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() + expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) const handle = await creating diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index c949685fcc..03b1a856ed 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -6,6 +6,8 @@ The ACP provider runs each subagent in a fresh subprocess and drives it as an Ag `start(request)` performs `spawn` → ACP `initialize` → `newSession` before it fulfills. Fulfillment therefore means a remote session is ready and ownership has transferred to the caller. A spawn, initialization, new-session, or pre-publication cancellation failure rejects only after the subprocess has been reaped. +The returned run id is minted in the parent namespace. The child server's session id remains private to ACP wire calls because ACP guarantees it only within that fresh child process; using it as the parent lifecycle id could collide with another remote run or a local agent. + After publication, the provider sends the prompt and collects streamed `agent_message_chunk` text into `SubagentResult.output`. A prompt/transport failure resolves with `stopReason: 'error'`, or `aborted` when the required request signal or disposal requested cancellation. `dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, closes stdin, waits `disposeEofGraceMs`, escalates to SIGTERM, waits `disposeGraceMs`, and finally uses SIGKILL if necessary. Every run uses a fresh process; process pooling is not implemented. diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1cc220204f..7d0c11cbe1 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,6 +23,7 @@ */ import { spawn } from 'node:child_process' +import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,6 +191,10 @@ function toError(value: unknown): Error { */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') + // ACP session ids are unique only within the child server. The lifecycle id + // is minted in the parent namespace so fresh processes cannot collide with + // each other or with a local agent that happens to use the same session id. + const id = SessionId(randomUUID()) // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP // response channel, stderr = INHERIT so the child's diagnostics surface on the @@ -257,7 +262,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: SessionId | undefined + let sessionId: string | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -306,7 +311,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = SessionId(session.sessionId) + sessionId = session.sessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -322,7 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // guard keeps that cross-closure invariant explicit for TypeScript. /* v8 ignore next */ if (sessionId === undefined) throw new Error('ACP child published without a session id') - const runId = sessionId + const remoteSessionId = sessionId const result: Promise = (async (): Promise => { try { @@ -334,7 +339,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: remoteSessionId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -368,7 +373,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id: runId, + id, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..e5fe05384e 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -121,16 +121,22 @@ describe('buildChildEnv', () => { }) describe('dsh-subagent-acp', () => { - it('drives a child process to completion and returns its streamed output', async () => { + it('drives child processes with parent-unique run ids and returns streamed output', async () => { const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) - expect(run.id).toBe('acp-child-session') + expect(run.id).not.toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') const disposal = run.dispose() expect(run.dispose()).toBe(disposal) await disposal + + const nextRun = await ctx.subagents.start('acp', request('do X again')) + expect(nextRun.id).not.toBe(run.id) + expect(nextRun.id).not.toBe('acp-child-session') + await nextRun.result + await nextRun.dispose() }) it('maps a max_tokens stop reason', async () => { diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 8d360b1182..827c2db7a7 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,7 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ + /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run From a415d8fdb1b3de4425495b6c87707b58f5c3f65f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:43:10 +0800 Subject: [PATCH 021/140] docs: remove stale streamed-prefix rationale --- .../implemented/testing/2026-06-11-property-based-testing.md | 2 +- packages/llm/llm/src/assembler.ts | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md index 67404ab49a..db7a9c8a79 100644 --- a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md +++ b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md @@ -20,7 +20,7 @@ Adopt `fast-check` (a root devDependency) with one `tests/properties.spec.ts` pe ## Consequences - Generator quality is the value lever — the generators bias toward small index pools and short strings so collisions and interleavings are common. -- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index overwrote an already-flushed block, so the streamed prefix disagreed with final `blocks()`. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. +- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index rewrote a completed block. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. - A property flake from a timeout is a finding, not something to retry away. The loop properties are deterministic by construction (settle on `agent/status`), so a hang is a real defect. - Property tests supplement, not replace, the example tests that pin specific branches for the 100%-coverage gate. diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index fb34afe0b9..1dd023d177 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -72,9 +72,8 @@ export class BlockAssembler { case 'block-end': { const partial = this.ensure(chunk.index, chunk.block.type) // First close wins: a second block-end for an already-closed index is - // a straggler (same rule as post-close deltas). Ignoring it keeps the - // streamed prefix and the final blocks() in agreement — otherwise a - // re-close could rewrite a block already flushed downstream. + // a straggler (same rule as post-close deltas). Ignoring it prevents a + // later chunk from rewriting a completed block. if (partial.block) return partial.block = chunk.block return From 60ce23d77c52b6f4c183c320d2a1b54c4aedea7f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:07:37 +0800 Subject: [PATCH 022/140] fix: surface ACP launcher spawn failures --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 1 + packages/support/acp-snapshot/src/launcher.ts | 22 ++++++++++++++++++- .../acp-snapshot/tests/harness.spec.ts | 13 ++++++++++- 4 files changed, 35 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 4a43d0eef9..0058e9116f 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 93bb556ba6..d04b0bc2b5 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -214,6 +214,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise }, }) const active = launched + await active.spawned const { client } = active for (const step of input.steps) { diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 975b1bb852..3508b02ec5 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -53,6 +53,8 @@ export interface AcpTestLaunchOptions { export interface LaunchedAcpTestAgent { /** The child process, exposed for process-level assertions. */ child: ChildProcessWithoutNullStreams + /** Resolve when the OS spawns the child; reject with its asynchronous spawn failure. */ + spawned: Promise /** The SDK connection backed by the child's stdio. */ client: ClientSideConnection /** Session updates in receive order. */ @@ -90,6 +92,18 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe stdio: ['pipe', 'pipe', 'pipe'], }, ) + // A spawn-level failure is an asynchronous `error` event. Observe it in the + // same tick as spawn so a missing cwd or OS rejection cannot crash the test + // runner, then make startup and shutdown surface the original error. + const childFailure = new Promise(resolve => child.once('error', resolve)) + const spawned = Promise.race([ + new Promise(resolve => child.once('spawn', resolve)), + childFailure.then((error): never => { throw error }), + ]) + // `spawned` is public and close() also awaits it, but a caller may ignore both. + // Keep that misuse from turning the already-observed child error into an + // unhandled promise rejection. + void spawned.catch(() => undefined) const stderrChunks: string[] = [] child.stderr.setEncoding('utf8') @@ -141,16 +155,22 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe return { child, + spawned, client, updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { + await spawned if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() else child.kill(signal) - await waitForExit(child) + const failure = await Promise.race([ + waitForExit(child).then((): undefined => undefined), + childFailure, + ]) + if (failure !== undefined) throw failure }, } } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index db715db90c..69c02a407f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -40,6 +40,13 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('surfaces an asynchronous child spawn failure through startup and close', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) + await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + }) + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) @@ -72,7 +79,11 @@ describe('runScenario', () => { // The minimal shape needs no environment or config override. const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - await minimal.close() + const childFailure = new Error('child process failed') + const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + minimal.child.emit('error', childFailure) + await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) + await exited }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From e9d1e1cdda70eedb49a12f9adce2afb18caa4c00 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:19:24 +0800 Subject: [PATCH 023/140] docs: update ACP ownership routing --- .../rfc/implemented/feature/2026-06-14-acp-multi-session.md | 4 ++-- .../rfc/implemented/feature/2026-06-25-ask-user-question.md | 2 +- docs/rfc/implemented/feature/2026-07-06-approval-seam.md | 6 +++--- packages/ui/acp/README.md | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md index 77fa2b4669..64961bee89 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md @@ -8,11 +8,11 @@ An ACP editor can keep several conversations alive over one agent subprocess. A ## Decision -The ACP bridge stores live sessions in `Map` and keeps a `WeakMap` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. +The ACP bridge stores live sessions in `Map`. Agent-scoped callbacks use `ownedRecord`: look up `agent.session.id` in that forward map and accept the record only when it owns the exact agent object, so a foreign same-id object cannot claim the session. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path. -Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. +Permission ownership uses the same exact-agent check against the forward map. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it. diff --git a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md index 9320189de1..42e5d9a7ab 100644 --- a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md +++ b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md @@ -22,7 +22,7 @@ Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is alway `dsh-stdio-agent`'s in-package readline module renders each question, shows each option's `description` on the next line, supports comma/space-separated numeric choices for `multi_select`, accepts free-form custom answers, and rejects pending questions on abort, provider disposal, or stdin EOF. A batched request is asked in order and resolved as one answer object. The stdio provider serializes simultaneous requests with an internal queue so only one prompt owns stdin at a time. -`dsh-acp` provides the same seam for ACP sessions. It routes an ask request from the calling `Agent` through the bridge's `agent→sessionId` reverse map and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. +`dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. The ACP mapping deliberately uses elicitation, not `session/request_permission`. `request_permission` is still reserved for the separate permission gate: it is a yes/no-or-policy authorization protocol around tool execution. `ask_user_question` is a general information-gathering tool with optional free-form answers, so ACP form elicitation is the closer protocol fit. The bridge's session routing is shared with the future permission gate, but the user intent is different. diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 5d82226a96..c5d61b0edb 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -65,9 +65,9 @@ The seam also owns the session-scoped approval policy — the approval knob of t #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. -The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). +The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees @@ -137,5 +137,5 @@ In-repo precedents this design copies or contrasts with: - The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses. - `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. - [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. -- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. +- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. - The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..4b9a278707 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -75,7 +75,7 @@ A `session/prompt` resolves or rejects exactly once from the canonical `session/ ## Permission prompts -The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning session through the reverse map and issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. +The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning `SessionRecord` through `ownedRecord`, which looks up `agent.session.id` in the forward session map and requires the record to own that exact agent object. It then issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. ## Disposal & disconnect From 140d32681ef2fc4b35dbae710044c7b7c4e693b7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:33:22 +0800 Subject: [PATCH 024/140] fix: make ACP test teardown failure-safe --- examples/acp-agent/tests/acp.e2e.ts | 14 ++++-- examples/acp-agent/tests/hooks.e2e.ts | 14 ++++-- .../sandbox-acp-agent/tests/escalation.e2e.ts | 14 ++++-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 44 ++++++++++++------- packages/support/acp-snapshot/src/launcher.ts | 25 +++++++++-- .../acp-snapshot/tests/harness.spec.ts | 8 ++-- 7 files changed, 86 insertions(+), 35 deletions(-) diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 4b6c675208..871006dfb4 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -30,10 +30,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index a553addc96..8dc169f437 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -38,10 +38,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index a7e8787e36..0ddaa6426e 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -81,10 +81,16 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 0058e9116f..26192f1cac 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index d04b0bc2b5..3db1355b0f 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -163,7 +163,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - try { + const outcome = await (async (): Promise => { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens // normalize the cwd, so the seeded paths stay stable across runs. @@ -231,22 +231,36 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) - } finally { - // Failure-safe teardown: kill a still-running child and drop the temp dirs - // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `launched` is undefined only if launch itself threw. - await launched?.close('SIGKILL') - await rm(cwd, { recursive: true, force: true }) - await rm(sessionsRoot, { recursive: true, force: true }) - } + return { + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), + cwd, + ...sessionId !== undefined ? { sessionId } : {}, + sessionLogs, + } + })().then( + value => ({ status: 'fulfilled', value } as const), + (error: unknown) => ({ status: 'rejected', error } as const), + ) - return { - rawStdout: launched.rawStdout(), - stderr: launched.stderr(), - cwd, - ...sessionId !== undefined ? { sessionId } : {}, - sessionLogs, + // Failure-safe teardown: wait for a still-running child, then attempt BOTH + // directory removals even when an earlier cleanup rejects. The main outcome + // wins over teardown noise so a step/harvest failure is never replaced; on a + // successful run, the first cleanup failure remains visible to the caller. + const cleanupResults: PromiseSettledResult[] = [] + const cleanup = async (action: () => Promise): Promise => { + cleanupResults.push(...await Promise.allSettled([action()])) } + /* v8 ignore next 1 -- launch itself can only throw on a defensive synchronous spawn API failure */ + await cleanup(() => launched?.close('SIGKILL') ?? Promise.resolve()) + await cleanup(() => rm(cwd, { recursive: true, force: true })) + await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + + if (outcome.status === 'rejected') throw outcome.error + const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') + /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ + if (cleanupFailure !== undefined) throw cleanupFailure.reason + return outcome.value } /** Drive one input step over the client connection. */ diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3508b02ec5..7f2ec9b0a7 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -95,7 +95,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // A spawn-level failure is an asynchronous `error` event. Observe it in the // same tick as spawn so a missing cwd or OS rejection cannot crash the test // runner, then make startup and shutdown surface the original error. - const childFailure = new Promise(resolve => child.once('error', resolve)) + // Keep observing after the first error: a fallback kill attempted during + // shutdown may itself report another process error, which must not become an + // unhandled EventEmitter error after the promise has already settled. + const childFailure = new Promise(resolve => child.on('error', resolve)) const spawned = Promise.race([ new Promise(resolve => child.once('spawn', resolve)), childFailure.then((error): never => { throw error }), @@ -163,14 +166,23 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { await spawned - if (child.exitCode !== null || child.signalCode !== null) return + if (!isRunning(child)) return + const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) const failure = await Promise.race([ - waitForExit(child).then((): undefined => undefined), + exited.then((): undefined => undefined), childFailure, ]) - if (failure !== undefined) throw failure + if (failure === undefined) return + + // An `error` after spawn is not an exit edge: in particular, a failed + // signal can leave the subprocess live. Force termination, await the + // already-observed exit edge, and only then propagate the child error so + // callers may safely remove cwd/session resources after close rejects. + child.kill('SIGKILL') + await exited + throw failure }, } } @@ -179,3 +191,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe function waitForExit(child: ChildProcessWithoutNullStreams): Promise { return new Promise(resolve => child.once('exit', () => { resolve() })) } + +/** Whether the child still lacks either OS termination marker. */ +function isRunning(child: ChildProcessWithoutNullStreams): boolean { + return child.exitCode === null && child.signalCode === null +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 69c02a407f..3c1bb0d44a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -80,10 +80,12 @@ describe('runScenario', () => { const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const childFailure = new Error('child process failed') - const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + let exited = false + minimal.child.once('exit', () => { exited = true }) minimal.child.emit('error', childFailure) - await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) - await exited + await expect(minimal.close('SIGTERM')).rejects.toBe(childFailure) + // close rejects only after the fallback SIGKILL has produced an exit edge. + expect(exited).toBe(true) }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From 58e61ae20ba28101be0bed01505b03ec20cd6a7e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:37:58 +0800 Subject: [PATCH 025/140] fix: retain stdio target across agent replacement --- packages/ui/stdio-agent/src/stdio-chat.ts | 19 +++++++++++------ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 21 +++++++++++++++++++ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index cb9ce0bc10..bfb58e3a57 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,13 +95,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns exactly one pre-created agent. Hold the live object directly: - // its per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one root agent. Hold the live object directly: its per-run id + // is intentionally fresh, while `main` remains only the terminal's fixed + // display label. HMR may publish the replacement before old teardown emits + // disposed, so a target disposal reselects the surviving root from the live + // registry instead of leaving the terminal detached. Fork children carry + // parentSession lineage and must never become the terminal target. + const rootAgent = (): Agent | undefined => + ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) + let target: Agent | undefined = rootAgent() + ctx.on('agent/created', (agent) => { + if (target === undefined && agent.session.header.parentSession === undefined) target = agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined + if (target === agent) target = rootAgent() }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 69ca5f8837..2b1df53921 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -230,6 +230,27 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) + it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { + const { ctx, input } = await setup() + const oldRoot = makeAgent('old-root') + const child = makeAgent('child') + ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id + const replacement = makeAgent('replacement') + const disposeOld = ctx.agents.register(oldRoot) + ctx.agents.register(child) + ctx.agents.register(replacement) + + // The replacement's created edge arrived while oldRoot was still targeted. + // Once oldRoot is removed, registry order is child then replacement; the + // UI must skip the surviving child and route input to the replacement root. + disposeOld() + input.feed('after hmr') + await new Promise(resolve => setImmediate(resolve)) + + expect(child.sent).toEqual([]) + expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session From 3bd2052d7251b9500e8afca02aaee64ca8b2ad40 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:52:46 +0800 Subject: [PATCH 026/140] fix: allow lineage-bearing stdio targets --- packages/ui/stdio-agent/src/stdio-chat.ts | 24 +++++++++---------- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 17 ++++++++++++- 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index bfb58e3a57..2a4d620494 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,20 +95,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one root agent. Hold the live object directly: its per-run id - // is intentionally fresh, while `main` remains only the terminal's fixed - // display label. HMR may publish the replacement before old teardown emits - // disposed, so a target disposal reselects the surviving root from the live - // registry instead of leaving the terminal detached. Fork children carry - // parentSession lineage and must never become the terminal target. - const rootAgent = (): Agent | undefined => - ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) - let target: Agent | undefined = rootAgent() - ctx.on('agent/created', (agent) => { - if (target === undefined && agent.session.header.parentSession === undefined) target = agent - }) + // This app owns one configured agent. Hold the live object directly: its + // per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. At install the configured agent is the + // earliest registry entry (it creates any subagents later). During HMR the + // replacement is published after the old tree, so when old teardown finally + // emits disposed, the newest survivor is the replacement. Persisted + // parentSession lineage is deliberately irrelevant: a resumed child session + // can itself be this process's configured top-level agent. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = rootAgent() + if (target === agent) target = ctx.agents.list().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2b1df53921..2654a05680 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -185,6 +185,9 @@ describe('createStdioChat rendering', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) const agent = makeAgent('main') + // Durable lineage does not imply runtime child ownership: the stdio app + // may explicitly resume a persisted fork as its one configured agent. + ;(agent.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(agent) // registered BEFORE the UI plugin below const { runtime, out } = makeRuntime() await ctx.plugin(Object.assign((inner: Context) => { @@ -196,6 +199,18 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) + it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + const { ctx, input } = await setup() + const resumed = makeAgent('resumed') + ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' + ctx.emit('agent/created', resumed) + + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + + expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) + }) + it('resets dim styling at turn/end if a turn ends mid-reasoning', async () => { const { ctx, out } = await setup() const session = makeSession('main') @@ -242,7 +257,7 @@ describe('createStdioChat rendering', () => { // The replacement's created edge arrived while oldRoot was still targeted. // Once oldRoot is removed, registry order is child then replacement; the - // UI must skip the surviving child and route input to the replacement root. + // most recently published survivor is the HMR replacement. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) From e2a5a160d3763ee7faaa9b4235ae7284144f05ee Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:00:10 +0800 Subject: [PATCH 027/140] fix: settle ACP update waiters on shutdown --- packages/support/acp-snapshot/src/launcher.ts | 43 ++++++++++++++----- .../acp-snapshot/tests/harness.spec.ts | 3 ++ 2 files changed, 36 insertions(+), 10 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 7f2ec9b0a7..253e67fd5a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -114,18 +114,26 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const rawBuffers: Buffer[] = [] const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buffer: Buffer) => { - rawBuffers.push(buffer) - passthrough.push(buffer) - }) - child.stdout.on('end', () => passthrough.push(null)) - const updates: SessionNotification['update'][] = [] const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void reject: (reason: unknown) => void }[] = [] + let updateStreamFailure: Error | undefined + const closeUpdateStream = (): void => { + if (updateStreamFailure !== undefined) return + updateStreamFailure = new Error('ACP test agent update stream closed before a matching session update arrived') + for (const waiter of updateWaiters.splice(0)) waiter.reject(updateStreamFailure) + } + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => { + passthrough.push(null) + closeUpdateStream() + }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, @@ -163,10 +171,21 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), + waitForUpdate(match): Promise { + if (updateStreamFailure !== undefined) return Promise.reject(updateStreamFailure) + return new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })) + }, async close(signal?: NodeJS.Signals): Promise { - await spawned - if (!isRunning(child)) return + try { + await spawned + } catch (error: unknown) { + closeUpdateStream() + throw error + } + if (!isRunning(child)) { + closeUpdateStream() + return + } const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) @@ -174,7 +193,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe exited.then((): undefined => undefined), childFailure, ]) - if (failure === undefined) return + if (failure === undefined) { + closeUpdateStream() + return + } // An `error` after spawn is not an exit edge: in particular, a failed // signal can leave the subprocess live. Force termination, await the @@ -182,6 +204,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + closeUpdateStream() throw failure }, } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 3c1bb0d44a..192d36dc6c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -73,7 +73,10 @@ describe('runScenario', () => { expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') expect(launched.stderr()).toContain('launcher stderr') + const unmatched = expect(launched.waitForUpdate(() => false)).rejects.toThrow(/update stream closed/) await launched.close() + await unmatched + await expect(launched.waitForUpdate(() => true)).rejects.toThrow(/update stream closed/) await launched.close('SIGKILL') // The minimal shape needs no environment or config override. From c2979322c8b938b1c2e91920740688788867e6d7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:13:42 +0800 Subject: [PATCH 028/140] fix: keep stdio targeting on runtime roots --- docs/cordis-catalog/services.md | 5 ++-- packages/core/agent-loop/src/index.ts | 2 +- .../agent-loop/tests/scope-lifecycle.spec.ts | 18 +++++++++++++ packages/core/agent/README.md | 3 ++- packages/core/agent/src/index.ts | 22 ++++++++++++++-- packages/core/agent/tests/agent.spec.ts | 24 +++++++++++++++--- packages/ui/stdio-agent/src/stdio-chat.ts | 20 +++++++-------- .../ui/stdio-agent/tests/readline.spec.ts | 4 +-- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 25 ++++++++++++------- 9 files changed, 92 insertions(+), 31 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..1366fcf6f6 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -30,15 +30,16 @@ setFactory(factory: AgentFactory): () => void async create(options: CreateAgentOptions): Promise async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void -enter(agent: Agent): () => void +enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined list(): Agent[] +roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..dbe503ff6a 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -229,7 +229,7 @@ class AgentCreationTransaction { this.publishing = true try { this.detachSession = agent.ctx.sessions.enter(session) - this.detachAgent = this.loopCtx.agents.enter(agent) + this.detachAgent = this.loopCtx.agents.enter(agent, this.ownerAgent) agent.ctx.sessions.announce(session) this.assertActive() diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index e29e73c393..610e077a67 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -149,6 +149,24 @@ describe('agent scope lifecycle', () => { await ctx.agents.get(SessionId('a1'))?.whenIdle() }) + it('records agents created through an agent context as non-root runtime children', async () => { + const ctx = await harness() + const root = await ctx.agents.create({ + sessionId: SessionId('runtime-root'), + agentOptions: { model: 'mock' }, + }) + const child = await root.agent.ctx.agents.create({ + sessionId: SessionId('runtime-child'), + agentOptions: { model: 'mock' }, + }) + + expect(ctx.agents.list()).toEqual([root.agent, child.agent]) + expect(ctx.agents.roots()).toEqual([root.agent]) + + await child.dispose() + await root.dispose() + }) + it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 4eddb050d5..643c15002b 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,9 +11,10 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` +- `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 1306e8004d..b25d1e3cac 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -178,6 +178,8 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug interface AgentEntry { readonly id: SessionId readonly agent: Agent + /** Runtime creator-agent ownership; independent of durable session lineage. */ + readonly owner: Agent | undefined readonly carrier: Scoped announced: boolean announcing: boolean @@ -303,7 +305,7 @@ export class AgentRegistry extends Service { */ register(agent: Agent): () => void { const dispose = this.ctx.effect(function* (this: AgentRegistry) { - yield this.enter(agent) + yield this.enter(agent, this.ctx.agent) this.announce(agent) }.bind(this), 'agents.register()') // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity @@ -317,12 +319,15 @@ export class AgentRegistry extends Service { * returned detach closure into its pre-installed composite teardown before * calling {@link announce}. Ordinary callers use {@link register}. * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. * @returns an idempotent closure that removes this exact entry and emits * `agent/disposed` with listener failures contained. When called from a * synchronous `agent/created` listener, removal and disposal wait until * that creation dispatch unwinds. */ - enter(agent: Agent): () => void { + enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume @@ -331,6 +336,7 @@ export class AgentRegistry extends Service { const entry: AgentEntry = { id, agent, + owner, carrier, announced: false, announcing: false, @@ -438,6 +444,18 @@ export class AgentRegistry extends Service { list(): Agent[] { return [...this.store.values()].map(entry => entry.agent) } + + /** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ + roots(): Agent[] { + return [...this.store.values()] + .filter(entry => entry.owner === undefined) + .map(entry => entry.agent) + } } export default AgentRegistry diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index cba833b212..5563d01cad 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -42,6 +42,7 @@ describe('AgentRegistry', () => { const dispose = ctx.agents.register(agent) expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.agents.list()).toEqual([agent]) + expect(ctx.agents.roots()).toEqual([agent]) expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/) dispose() @@ -49,6 +50,23 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('tracks runtime creator ownership separately from registry order', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const root = stubAgent('root') + const child = stubAgent('child') + const detachRoot = ctx.agents.enter(root, undefined) + ctx.agents.announce(root) + const detachChild = ctx.agents.enter(child, root) + ctx.agents.announce(child) + + expect(ctx.agents.list()).toEqual([root, child]) + expect(ctx.agents.roots()).toEqual([root]) + + detachChild() + detachRoot() + }) + it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -94,7 +112,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) const first = stubAgent('split') - const detachFirst = ctx.agents.enter(first) + const detachFirst = ctx.agents.enter(first, undefined) expect(lifecycle).toEqual([]) ctx.agents.announce(first) expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/) @@ -102,7 +120,7 @@ describe('AgentRegistry', () => { detachFirst() const replacement = stubAgent('split') - const detachReplacement = ctx.agents.enter(replacement) + const detachReplacement = ctx.agents.enter(replacement, undefined) detachFirst() expect(ctx.agents.get(replacement.id)).toBe(replacement) expect(() => { ctx.agents.announce(first) }).toThrow(/not live/) @@ -122,7 +140,7 @@ describe('AgentRegistry', () => { }) ctx.on('agent/created', () => void order.push(`second:${ctx.agents.get(agent.id) === agent}`)) ctx.on('agent/disposed', () => void order.push('disposed')) - const detach = ctx.agents.enter(agent) + const detach = ctx.agents.enter(agent, undefined) ctx.agents.announce(agent) expect(order).toEqual(['first:true', 'after-detach:true', 'second:true', 'disposed']) expect(ctx.agents.get(agent.id)).toBeUndefined() diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 2a4d620494..a295274786 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,18 +95,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured agent. Hold the live object directly: its - // per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. At install the configured agent is the - // earliest registry entry (it creates any subagents later). During HMR the - // replacement is published after the old tree, so when old teardown finally - // emits disposed, the newest survivor is the replacement. Persisted - // parentSession lineage is deliberately irrelevant: a resumed child session - // can itself be this process's configured top-level agent. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one configured top-level agent. Hold the live object + // directly: its per-run id is intentionally fresh, while `main` remains only + // the terminal's fixed display label. Runtime creator ownership distinguishes + // that root from its subagents even if a child is registered after an HMR + // replacement. Persisted parentSession lineage is deliberately irrelevant: + // a resumed child session can itself be this process's configured root. + let target: Agent | undefined = ctx.agents.roots()[0] + ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.list().at(-1) + if (target === agent) target = ctx.agents.roots().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index 6116aa356f..fa82db4d96 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,9 +16,9 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its target object from the registry at install; this suite only + // The UI seeds its root target from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. - agents: { list: vi.fn(() => []) }, + agents: { roots: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, } as unknown as Context } diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2654a05680..2600fdb24f 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -154,8 +154,7 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created supplies the app-owned target object. - ctx.emit('agent/created', agent) + ctx.agents.register(agent) const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, @@ -203,7 +202,7 @@ describe('createStdioChat rendering', () => { const { ctx, input } = await setup() const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' - ctx.emit('agent/created', resumed) + ctx.agents.register(resumed) input.feed('continue') await new Promise(resolve => setImmediate(resolve)) @@ -224,8 +223,8 @@ describe('createStdioChat rendering', () => { it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - ctx.emit('agent/created', agent) - ctx.emit('agent/disposed', agent) + const dispose = ctx.agents.register(agent) + dispose() // After disposal the event belongs to a non-target session, so its durable // identity is rendered directly. ctx.emit('session/event', agent.session, { @@ -237,7 +236,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() const target = makeAgent('target') - ctx.emit('agent/created', target) + ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, @@ -251,19 +250,27 @@ describe('createStdioChat rendering', () => { const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id const replacement = makeAgent('replacement') + const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) - ctx.agents.register(child) + const disposeChild = ctx.agents.enter(child, oldRoot) + ctx.agents.announce(child) ctx.agents.register(replacement) + const disposeLateChild = ctx.agents.enter(lateChild, replacement) + ctx.agents.announce(lateChild) // The replacement's created edge arrived while oldRoot was still targeted. - // Once oldRoot is removed, registry order is child then replacement; the - // most recently published survivor is the HMR replacement. + // A replacement-owned child then arrived even later. Once oldRoot is + // removed, runtime ownership still identifies replacement as the only + // surviving root instead of selecting either newer child by insertion order. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) expect(child.sent).toEqual([]) + expect(lateChild.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + disposeLateChild() + disposeChild() }) it('renders tool/call and tool/result session events', async () => { From 0b492e6e62be53abb8560d16f806a4078f56c651 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:22:22 +0800 Subject: [PATCH 029/140] fix: drain ACP test launcher streams --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/launcher.ts | 17 +++++++++++++-- .../tests/fixtures/fake-acp-agent.ts | 21 +++++++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 21 +++++++++++++++++++ 4 files changed, 58 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 26192f1cac..b95615abea 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 253e67fd5a..815753ae5f 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, and wait for process exit. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ close(signal?: NodeJS.Signals): Promise } @@ -132,7 +132,6 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe }) child.stdout.on('end', () => { passthrough.push(null) - closeUpdateStream() }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -163,6 +162,17 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), }) const client = new ClientSideConnection(makeClient, stream) + // `exit` only reports the parent process's status. Descendants may retain + // inherited stdout/stderr handles and buffered ACP frames may still be + // crossing the SDK parser. Node's `close` follows stdio closure; the SDK's + // `closed` follows parser exhaustion. Capture both eagerly so a caller that + // invokes close after process exit still joins the complete drain boundary. + const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) + const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + // A caller may await a pending update without calling close(). Make natural + // stream exhaustion terminal for those waiters too, but only after the + // parser has dispatched every buffered frame. + void client.closed.then(closeUpdateStream) return { child, @@ -183,6 +193,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe throw error } if (!isRunning(child)) { + await drained closeUpdateStream() return } @@ -194,6 +205,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe childFailure, ]) if (failure === undefined) { + await drained closeUpdateStream() return } @@ -204,6 +216,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + await drained closeUpdateStream() throw failure }, diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index 861c9d2b04..9b0760213c 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -18,6 +18,7 @@ import { mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { readdirSync } from 'node:fs' +import { spawn } from 'node:child_process' import { dirname, join } from 'node:path' import { randomUUID } from 'node:crypto' import { createInterface } from 'node:readline' @@ -50,6 +51,8 @@ interface Behavior { echoWorkspace?: boolean /** Write a line to stderr on boot (spec-side stderr-capture assertions). */ stderrNote?: string + /** Let a short-lived descendant retain stdio and emit one final ACP update plus stderr line after this parent exits. */ + lateInheritedOutput?: boolean /** Session logs to persist on stdin EOF. */ logs?: ScriptedLog[] /** Leave a stray FILE directly under the sessions root (harvest must skip it). */ @@ -256,6 +259,24 @@ function flushLogsAndExit(): void { writeFileSync(join(sessionsRoot, 'bucket-noise', 'notes.txt'), 'not a session log\n') } if (behavior.deleteSessionsRoot === true) rmSync(sessionsRoot, { recursive: true, force: true }) + if (behavior.lateInheritedOutput === true) { + const frame = JSON.stringify({ + jsonrpc: '2.0', + method: 'session/update', + params: { + sessionId, + update: { + sessionUpdate: 'agent_message_chunk', + content: { type: 'text', text: 'late inherited stdout' }, + }, + }, + }) + const code = [ + `setTimeout(() => process.stdout.write(${JSON.stringify(`${frame}\n`)}), 50)`, + `setTimeout(() => process.stderr.write(${JSON.stringify('late inherited stderr\n')}), 75)`, + ].join(';') + spawn(process.execPath, ['-e', code], { stdio: ['ignore', 1, 2] }).unref() + } process.exit(0) } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 192d36dc6c..051db6a0ba 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -91,6 +91,27 @@ describe('runScenario', () => { expect(exited).toBe(true) }) + it('waits for inherited stdio and buffered ACP parsing after the parent exits', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ lateInheritedOutput: true }) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const lateUpdate = launched.waitForUpdate(update => + update.sessionUpdate === 'agent_message_chunk' + && update.content.type === 'text' + && update.content.text === 'late inherited stdout') + + await launched.close() + + await expect(lateUpdate).resolves.toMatchObject({ sessionUpdate: 'agent_message_chunk' }) + expect(launched.rawStdout()).toContain('late inherited stdout') + expect(launched.stderr()).toContain('late inherited stderr') + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 99b5f04c9bb5ff2ac78d9cc30ce22d65a181c097 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:26:46 +0800 Subject: [PATCH 030/140] fix: use unified identity for bash ownership --- docs/core-data-structures/bash.md | 2 +- ...-18-agent-lifecycle-and-ownership-seams.md | 4 +- .../architecture/2026-06-20-branded-ids.md | 4 +- packages/bash/bash/src/types.ts | 2 +- packages/bash/tool-bash/README.md | 4 +- packages/bash/tool-bash/src/index.ts | 22 ++++----- packages/bash/tool-bash/tests/tools.spec.ts | 46 +++++++++---------- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- 8 files changed, 40 insertions(+), 47 deletions(-) diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index df6c5ab16b..0cc82e5165 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -37,7 +37,7 @@ interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index d64329262e..d75ec379fc 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -22,7 +22,7 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit ### 3. Bash owner token in the seam -Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.session.header.id` as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.session.header.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## Verification @@ -35,7 +35,7 @@ These invariants hold and are pinned by tests: ## Session owner tokens are unique among live agents -The bash owner-token comparison relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. +The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 4fe7f58168..fd5c5bf953 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/bash/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -18,7 +18,7 @@ A type-only change. Brands are zero-cost casts; nothing about runtime behavior, - **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). -- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) +- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) - **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..c4c48645e1 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -117,7 +117,7 @@ export interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 800de0132c..c4ea498e07 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -34,7 +34,7 @@ Result text: stdout, then a `[stderr]` section, then status markers — `[sandbo ### Task ownership (cross-session isolation) -The owning agent's session token (`session.header.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token (`session.header.id`) with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +The owning agent's shared registry/session id (`agent.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's shared id with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## UI presentation @@ -42,7 +42,7 @@ These tools own how their calls render in a UI (an editor's tool-call card) via ## Background completion notices -When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The owning agent is found by its session token: the listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for an agent whose `session.header.id` matches (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. +When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for that shared agent/session id (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. ## The tool builds its request from named args only diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..fe07b80989 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -12,7 +12,7 @@ * `bash_output`. * * Task ownership: a background task's OWNER is an opaque token — the owning - * agent's `session.header.id` — passed to the executor at spawn + * agent's shared `id` — passed to the executor at spawn * (`resolve({ …, owner })`) and stored ON THE TASK inside the executor * (`@deepseek-ai/dsh-bash`'s `ownerOf(id)` seam), NOT in a plugin-local map. * `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token @@ -414,16 +414,12 @@ export function apply(ctx: Context): void { }) /** - * The caller's owner TOKEN — the owning agent's `session.header.id`, or - * `undefined` for a non-agent caller. Read `session.header.id` (NOT - * `session.id`): every other subsystem keys off the header id (the ACP bridge, - * both persistence backends), and the sibling `resolveWorkdir` already reads - * `session.header.cwd`, so using `session.id` here would be the asymmetry smell - * the conventions flag. The two are equal in production, but the header is the - * canonical identity. + * The caller's owner TOKEN — the owning agent's shared registry/session id, + * or `undefined` for a non-agent caller. Agent and Session deliberately have + * one live identity; workdir remains separate session metadata. */ const callerToken = (exec: { agent?: Agent }): OwnerToken | undefined => - exec.agent ? OwnerToken(exec.agent.session.header.id) : undefined + exec.agent ? OwnerToken(exec.agent.id) : undefined /** * Authorize a `bash_output`/`bash_kill` call against the task's stored owner @@ -443,18 +439,16 @@ export function apply(ctx: Context): void { } // Background completion → inject a notice into the owning agent's session. - // Find the live agent by its session id token via the agent registry, read + // Find the live agent by its shared registry/session token, read // opportunistically with `ctx.get('agents')` (NOT `ctx.agents`/static inject): // this listener runs from `task.done.then` on the bash fiber — a foreign // fiber — where the `ctx.agents` property proxy would throw through the // traceable shadow; `ctx.get(name)` is the topology-independent lookup. No - // registry mounted (`undefined`) → drop the notice. Match on - // `agent.session.header.id`, NOT the registry key: a config agent's id differs - // from its session id, and the owner token IS the session id. + // registry mounted (`undefined`) → drop the notice. ctx.bash.onTaskDone((task) => { const ownerToken = ctx.bash.ownerOf(task.id) if (ownerToken === undefined) return - const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.session.header.id) === ownerToken) + const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.id) === ownerToken) if (!agent) return try { agent.inject( diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index c68c445f0a..639dd8631a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -47,22 +47,16 @@ async function setup() { } /** - * Build a fake {@link Agent} whose session token is `sessionId`, REGISTER it in - * `ctx.agents` (the completion-notice path finds the owning agent by scanning - * the registry for a matching `session.header.id`), and return it. The returned + * Build a fake {@link Agent} with the shared registry/session `sessionId`, + * REGISTER it in `ctx.agents`, and return it. The returned * agent is also passed to `execute` as `exec.agent` so it owns the spawned task. * The registration disposer is tracked so {@link unregisterFakeAgents} can drop * it (simulating the owning session disconnecting before a task completes). */ const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { - // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id), which is also the agent's durable id. The - // owner token IS the session id, so the notice path must find the agent by - // `session.header.id`, NOT the registry key. Using distinct values here makes - // the test fail if a regression matched on the wrong field (a same-value fake - // would pass either way — the "hits the line but not the scenario" trap). - const agent = { id: `agent-${sessionId}`, inject, session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as unknown as Agent + const id = SessionId(sessionId) + const agent = { id, inject, session: new Session(id) } as unknown as Agent const dispose = ctx.agents.register(agent) const list = fakeAgentDisposers.get(ctx) ?? [] list.push(dispose) @@ -418,9 +412,9 @@ describe('background tools', () => { it('injects a completion notice into the owning agent (found via the registry by session token)', async () => { const ctx = await setup() const inject = vi.fn() - // The notice path looks the agent up in ctx.agents by its session token, so + // The notice path looks the agent up in ctx.agents by its shared id, so // the agent must be REGISTERED (not merely passed to execute). Mount a - // registry and register a fake whose session.header.id IS the owner token. + // registry and register a fake whose agent/session id IS the owner token. const agent = registerFakeAgent(ctx, 'bg', inject) const started = await ctx.tools.execute({ @@ -517,13 +511,14 @@ describe('background task ownership (cross-session isolation)', () => { function callAs(ctx: Context, agent: import('@deepseek-ai/dsh-agent').Agent | undefined, name: string, args: unknown) { return ctx.tools.execute({ callId: CallId(`own-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} }) } - // Ownership is by TOKEN (session.header.id), NOT agent object identity — so - // each agent needs a DISTINCT session id, else every fake yields the same + // Ownership is by the shared agent/session TOKEN, NOT agent object identity — + // so each agent needs a DISTINCT id, else every fake yields the same // token and the isolation tests pass for the wrong reason (all tasks owned by - // the same token). The impl reads `session.header.id`, so the fakes MUST carry - // it. - const fakeAgent = (sessionId: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: sessionId, createdAt: 0 } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + // the same token). + const fakeAgent = (sessionId: string) => { + const id = SessionId(sessionId) + return { id, inject: () => undefined, session: new Session(id) } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('rejects bash_output/bash_kill for a task owned by a DIFFERENT session token', async () => { const ctx = await setup() @@ -548,7 +543,7 @@ describe('background task ownership (cross-session isolation)', () => { }) it('a DIFFERENT Agent object with the SAME session token may access the task (ownership is by token, not object identity)', async () => { - // Ownership fences by session.header.id, NOT Agent object identity. Two + // Ownership fences by the shared id, NOT Agent object identity. Two // distinct Agent objects sharing one session token (e.g. an agent re-created // on the same session) are the SAME owner. const ctx = await setup() @@ -638,8 +633,10 @@ describe('session-cwd routing (per-session workdir)', () => { return ctx.tools.execute({ callId: CallId(`cwd-${++callCounter}`), name: 'bash', arguments: args, ...agent ? { agent } : {} }) } // An agent whose session header carries a cwd (what session/new records). - const agentInCwd = (cwd: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: 'c', createdAt: 0, cwd } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + const agentInCwd = (cwd: string) => { + const id = SessionId('c') + return { id, inject: () => undefined, session: { header: { version: 0, id, createdAt: 0, cwd } } } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('defaults bash to the agent\'s session cwd (not the server launch dir)', async () => { const ctx = await setup() @@ -1188,10 +1185,11 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { * enforces the enclosure. */ function escalationAgent(events: Array<{ type: string; data: Record }>): Agent { + const id = SessionId('sess-esc') return { - id: 'agent-esc', + id, session: { - header: { version: 0, id: 'sess-esc', createdAt: 0 }, + header: { version: 0, id, createdAt: 0 }, events: [{ type: 'turn/start' }], append: (type: string, data: Record) => { events.push({ type, data }) }, }, @@ -1406,7 +1404,7 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const injected: string[] = [] const agent = { - id, + id: SessionId(id), session, inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') }, } as unknown as Agent diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { From 03f91a547183919422aeb1d699af58d678a8984d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:29:40 +0800 Subject: [PATCH 031/140] fix: retain local subagent completion identity --- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 +++++++++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 23 ++++++++++++- 4 files changed, 45 insertions(+), 17 deletions(-) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 2324227ff7..735cfead0a 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 3c803a6c8c..bf21f7fc2d 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,6 +58,11 @@ interface SessionRecord { activePrompt: boolean } +/** Runtime-local agent identity plus optional durable fork lineage. */ +interface LocalAgentRecord { + parentSessionId?: SessionId +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -71,7 +76,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentParents = new Map() + private readonly localAgents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -95,23 +100,24 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache parent lineage on creation: by the time `subagent/end` fires the - // child agent may already be disposed and gone from the registry. The child - // session id needs no cache because it is the shared agent/session id. + // Cache runtime-local identity and optional lineage on creation: by the + // time `subagent/end` fires the child agent may already be disposed and + // gone from the registry. Parent lineage is not required by the provider + // contract, so an empty record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession - if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) + this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const cachedParentSessionId = this.subagentParents.get(info.id) - this.subagentParents.delete(info.id) - // This protocol reports LOCAL child sessions, paired with the - // session/created-driven subagent.started notification above. A remote - // provider may use a real remote SessionId for its run, but that session - // does not exist in this harness and therefore has no paired start event. - if (cachedParentSessionId === undefined && agent === undefined) return - const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession + const cachedLocalAgent = this.localAgents.get(info.id) + this.localAgents.delete(info.id) + // This protocol reports LOCAL child sessions. A lineage-bearing child + // has the session/created-driven start notification above; a parentless + // local provider still gets its terminal notification. A remote provider + // has neither a cached creation nor a live local agent and is ignored. + if (cachedLocalAgent === undefined && agent === undefined) return + const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -189,7 +195,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentParents.clear() + this.localAgents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index e7f591b88f..163aee4c0c 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,15 +272,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + const parentlessHandle = await ctx.agents.create({ + sessionId: SessionId('parentless-child-session'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) // The backend may dispose the child before publishing its run outcome; - // only the cached parent lineage should be needed at this point. + // cached locality must survive with or without optional parent lineage. await handle.dispose() + await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'spawn', + id: SessionId('parentless-child-session'), + stopReason: 'error', + }) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -294,6 +305,16 @@ describe('HarnessSdkServer', () => { lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, }) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'spawn', + agentId: 'parentless-child-session', + childSessionId: 'parentless-child-session', + status: 'error', + stopReason: 'error', + }, + }) await parentHandle.dispose() await server.shutdown() From f02005c832b450d65d372c935c612c7d83eec54d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:39:28 +0800 Subject: [PATCH 032/140] fix: enforce unified agent startup invariants --- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 3 +++ packages/core/agent/tests/agent.spec.ts | 12 ++++++++- .../hooks/hooks-claude/tests/coverage.spec.ts | 8 +++--- packages/subagent/subagent-acp/src/run.ts | 11 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 3 +++ .../subagent-acp/tests/subagent-acp.spec.ts | 26 +++++++++++++++++++ 7 files changed, 55 insertions(+), 10 deletions(-) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 643c15002b..a45603f191 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,7 +11,7 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index b25d1e3cac..abafa38e45 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -329,6 +329,9 @@ export class AgentRegistry extends Service { */ enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id + if (id !== agent.session.id) { + throw new Error(`agent id "${id}" does not match session id "${agent.session.id}"`) + } const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5563d01cad..d2866cacb3 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -11,7 +11,7 @@ function stubAgent(rawId: string): Agent { return { id, options: {}, - session: new Session(SessionId(`${id}-session`)), + session: new Session(id), status: 'idle', ctx: new Context(), send() {}, @@ -50,6 +50,16 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('rejects an agent whose registry and session identities differ', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + + expect(() => ctx.agents.enter(agent, undefined)) + .toThrow('agent id "agent-id" does not match session id "session-id"') + expect(ctx.agents.list()).toEqual([]) + }) + it('tracks runtime creator ownership separately from registry order', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..0b41fd0d10 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,7 +4,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { Session, SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' @@ -209,7 +209,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const childId = SessionId('child-x') + const child = { id: childId, inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) @@ -225,7 +226,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const childId = SessionId('child-y') + const child = { id: childId, inject: () => { throw new Error('inject boom') }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 7d0c11cbe1..8ef49f0f7d 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -311,7 +311,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + const returnedSessionId: unknown = Reflect.get(session, 'sessionId') + if (typeof returnedSessionId !== 'string') throw new Error('ACP child published without a session id') + sessionId = returnedSessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -323,10 +325,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } - // The startup race can fulfill only after newSession assigned the id; this - // guard keeps that cross-closure invariant explicit for TypeScript. - /* v8 ignore next */ - if (sessionId === undefined) throw new Error('ACP child published without a session id') + // The startup transaction validates the returned id before it can fulfill. + // This assertion carries that cross-closure invariant into TypeScript. + if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId const result: Promise = (async (): Promise => { diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index 5145941526..f56404834b 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -19,6 +19,8 @@ * handler is in flight (it has streamed its chunk). A test * polls for this file to cancel on a CONDITION rather than * an arbitrary timeout (subprocess cold-start is variable). + * - `MOCK_MISSING_SESSION_ID` — if `1`, return a malformed empty `session/new` + * response to exercise startup rollback. * - `MOCK_FLUSH_ON_EOF` — if set, on stdin EOF the agent takes an async beat * (MOCK_FLUSH_DELAY_MS, default 150) simulating the real * acp-agent's EOF-driven quiesce+flush, then touches this @@ -99,6 +101,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } + if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index e5fe05384e..daa037ca20 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -195,6 +195,32 @@ describe('dsh-subagent-acp', () => { } }) + it('reaps a child whose session/new response omits the session id', async () => { + const tmp = mkdtempSync(join(tmpdir(), 'acp-malformed-session-')) + const flushed = join(tmp, 'flushed') + try { + await expect(startAcpRun(request(), { + command: process.execPath, + args: ['--import', tsxLoader, mockServer], + cwd: process.cwd(), + permission: 'reject', + env: { + MOCK_MISSING_SESSION_ID: '1', + MOCK_FLUSH_ON_EOF: flushed, + MOCK_FLUSH_DELAY_MS: '20', + TSX_TSCONFIG_PATH: repoTsconfig, + }, + disposeEofGraceMs: 1000, + disposeGraceMs: 100, + })).rejects.toThrow('ACP child published without a session id') + // Startup rejects only after its private child reaches quiescence. The + // marker proves rollback closed stdin and allowed the child's EOF flush. + expect(existsSync(flushed)).toBe(true) + } finally { + rmSync(tmp, { recursive: true, force: true }) + } + }) + it('dispose escalates SIGTERM → SIGKILL for a child that traps SIGTERM (bounded quiescence)', async () => { // The child traps SIGTERM and keeps its event loop alive, so a graceful // term alone would hang dispose forever. With a short grace, dispose must From a9c4fe2c4ba9f92a85117d60ad01ce1ee5930c69 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:43:01 +0800 Subject: [PATCH 033/140] test: exclude validated ACP assertion --- packages/subagent/subagent-acp/src/run.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 8ef49f0f7d..e135beb210 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -327,6 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe } // The startup transaction validates the returned id before it can fulfill. // This assertion carries that cross-closure invariant into TypeScript. + /* v8 ignore next */ if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId From 47812b45db85a9824530e800b12de1c82fdd6972 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:57:45 +0800 Subject: [PATCH 034/140] test: re-record Codex hook snapshot --- .../hook-codex-posttool-block/session.jsonl | 340 ++++++------------ .../stdout.golden.jsonl | 153 ++------ 2 files changed, 142 insertions(+), 351 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index ae105f6679..94bbbc5a08 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -1,222 +1,118 @@ -{"type":"session","version":0,"id":"7a5183c0-ec3a-46a8-a382-475eaa0c205b","createdAt":1783352220743,"cwd":"/tmp/acp-snap-cwd-vGnYqn"} -{"type":"turn/start","seq":0,"time":1783352220747,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352220748,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352220749,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352221651,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} -{"type":"assistant/chunk","seq":11,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":13,"time":1783352221709,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":14,"time":1783352221710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} -{"type":"assistant/chunk","seq":15,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} -{"type":"assistant/chunk","seq":16,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} -{"type":"assistant/chunk","seq":17,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} -{"type":"assistant/chunk","seq":18,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":19,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} -{"type":"assistant/chunk","seq":20,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":21,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":22,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":23,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":24,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":25,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":26,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":27,"time":1783352221794,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":28,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":29,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":30,"time":1783352221884,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":31,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":32,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":33,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":34,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":35,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":36,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":37,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":38,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"echo"}}} -{"type":"assistant/chunk","seq":39,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":40,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":41,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":42,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":43,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":44,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":46,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":47,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":48,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":49,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"Print"}}} -{"type":"assistant/chunk","seq":50,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":51,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":52,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":53,"time":1783352222058,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" to"}}} -{"type":"assistant/chunk","seq":54,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" stdout"}}} -{"type":"assistant/chunk","seq":55,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":56,"time":1783352222088,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":57,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."}}}} -{"type":"assistant/chunk","seq":58,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}}}} -{"type":"assistant/chunk","seq":59,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}}}} -{"type":"assistant/chunk","seq":60,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} -{"type":"tool/call","seq":62,"time":1783352222124,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}} -{"type":"hook/invoked","seq":63,"time":1783352222138,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} -{"type":"hook/result","seq":64,"time":1783352222148,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":9.571565000000192}} -{"type":"tool/result","seq":65,"time":1783352222148,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[62],"surfaceOp":"append"} -{"type":"step/end","seq":66,"time":1783352222149,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":67,"time":1783352222149,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":68,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":69,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":70,"time":1783352223301,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":71,"time":1783352223315,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":72,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":73,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":74,"time":1783352223343,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":75,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":76,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":77,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":78,"time":1783352223372,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":79,"time":1783352223406,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":80,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instruction"}}} -{"type":"assistant/chunk","seq":81,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":82,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":83,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"sum"}}} -{"type":"assistant/chunk","seq":84,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"mar"}}} -{"type":"assistant/chunk","seq":85,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ize"}}} -{"type":"assistant/chunk","seq":86,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":87,"time":1783352223458,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":88,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" This"}}} -{"type":"assistant/chunk","seq":89,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" means"}}} -{"type":"assistant/chunk","seq":90,"time":1783352223488,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":91,"time":1783352223519,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" cannot"}}} -{"type":"assistant/chunk","seq":92,"time":1783352223520,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" show"}}} -{"type":"assistant/chunk","seq":93,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":94,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" raw"}}} -{"type":"assistant/chunk","seq":95,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":96,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":97,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":98,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":99,"time":1783352223605,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":100,"time":1783352223640,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":101,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" requested"}}} -{"type":"assistant/chunk","seq":102,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":103,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":104,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":105,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" try"}}} -{"type":"assistant/chunk","seq":106,"time":1783352223663,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":107,"time":1783352223664,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" comply"}}} -{"type":"assistant/chunk","seq":108,"time":1783352223691,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" but"}}} -{"type":"assistant/chunk","seq":109,"time":1783352223692,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":110,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} -{"type":"assistant/chunk","seq":111,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" happened"}}} -{"type":"assistant/chunk","seq":112,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".\n\n"}}} -{"type":"assistant/chunk","seq":113,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Actually"}}} -{"type":"assistant/chunk","seq":114,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":115,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":116,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":117,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":118,"time":1783352223778,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":119,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":120,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":121,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":122,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":123,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":124,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":125,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":126,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":127,"time":1783352223865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":128,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":129,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":130,"time":1783352223896,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":131,"time":1783352223897,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} -{"type":"assistant/chunk","seq":132,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} -{"type":"assistant/chunk","seq":133,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":134,"time":1783352223952,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":135,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":136,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"tool"}}} -{"type":"assistant/chunk","seq":137,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":138,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":139,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":140,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":141,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":142,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":143,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":144,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" summarize"}}} -{"type":"assistant/chunk","seq":145,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":146,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n\n"}}} -{"type":"assistant/chunk","seq":147,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"So"}}} -{"type":"assistant/chunk","seq":148,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":149,"time":1783352224018,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":150,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":151,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":152,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":153,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":154,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":155,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":156,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} -{"type":"assistant/chunk","seq":157,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":158,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":159,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" I"}}} -{"type":"assistant/chunk","seq":160,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" got"}}} -{"type":"assistant/chunk","seq":161,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" back"}}} -{"type":"assistant/chunk","seq":162,"time":1783352224129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":163,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":164,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} -{"type":"assistant/chunk","seq":165,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":166,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} -{"type":"assistant/chunk","seq":167,"time":1783352224187,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":168,"time":1783352224215,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} -{"type":"assistant/chunk","seq":169,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} -{"type":"assistant/chunk","seq":170,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":171,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":172,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":173,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} -{"type":"assistant/chunk","seq":174,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":175,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":176,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`\n\n"}}} -{"type":"assistant/chunk","seq":177,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"This"}}} -{"type":"assistant/chunk","seq":178,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":179,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":180,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" verb"}}} -{"type":"assistant/chunk","seq":181,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"atim"}}} -{"type":"assistant/chunk","seq":182,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":183,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" from"}}} -{"type":"assistant/chunk","seq":184,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":185,"time":1783352224331,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":186,"time":1783352224360,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" —"}}} -{"type":"assistant/chunk","seq":187,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":188,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}} -{"type":"assistant/chunk","seq":189,"time":1783352224392,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" not"}}} -{"type":"assistant/chunk","seq":190,"time":1783352224418,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":191,"time":1783352224446,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" expected"}}} -{"type":"assistant/chunk","seq":192,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":193,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":194,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"HE"}}} -{"type":"assistant/chunk","seq":195,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"LL"}}} -{"type":"assistant/chunk","seq":196,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"O"}}} -{"type":"assistant/chunk","seq":197,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":198,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`"}}} -{"type":"assistant/chunk","seq":199,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":200,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" because"}}} -{"type":"assistant/chunk","seq":201,"time":1783352224533,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":202,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":203,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":204,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":205,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" blocked"}}} -{"type":"assistant/chunk","seq":206,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":207,"time":1783352224592,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" and"}}} -{"type":"assistant/chunk","seq":208,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instructed"}}} -{"type":"assistant/chunk","seq":209,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" me"}}} -{"type":"assistant/chunk","seq":210,"time":1783352224653,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}} -{"type":"assistant/chunk","seq":211,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":212,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":213,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}} -{"type":"assistant/chunk","seq":214,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."}}}} -{"type":"assistant/chunk","seq":215,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}}}} -{"type":"assistant/chunk","seq":216,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}}}} -{"type":"assistant/chunk","seq":217,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} -{"type":"step/end","seq":219,"time":1783352224655,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":220,"time":1783352224655,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"01aa6a36-e9c2-42ba-934b-30bec80a1658","createdAt":1783986962232,"cwd":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-x67BsP"} +{"type":"turn/start","seq":0,"time":1783986962235,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783986962235,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783986962240,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783986962240,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} +{"type":"assistant/chunk","seq":11,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":13,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":14,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":15,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":17,"time":1783986963160,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} +{"type":"assistant/chunk","seq":18,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} +{"type":"assistant/chunk","seq":19,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} +{"type":"assistant/chunk","seq":20,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} +{"type":"assistant/chunk","seq":21,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`,"}}} +{"type":"assistant/chunk","seq":22,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":23,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":24,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":25,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} +{"type":"assistant/chunk","seq":26,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} +{"type":"assistant/chunk","seq":27,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} +{"type":"assistant/chunk","seq":28,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":29,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":30,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":31,"time":1783986963314,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":32,"time":1783986963315,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":33,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":34,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":35,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":36,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":37,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":38,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":39,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":40,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":41,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":42,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":43,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":44,"time":1783986963428,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":45,"time":1783986963429,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":46,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":47,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":48,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":49,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":50,"time":1783986963489,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"E"}}} +{"type":"assistant/chunk","seq":51,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"cho"}}} +{"type":"assistant/chunk","seq":52,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":53,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":54,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":55,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":56,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" stdout"}}} +{"type":"assistant/chunk","seq":57,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1783986963658,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":59,"time":1783986963659,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."}}}} +{"type":"assistant/chunk","seq":60,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}}}} +{"type":"assistant/chunk","seq":61,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}}}} +{"type":"assistant/chunk","seq":62,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":63,"time":1783986963663,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."},{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62],"surfaceOp":"append"} +{"type":"tool/call","seq":64,"time":1783986963664,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}} +{"type":"hook/invoked","seq":65,"time":1783986963673,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} +{"type":"hook/result","seq":66,"time":1783986963677,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":4.42941699999983}} +{"type":"tool/result","seq":67,"time":1783986963678,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[64],"surfaceOp":"append"} +{"type":"step/end","seq":68,"time":1783986963678,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":69,"time":1783986963679,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":70,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":71,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":72,"time":1783986964809,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":73,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":74,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":75,"time":1783986964836,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} +{"type":"assistant/chunk","seq":76,"time":1783986964864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} +{"type":"assistant/chunk","seq":77,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} +{"type":"assistant/chunk","seq":78,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} +{"type":"assistant/chunk","seq":79,"time":1783986964893,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} +{"type":"assistant/chunk","seq":80,"time":1783986964899,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":81,"time":1783986964900,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":82,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":83,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":84,"time":1783986964955,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} +{"type":"assistant/chunk","seq":85,"time":1783986964985,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":86,"time":1783986965013,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} +{"type":"assistant/chunk","seq":87,"time":1783986965014,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} +{"type":"assistant/chunk","seq":88,"time":1783986965045,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":89,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":90,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```\n"}}} +{"type":"assistant/chunk","seq":91,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"<"}}} +{"type":"assistant/chunk","seq":92,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":93,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_result"}}} +{"type":"assistant/chunk","seq":94,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} +{"type":"assistant/chunk","seq":95,"time":1783986965233,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":96,"time":1783986965234,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} +{"type":"assistant/chunk","seq":97,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} +{"type":"assistant/chunk","seq":98,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} +{"type":"assistant/chunk","seq":99,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} +{"type":"assistant/chunk","seq":100,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} +{"type":"assistant/chunk","seq":101,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} +{"type":"assistant/chunk","seq":102,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} +{"type":"assistant/chunk","seq":103,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} +{"type":"assistant/chunk","seq":104,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} +{"type":"assistant/chunk","seq":105,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\n"}}} +{"type":"assistant/chunk","seq":109,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```"}}} +{"type":"assistant/chunk","seq":110,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."}}}} +{"type":"assistant/chunk","seq":111,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}}}} +{"type":"assistant/chunk","seq":112,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":113,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":114,"time":1783986965238,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."},{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}],"usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}},"sourceEventSeqs":[70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"surfaceOp":"append"} +{"type":"step/end","seq":115,"time":1783986965238,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":116,"time":1783986965238,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index fddecc08c6..1c99b178a3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -5,124 +5,52 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" call"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" once"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"echo"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" HE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"LL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`,"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Print HELLO to stdout"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Echo HELLO to stdout"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instruction"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sum"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"mar"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" means"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cannot"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" show"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" raw"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" requested"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" try"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" comply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" but"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" what"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" happened"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Actually"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" got"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"So"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" got"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"<"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":">"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}} @@ -133,42 +61,9 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" from"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" —"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" expected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"HE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"LL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" because"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" blocked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instructed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} From 8ada835396a021a7dce8f72d6b025dcd3a264c15 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:03:33 +0800 Subject: [PATCH 035/140] docs: remove links to private subagent helpers --- packages/subagent/subagent-subprocess/src/index.ts | 12 +++++------- packages/subagent/tool-subagent/src/index.ts | 10 +++++----- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 2ee2745985..bd792e7f23 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -2,11 +2,10 @@ * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn * an external agent as a child process and must keep the parent deployment's * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: the credential env scrub - * ({@link SENSITIVE_ENV_PATTERN} / {@link buildChildEnv}), the spawn-failure - * capture ({@link spawnFailure}), the child-exit waits ({@link waitForExit} / - * {@link exitsWithin}), the stdin-EOF → SIGTERM → SIGKILL dispose ladder - * ({@link disposeChildProcess}), and the per-run isolated config dir + * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing + * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), + * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose + * ladder ({@link disposeChildProcess}), and the per-run isolated config dir * ({@link createIsolatedConfigDir}). * * This package owns no provider and registers nothing; it is a pure library @@ -37,8 +36,7 @@ const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit * env. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive the scrub, so - * a child CLI runs normally; only {@link SENSITIVE_ENV_PATTERN}-shaped names - * are dropped. + * a child CLI runs normally; only credential-shaped names are dropped. * @param extra - explicit vars layered on top AFTER the scrub, so a * credential-shaped name supplied deliberately still reaches the child. * @returns the environment to spawn the child with. diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index 426753dbb9..ff54bc109a 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -12,11 +12,11 @@ * sees only `{ description, prompt }`. * * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link providerWording}): a fresh-conversation provider (spawn, - * ACP) gets the standalone-prompt wording, while a seeded-conversation provider - * (fork) tells the model the child already sees the conversation's completed - * turns. This descriptor says nothing about Cordis scope, services, tools, or - * authority. The tool MIRRORS the + * descriptor ({@link SubagentProvider.inheritsParentContext}): a + * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, + * while a seeded-conversation provider (fork) tells the model the child already + * sees the conversation's completed turns. This descriptor says nothing about + * Cordis scope, services, tools, or authority. The tool MIRRORS the * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers * when the provider is (or becomes) available and unregisters when the * provider goes away — so no load-order requirement exists and an HMR reload From cb80277e60c17ac5238dc7ee740ae315ee3521ff Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:11:13 +0800 Subject: [PATCH 036/140] fix: retain JSON-RPC subagent locality per run --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +++++++++++---- packages/ui/jsonrpc/tests/server.spec.ts | 73 ++++++++++++++++++++---- 4 files changed, 98 insertions(+), 26 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..04aff464a9 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,7 +8,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | @@ -34,7 +34,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 735cfead0a..95d7d7c7d7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index bf21f7fc2d..12bf82de3c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -17,7 +17,7 @@ import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' -import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -65,10 +65,11 @@ interface LocalAgentRecord { /** * The SDK server over a booted harness context. Constructing it subscribes to - * the context's `session/event`, `session/created`, `agent/created`, and - * `subagent/end` events and forwards them to the host as notifications; the - * subscriptions live until {@link shutdown}. One instance serves one transport - * peer for the process lifetime — there is no re-`initialize`. + * session, agent, and subagent lifecycle events, forwarding durable session + * events and SDK-facing completion notifications while retaining local-run + * identity across child disposal. The subscriptions live until + * {@link shutdown}. One instance serves one transport peer for the process + * lifetime — there is no re-`initialize`. */ export class HarnessSdkServer { private cwd = process.cwd() @@ -77,6 +78,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() + private readonly localRuns = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,18 +102,38 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage on creation: by the - // time `subagent/end` fires the child agent may already be disposed and - // gone from the registry. Parent lineage is not required by the provider - // contract, so an empty record remains a load-bearing locality marker. + // Cache runtime-local identity and optional lineage for each agent lifetime. + // Parent lineage is not required by the provider contract, so an empty + // record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + this.disposers.push(ctx.on('agent/disposed', (agent) => { + this.localAgents.delete(agent.id) + })) + // Snapshot locality per run. A provider may settle one run, continue the + // same live child in another run, and dispose that child before the later + // result settles. Consuming an agent-lifetime marker at the first end would + // lose the later notification; this queue pairs each start with one end. + this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) - this.localAgents.delete(info.id) + const localAgent = cachedLocalAgent ?? (agent === undefined + ? undefined + : agent.session.header.parentSession === undefined + ? {} + : { parentSessionId: agent.session.header.parentSession }) + if (localAgent === undefined) return + const runs = this.localRuns.get(info.id) ?? [] + runs.push(localAgent) + this.localRuns.set(info.id, runs) + })) + this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + const agent = this.ctx.agents.get(info.id) + const runs = this.localRuns.get(info.id) + const cachedLocalAgent = runs?.shift() + if (runs?.length === 0) this.localRuns.delete(info.id) // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider @@ -196,6 +218,7 @@ export class HarnessSdkServer { const records = [...this.sessions.values()] this.sessions.clear() this.localAgents.clear() + this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 163aee4c0c..d56f3000f6 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -11,7 +11,7 @@ import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import SubagentService, { type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import SubagentService, { type SubagentResult, type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import { HarnessSdkServer, type JsonRpcTransportPeer } from '../src/index.ts' class FakeTransport implements JsonRpcTransportPeer { @@ -67,7 +67,13 @@ async function makeHarness(storageDir: string) { } /** Drive the owning service so test lifecycle events carry the real parent scope. */ -async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndInfo): Promise { +async function settleSubagent( + ctx: Context, + parent: Agent, + info: SubagentRunEndInfo, + beforeSettle?: () => Promise, +): Promise { + const result = Promise.withResolvers() const disposeProvider = ctx.subagents.registerProvider({ name: info.provider, capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -75,9 +81,7 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI async start() { return { id: info.id, - result: info.lastAssistantMessage === undefined - ? Promise.reject(new Error('synthetic infrastructure failure')) - : Promise.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }), + result: result.promise, dispose: () => Promise.resolve(), } }, @@ -88,6 +92,12 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI prompt: [], signal: new AbortController().signal, }) + await beforeSettle?.() + if (info.lastAssistantMessage === undefined) { + result.reject(new Error('synthetic infrastructure failure')) + } else { + result.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }) + } await run.result.then(() => undefined, () => undefined) await run.dispose() } finally { @@ -277,21 +287,17 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - // The backend may dispose the child before publishing its run outcome; - // cached locality must survive with or without optional parent lineage. - await handle.dispose() - await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], - }) + }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), stopReason: 'error', - }) + }, () => parentlessHandle.dispose()) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -324,6 +330,49 @@ describe('HarnessSdkServer', () => { } }) + it('retains locality across continuation runs on one live child', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const childHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-child'), + meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'first' }], + }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'second' }], + }, () => childHandle.dispose()) + + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'continuation-child', + )).toHaveLength(2) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -585,6 +634,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(6) }) }) From d898d1faf0739e4e4f2edd5b6f7a156f54ed2d25 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:25:52 +0800 Subject: [PATCH 037/140] fix: avoid FIFO subagent lineage attribution --- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 49 ++++++--- packages/ui/jsonrpc/tests/server.spec.ts | 123 ++++++++++++++++++++++- 3 files changed, 158 insertions(+), 16 deletions(-) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 95d7d7c7d7..5ff7eb7f8e 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 12bf82de3c..ce0ac9c75a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -63,6 +63,13 @@ interface LocalAgentRecord { parentSessionId?: SessionId } +/** Pending local runs that share one provider/id correlation key. */ +interface PendingLocalRuns { + count: number + parentSessionId?: SessionId + parentAmbiguous: boolean +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session, agent, and subagent lifecycle events, forwarding durable session @@ -78,7 +85,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() - private readonly localRuns = new Map() + private readonly localRuns = new Map>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -112,10 +119,12 @@ export class HarnessSdkServer { this.disposers.push(ctx.on('agent/disposed', (agent) => { this.localAgents.delete(agent.id) })) - // Snapshot locality per run. A provider may settle one run, continue the - // same live child in another run, and dispose that child before the later - // result settles. Consuming an agent-lifetime marker at the first end would - // lose the later notification; this queue pairs each start with one end. + // Snapshot locality per provider/id run key. A provider may settle one run, + // continue the same live child in another run, and dispose that child before + // the later result settles. Counts preserve every completion without + // assuming settlement order. If id reuse produces disagreeing lineage, the + // optional parent is omitted until that pending group drains rather than + // attributed to the wrong completion. this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) @@ -125,21 +134,35 @@ export class HarnessSdkServer { ? {} : { parentSessionId: agent.session.header.parentSession }) if (localAgent === undefined) return - const runs = this.localRuns.get(info.id) ?? [] - runs.push(localAgent) - this.localRuns.set(info.id, runs) + const providerRuns = this.localRuns.get(info.provider) ?? new Map() + const pending = providerRuns.get(info.id) + if (pending === undefined) { + providerRuns.set(info.id, localAgent.parentSessionId === undefined + ? { count: 1, parentAmbiguous: false } + : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) + } else { + pending.count += 1 + if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true + } + this.localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const runs = this.localRuns.get(info.id) - const cachedLocalAgent = runs?.shift() - if (runs?.length === 0) this.localRuns.delete(info.id) + const providerRuns = this.localRuns.get(info.provider) + const pending = providerRuns?.get(info.id) + if (pending !== undefined) { + pending.count -= 1 + if (pending.count === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider // has neither a cached creation nor a live local agent and is ignored. - if (cachedLocalAgent === undefined && agent === undefined) return - const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession + if (pending === undefined && agent === undefined) return + const parentSessionId = pending === undefined + ? agent?.session.header.parentSession + : pending.parentAmbiguous ? undefined : pending.parentSessionId this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index d56f3000f6..48b8c4b1be 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -373,6 +373,100 @@ describe('HarnessSdkServer', () => { } }) + it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const oldParent = await ctx.agents.create({ + sessionId: SessionId('old-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const oldChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const first = Promise.withResolvers() + const sameLifetime = Promise.withResolvers() + const replacement = Promise.withResolvers() + const results = [first.promise, sameLifetime.promise, replacement.promise] + let starts = 0 + const disposeProvider = ctx.subagents.registerProvider({ + name: 'reused', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + const result = results[starts] + starts += 1 + if (result === undefined) throw new Error('unexpected fourth reused-id run') + return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + }, + }) + + const firstRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + const sameLifetimeRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + sameLifetime.resolve({ output: [{ type: 'text', text: 'same lifetime' }], stopReason: 'completed' }) + await sameLifetimeRun.result + await oldChild.dispose() + const newParent = await ctx.agents.create({ + sessionId: SessionId('new-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const newChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const secondRun = await ctx.subagents.start('reused', { + parent: newParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + replacement.resolve({ output: [{ type: 'text', text: 'new lifetime' }], stopReason: 'completed' }) + await secondRun.result + first.resolve({ output: [{ type: 'text', text: 'old lifetime' }], stopReason: 'completed' }) + await firstRun.result + await Promise.resolve() + + const finished = transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'reused-child', + ) + expect(finished.map(notification => notification.params?.lastAssistantMessage)).toEqual([ + [{ type: 'text', text: 'same lifetime' }], + [{ type: 'text', text: 'new lifetime' }], + [{ type: 'text', text: 'old lifetime' }], + ]) + expect(finished[0]?.params?.parentSessionId).toBe('old-parent') + expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + + await firstRun.dispose() + await sameLifetimeRun.dispose() + await secondRun.dispose() + disposeProvider() + await newChild.dispose() + await oldParent.dispose() + await newParent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -395,13 +489,38 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) + const missedStartResult = Promise.withResolvers() + const disposeMissedStartProvider = ctx.subagents.registerProvider({ + name: 'fork', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: true, + start: () => Promise.resolve({ + id: SessionId('fallback-child-session'), + result: missedStartResult.promise, + dispose: () => Promise.resolve(), + }), + }) + // Start before the server subscribes, so the terminal fallback must use + // the still-live registry entry rather than a cached start record. + const missedStartRun = await ctx.subagents.start('fork', { + parent: parentHandle.agent, + prompt: [], + signal: new AbortController().signal, + }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) + missedStartResult.resolve({ output: [], stopReason: 'max-tokens' }) + await missedStartRun.result + await Promise.resolve() + await missedStartRun.dispose() + disposeMissedStartProvider() + // The server also missed this agent's creation, but observes the start; + // recover its lineage from the still-live registry entry. await settleSubagent(ctx, parentHandle.agent, { - provider: 'fork', + provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), - stopReason: 'max-tokens', + stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { From 45e3997efcecf48c57e171a7d77401b1c914ea32 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:41:31 +0800 Subject: [PATCH 038/140] fix: correlate subagent completion by parent scope --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 101 ++++++++--------------- packages/ui/jsonrpc/tests/server.spec.ts | 13 ++- 4 files changed, 47 insertions(+), 73 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 04aff464a9..bc1c0d38d0 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,8 +7,8 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 5ff7eb7f8e..ffbd7a1288 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index ce0ac9c75a..352563f7f2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -15,8 +15,10 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { AgentHandle } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' +import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' +import type SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -58,21 +60,14 @@ interface SessionRecord { activePrompt: boolean } -/** Runtime-local agent identity plus optional durable fork lineage. */ -interface LocalAgentRecord { - parentSessionId?: SessionId -} - -/** Pending local runs that share one provider/id correlation key. */ -interface PendingLocalRuns { - count: number - parentSessionId?: SessionId - parentAmbiguous: boolean +/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +function subagentParentOf(carrier: Scoped): Agent { + return carrierKeyOf(carrier) as Agent } /** * The SDK server over a booted harness context. Constructing it subscribes to - * session, agent, and subagent lifecycle events, forwarding durable session + * session and subagent lifecycle events, forwarding durable session * events and SDK-facing completion notifications while retaining local-run * identity across child disposal. The subscriptions live until * {@link shutdown}. One instance serves one transport peer for the process @@ -84,8 +79,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localAgents = new Map() - private readonly localRuns = new Map>() + private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -109,64 +103,40 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage for each agent lifetime. - // Parent lineage is not required by the provider contract, so an empty - // record remains a load-bearing locality marker. - this.disposers.push(ctx.on('agent/created', (agent) => { - const parentSessionId = agent.session.header.parentSession - this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) + // In-process providers publish the child before start. Count those starts by + // the exact delegating-parent carrier so later completions remain local after + // child disposal and reused ids need no settlement-order assumption. + const localRuns = this.localRuns + this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { + if (ctx.agents.get(info.id) === undefined) return + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) ?? new Map>() + const parentRuns = providerRuns.get(info.id) ?? new Map() + parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) + providerRuns.set(info.id, parentRuns) + localRuns.set(info.provider, providerRuns) })) - this.disposers.push(ctx.on('agent/disposed', (agent) => { - this.localAgents.delete(agent.id) - })) - // Snapshot locality per provider/id run key. A provider may settle one run, - // continue the same live child in another run, and dispose that child before - // the later result settles. Counts preserve every completion without - // assuming settlement order. If id reuse produces disagreeing lineage, the - // optional parent is omitted until that pending group drains rather than - // attributed to the wrong completion. - this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { - const agent = this.ctx.agents.get(info.id) - const cachedLocalAgent = this.localAgents.get(info.id) - const localAgent = cachedLocalAgent ?? (agent === undefined - ? undefined - : agent.session.header.parentSession === undefined - ? {} - : { parentSessionId: agent.session.header.parentSession }) - if (localAgent === undefined) return - const providerRuns = this.localRuns.get(info.provider) ?? new Map() - const pending = providerRuns.get(info.id) - if (pending === undefined) { - providerRuns.set(info.id, localAgent.parentSessionId === undefined - ? { count: 1, parentAmbiguous: false } - : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) - } else { - pending.count += 1 - if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true - } - this.localRuns.set(info.provider, providerRuns) - })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const agent = this.ctx.agents.get(info.id) - const providerRuns = this.localRuns.get(info.provider) - const pending = providerRuns?.get(info.id) - if (pending !== undefined) { - pending.count -= 1 - if (pending.count === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { + const agent = ctx.agents.get(info.id) + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) + const parentRuns = providerRuns?.get(info.id) + const pendingCount = parentRuns?.get(parent) + if (pendingCount !== undefined) { + if (pendingCount === 1) parentRuns?.delete(parent) + else parentRuns?.set(parent, pendingCount - 1) + if (parentRuns?.size === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider - // has neither a cached creation nor a live local agent and is ignored. - if (pending === undefined && agent === undefined) return - const parentSessionId = pending === undefined - ? agent?.session.header.parentSession - : pending.parentAmbiguous ? undefined : pending.parentSessionId - this.transport.notify('subagent.finished', { + // has neither a pending local start nor a live local agent and is ignored. + if (pendingCount === undefined && agent === undefined) return + transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + parentSessionId: String(parent.session.id), childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, @@ -240,7 +210,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localAgents.clear() this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 48b8c4b1be..427a190c36 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -316,6 +316,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'spawn', agentId: 'parentless-child-session', + parentSessionId: 'main', childSessionId: 'parentless-child-session', status: 'error', stopReason: 'error', @@ -373,7 +374,7 @@ describe('HarnessSdkServer', () => { } }) - it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + it('correlates reused local ids by parent scope when runs settle out of order', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) const ctx = await makeHarness(storageDir) try { @@ -450,8 +451,11 @@ describe('HarnessSdkServer', () => { [{ type: 'text', text: 'new lifetime' }], [{ type: 'text', text: 'old lifetime' }], ]) - expect(finished[0]?.params?.parentSessionId).toBe('old-parent') - expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + expect(finished.map(notification => notification.params?.parentSessionId)).toEqual([ + 'old-parent', + 'new-parent', + 'old-parent', + ]) await firstRun.dispose() await sameLifetimeRun.dispose() @@ -551,6 +555,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'fork', agentId: 'failed-child-session', + parentSessionId: 'fallback-parent', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', @@ -753,6 +758,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(6) + expect(on).toHaveBeenCalledTimes(4) }) }) From d33a819d15964fac1212f7b716f50106c8bb0ed1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 039/140] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 39c6c1120abdcc0414325bbdd1624917b0cb8624 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:56:21 +0800 Subject: [PATCH 040/140] Revert "fix: share scope carrier across built JSON-RPC" This reverts commit 835fd3ca4f46e0c6464098e3d0864dc56f31398d. --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 - .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ------------------ pnpm-lock.yaml | 3 - scripts/run-gates.ts | 1 - 6 files changed, 2 insertions(+), 129 deletions(-) delete mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 1494d3fcf8..4dfbedb97b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index a1a841296a..23cca651fe 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index bf4fe39118..be19ab7217 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,7 +28,6 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", - "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -39,7 +38,6 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", - "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts deleted file mode 100644 index 159600e49c..0000000000 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ /dev/null @@ -1,121 +0,0 @@ -/** - * Built-artifact guard for the scope carrier shared by `dsh-subagent` and - * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must - * externalize `dsh-scope`; source-mode tests cannot expose an accidentally - * inlined second registry. This test runs the real `lib/index.js` bundles in a - * plain Node subprocess, disposes the child before settlement, and requires the - * SDK completion notification to retain the delegating parent. - */ - -import { execFile } from 'node:child_process' -import { existsSync } from 'node:fs' -import { fileURLToPath } from 'node:url' -import { promisify } from 'node:util' -import { describe, expect, it } from 'vitest' - -const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) -const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) -const execFileAsync = promisify(execFile) - -const builtRuntimeProbe = String.raw` -import { mkdtemp, rm } from "node:fs/promises"; -import { tmpdir } from "node:os"; -import { join, resolve } from "node:path"; -import { pathToFileURL } from "node:url"; - -const load = (path) => import(pathToFileURL(resolve(path)).href); -const [ - { Context }, - agentCore, - { default: SubagentService }, - { default: SessionPersistenceJsonl }, - { HarnessSdkServer }, - { SessionId }, -] = await Promise.all([ - load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), - load("packages/subagent/subagent/lib/index.js"), - load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), - load("packages/ui/jsonrpc/lib/index.js"), - load("packages/core/session/lib/index.js"), -]); - -const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); -const ctx = new Context(); -try { - await ctx.plugin(agentCore); - await ctx.plugin(SubagentService); - await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); - await new Promise((ready) => setTimeout(ready, 50)); - - const notifications = []; - const server = new HarnessSdkServer(ctx, { - request() { return Promise.reject(new Error("unexpected host request")); }, - notify(method, params) { notifications.push({ method, params }); }, - }); - const parent = await ctx.agents.create({ - sessionId: SessionId("built-parent"), - meta: { cwd: storageRoot }, - agentOptions: { model: "test" }, - }); - const child = await ctx.agents.create({ - sessionId: SessionId("built-child"), - meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, - agentOptions: { model: "test" }, - }); - const result = Promise.withResolvers(); - const unregister = ctx.subagents.registerProvider({ - name: "built-local", - capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, - inheritsParentContext: false, - start() { - return Promise.resolve({ - id: child.agent.id, - result: result.promise, - dispose() { return Promise.resolve(); }, - }); - }, - }); - const run = await ctx.subagents.start("built-local", { - parent: parent.agent, - prompt: [], - signal: new AbortController().signal, - }); - await child.dispose(); - result.resolve({ output: [], stopReason: "completed" }); - await run.result; - await Promise.resolve(); - - console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); - await run.dispose(); - unregister(); - await parent.dispose(); - await server.shutdown(); -} finally { - await ctx.fiber.dispose(); - await rm(storageRoot, { recursive: true, force: true }); -} -` - -describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { - it('preserves parent-scoped completion after child disposal', async () => { - const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { - cwd: repoRoot, - timeout: 15_000, - }) - - expect(stderr).not.toContain('listener threw') - expect(JSON.parse(stdout) as unknown).toEqual([{ - method: 'subagent.finished', - params: { - provider: 'built-local', - agentId: 'built-child', - parentSessionId: 'built-parent', - childSessionId: 'built-child', - status: 'ok', - stopReason: 'completed', - lastAssistantMessage: [], - }, - }]) - }) -}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index dec8c3024f..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,9 +1288,6 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek - '@deepseek-ai/dsh-scope': - specifier: workspace:^ - version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index e1c41149ca..131501abb0 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,7 +332,6 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', - 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From c6cb9f4210d9303c197ac985fca7a4dc3b11cb88 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 041/140] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 151d6387e03b9f41b553e7f079588f76d7317516 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:57:46 +0800 Subject: [PATCH 042/140] docs: refresh module dependency graph --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..864f39359f 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -293,6 +293,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_workflow_workerthread --> pkg_agent @@ -389,7 +390,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | From 82c0d1fb7cc291196bc3fd5733dfec867d84dac7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:59:33 +0800 Subject: [PATCH 043/140] test: register JSON-RPC artifact smoke --- knip.json | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/knip.json b/knip.json index 825980f205..fe2366e3fa 100644 --- a/knip.json +++ b/knip.json @@ -77,13 +77,17 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, - "packages/ui/stdio-agent": { + "packages/ui/jsonrpc": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/ui/jsonrpc-agent": { "project": ["src/**/*.ts"] }, + "packages/ui/stdio-agent": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/subagent/subagent-spawn": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] From e784e4dce5f5178b5e22a3d3376599144d8bea1b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:12:32 +0800 Subject: [PATCH 044/140] fix: await ACP client callbacks during shutdown --- packages/support/acp-snapshot/src/launcher.ts | 59 ++++++++++++------- .../acp-snapshot/tests/harness.spec.ts | 36 +++++++++++ 2 files changed, 75 insertions(+), 20 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 815753ae5f..30702a5888 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ close(signal?: NodeJS.Signals): Promise } @@ -137,29 +137,41 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, ) + const inFlightClientCallbacks = new Set>() + const trackClientCallback = (callback: () => T | PromiseLike): Promise => { + const pending = Promise.resolve().then(callback) + inFlightClientCallbacks.add(pending) + void pending.then( + () => { inFlightClientCallbacks.delete(pending) }, + () => { inFlightClientCallbacks.delete(pending) }, + ) + return pending + } + const requestPermission = options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' as const } })) const makeClient = (_agent: AcpAgent): Client => ({ sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - for (let index = updateWaiters.length - 1; index >= 0; index--) { - const waiter = updateWaiters[index] - /* v8 ignore next 1 -- index is bounded by the array length */ - if (waiter === undefined) continue - let matches: boolean - try { - matches = waiter.match(params.update) - } catch (error: unknown) { + return trackClientCallback(() => { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) - waiter.reject(error) - continue + waiter.resolve(params.update) } - if (!matches) continue - updateWaiters.splice(index, 1) - waiter.resolve(params.update) - } - return Promise.resolve() + }) }, - requestPermission: options.requestPermission - ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + requestPermission: params => trackClientCallback(() => requestPermission(params)), }) const client = new ClientSideConnection(makeClient, stream) // `exit` only reports the parent process's status. Descendants may retain @@ -168,7 +180,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + // The ACP SDK's readable loop dispatches client callbacks without awaiting + // them. Once `closed` settles no new callbacks can start, but callbacks + // already in flight still belong to this launch's teardown boundary. + while (inFlightClientCallbacks.size > 0) { + await Promise.allSettled([...inFlightClientCallbacks]) + } + }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the // parser has dispatched every buffered frame. diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 051db6a0ba..902f48d2cf 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -1,4 +1,5 @@ import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -112,6 +113,41 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true }) + let releasePermission: (() => void) | undefined + const permissionReleased = new Promise((resolve) => { releasePermission = resolve }) + let markPermissionStarted: (() => void) | undefined + const permissionStarted = new Promise((resolve) => { markPermissionStarted = resolve }) + let permissionFinished = false + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + async requestPermission() { + markPermissionStarted?.() + await permissionReleased + permissionFinished = true + return { outcome: { outcome: 'cancelled' } } + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + void launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => undefined) + await permissionStarted + + const childClosed = once(launched.child, 'close') + let closeSettled = false + const closing = launched.close('SIGKILL').then(() => { closeSettled = true }) + await childClosed + await launched.client.closed + expect(closeSettled).toBe(false) + + releasePermission?.() + await closing + expect(permissionFinished).toBe(true) + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From d4c96deac3802164c430335309f936f3e5ab4f1d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:19:02 +0800 Subject: [PATCH 045/140] refactor: share ACP callback cleanup --- packages/support/acp-snapshot/src/launcher.ts | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30702a5888..f1271986c0 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -141,10 +141,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const trackClientCallback = (callback: () => T | PromiseLike): Promise => { const pending = Promise.resolve().then(callback) inFlightClientCallbacks.add(pending) - void pending.then( - () => { inFlightClientCallbacks.delete(pending) }, - () => { inFlightClientCallbacks.delete(pending) }, - ) + const untrack = (): void => { inFlightClientCallbacks.delete(pending) } + void pending.then(untrack, untrack) return pending } const requestPermission = options.requestPermission From 2dea4afac0d49976700139a766d40734e3204f4e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:23:02 +0800 Subject: [PATCH 046/140] fix: bind stdio to its configured agent --- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 5 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 30 +++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 35 ++++++++++++++----- 4 files changed, 53 insertions(+), 19 deletions(-) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 82da64cd81..d7d30ee49d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index f01c48a615..2eca0cceb3 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -124,5 +124,8 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index a295274786..76347c91e4 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,10 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string + /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ + resumeSessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), + resumeSessionId: z.string(), }) /** @@ -95,16 +98,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured top-level agent. Hold the live object - // directly: its per-run id is intentionally fresh, while `main` remains only - // the terminal's fixed display label. Runtime creator ownership distinguishes - // that root from its subagents even if a child is registered after an HMR - // replacement. Persisted parentSession lineage is deliberately irrelevant: - // a resumed child session can itself be this process's configured root. - let target: Agent | undefined = ctx.agents.roots()[0] - ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) + // Bind only to this app's configured top-level agent. Fresh runs own the + // `main-session-*` namespace; resumed runs own the exact persisted id. The + // registry's runtime-root relation excludes subagents without confusing it + // with durable parentSession lineage. Keeping the matching candidates also + // covers HMR's publish-new-before-dispose-old ordering without ever falling + // through to an unrelated root owned by another app or test fixture. + const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + ? agent.id.startsWith('main-session-') + : agent.id === config.resumeSessionId + const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) + let target: Agent | undefined = [...configuredRoots].at(-1) + ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return + configuredRoots.add(agent) + target ??= agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.roots().at(-1) + configuredRoots.delete(agent) + if (target === agent) target = [...configuredRoots].at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2600fdb24f..668068a72d 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there' } +const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,9 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup() + const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) @@ -207,6 +209,7 @@ describe('createStdioChat rendering', () => { input.feed('continue') await new Promise(resolve => setImmediate(resolve)) + expect(unrelated.sent).toEqual([]) expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) }) @@ -235,7 +238,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() - const target = makeAgent('target') + const target = makeAgent('main') ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { @@ -245,11 +248,11 @@ describe('createStdioChat rendering', () => { }) it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup() - const oldRoot = makeAgent('old-root') + const { ctx, input } = await setup({ welcome: 'hi there' }) + const oldRoot = makeAgent('main-session-old') const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('replacement') + const replacement = makeAgent('main-session-replacement') const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) const disposeChild = ctx.agents.enter(child, oldRoot) @@ -273,6 +276,22 @@ describe('createStdioChat rendering', () => { disposeChild() }) + it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { + const { ctx, input } = await setup() + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) + const configured = makeAgent('main') + const disposeConfigured = ctx.agents.register(configured) + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + + disposeConfigured() + input.feed('must not leak') + await new Promise(resolve => setImmediate(resolve)) + + expect(unrelated.sent).toEqual([]) + expect(error).toHaveBeenCalledWith('ui-stdio: main agent is not running') + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session @@ -720,8 +739,8 @@ describe('createStdioChat input', () => { expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the app-owned agent without a duplicate id config', async () => { - const { ctx, input } = await setup({ welcome: 'w' }) + it('drives the exact app-configured resumed session', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') From 1bb9995128f75474eeec9933e2bab6fc69a8b60e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:28:41 +0800 Subject: [PATCH 047/140] docs: state subagent carrier invariant --- packages/ui/jsonrpc/src/server.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 352563f7f2..fe605a8536 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -62,6 +62,7 @@ interface SessionRecord { /** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ function subagentParentOf(carrier: Scoped): Agent { + // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } From ba8a5c89ed4390b4b1679b736f2c44d79bdbaab9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:29:02 +0800 Subject: [PATCH 048/140] docs: name the public agent injection seam --- packages/bash/tool-bash/src/index.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index fe07b80989..cda683c5b4 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -457,7 +457,7 @@ export function apply(ctx: Context): void { ) } catch (error: unknown) { // The ONE expected failure: the agent was disposed between task - // completion and this injection (ReactLoopAgent.inject throws + // completion and this injection (Agent.inject throws // `agent "" is disposed`). That race is benign — drop the notice. // Anything else is a real bug and must surface, not be swallowed. if (error instanceof Error && error.message.includes('is disposed')) return From ccd810f84d74ce452d858b553eb0cbdb282d715c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:36:22 +0800 Subject: [PATCH 049/140] fix: normalize empty stdio resume identity --- packages/ui/stdio-agent/src/stdio-chat.ts | 5 +++-- packages/ui/stdio-agent/tests/stdio-chat.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 76347c91e4..17a11168db 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -104,9 +104,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // with durable parentSession lineage. Keeping the matching candidates also // covers HMR's publish-new-before-dispose-old ordering without ever falling // through to an unrelated root owned by another app or test fixture. - const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined ? agent.id.startsWith('main-session-') - : agent.id === config.resumeSessionId + : agent.id === resumeSessionId const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) let target: Agent | undefined = [...configuredRoots].at(-1) ctx.on('agent/created', (agent) => { diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 668068a72d..2ebc51e14e 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -747,6 +747,15 @@ describe('createStdioChat input', () => { await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) }) + + it('treats an empty resume session id as a fresh configured identity', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) + const agent = makeAgent('main-session-fresh') + ctx.agents.register(agent) + input.feed('hi') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toHaveLength(1) + }) }) describe('createStdioChat EOF exit', () => { From 6b59b6050e379de30bb8f53bbc38172f8ffe896a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:43:12 +0800 Subject: [PATCH 050/140] fix: preserve ACP scenario cleanup failures --- packages/support/acp-snapshot/src/harness.ts | 20 +++++++--- .../acp-snapshot/tests/harness.spec.ts | 38 ++++++++++++++++++- 2 files changed, 51 insertions(+), 7 deletions(-) diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 3db1355b0f..22b22deacd 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -244,9 +244,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise ) // Failure-safe teardown: wait for a still-running child, then attempt BOTH - // directory removals even when an earlier cleanup rejects. The main outcome - // wins over teardown noise so a step/harvest failure is never replaced; on a - // successful run, the first cleanup failure remains visible to the caller. + // directory removals even when an earlier cleanup rejects. Report every + // teardown failure alongside a scenario failure so neither orthogonal + // outcome hides the other. const cleanupResults: PromiseSettledResult[] = [] const cleanup = async (action: () => Promise): Promise => { cleanupResults.push(...await Promise.allSettled([action()])) @@ -256,10 +256,18 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cleanup(() => rm(cwd, { recursive: true, force: true })) await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + const cleanupFailures = cleanupResults + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (cleanupFailures.length > 0) { + throw new AggregateError( + outcome.status === 'rejected' ? [outcome.error, ...cleanupFailures] : cleanupFailures, + outcome.status === 'rejected' + ? 'snapshot scenario and cleanup failed' + : 'snapshot cleanup failed', + ) + } if (outcome.status === 'rejected') throw outcome.error - const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') - /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ - if (cleanupFailure !== undefined) throw cleanupFailure.reason return outcome.value } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 902f48d2cf..de764cfd8a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,11 +3,29 @@ import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' -import { afterAll, describe, expect, it } from 'vitest' +import { afterAll, describe, expect, it, vi } from 'vitest' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' import { launchAcpTestAgent } from '../src/launcher.ts' +const fsControl = vi.hoisted(() => ({ cleanupFailure: undefined as Error | undefined })) + +vi.mock('node:fs/promises', async (importOriginal) => { + const actual = await importOriginal() + return { + ...actual, + async rm(...args: Parameters): Promise { + if (String(args[0]).includes('acp-snap-cwd-') && fsControl.cleanupFailure !== undefined) { + const failure = fsControl.cleanupFailure + fsControl.cleanupFailure = undefined + await actual.rm(...args) + throw failure + } + await actual.rm(...args) + }, + } +}) + /** * Unit tests for the subprocess harness, driven through the REAL spawn path * (tsx loader, temp cwd, env plumbing) against the scripted fake ACP bin in @@ -238,6 +256,24 @@ describe('runScenario', () => { )).rejects.toThrow(/expected the prompt to fail/) }) + it('reports scenario and cleanup failures together', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ prompt: 'respond' }) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: [...boot, { op: 'promptExpectError', text: 'fine' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + const failures = (failure as AggregateError).errors as unknown[] + expect(failures).toHaveLength(2) + expect(failures[0]).toBeInstanceOf(Error) + expect((failures[0] as Error).message).toMatch(/expected the prompt to fail/) + expect(failures[1]).toBe(cleanupFailure) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 2333ab19e3b03bc84cf050b16e897b830b2dfdf2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:46:05 +0800 Subject: [PATCH 051/140] fix: verify JSON-RPC child ownership --- docs/cordis-catalog/services.md | 1 + packages/core/agent/README.md | 1 + packages/core/agent/src/index.ts | 12 ++++++ packages/core/agent/tests/agent.spec.ts | 4 ++ packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 11 +++-- packages/ui/jsonrpc/tests/server.spec.ts | 51 ++++++++++++++++++++---- 7 files changed, 68 insertions(+), 14 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6a40f88a23 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -33,6 +33,7 @@ register(agent: Agent): () => void enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined +isOwnedBy(id: SessionId, owner: Agent): boolean list(): Agent[] roots(): Agent[] ``` diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index a45603f191..941f46baf0 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -13,6 +13,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` +- `ctx.agents.isOwnedBy(id: SessionId, owner: Agent): boolean` — whether the exact live entry was created through that parent agent's scoped context; runtime ownership is independent of durable session lineage. - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index abafa38e45..8a9ed68ab6 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -440,6 +440,18 @@ export class AgentRegistry extends Service { return this.store.get(id)?.agent } + /** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ + isOwnedBy(id: SessionId, owner: Agent): boolean { + return this.store.get(id)?.owner === owner + } + /** * All live agents, in registration order. * @returns a fresh array; mutating it does not affect the registry. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index d2866cacb3..5d79d1a91f 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -72,8 +72,12 @@ describe('AgentRegistry', () => { expect(ctx.agents.list()).toEqual([root, child]) expect(ctx.agents.roots()).toEqual([root]) + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(true) + expect(ctx.agents.isOwnedBy(root.id, root)).toBe(false) + expect(ctx.agents.isOwnedBy(SessionId('missing'), root)).toBe(false) detachChild() + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(false) detachRoot() }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index ffbd7a1288..df612ac263 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index fe605a8536..d78f24b5ab 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -109,8 +109,8 @@ export class HarnessSdkServer { // child disposal and reused ids need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - if (ctx.agents.get(info.id) === undefined) return const parent = subagentParentOf(this) + if (!ctx.agents.isOwnedBy(info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -118,7 +118,6 @@ export class HarnessSdkServer { localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { - const agent = ctx.agents.get(info.id) const parent = subagentParentOf(this) const providerRuns = localRuns.get(info.provider) const parentRuns = providerRuns?.get(info.id) @@ -130,10 +129,10 @@ export class HarnessSdkServer { if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above; a parentless - // local provider still gets its terminal notification. A remote provider - // has neither a pending local start nor a live local agent and is ignored. - if (pendingCount === undefined && agent === undefined) return + // has the session/created-driven start notification above. A remote run + // has neither a cached owned start nor a live child owned by this exact + // parent; an unrelated local agent with the same id never makes it local. + if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 427a190c36..c97bd1a6e1 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,12 +277,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await ctx.agents.create({ + const handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) - const parentlessHandle = await ctx.agents.create({ + const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -331,6 +331,43 @@ describe('HarnessSdkServer', () => { } }) + it('ignores a remote run id that collides with an unrelated local agent', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('collision-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const unrelatedHandle = await ctx.agents.create({ + sessionId: SessionId('remote-run-id'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'remote', + id: SessionId('remote-run-id'), + stopReason: 'completed', + lastAssistantMessage: [], + }, () => unrelatedHandle.dispose()) + + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.agentId === 'remote-run-id', + )).toBe(false) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('retains locality across continuation runs on one live child', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) const ctx = await makeHarness(storageDir) @@ -342,7 +379,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const childHandle = await ctx.agents.create({ + const childHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('continuation-child'), meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, agentOptions: { model: 'deepseek' }, @@ -385,7 +422,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const oldChild = await ctx.agents.create({ + const oldChild = await oldParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, agentOptions: { model: 'deepseek' }, @@ -425,7 +462,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const newChild = await ctx.agents.create({ + const newChild = await newParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, @@ -483,12 +520,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - handle = await ctx.agents.create({ + handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) - failedHandle = await ctx.agents.create({ + failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, From 6b782b018927139ea07e5907488b0b948d90c813 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:54:34 +0800 Subject: [PATCH 052/140] fix: bind stdio to its exact fresh identity --- docs/config-catalog.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/core/agent-loop/README.md | 5 ++- packages/core/agent-loop/src/index.ts | 11 +++-- .../tests/config-session-id.spec.ts | 30 +++++++++++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 7 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 32 +++++--------- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 13 ++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 44 +++++-------------- 10 files changed, 88 insertions(+), 62 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..66791edb0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,6 +119,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -645,7 +647,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 032eae4f7d..404ba83636 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,7 +16,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..246c9cdc27 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids + sessionId?: string // optional exact identity for a fresh session model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index dbe503ff6a..0041b984d1 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,6 +326,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -341,6 +343,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + sessionId: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -360,12 +363,14 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) - for (const { id, cwd, resumeSessionId, ...options } of config.agents) { + for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - this.create(sessionId, options, cwd === undefined ? {} : { cwd }) + this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) continue } + if (sessionId !== undefined) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..543335e5fd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -24,7 +24,37 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } +async function makeCoreContext(): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + return ctx +} + describe('config-driven session id', () => { + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { + const exact = await makeCoreContext() + await exact.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact'), model: 'mock' }], + }) + expect(exact.agents.get(SessionId('stdio-exact'))?.session.id).toBe('stdio-exact') + await exact.fiber.dispose() + + const conflicting = await makeCoreContext() + await expect(conflicting.plugin(AgentLoop, { + agents: [{ + id: 'main', + sessionId: SessionId('fresh'), + resumeSessionId: SessionId('persisted'), + model: 'mock', + }], + })).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive') + await conflicting.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index d7d30ee49d..b509e46781 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 2eca0cceb3..03f3d49555 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -39,6 +39,7 @@ */ import type { Context } from 'cordis' +import { randomUUID } from 'node:crypto' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' import { SessionId } from '@deepseek-ai/dsh-session' @@ -108,6 +109,8 @@ export const Config: z = z.object({ * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, @@ -117,7 +120,7 @@ export function apply(ctx: Context, config: Config): void { id: 'main', model: config.model, cwd: process.cwd(), - ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, + ...resumeSessionId === undefined ? { sessionId } : { resumeSessionId: sessionId }, }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) @@ -126,6 +129,6 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(toolAskUser) ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', - ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + sessionId, }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17a11168db..93c8f9b4f1 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,13 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ - resumeSessionId?: string + /** Exact shared agent/session identity this app instance created or resumed. */ + sessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - resumeSessionId: z.string(), + sessionId: z.string(), }) /** @@ -98,26 +98,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // Bind only to this app's configured top-level agent. Fresh runs own the - // `main-session-*` namespace; resumed runs own the exact persisted id. The - // registry's runtime-root relation excludes subagents without confusing it - // with durable parentSession lineage. Keeping the matching candidates also - // covers HMR's publish-new-before-dispose-old ordering without ever falling - // through to an unrelated root owned by another app or test fixture. - const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId - const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined - ? agent.id.startsWith('main-session-') - : agent.id === resumeSessionId - const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) - let target: Agent | undefined = [...configuredRoots].at(-1) + // Bind only to the exact identity this app passed to its config-created + // agent. Session ids are opaque: neither a prefix nor registry order can + // identify ownership. The root check rejects a child that somehow preempts + // the configured id; later recreation under the same id supports loop HMR. + const matchesConfiguredIdentity = (agent: Agent): boolean => + agent.id === config.sessionId && ctx.agents.roots().includes(agent) + let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) ctx.on('agent/created', (agent) => { - if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return - configuredRoots.add(agent) - target ??= agent + if (matchesConfiguredIdentity(agent)) target = agent }) ctx.on('agent/disposed', (agent) => { - configuredRoots.delete(agent) - if (target === agent) target = [...configuredRoots].at(-1) + if (target === agent) target = undefined }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 5c5c0d2667..9a7bf10bad 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -93,6 +93,19 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) + it('normalizes an empty resume id to a fresh exact app identity', async () => { + const ctx = await mount({ + model: 'mock', + resumeSessionId: '', + persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', + skills: await isolatedSkillsConfig(), + }) + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) + expect(agent?.id).toBe(agent?.session.id) + await ctx.fiber.dispose() + }) + it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2ebc51e14e..f1ca914525 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } +const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,7 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const resumed = makeAgent('resumed') @@ -247,33 +247,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) - it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup({ welcome: 'hi there' }) - const oldRoot = makeAgent('main-session-old') - const child = makeAgent('child') - ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('main-session-replacement') - const lateChild = makeAgent('late-child') + it('retargets only the exact identity after loop HMR recreation', async () => { + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'main-session-fixed' }) + const oldRoot = makeAgent('main-session-fixed') + const prefixCollision = makeAgent('main-session-unrelated') const disposeOld = ctx.agents.register(oldRoot) - const disposeChild = ctx.agents.enter(child, oldRoot) - ctx.agents.announce(child) - ctx.agents.register(replacement) - const disposeLateChild = ctx.agents.enter(lateChild, replacement) - ctx.agents.announce(lateChild) - - // The replacement's created edge arrived while oldRoot was still targeted. - // A replacement-owned child then arrived even later. Once oldRoot is - // removed, runtime ownership still identifies replacement as the only - // surviving root instead of selecting either newer child by insertion order. + ctx.agents.register(prefixCollision) disposeOld() + const replacement = makeAgent('main-session-fixed') + ctx.agents.register(replacement) + input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) - expect(child.sent).toEqual([]) - expect(lateChild.sent).toEqual([]) + expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) - disposeLateChild() - disposeChild() }) it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { @@ -740,7 +728,7 @@ describe('createStdioChat input', () => { }) it('drives the exact app-configured resumed session', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) + const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') @@ -748,14 +736,6 @@ describe('createStdioChat input', () => { expect(agent.sent).toHaveLength(1) }) - it('treats an empty resume session id as a fresh configured identity', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) - const agent = makeAgent('main-session-fresh') - ctx.agents.register(agent) - input.feed('hi') - await new Promise(r => setImmediate(r)) - expect(agent.sent).toHaveLength(1) - }) }) describe('createStdioChat EOF exit', () => { From a8c0e8a03c35b1303d7780b8215e482809c32d6f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:55:15 +0800 Subject: [PATCH 053/140] test: cover successful ACP cleanup failure --- .../support/acp-snapshot/tests/harness.spec.ts | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index de764cfd8a..23b4192a4d 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -274,6 +274,21 @@ describe('runScenario', () => { expect(failures[1]).toBe(cleanupFailure) }) + it('reports cleanup failure after an otherwise successful scenario', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({}) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: boot }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).message).toBe('snapshot cleanup failed') + expect((failure as AggregateError).errors as unknown[]).toEqual([cleanupFailure]) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 2dca8e2151ef3745f88507fe2aac17cabd630eac Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:58:35 +0800 Subject: [PATCH 054/140] docs: refresh agent loop catalog location --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6b456ef942 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 00462f80a6ff59604e44b71446bb9b2427a212c8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:01:36 +0800 Subject: [PATCH 055/140] docs: expose agent ownership in Cordis catalog --- packages/cordis/tool-cordis/src/api-catalog.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..ede7935f8e 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -72,6 +72,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', + 'isOwnedBy(id: SessionId, owner: Agent): boolean', 'list(): Agent[]', 'roots(): Agent[]', ], From db3e97fc17a0f96fda7a2ecee94af86e7fad2102 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:05:19 +0800 Subject: [PATCH 056/140] test: create built probe child in parent scope --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 159600e49c..bc6642263e 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -58,7 +58,7 @@ try { meta: { cwd: storageRoot }, agentOptions: { model: "test" }, }); - const child = await ctx.agents.create({ + const child = await parent.agent.ctx.agents.create({ sessionId: SessionId("built-child"), meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, agentOptions: { model: "test" }, From 3e2ba3f5574b43dc5af5d03e146769be241f96a3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:13:05 +0800 Subject: [PATCH 057/140] fix: stop ACP teardown when fallback kill fails --- packages/support/acp-snapshot/src/launcher.ts | 27 ++++++++- .../acp-snapshot/tests/harness.spec.ts | 59 +++++++++++++++++++ 2 files changed, 83 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index f1271986c0..8d25a6f56c 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ + /** Close the process and drain its streams and callbacks; rejects promptly if fallback termination is refused. */ close(signal?: NodeJS.Signals): Promise } @@ -231,8 +231,29 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // signal can leave the subprocess live. Force termination, await the // already-observed exit edge, and only then propagate the child error so // callers may safely remove cwd/session resources after close rejects. - child.kill('SIGKILL') - await exited + const fallbackError = Promise.withResolvers() + const observeFallbackError = (error: Error): void => { fallbackError.resolve(error) } + child.once('error', observeFallbackError) + if (!child.kill('SIGKILL')) { + child.off('error', observeFallbackError) + closeUpdateStream() + throw new AggregateError( + [failure, new Error('Fallback SIGKILL was not accepted by the child process')], + 'ACP test agent failed and fallback termination was refused', + ) + } + const fallbackFailure = await Promise.race([ + exited.then((): undefined => undefined), + fallbackError.promise, + ]) + child.off('error', observeFallbackError) + if (fallbackFailure !== undefined) { + closeUpdateStream() + throw new AggregateError( + [failure, fallbackFailure], + 'ACP test agent failed and fallback termination was refused', + ) + } await drained closeUpdateStream() throw failure diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 23b4192a4d..ff7c304121 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -131,6 +131,65 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('rejects promptly when fallback termination is refused', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockReturnValue(false) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [ + childFailure, + expect.objectContaining({ message: 'Fallback SIGKILL was not accepted by the child process' }), + ], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + + it('rejects promptly when fallback termination emits an error', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const fallbackFailure = Object.assign(new Error('fallback signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockImplementation((signal) => { + if (signal === 'SIGKILL') queueMicrotask(() => launched.child.emit('error', fallbackFailure)) + return signal === 'SIGKILL' + }) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [childFailure, fallbackFailure], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true }) let releasePermission: (() => void) | undefined From 816b6e4c68e26c38c4ac0aab1cad3ee14714a510 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:25:49 +0800 Subject: [PATCH 058/140] fix: restore exact config sessions on loop reload --- docs/config-catalog.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 10 ++--- .../2026-07-02-remove-stream-chunk-mirror.md | 2 +- packages/core/agent-loop/README.md | 6 +-- packages/core/agent-loop/src/index.ts | 29 ++++++++++++++- .../tests/config-session-id.spec.ts | 37 +++++++++++++++++++ packages/ui/stdio-agent/README.md | 2 +- 7 files changed, 75 insertions(+), 13 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 66791edb0a..024d3b766b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,7 +119,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 404ba83636..20ba40c196 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -4,19 +4,19 @@ Status: implemented ## Problem -The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. +A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle. -ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. +ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids. -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. -Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. +Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation. ## Decision An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. An ordinary fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide. A coupled app may pre-mint and pass an exact `sessionId`: first use creates it, while an AgentLoop remount with an already-present persistence service resumes materialized history under that same identity. `resumeSessionId` instead requires an existing persisted identity. The two exact-id inputs are mutually exclusive. Stdio uses the resume-or-create form so its config-created agent and UI share one opaque identity across loop reloads instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index a272dfe0b2..6ca85b3d16 100644 --- a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -42,4 +42,4 @@ Not touched: ## Consequences -A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event` and filters `assistant/chunk` (the `Agent` handle, if needed, is recovered from a session-id→agent map built from `agent/created`/`agent/disposed`, exactly as boundary consumers already do). No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. +A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event`, filters `assistant/chunk`, and looks up the corresponding live handle directly with `ctx.agents.get(session.id)` when needed. No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 246c9cdc27..2db1a6c079 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary. An app may instead supply a stable exact `sessionId`: first use creates it, while a remount with persistence already present resumes its materialized history. `resumeSessionId` requires and loads an existing persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,7 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids - sessionId?: string // optional exact identity for a fresh session + sessionId?: string // optional exact resume-or-create identity model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 0041b984d1..33e8c3c443 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,7 +326,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string @@ -364,8 +364,17 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { + const meta = cwd === undefined ? {} : { cwd } if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) + const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`) + const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence') + if (persistence === undefined) { + this.create(configuredId, options, meta) + } else { + void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + }) + } continue } if (sessionId !== undefined) { @@ -385,6 +394,22 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Restore a materialized exact config identity on remount, or create it on first use. */ + private async restoreOrCreateConfigured( + ownerCtx: Context, + persistence: SessionPersistence, + sessionId: SessionId, + agentOptions: AgentOptions, + meta: Pick, + ): Promise { + const exists = (await persistence.list()).some(header => header.id === sessionId) + if (exists) { + await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) + return + } + this.create(sessionId, agentOptions, meta) + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 543335e5fd..9382804527 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -55,6 +55,43 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')])) + const config = { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-reload'), model: 'mock' }] } + + const firstLoop = await ctx.plugin(AgentLoop, config) + let first: ReactLoopAgent | undefined + for (let i = 0; i < 50 && first === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + first = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(first).toBeDefined() + first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, first!) + await firstLoop.dispose() + + const secondLoop = await ctx.plugin(AgentLoop, config) + let second: ReactLoopAgent | undefined + for (let i = 0; i < 50 && second === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + second = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(second).toBeDefined() + expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me') + second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, second!) + await ctx.sessions.flush(second!.session) + const loaded = await ctx.sessionPersistence.load(SessionId('stdio-exact-reload')) + expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index b509e46781..15b1c78f09 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin From 656ae95263cfd9f832bdeefbf9da6a91b8ce72bb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:28:04 +0800 Subject: [PATCH 059/140] test: await exact stdio startup condition --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 9a7bf10bad..a14848a549 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -114,9 +114,8 @@ describe('dsh-stdio-agent app', () => { const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) - await new Promise(resolve => setTimeout(resolve, 80)) - expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.list()).toHaveLength(1) + await expect.poll(() => ctx.get('sessionPersistence')).toBeDefined() + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) From cf21e252fa8fd7e66c4b0c6a5acface4821d4712 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:32:02 +0800 Subject: [PATCH 060/140] fix: recognize provider-owned local subagents --- packages/subagent/subagent/README.md | 2 ++ packages/subagent/subagent/src/types.ts | 6 +++++- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 22 ++++++++++++++++------ packages/ui/jsonrpc/tests/server.spec.ts | 5 ++++- 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 413bbbdafc..016d363d78 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,6 +50,8 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. + The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 827c2db7a7..37e0b28323 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,11 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ + /** + * Parent-scoped run id. A local run publishes a child session whose + * `parentSession` records `request.parent`; a remote provider mints an id + * unique in the parent namespace. + */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index df612ac263..4ef9e86ffc 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server recognizes a live child through either exact delegating-parent runtime ownership or matching durable `parentSession` lineage, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index d78f24b5ab..723f2eb4eb 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -66,6 +66,15 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } +/** Whether the live id names a local child related to this exact delegating parent. */ +function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { + const child = ctx.agents.get(id) + return child !== undefined && ( + ctx.agents.isOwnedBy(id, parent) + || child.session.header.parentSession === parent.session.id + ) +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -104,13 +113,14 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count those starts by - // the exact delegating-parent carrier so later completions remain local after - // child disposal and reused ids need no settlement-order assumption. + // In-process providers publish the child before start. Count starts related + // by exact runtime ownership or durable parent lineage so provider-owned + // roots remain local, completions survive child disposal, and reused ids + // need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { const parent = subagentParentOf(this) - if (!ctx.agents.isOwnedBy(info.id, parent)) return + if (!isLocalChild(ctx, info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -130,9 +140,9 @@ export class HarnessSdkServer { } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above. A remote run - // has neither a cached owned start nor a live child owned by this exact + // has neither a cached local start nor a live child related to this // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return + if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index c97bd1a6e1..3861a6729d 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,11 +277,14 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await parentHandle.agent.ctx.agents.create({ + // A custom in-process provider may own its child at the provider/root + // scope while preserving durable parent lineage. + const handle = await ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + expect(ctx.agents.roots()).toContain(handle.agent) const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, From 949ee03377719aea96a26fd96ba0bc284cf740ec Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:38:53 +0800 Subject: [PATCH 061/140] test: cover exact session restore failure --- .../tests/config-session-id.spec.ts | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 9382804527..dcde82efe2 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,27 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains an exact-id persistence lookup failure', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const failure = new Error('persistence index failed') + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-failure'), model: 'mock' }], + }) + + await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( + 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', + )) + expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 46b8bce03acebd579cdcb4daf91c02e51eddf78e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:47:47 +0800 Subject: [PATCH 062/140] fix: join exact session startup on teardown --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- packages/core/agent-loop/src/index.ts | 19 +++++++++++--- .../tests/config-session-id.spec.ts | 25 +++++++++++++++++++ 4 files changed, 42 insertions(+), 6 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 024d3b766b..d22bcca6f7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 6b456ef942..e79422b94f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33e8c3c443..d2d8648595 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -45,6 +45,7 @@ const INACTIVE_STATES: ReadonlySet = new Set([ class FactoryOwnership { private accepting = true private transactions = new Set() + private startupTasks = new Set>() constructor(private readonly fiber: Context['fiber']) {} @@ -57,12 +58,20 @@ class FactoryOwnership { return () => { this.transactions.delete(transaction) } } + /** Join config startup work that begins before an agent transaction exists. */ + trackStartup(task: Promise): void { + this.startupTasks.add(task) + const forget = () => { this.startupTasks.delete(task) } + void task.then(forget, forget) + } + async dispose(): Promise { this.accepting = false const reason = new Error('agent loop is not active') - await Promise.all( - [...this.transactions].map(transaction => transaction.disposeForFactory(reason)), - ) + await Promise.all([ + ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), + ...this.startupTasks, + ]) } } @@ -371,9 +380,10 @@ export class AgentLoop extends Service implements AgentFactory { if (persistence === undefined) { this.create(configuredId, options, meta) } else { - void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) }) + this.ownership.trackStartup(startup) } continue } @@ -403,6 +413,7 @@ export class AgentLoop extends Service implements AgentFactory { meta: Pick, ): Promise { const exists = (await persistence.list()).some(header => header.id === sessionId) + if (!this.ownership.isActive()) return if (exists) { await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) return diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index dcde82efe2..c1a04fadd0 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -113,6 +113,31 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + listing.resolve([]) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 288023dac182c407c296571f3730ff3a89a0696a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:51:36 +0800 Subject: [PATCH 063/140] docs: define local subagent lineage --- docs/core-data-structures/subagent.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 883c33020a..7b57789a7c 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -76,6 +76,8 @@ interface SubagentRun { } ``` +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. + ## The provider seam: `SubagentProvider` One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it. It describes conversation history only, not tool registrations, injected services, or authority inheritance. From e8f1bd41f5bd96c529c59ed524cfdeef7d3d1ce3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:02:18 +0800 Subject: [PATCH 064/140] fix: buffer stdio until exact session starts --- docs/event-producer-consumer.md | 2 +- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/stdio-chat.ts | 65 ++++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 72 +++++++++++++++---- 4 files changed, 108 insertions(+), 33 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..1439873f69 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -15,7 +15,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 15b1c78f09..bbf175d92d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 93c8f9b4f1..17d396c042 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -3,9 +3,10 @@ * `steer()`, and renders the durable transcript to stdout. A UI is "just a * plugin" — it consumes the `session/event` feed (the assistant token stream, * turn/step boundaries, tool activity, todos) plus a few `agent/*` control - * events (`agent/status`, `agent/created`/`agent/disposed`) and the `agents` - * service. Dimmed chain-of-thought rendering plus robust piped-stdin EOF→idle - * exit handling, configured via {@link Config}. + * events (`agent/status`, `agent/created`/`agent/disposed`, + * `agent/session-start`) and the `agents` service. Dimmed chain-of-thought + * rendering plus robust piped-stdin EOF→idle exit handling, configured via + * {@link Config}. * * An internal module of the stdio app, not a package of its own: the app's * front-door cluster always includes this UI, and nothing else composes it. @@ -105,12 +106,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const matchesConfiguredIdentity = (agent: Agent): boolean => agent.id === config.sessionId && ctx.agents.roots().includes(agent) let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) - ctx.on('agent/created', (agent) => { - if (matchesConfiguredIdentity(agent)) target = agent - }) - ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined - }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -158,7 +153,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt }) ctx.effect(() => { - const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) // Piped-input exit, once stdin reaches EOF: // - If no line ever submitted work (empty stdin, blank-only lines), exit // immediately — no turn will ever start, so there is nothing to wait @@ -176,6 +170,36 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt let exitTimer: ReturnType | undefined let activeQuestion: PendingQuestion | undefined const questionQueue: PendingQuestion[] = [] + const queuedInput: string[] = [] + let targetReady = target !== undefined + let hadReadyTarget = targetReady + + const submit = (agent: Agent, text: string): void => { + submittedWork = true + if (agent.status === 'running') { + agent.steer([{ type: 'text', text }]) + } else { + agent.send([{ type: 'text', text }]) + } + } + + const disposeCreatedListener = ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent)) return + target = agent + targetReady = false + }) + const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { + if (agent !== target) return + targetReady = true + hadReadyTarget = true + for (const text of queuedInput.splice(0)) submit(agent, text) + }) + const disposeDisposedListener = ctx.on('agent/disposed', (agent) => { + if (target !== agent) return + target = undefined + targetReady = false + }) + const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) const maybeExit = (): void => { if (disposed || !stdinClosed) return @@ -351,16 +375,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return const agent = target - if (!agent) { + if (agent === undefined || !targetReady) { + // Initial exact-id restoration is asynchronous. Preserve input until + // session-start, the first supported point for queueing agent work. + // After a previously ready target disappears, a line in the HMR gap + // still fails loud unless its exact replacement is already publishing. + if (!hadReadyTarget || agent !== undefined) { + submittedWork = true + queuedInput.push(text) + return + } ctx.logger.error('ui-stdio: main agent is not running') return } - submittedWork = true - if (agent.status === 'running') { - agent.steer([{ type: 'text', text }]) - } else { - agent.send([{ type: 'text', text }]) - } + submit(agent, text) }) reader.on('close', () => { // Fires for BOTH stdin EOF and plugin disposal (reader.close() below); @@ -376,6 +404,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposePendingQuestions() disposeUserInteractionProvider() disposeStatusListener() + disposeCreatedListener() + disposeSessionStartListener() + disposeDisposedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index f1ca914525..943c48ef08 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -64,6 +64,13 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { } as never } +/** Register a fake configured agent and cross the supported startup-work boundary. */ +function registerReady(ctx: Context, agent: Agent, source: 'startup' | 'resume' = 'startup'): () => void { + const dispose = ctx.agents.register(agent) + ctx.emit('agent/session-start', agent, source) + return dispose +} + /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ function makeSession(id: string): Session { return { id, header: { id } } as Session @@ -198,15 +205,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) - it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + it('buffers input for a lineage-bearing configured agent until its session starts', async () => { const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) + ctx.emit('agent/session-start', unrelated, 'startup') const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) + await new Promise(resolve => setImmediate(resolve)) + expect(resumed.sent).toEqual([]) - input.feed('continue') + ctx.emit('agent/session-start', resumed, 'resume') await new Promise(resolve => setImmediate(resolve)) expect(unrelated.sent).toEqual([]) @@ -256,9 +269,11 @@ describe('createStdioChat rendering', () => { disposeOld() const replacement = makeAgent('main-session-fixed') ctx.agents.register(replacement) - input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) + expect(replacement.sent).toEqual([]) + ctx.emit('agent/session-start', replacement, 'resume') + await new Promise(resolve => setImmediate(resolve)) expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) @@ -269,7 +284,7 @@ describe('createStdioChat rendering', () => { const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const configured = makeAgent('main') - const disposeConfigured = ctx.agents.register(configured) + const disposeConfigured = registerReady(ctx, configured) const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) disposeConfigured() @@ -693,7 +708,7 @@ describe('createStdioChat input', () => { it('sends a typed line to an idle agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('do a thing') await new Promise(r => setImmediate(r)) expect(agent.sent).toEqual([[{ type: 'text', text: 'do a thing' }]]) @@ -703,7 +718,7 @@ describe('createStdioChat input', () => { it('steers a typed line into a running agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('steer me') await new Promise(r => setImmediate(r)) expect(agent.steered).toEqual([[{ type: 'text', text: 'steer me' }]]) @@ -719,18 +734,26 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([]) }) - it('logs and drops a line when the target agent is not running', async () => { + it('buffers a line until the initial target session starts', async () => { const { ctx, input } = await setup() const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') + expect(spy).not.toHaveBeenCalled() + + const agent = makeAgent('main') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') - ctx.agents.register(agent) + registerReady(ctx, agent, 'resume') input.feed('hi') await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) @@ -749,7 +772,7 @@ describe('createStdioChat EOF exit', () => { it('waits for the agent to settle idle after running before exiting', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -764,10 +787,31 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('keeps piped EOF pending until buffered startup input runs', async () => { + const { ctx, input, exit } = await setup() + input.feed('work') + input.finish() + await flushExit() + expect(exit).not.toHaveBeenCalled() + + const agent = makeAgent('main', 'idle') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'work' }]]) + ctx.emit('agent/status', agent, 'running') + ;(agent as { status: AgentStatus }).status = 'idle' + ctx.emit('agent/status', agent, 'idle') + await flushExit() + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') // sawRunning = true @@ -785,7 +829,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit on an idle transition for a different agent', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -799,7 +843,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit while a turn is still running at EOF', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') @@ -848,7 +892,7 @@ describe('createStdioChat disposal (HMR safety)', () => { it('removes the agent/status listener on dispose', async () => { const { ctx, fiber, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) await fiber.dispose() From c1fb97c63a3ac7c3a6d4066ccc7615d292c0dfa7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:23:38 +0800 Subject: [PATCH 065/140] fix: surface config startup failures --- docs/architecture.md | 7 ++- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 12 +++++ docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 1 + docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 6 +++ packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 30 +++++++++++- .../tests/config-session-id.spec.ts | 10 ++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/package.json | 2 + packages/ui/stdio-agent/src/index.ts | 23 ++++----- packages/ui/stdio-agent/src/stdio-chat.ts | 20 ++++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 47 ++++++++++++++++++- pnpm-lock.yaml | 3 ++ 16 files changed, 151 insertions(+), 21 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..06a3a86fb4 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -51,14 +51,17 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +Default loop processing remains exposed through plugin-visible services and events. A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +Declarative startup chooses one agent/session identity. No id mints `-session-`; exact `sessionId` resumes when stored and otherwise creates; `resumeSessionId` requires stored history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, letting front doors reject buffered work. + ### Turn Flow ```text -prepare private session + agent.ctx -> await unpublished setup +choose declarative identity and fresh/resume path + -> prepare private session + agent.ctx -> await unpublished setup -> enter session + agent -> session/created -> agent/created -> enable driving -> agent/session-start(source) -> start driver forever: diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d22bcca6f7..839e7967e6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..3c56882494 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -175,6 +175,18 @@ Types: [Agent](../core-data-structures/core.md) Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +## `agent-loop/*` + +### `agent-loop/config-start-failed` — emit + +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. + +```ts cordis-catalog +'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void +``` + +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) + ## `approval/*` ### `approval/request` — waterfall diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e79422b94f..63375a46bf 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 1439873f69..0ab96fca31 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,6 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..cc4cd86c47 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -316,6 +316,7 @@ flowchart TD pkg_acp_agent --> pkg_user_interaction pkg_stdio_agent --> pkg_agent pkg_stdio_agent --> pkg_agent_core + pkg_stdio_agent --> pkg_agent_loop pkg_stdio_agent --> pkg_app_boot pkg_stdio_agent --> pkg_llm pkg_stdio_agent --> pkg_session @@ -394,4 +395,4 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-agent`](../packages/ui/acp-agent) | `ui` | [`acp`](../packages/ui/acp), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`agent-loop`](../packages/core/agent-loop), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..a9d1d5acaa 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -237,6 +237,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ /** Every harness event, sorted by name. */ export const EVENT_API: readonly EventApiEntry[] = [ + { + name: 'agent-loop/config-start-failed', + mode: 'emit', + signature: '\'agent-loop/config-start-failed\'(sessionId: SessionId, error: unknown): void', + summary: 'A declarative agent entry failed before it could publish a live agent.', + }, { name: 'agent/created', mode: 'emit', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2db1a6c079..2593da7c47 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index d2d8648595..62c5d94b06 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -327,6 +327,17 @@ declare module 'cordis' { interface Context { agentLoop: AgentLoop } + interface Events { + /** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ + 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void + } } /** Plugin configuration for declarative startup agents. */ @@ -381,7 +392,7 @@ export class AgentLoop extends Service implements AgentFactory { this.create(configuredId, options, meta) } else { const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'restore', configuredId, error) }) this.ownership.trackStartup(startup) } @@ -396,7 +407,7 @@ export class AgentLoop extends Service implements AgentFactory { resumeSessionId, agentOptions: options, }).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error) }) }) return fiber.dispose @@ -404,6 +415,21 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Report a contained declarative-start failure to identity-bound consumers. */ + private reportConfiguredStartupFailure( + configId: string, + action: 'restore' | 'resume', + sessionId: SessionId, + error: unknown, + ): void { + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + try { + this.ctx.emit('agent-loop/config-start-failed', sessionId, error) + } catch (listenerError) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } + } + /** Restore a materialized exact config identity on remount, or create it on first use. */ private async restoreOrCreateConfigured( ownerCtx: Context, diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index c1a04fadd0..ad9ec6b792 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -98,6 +98,12 @@ describe('config-driven session id', () => { const ctx = await makeCoreContext() await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') + const listenerFailure = new Error('failure observer failed') + const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + failures.push({ sessionId, error }) + }) + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -108,6 +114,10 @@ describe('config-driven session id', () => { await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', )) + expect(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: Error: failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index bbf175d92d..a91bef85a0 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt; `agent-loop/config-start-failed` instead drains and reports buffered input so a missing or corrupt persisted session cannot hang EOF. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/package.json b/packages/ui/stdio-agent/package.json index fcd432a9fd..60a9529d47 100644 --- a/packages/ui/stdio-agent/package.json +++ b/packages/ui/stdio-agent/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-app-boot": "^0.0.1", "@cordisjs/plugin-logger-console": "^1.0.0", "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-core": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -51,6 +52,7 @@ "@deepseek-ai/dsh-app-boot": "workspace:^", "@cordisjs/plugin-logger-console": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 03f3d49555..1278ded88a 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -102,16 +102,23 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating one agent from this app's - * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is - * a leaf concern (see the module doc), so it is not mounted here. + * Compose the spine with the stdio front door. Console logging, persistence, + * and user interaction mount first; the readline UI then waits on the agent + * registry and subscribes to config-start failures before agent-core can start + * the configured identity. The ask-user tool waits on the completed spine. + * The `hmr` dev-reload plugin is a leaf concern (see the module doc), so it is + * not mounted here. */ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(UserInteractionService) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + sessionId, + }) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, @@ -124,11 +131,5 @@ export function apply(ctx: Context, config: Config): void { }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', - sessionId, - }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17d396c042..39d59dfdc0 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -21,6 +21,7 @@ import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-agent-loop' import { UserInteractionError, type AskUserQuestionAnswer, @@ -173,6 +174,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const queuedInput: string[] = [] let targetReady = target !== undefined let hadReadyTarget = targetReady + let failedStartup: { error: unknown } | undefined const submit = (agent: Agent, text: string): void => { submittedWork = true @@ -187,6 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt if (!matchesConfiguredIdentity(agent)) return target = agent targetReady = false + failedStartup = undefined }) const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { if (agent !== target) return @@ -220,6 +223,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt exitTimer = setTimeout(() => { exit(0) }, 200) } + const disposeStartupFailedListener = ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + if (sessionId !== config.sessionId || targetReady) return + failedStartup = { error } + const dropped = queuedInput.length + queuedInput.length = 0 + submittedWork = sawRunning + if (dropped > 0) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + } + maybeExit() + }) + const disposeStatusListener = ctx.on('agent/status', (subject, status) => { if (subject !== target) return if (status === 'running') sawRunning = true @@ -374,6 +389,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return + if (failedStartup !== undefined) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + return + } const agent = target if (agent === undefined || !targetReady) { // Initial exact-id restoration is asynchronous. Preserve input until @@ -407,6 +426,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposeCreatedListener() disposeSessionStartListener() disposeDisposedListener() + disposeStartupFailedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 943c48ef08..11e64ac19c 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -4,7 +4,7 @@ import { Context } from 'cordis' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' -import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts' @@ -750,6 +750,32 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) + it('drops later input after the configured startup fails', async () => { + const { ctx, input } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + const failure = new Error('persisted session is corrupt') + ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) + + input.feed('cannot run') + await new Promise(r => setImmediate(r)) + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + ) + }) + + it('ignores a stale config-start failure after the exact target is ready', async () => { + const { ctx, input } = await setup() + const agent = makeAgent('main') + registerReady(ctx, agent) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('stale')) + + input.feed('still live') + await new Promise(r => setImmediate(r)) + + expect(agent.sent).toEqual([[{ type: 'text', text: 'still live' }]]) + }) + it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') @@ -808,6 +834,25 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('drains buffered piped input and exits when configured startup fails', async () => { + const { ctx, input, exit } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + input.feed('work') + input.finish() + await new Promise(r => setImmediate(r)) + ctx.emit('agent-loop/config-start-failed', SessionId('other'), new Error('unrelated')) + await flushExit() + expect(exit).not.toHaveBeenCalled() + + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + await flushExit() + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + ) + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..7a8fe5a6ea 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1328,6 +1328,9 @@ importers: '@deepseek-ai/dsh-agent-core': specifier: workspace:^ version: link:../../core/agent-core + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../app-boot From 7d6ef0a47260a096a7594e54c797fde9e1ba8ca0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:33:36 +0800 Subject: [PATCH 066/140] fix: contain config failure observers --- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 14 ++++++++++---- .../agent-loop/tests/config-session-id.spec.ts | 7 ++++++- scripts/gen-doc-graphs.ts | 3 +++ 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 0ab96fca31..de89a69f18 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 62c5d94b06..5a7484a378 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -423,10 +423,16 @@ export class AgentLoop extends Service implements AgentFactory { error: unknown, ): void { this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) - try { - this.ctx.emit('agent-loop/config-start-failed', sessionId, error) - } catch (listenerError) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(...args) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index ad9ec6b792..a7292b2284 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -99,11 +99,13 @@ describe('config-driven session id', () => { await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') const listenerFailure = new Error('failure observer failed') + const asyncListenerFailure = new Error('async failure observer failed') const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) + ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never) ctx.on('agent-loop/config-start-failed', (sessionId, error) => { failures.push({ sessionId, error }) }) - ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -118,6 +120,9 @@ describe('config-driven session id', () => { expect(warn).toHaveBeenCalledWith( 'agent "main": config-start-failed listener threw: Error: failure observer failed', ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: Error: async failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5144e388a2..fa7daed85e 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -245,6 +245,9 @@ const DYNAMIC_EVENT_DISPATCHERS: Array<{ event: string; pkg: string; method: str // Registry disposal reuses the stable carrier captured before entry commit // and contains each listener directly rather than rebuilding via agentEvents. { event: 'agent/disposed', pkg: 'agent', method: 'events.dispatch' }, + // Config startup failures have no live Agent carrier; AgentLoop resolves the + // callbacks directly to contain each synchronous throw and async rejection. + { event: 'agent-loop/config-start-failed', pkg: 'agent-loop', method: 'events.dispatch' }, { event: 'session/created', pkg: 'session', method: 'events.dispatch' }, // Session event callbacks are likewise resolved before the log push, then // invoked individually after commit so observer failures are contained. From a25c0f084f035f94a11292b17ec9a31e93349c2e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:25:30 +0800 Subject: [PATCH 067/140] fix: totalize configured startup failures --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 15 ++++++-- .../tests/config-session-id.spec.ts | 36 +++++++++++++++++++ 6 files changed, 52 insertions(+), 7 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d7a973fd81..484ba1c632 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 088e60450d..e44df3c3b2 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 8c00bd45ef..699c73fe2c 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 825f54b077..78a30bd4e1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 5a7484a378..3c09ef2e7f 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -41,6 +41,15 @@ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.FAILED, ]) +/** Render an arbitrary thrown value without letting coercion escape containment. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true @@ -422,16 +431,16 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { - this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { try { const returned: unknown = callback(...args) void Promise.resolve(returned).catch((listenerError: unknown) => { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${renderThrown(listenerError)}`) }) } catch (listenerError: unknown) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${renderThrown(listenerError)}`) } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index a7292b2284..b35dc71739 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -128,6 +128,42 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains startup and observer failures whose string coercion throws', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const unrenderable = { + [Symbol.toPrimitive](): never { + throw new Error('coercion escaped') + }, + } + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw unrenderable }) + // Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never) + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-unrenderable'), model: 'mock' }], + }) + + await expect.poll(() => failures).toEqual([unrenderable]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-driven restore of "stdio-exact-unrenderable" failed: ', + ) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: ', + ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: ', + ) + await ctx.fiber.dispose() + }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) dirs.push(root) From 287041e39e93b368646f0fe8298b65feab692acc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:35:25 +0800 Subject: [PATCH 068/140] fix: preserve malformed snapshot fixtures --- packages/support/acp-snapshot/src/suite.ts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 4d87093c8a..906521c42d 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -486,8 +486,10 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const entries = await readdir(dir, { withFileTypes: true }) await Promise.all(entries .filter(entry => entry.isFile() - && entry.name.startsWith('session.') - && entry.name.endsWith('.jsonl') + // Only valid numbered children are record-owned stale output. + // Malformed session-like names stay for the inventory guard to + // reject instead of being silently deleted during mutation. + && /^session\.[1-9]\d*\.jsonl$/.test(entry.name) && !outputNames.has(entry.name)) .map(entry => rm(join(dir, entry.name)))) fixtureFiles = outputFixtureFiles From 2027c70a17661fe2b8b5aab1685cd443ac2c3b56 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:38:32 +0800 Subject: [PATCH 069/140] fix: drain failed ACP launches --- packages/support/acp-snapshot/src/launcher.ts | 4 +++- packages/support/acp-snapshot/tests/harness.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3f9a21d596..30ca0b42b8 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,13 +178,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } + if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -206,6 +207,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { + await drained.catch(() => undefined) closeUpdateStream() throw error } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ff7c304121..6adb0d4268 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -62,8 +62,17 @@ describe('runScenario', () => { it('surfaces an asynchronous child spawn failure through startup and close', async () => { const { dir } = await scenario({}) const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + let stdioClosed = false + let clientClosed = false + launched.child.once('close', () => { stdioClosed = true }) + void launched.client.closed.then( + () => { clientClosed = true }, + () => { clientClosed = true }, + ) await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + expect(stdioClosed).toBe(true) + expect(clientClosed).toBe(true) }) it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { From 9f9f83c11f0ba190da488156efb015e3f7d921f4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:40:22 +0800 Subject: [PATCH 070/140] docs: align compaction output contract --- packages/compact/compact/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index fafcad76b8..adad9cfdfa 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -10,7 +10,7 @@ This package is the interface tier of the compaction capability, split so each c | `@deepseek-ai/dsh-compact-basic` (deferred) | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | -Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). +Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session`, and its durable `compact/summary` event uses the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). ## Service API (`ctx.compact`) From b47e4c5276604dd1e5a400f5f60d2c16e195df10 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:45:12 +0800 Subject: [PATCH 071/140] fix: suppress teardown startup failures --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 4 ++-- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 4 +++- packages/core/agent-loop/tests/config-session-id.spec.ts | 5 ++++- 8 files changed, 14 insertions(+), 9 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 41ab5c716b..0eb7f1fe55 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -56,7 +56,7 @@ Default loop processing remains exposed through plugin-visible services and even A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. -Startup resolves one identity. No id mints `-session-`; `sessionId` resumes stored or creates; `resumeSessionId` requires history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject buffered work. +Startup resolves identity. No id mints `-session-`; `sessionId` resumes or creates; `resumeSessionId` requires history. Active failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject work; teardown stays silent. ### Turn Flow diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 484ba1c632..173806572a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index e44df3c3b2..df3aec8b12 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -179,13 +179,13 @@ Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/t ### `agent-loop/config-start-failed` — emit -A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 965a640966..74496739e2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 78a30bd4e1..cc155ebb16 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2593da7c47..e27e8b625a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3c09ef2e7f..06c108d324 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -340,7 +340,8 @@ declare module 'cordis' { /** * A declarative agent entry failed before it could publish a live agent. * Consumers that buffer work for the configured identity use this - * transient signal to reject that work instead of waiting forever. + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. * @param sessionId - exact shared agent/session identity that failed startup. * @param error - persistence, setup, or publication failure. * @mode emit @@ -431,6 +432,7 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { + if (!this.ownership.isActive()) return this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index b35dc71739..53782fe03c 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -172,6 +172,8 @@ describe('config-driven session id', () => { const listing = Promise.withResolvers>>() vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) const loop = await ctx.plugin(AgentLoop, { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], @@ -181,9 +183,10 @@ describe('config-driven session id', () => { await Promise.resolve() expect(disposed).toBe(false) - listing.resolve([]) + listing.reject(new Error('startup cancelled by teardown')) await disposal expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) expect(warn).not.toHaveBeenCalled() warn.mockRestore() await ctx.fiber.dispose() From 1f2c85c854985384febdf6829cc3d9eb2181b3ed Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:47:44 +0800 Subject: [PATCH 072/140] test: await fresh stdio agent publication --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index a14848a549..4d555f5965 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -85,6 +85,7 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() // The sole pre-created agent the UI drives. `main` is its stable config // label; each fresh process mints a durable combined agent/session id. + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() expect(agent?.id).toBe(agent?.session.id) @@ -100,6 +101,7 @@ describe('dsh-stdio-agent app', () => { persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', skills: await isolatedSkillsConfig(), }) + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) expect(agent?.id).toBe(agent?.session.id) From 628006889e07846af0816a127683b3e5aa5f2b5c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:51:21 +0800 Subject: [PATCH 073/140] docs: keep agent-loop map concise --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 0e83cba072..89bb27604b 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | concrete `Agent` driver | ### Capability Services From bb40259083f10cb2071c024f05810c74021e4035 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:11:33 +0800 Subject: [PATCH 074/140] test: preserve ACP cleanup failures --- examples/acp-agent/tests/acp.e2e.ts | 18 ++++------ examples/acp-agent/tests/cleanup.e2e.ts | 38 ++++++++++++++++++++++ examples/acp-agent/tests/cleanup.ts | 23 +++++++++++++ examples/acp-agent/tests/escalation.e2e.ts | 18 ++++------ examples/acp-agent/tests/hooks.e2e.ts | 18 ++++------ 5 files changed, 82 insertions(+), 33 deletions(-) create mode 100644 examples/acp-agent/tests/cleanup.e2e.ts create mode 100644 examples/acp-agent/tests/cleanup.ts diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index a1ddbeccc6..a0bfc9d943 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, readFile } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -31,16 +32,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/cleanup.e2e.ts b/examples/acp-agent/tests/cleanup.e2e.ts new file mode 100644 index 0000000000..1f6e6493e0 --- /dev/null +++ b/examples/acp-agent/tests/cleanup.e2e.ts @@ -0,0 +1,38 @@ +/** Regression coverage for ACP example teardown. */ + +import { access, mkdtemp, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanupAcpExampleTest } from './cleanup.ts' + +let fallbackWorkdir: string | undefined + +afterEach(async () => { + if (fallbackWorkdir !== undefined) await rm(fallbackWorkdir, { recursive: true, force: true }) + fallbackWorkdir = undefined +}) + +describe('cleanupAcpExampleTest', () => { + it('removes the workspace after process shutdown fails', async () => { + fallbackWorkdir = await mkdtemp(join(tmpdir(), 'acp-cleanup-')) + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + await expect(cleanupAcpExampleTest(spawned, fallbackWorkdir)) + .rejects.toMatchObject({ errors: [closeFailure] }) + await expect(access(fallbackWorkdir)).rejects.toThrow() + fallbackWorkdir = undefined + }) + + it('reports process and workspace failures together', async () => { + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + const failure = await cleanupAcpExampleTest(spawned, '\0').catch((error: unknown) => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).errors).toHaveLength(2) + expect((failure as AggregateError).errors[0]).toBe(closeFailure) + }) +}) diff --git a/examples/acp-agent/tests/cleanup.ts b/examples/acp-agent/tests/cleanup.ts new file mode 100644 index 0000000000..28a896334a --- /dev/null +++ b/examples/acp-agent/tests/cleanup.ts @@ -0,0 +1,23 @@ +/** Shared teardown for ACP example tests. */ + +import { rm } from 'node:fs/promises' +import type { LaunchedAcpTestAgent } from '@deepseek-ai/dsh-acp-snapshot' + +/** + * Close the test agent, then remove its workspace, attempting both operations + * and reporting every failure instead of allowing the later one to mask the + * earlier one. + */ +export async function cleanupAcpExampleTest( + spawned: Pick | undefined, + workdir: string | undefined, +): Promise { + const results: PromiseSettledResult[] = [] + if (spawned !== undefined) results.push(...await Promise.allSettled([spawned.close('SIGKILL')])) + if (workdir !== undefined) results.push(...await Promise.allSettled([rm(workdir, { recursive: true, force: true })])) + + const failures = results + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (failures.length > 0) throw new AggregateError(failures, 'ACP example cleanup failed') +} diff --git a/examples/acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts index da8d3408c2..3b84dd721c 100644 --- a/examples/acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -1,5 +1,5 @@ import { spawnSync } from 'node:child_process' -import { mkdtemp, readFile, rm } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -13,6 +13,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * The default ACP composition (`cordis.yml`) end to end. @@ -81,16 +82,11 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('default sandbox composition keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index df231184c3..dbe98ab358 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' +import { mkdtemp, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -38,16 +39,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { From b58cf7ec2fdb3ba7d88ec097766dd47f2a188a2a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:24:21 +0800 Subject: [PATCH 075/140] fix: coordinate overlapping configured reloads --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 35 +++++++++++++++ .../tests/config-session-id.spec.ts | 44 +++++++++++++++++++ packages/ui/stdio-agent/src/stdio-chat.ts | 13 +++++- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 12 +++-- 9 files changed, 103 insertions(+), 11 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 173806572a..9bebe62380 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:361`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index df3aec8b12..f913b95c36 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:356`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d3e8b74edf..e4e68fe17f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:376`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cc155ebb16..2b62ec93eb 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:356`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e27e8b625a..881d60027a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. An overlapping remount waits for an already-disposed same-id agent to finish detaching both registries before it inspects persistence, so asynchronous teardown cannot strand the configured identity. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 06c108d324..3274e36587 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -53,6 +53,7 @@ function renderThrown(value: unknown): string { /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true + private readonly inactive = Promise.withResolvers() private transactions = new Set() private startupTasks = new Set>() @@ -74,8 +75,14 @@ class FactoryOwnership { void task.then(forget, forget) } + /** Resolve `task`, or stop waiting when factory teardown begins. */ + async waitWhileActive(task: Promise): Promise { + await Promise.race([task, this.inactive.promise]) + } + async dispose(): Promise { this.accepting = false + this.inactive.resolve() const reason = new Error('agent loop is not active') await Promise.all([ ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), @@ -455,6 +462,8 @@ export class AgentLoop extends Service implements AgentFactory { agentOptions: AgentOptions, meta: Pick, ): Promise { + await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId) + if (!this.ownership.isActive()) return const exists = (await persistence.list()).some(header => header.id === sessionId) if (!this.ownership.isActive()) return if (exists) { @@ -464,6 +473,32 @@ export class AgentLoop extends Service implements AgentFactory { this.create(sessionId, agentOptions, meta) } + /** Wait for an already-disposed same-id lifecycle to finish registry teardown. */ + private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise { + const current = ownerCtx.agents.get(sessionId) + if (current?.status !== 'disposed') return + + const released = Promise.withResolvers() + const checkReleased = (): void => { + if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) { + released.resolve() + } + } + const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { + if (agent.id === sessionId) checkReleased() + }) + const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { + if (session.id === sessionId) checkReleased() + }) + try { + checkReleased() + await this.ownership.waitWhileActive(released.promise) + } finally { + disposeAgentListener() + disposeSessionListener() + } + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 53782fe03c..fda5681c29 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,50 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('waits for a draining exact-id lifecycle during an overlapping reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-overlap') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + let flushStarted = false + ctx.on('session/flush', (session) => { + if (session !== first.session) return + flushStarted = true + return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before replacement' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + expect(flushStarted).toBe(true) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) }) + const secondLoop = await ctx.plugin(AgentLoop, config) + await new Promise(resolve => setTimeout(resolve, 0)) + expect(ctx.agents.get(sessionId)).toBe(first) + expect(failures).toEqual([]) + + flushGate.resolve(undefined) + await firstDisposal + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const second = ctx.agents.get(sessionId) as ReactLoopAgent + expect(second).not.toBe(first) + expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement') + expect(failures).toEqual([]) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 39d59dfdc0..4505f19b98 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -67,6 +67,15 @@ function isTTYPair(input: Readable, output: Writable): boolean { return Boolean((input as { isTTY?: boolean }).isTTY && (output as { isTTY?: boolean }).isTTY) } +/** Render an arbitrary failure without allowing hostile coercion to escape the UI boundary. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + interface PendingQuestion { request: AskUserQuestionRequest questionIndex: number @@ -230,7 +239,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt queuedInput.length = 0 submittedWork = sawRunning if (dropped > 0) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${renderThrown(error)}`) } maybeExit() }) @@ -390,7 +399,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return if (failedStartup !== undefined) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${renderThrown(failedStartup.error)}`) return } const agent = target diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 11e64ac19c..c303577c48 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -83,6 +83,10 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } +function unrenderableFailure(): unknown { + return { [Symbol.toPrimitive](): never { throw new Error('coercion escaped') } } +} + async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -753,14 +757,14 @@ describe('createStdioChat input', () => { it('drops later input after the configured startup fails', async () => { const { ctx, input } = await setup() const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) - const failure = new Error('persisted session is corrupt') + const failure = unrenderableFailure() ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) input.feed('cannot run') await new Promise(r => setImmediate(r)) expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) }) @@ -844,11 +848,11 @@ describe('createStdioChat EOF exit', () => { await flushExit() expect(exit).not.toHaveBeenCalled() - ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), unrenderableFailure()) await flushExit() expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) expect(exit).toHaveBeenCalledWith(0) }) From 7e9bf9b951913b1c5d70b5e94e22ccd8f60bed76 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:03:01 +0800 Subject: [PATCH 076/140] refactor: remove impossible ACP drain branch --- packages/support/acp-snapshot/src/launcher.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30ca0b42b8..c0dc21dc06 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,14 +178,13 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } - if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -207,7 +206,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { - await drained.catch(() => undefined) + await drained closeUpdateStream() throw error } From d83aa8d11aa217fdbee379dce37aa5146228dd21 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:31:00 +0800 Subject: [PATCH 077/140] test: cover exact-id reload cancellation --- packages/core/agent-loop/src/index.ts | 8 +- .../tests/config-session-id.spec.ts | 85 +++++++++++++------ 2 files changed, 62 insertions(+), 31 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3274e36587..ff0c692928 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -484,12 +484,8 @@ export class AgentLoop extends Service implements AgentFactory { released.resolve() } } - const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { - if (agent.id === sessionId) checkReleased() - }) - const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { - if (session.id === sessionId) checkReleased() - }) + const disposeAgentListener = ownerCtx.on('agent/disposed', checkReleased) + const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased) try { checkReleased() await this.ownership.waitWhileActive(released.promise) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index fda5681c29..ceaf6597cb 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -136,6 +136,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('cancels an exact-id reload while the prior lifecycle is still draining', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-cancel') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + ctx.on('session/flush', (session) => { + if (session === first.session) return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before cancellation' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const secondLoop = await ctx.plugin(AgentLoop, config) + await secondLoop.dispose() + expect(ctx.agents.get(sessionId)).toBe(first) + + flushGate.resolve(undefined) + await firstDisposal + expect(ctx.agents.get(sessionId)).toBeUndefined() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) @@ -208,33 +239,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) - it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { - const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) - dirs.push(root) - const ctx = await makeCoreContext() - await ctx.plugin(SessionPersistenceJsonl, { root }) - const listing = Promise.withResolvers>>() - vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const failures: unknown[] = [] - ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + it.each(['resolve', 'reject'] as const)( + 'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes', + async (outcome) => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) - const loop = await ctx.plugin(AgentLoop, { - agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], - }) - let disposed = false - const disposal = loop.dispose().then(() => { disposed = true }) - await Promise.resolve() - expect(disposed).toBe(false) + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) - listing.reject(new Error('startup cancelled by teardown')) - await disposal - expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() - expect(failures).toEqual([]) - expect(warn).not.toHaveBeenCalled() - warn.mockRestore() - await ctx.fiber.dispose() - }) + if (outcome === 'resolve') listing.resolve([]) + else listing.reject(new Error('startup cancelled by teardown')) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }, + ) it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() From 4a5463cfc49b8f505b5f47aa7634909c08602a08 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 16:53:38 +0800 Subject: [PATCH 078/140] test: use the public agent type --- packages/core/agent-loop/tests/config-session-id.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index f001fa3154..2c8a5c31bd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -145,7 +145,7 @@ describe('config-driven session id', () => { const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } const firstLoop = await ctx.plugin(AgentLoop, config) await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() - const first = ctx.agents.get(sessionId) as ReactLoopAgent + const first = ctx.agents.get(sessionId) as Agent const flushGate = Promise.withResolvers() ctx.on('session/flush', (session) => { From 64a3933270a0f4636b36b485197597c66945599b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:03:07 +0800 Subject: [PATCH 079/140] docs: refresh config catalog after parent merge --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 14cc973995..6f74792213 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -899,7 +899,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 5409452cc705804386fe029908f14b31840efe96 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:30:29 +0800 Subject: [PATCH 080/140] test: refresh snapshots after master merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/stdout.golden.jsonl | 2 +- .../snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/cancel/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/config-options/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/error-finish/stdout.golden.jsonl | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-approved/stdout.golden.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/stdout.golden.jsonl | 4 ++-- .../acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-policy-reject/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-read-window/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-terminal-card/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-write-overwrite/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/handshake/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-block/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-context/stdout.golden.jsonl | 2 +- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-posttool-block/stdout.golden.jsonl | 2 +- .../hook-codex-posttool-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-pretool-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-stop-continue/stdout.golden.jsonl | 2 +- .../tests/snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- .../snapshots/permission-switching/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/repeat-tool-guard/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/skill-load/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-fork/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-mixed/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-multi/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-spawn/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- .../acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tests/snapshots/tool-call-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/workflow-run/stdout.golden.jsonl | 2 +- .../tests/snapshots/workspace-edit/stdout.golden.jsonl | 2 +- 55 files changed, 64 insertions(+), 64 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 991806d74b..cdc09c92c0 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index a6a3371913..79d9b94ad9 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index c6213cd558..7155b1c2a6 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..80a9cc9339 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 5ad12cddff..6e8f157ace 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index a68bb37f9f..66cdecedfb 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..c9d2c87c27 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..1f8c0ca024 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index bfa379815e..5fe0944ac7 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl index aa033fb673..7c85717676 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} {"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index d5d4f1c400..99e00460c6 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 8aac1627bc..74fbed6ee3 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..5c63764aae 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 7c0a743413..bf86999cd9 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..07e48d9e22 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index acc193ad1e..919c0f169e 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index 5aa75c026c..c27544a176 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index 05832400c8..8b75c30e8c 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index 19abb7f418..30aa0d2460 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index 0e7dcca6f8..e045c7b228 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index 4801d9410d..f554fa3123 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index d5b3ca5d15..d04def6af2 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index e4c4984fc5..312569a491 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index 0a93b649da..36f050a694 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index e9243d8a05..bbc16779ba 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index b975c54aac..faed620b4c 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..db38650167 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index 92906adb59..f0c5e005d9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index c4ad3ba541..ac203d50cc 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index 5c4a564d26..01297aa39d 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index cbaec45f9f..57b297ccfc 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 4bf92f3197..faa1255a32 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 5459da1a17..11b47d6e58 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 8cae81a5c9..116a8ebbbd 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 66d8c816be..d231f60e0a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..b45d9e947c 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 0d8e018ae5..a30f9e4a46 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..9c3c78be5c 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -44,7 +44,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a0901b6297..876f6c490a 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 9a26fa2efe..1c85ee81ba 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..b5f25f2c07 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index 44fc4402fc..e390bda86a 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index 08ad14dc9c..db5f28fa79 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 93b38e33cb..4c0c7d2601 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 26d45699cc..ce114fccf0 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 0643740e4f..c66f5676cc 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..8de447de6d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index f060b6b92f..a947ed4997 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 041ea02703..9d06e9d6ac 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 9c0bbd37be..56b8f3537a 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 23f13ff3c2..513a02a6af 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} From 8be096c540c6b82187051eab9febd461a46e4fc2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:08:37 +0800 Subject: [PATCH 081/140] fix: preserve master bash guidance wording --- packages/bash/tool-bash/src/index.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 662b7a065f..4c699cd6c0 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -173,15 +173,15 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { + 'poll it with `bash_output` and stop it with `bash_kill`.' if (escalationModes.length === 0) return base return base + ' Attempting a command the sandbox may deny is safe and expected: run it and read the ' - + 'marker rather than assuming the denial. When a command IS denied and a wider mode would let it ' - + 'succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry ' + + 'marker rather than assuming the denial. When a command is denied and a wider mode would let it ' + + 'succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry ' + 'the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) ' + 'plus a one-sentence `justification`. Do not detour through chat to ask permission first — the ' - + 'approval prompt raised by that retry IS how the user consents. If the session states approval ' + + 'approval prompt raised by that retry is how the user consents. If the session states approval ' + 'prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. ' - + 'Never escalate speculatively: ground the request in a real denial — normally the one THIS command ' + + 'Never escalate speculatively: ground the request in a real denial — normally the one this command ' + 'just hit; escalating up front is fine only when this session already denied the same access. ' - + 'A rejected escalation is final for THAT command — stop and explain, never work around ' + + 'A rejected escalation is final for that command — stop and explain, never work around ' + 'it — but it does not forbid attempting or escalating other commands later.' } From 5a1194bf301ecd9f2ab007a599a2e121e57b72e6 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:18:24 +0800 Subject: [PATCH 082/140] test: refresh snapshots after bash guidance merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../acp-agent/tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index cdc09c92c0..991806d74b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 79d9b94ad9..a6a3371913 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7155b1c2a6..c6213cd558 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 6e8f157ace..5ad12cddff 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 66cdecedfb..a68bb37f9f 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 1f33766ec9..07cd6233b3 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 1c85ee81ba..9a26fa2efe 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index c66f5676cc..0643740e4f 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} From 10fd0b4504b47285b67aed611e4cc0a2e86c5db4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:22:37 +0800 Subject: [PATCH 083/140] docs: align unified identity translation --- docs/cookbook/extension-cookbook.i18n.yaml | 4 ++-- docs/cookbook/extension-cookbook.zh.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..2761b419e9 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 0b95866515efa1b28a95ed48de0fe20d76a62b82 +extension-cookbook.zh.md: 038bf093ce2d289fb59be165a154cbe4df831d9e diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..038bf093ce 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -40,7 +40,7 @@ UI 插件从 `session/event` 事件流渲染（助手 token 流以 `assistant/ch ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -54,7 +54,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` From 9745a0d43a979d34c44c2a42d8a485d03a25de71 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:36:04 +0800 Subject: [PATCH 084/140] fix: reject empty configured session ids --- packages/core/agent-loop/src/index.ts | 2 +- packages/core/agent-loop/tests/config-session-id.spec.ts | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 8d9a184cc7..325ba7b92d 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -377,7 +377,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), - sessionId: z.string(), + sessionId: z.string().min(1), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 096a6eff9e..bd2a5522df 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -35,6 +35,15 @@ async function makeCoreContext(): Promise { } describe('config-driven session id', () => { + it('rejects an empty exact id before publishing an agent', async () => { + const ctx = await makeCoreContext() + await expect(ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }], + })).rejects.toThrow('expected string length >= 1') + expect(ctx.agents.get(SessionId(''))).toBeUndefined() + await ctx.fiber.dispose() + }) + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { const exact = await makeCoreContext() await exact.plugin(AgentLoop, { From ed3654da00fd14597b79e8e97bf61f09c5981ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:38:53 +0800 Subject: [PATCH 085/140] docs: reconcile hidden internals with prose standard --- ...t-variables-and-tool-guidance-ownership.md | 16 ++--- .../subagent/subagent-subprocess/src/index.ts | 61 +++++-------------- packages/subagent/tool-subagent/src/index.ts | 49 +++------------ 3 files changed, 31 insertions(+), 95 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index aae4564513..854807c109 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -24,21 +24,21 @@ The assembled system prompt had four defects, all of one family: facts the harne ### Prompt variables -Plugins contribute named values via `ctx.systemPrompt.variable(name, provider)`; prompt text references them as `{{name}}`. Providers are functions of the `AssembleContext` and may return `undefined` — "no value for THIS assembly". `assemble()` resolves every registered variable into `PromptAssembly.variables` (waterfall listeners can see, add, or override); `renderPrompt` interpolates. Rendering is STRICT — fail loud beats shipping a malformed prompt: a reference to an unregistered name throws (listing what exists; lookup is `Object.hasOwn`, so a prototype property like `{{constructor}}` is unknown, not a function spliced into the prompt), a registered-but-valueless reference throws, a complete `{{…}}` group that is not a well-formed name (`[a-z][a-z0-9_]*`, e.g. `{{ model }}`) throws, and a `{{` that opens no complete group while a `}}` still follows (`{{{model}}}`, `{{a{b}}`) throws. A lone `{{` with no `}}` anywhere after it is ordinary prose and passes through verbatim; substituted values are never re-scanned. Registration rejects duplicate and unreferenceable names, mirroring the tool registry — and `section()` now rejects duplicate section names, making the documented dedup real. +Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, provider)`. Assembly resolves them into the waterfall-visible variable map. Rendering rejects unknown own-property references, registered providers that return `undefined`, malformed complete references, and unbalanced references that still contain a closing `}}`; a lone unmatched `{{` remains prose, and substituted values are not rescanned. Registration rejects invalid or duplicate variable names, and section names are unique. `dsh-agent-loop` registers the two built-ins, both pure projections of the context agent: `model` (= `options.model`) and `cwd` (= `session.header.cwd`). The example personas write `powered by the {{model}} model` — the model name is stated once, in the `model:` config key. `{{cwd}}` is demonstrated in the ACP example only: every ACP session carries the client's cwd, while config-pre-created stdio agents have none (a persona claiming `{{cwd}}` there fails the turn — by design). The variables stay on the loop plugin (unlike the sections below): they are runtime facts of the agents THIS loop drives, and a replacement loop supplies its own. ### Persona as the order-0 section -`dsh-system-prompt` itself registers the two harness-owned sections (they must survive a swapped loop plugin, so they do NOT live on `dsh-agent-loop`): the static `harness:identity` at order `-100` — every prompt opens by stating the agent is powered by the DeepSeek Harness SDK — and the global default `deployment:persona` at order 0, whose text is the plugin's own `persona` config. `AgentOptions.systemPrompt` and the loop's special-case join are gone: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. An agent-scoped section with the same `deployment:persona` name shadows the default for that agent; programmatic setup may register one directly, and the subagent persona feature installs one before publishing an in-process child when the selected provider supports it. Order bands are convention: harness identity `-100`, persona `0`, tool guidance `100–199`; other negative orders also render before the persona. +`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and `agent/pre-step` therefore measures the exact prompt used for compaction. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. ### Tool guidance ownership -Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship in every request — the YAML prose was ~fully redundant with them. Sections carry only the cross-call habits a single call's description cannot: `dsh-tool-bash` contributes `tool:bash` (order 105) — check the `[exit code: N]` marker on every result; `dsh-tool-fs`'s read section gains the "not shell commands like cat" contrast. `todo_write` and the subagent tools need NO section — their descriptions already carry the whole contract. The leaf personas shrink to identity + behavior (verify your work; keep answers brief), and the welcome banner stops enumerating tools. +Per-tool semantics and selection guidance live in tool descriptions. Prompt sections carry only cross-call habits, such as checking bash exit markers or preferring filesystem tools over shell commands. `todo_write` and subagent tools need no section because their descriptions contain the full contract. Deployment personas contain only role and behavior. ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider.inheritsParentContext` describes conversation seeding, not scope, services, tools, or authority. Spawn and ACP set it to `false`; fork sets it to `true`. `dsh-tool-subagent` derives its tool and prompt-parameter descriptions from the flag, including that fork inherits completed turns but not the in-flight turn. Provider lifecycle events keep that wording synchronized with reactive provider registration; their rationale lives in the [provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered @@ -56,10 +56,10 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ## Shipped invariants -- `renderPrompt(await assemble(assembleContextFor(agent)))` for the coding-agent example renders the harness identity, then the persona (with the agent's model name interpolated), then the fs/bash/web guidance sections; the loop has no other prompt-composition path. -- The `subagent_fork` schema description says the child inherits the conversation; the `subagent` one says it does not. The tool follows its provider: absent before the backend activates, present after, gone when the backend unloads, re-worded from the fresh provider on reload. -- Unknown/valueless/malformed/unbalanced `{{…}}` references throw with the section name in the message; duplicate section, variable, and tool-name registrations all throw. -- Snapshot goldens are prompt-independent by construction: llm-replay keys replay on (turn, step) chunk streams and never re-verifies the outgoing request. +- The coding-agent prompt renders identity, persona with the interpolated model, then fs/bash/web guidance through one assembly path. +- Fork and fresh subagent descriptions reflect whether the provider inherits completed conversation turns; the tool appears, disappears, and is reworded with provider lifecycle changes. +- Unknown, valueless, malformed, or unbalanced variable references name the section and throw; duplicate section, variable, and tool registrations also throw. +- Snapshot replay is prompt-independent: it keys recorded chunk streams by turn and step without comparing the outgoing request. ## Consequences diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index bd792e7f23..3831d2bb6a 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -1,19 +1,8 @@ /** - * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn - * an external agent as a child process and must keep the parent deployment's - * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing - * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), - * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose - * ladder ({@link disposeChildProcess}), and the per-run isolated config dir - * ({@link createIsolatedConfigDir}). - * - * This package owns no provider and registers nothing; it is a pure library - * the out-of-process backend packages depend on (the `subagent-inprocess` - * shape, for the process boundary). Every tunable — the ladder's grace - * periods, a pinned config dir — is a PARAMETER here: defaults belong in each - * consuming plugin's Config, per the no-hardcoded-tunables rule. - * + * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn an external + * agent as a child process and must keep the parent deployment's credentials out of it, tear + * it down to quiescence, and isolate it from the host user's on-disk CLI state. This package + * registers no provider; consuming plugins own and validate every timing or path default. * @module @deepseek-ai/dsh-subagent-subprocess */ @@ -50,11 +39,8 @@ export function buildChildEnv(extra: Record): NodeJS.ProcessEnv } /** - * Capture the child's spawn-level failure as a promise the run's result path - * can race. A spawn failure (e.g. `ENOENT` for a bad command) is emitted as an - * `error` EVENT, not a thrown exception — and without a listener Node treats - * it as an unhandled error and crashes the parent process. Call this in the - * SAME TICK as `spawn()`, so no window exists for the event to fire unheard. + * Capture the child's spawn-level `error` event as a promise. Call in the same tick as + * `spawn()`; otherwise an early event can be unhandled and crash the parent. * @param child - the just-spawned child process. * @returns a promise that RESOLVES (never rejects) with the child's first * `error` event; for a child that spawns cleanly it never settles. @@ -123,15 +109,8 @@ export interface DisposeLadderGraces { } /** - * Tear a child process down to QUIESCENCE: resolves only once the child has - * actually exited (or was already gone), never merely after requesting it. - * Three-tier escalation — - * - * 1. stdin EOF (when stdin is piped), then wait `disposeEofGraceMs`: a - * cooperative child quiesces on its own, its teardown and flushes intact; - * 2. `SIGTERM`, then wait `disposeGraceMs`; - * 3. `SIGKILL`, then await the (now-certain) exit — a child that ignores EOF - * and traps `SIGTERM` must not wedge dispose forever. + * Tear a child process down to quiescence, resolving only after exit: close stdin and allow + * cooperative flush, then send `SIGTERM`, then `SIGKILL` and await the forced exit. * * @param child - the child process to tear down. * @param graces - the two grace periods, from the consuming plugin's Config. @@ -139,10 +118,7 @@ export interface DisposeLadderGraces { export async function disposeChildProcess(child: ChildProcess, graces: DisposeLadderGraces): Promise { // Already gone: nothing to reap. if (child.exitCode !== null || child.signalCode !== null) return - // 1. Graceful: end the request stream (stdin EOF) and let the child quiesce - // on its own. Sending SIGTERM in the same tick (or too soon) would - // default-terminate a cooperative child mid-flush, orphaning its nested - // work. A child spawned without a stdin pipe skips straight to the wait. + // 1. Close stdin and allow cooperative teardown and durable-state flush. child.stdin?.end() if (await exitsWithin(child, graces.disposeEofGraceMs)) return // 2. SIGTERM, escalating if the child still does not exit within the grace. @@ -171,16 +147,9 @@ export interface IsolatedConfigDir { } /** - * An isolated config dir for one child run, so the child's behavior is a - * function of deployment config alone — never of whatever `~/.claude` / - * `~/.codex`-style state happens to exist on the host machine. Two modes: - * - * - no `pinnedPath` (the default): creates a FRESH private (0700) `mkdtemp` - * dir under the OS temp root; {@link IsolatedConfigDir.remove} deletes it - * best-effort; - * - `pinnedPath` set (a deployment deliberately sharing state across runs): - * the pinned path is returned as-is — never created, never removed — the - * deployment owns that directory's lifecycle. + * An isolated config dir for one child run, independent of host CLI state. Without + * `pinnedPath`, creates a private temp directory and removes it best-effort; a pinned directory + * is returned unchanged and remains deployment-owned. * * @param prefix - the `mkdtemp` name prefix for a fresh dir (e.g. * `dsh-subagent-codex-`); ignored when `pinnedPath` is set. @@ -207,10 +176,8 @@ export async function createIsolatedConfigDir(prefix: string, pinnedPath?: strin try { await rm(path, { recursive: true, force: true }) } catch { - // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — - // e.g. the dead child left an unreadable entry behind). The dir lives - // under the OS temp root, which reclaims it; failing dispose over - // cleanup would be worse than a leftover temp dir. + // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — e.g. the dead + // child left an unreadable entry behind). } }, } diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index ff54bc109a..59821147af 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -1,34 +1,11 @@ /** - * The model-facing `subagent` tool: delegate a task to a child agent and return - * its final output. Pure schema + lifecycle shaping — every transport concern - * lives behind the `ctx.subagents` provider registry - * (`@deepseek-ai/dsh-subagent`), so an in-process, ACP, or future A2A backend - * swaps in without touching what the model sees. - * - * Provider selection is config, not model-facing: this plugin is bound to - * EXACTLY ONE provider name (`Config.provider`). To expose more than one - * transport, load the plugin more than once, each bound to a different provider - * — there is no provider/type parameter in the model-facing schema. The model - * sees only `{ description, prompt }`. - * - * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link SubagentProvider.inheritsParentContext}): a - * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, - * while a seeded-conversation provider (fork) tells the model the child already - * sees the conversation's completed turns. This descriptor says nothing about - * Cordis scope, services, tools, or authority. The tool MIRRORS the - * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers - * when the provider is (or becomes) available and unregisters when the - * provider goes away — so no load-order requirement exists and an HMR reload - * of the backend re-derives the wording from the fresh provider. - * - * Collection is SYNCHRONOUS this cut: `execute` starts a run and awaits - * `run.result` inside a `try/finally` that always disposes the run, so the - * owned child agent/session is torn down on every path (success, error, abort) - * and never leaks as a live idle child. A non-`completed` stop reason maps to an - * `isError` tool result (by throwing) rather than returning partial output as - * success. + * Model-facing delegation tool bound by configuration to one provider; transport selection is not + * exposed in its `{ description, prompt }` schema. Provider lifecycle controls registration and + * re-derives conversation-history wording after reload, so load order is irrelevant. * + * Execution synchronously awaits the child result and always disposes the run. Non-completed stop + * reasons become error results, while transport details remain behind `ctx.subagents`. Load this + * plugin more than once to expose multiple configured providers. * @module @deepseek-ai/dsh-tool-subagent */ @@ -105,16 +82,8 @@ export const Config: z = z.object({ model: z.string(), }).default(undefined as unknown as { model: string }), persona: z.string(), - // A schemastery object materializes {} (with [] for nested arrays) when the - // key is omitted — for toolFilter that would mean an EMPTY ALLOW-LIST, i.e. - // deny-everything, silently. Force the omitted key to stay absent (the same - // shape discipline as SystemPrompt's toolOrder); the cast is needed because - // .default() expects the object type. - // The NESTED arrays get the same treatment as the object itself: a partial - // filter ({deny: […]}) must not materialize allow: [] beside it — an empty - // allow-list means deny-EVERYTHING, so the materialized default would turn - // a deny-one config into deny-all. An EXPLICIT allow: [] (grant-only - // children) survives, since only the omitted key defaults to undefined. + // Schemastery otherwise materializes omitted objects and nested arrays as `{ allow: [] }`, which + // silently means deny all. Preserve omission while retaining an explicit empty allow-list. toolFilter: z.object({ allow: z.array(z.string()).default(undefined as unknown as string[]), deny: z.array(z.string()).default(undefined as unknown as string[]), @@ -290,7 +259,7 @@ export function apply(ctx: Context, config: Config): void { if (present !== undefined) { mount(present) } else { - // Not an error: the backend's fiber may simply activate after this one. + // Not an error: the backend's fiber may activate after this one. // The tool appears the moment the provider registers; a typo'd provider // name shows up as this note plus a tool that never materializes. ctx.logger.info(`subagent provider "${config.provider}" not registered yet; the "${config.toolName ?? 'subagent'}" tool will register when it appears`) From d0df50aa8eee0c98b7eacadcdbc797f7780de565 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:43:53 +0800 Subject: [PATCH 086/140] fix: retain LLM HTTP status metadata --- packages/llm/llm-deepseek/src/adapter.ts | 2 +- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 ++++++- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++++-- packages/llm/llm/tests/service.spec.ts | 5 ++--- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 7 files changed, 21 insertions(+), 15 deletions(-) diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index f6051d1ccd..30760a8fbc 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -76,7 +76,7 @@ export class DeepSeekAdapter extends LlmAdapter { // Only swallow error-body parsing: status and code are already captured, // so malformed gateway JSON must not mask the actionable HTTP failure. } - throw new LlmError(message, code) + throw new LlmError(message, code, response.status) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..46f123a1c7 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior]) + const server = await mockServer([behavior, behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,6 +166,11 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) + // The numeric HTTP status is carried on the error for explicit handling. + await expect( + assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) + .catch((error: unknown) => (error as LlmError).status), + ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index c8f2002f9f..296fd0c3d3 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. +- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 8f2c9b4f39..08f3f54c51 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,10 +42,12 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; + * `status` carries the HTTP status when the error originated from a non-2xx + * provider response (absent for protocol/usage errors that have no HTTP status). */ export class LlmError extends HarnessError { - constructor(message: string, code: string, options?: ErrorOptions) { + constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 125a810261..f669069c44 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,12 +79,11 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const cause = new Error('root cause') - const err = new LlmError('boom', 'AUTH', { cause }) + const err = new LlmError('boom', 'AUTH', 401) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.cause).toBe(cause) + expect(err.status).toBe(401) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index b7e4e30a46..2e509973e5 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code) + throw new LlmError(entry.message, entry.code, entry.status) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index aa3fea20d5..ac52ec11c9 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From cb177090f9573b30947af31daa876d586bea844a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:53:23 +0800 Subject: [PATCH 087/140] docs: refresh subagent config catalog --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 093e534d23..d9e42366ba 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -915,7 +915,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 0892831177c895b4139cb61b9c20a32b465fc923 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:01:00 +0800 Subject: [PATCH 088/140] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From ff064917a25fe72af8ba109847fa822220cc4330 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:18:04 +0800 Subject: [PATCH 089/140] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From 8e7cf8cc10c3559ded0ee7f93f62d14ff5f18ad4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:09:18 +0800 Subject: [PATCH 090/140] Update ACP launcher example path --- packages/support/acp-snapshot/src/launcher.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index c0dc21dc06..95292df38a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -27,7 +27,7 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) /** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ export interface AgentUnderTest { - /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + /** The agent bin entry (for example `packages/examples/acp-demo/src/bin.ts`). */ binScript: string /** The leaf `cordis.yml` loaded by the bin. */ configPath: string From f6350ac553dc9f34b7c397eb62991e2566f1ca6b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:10:46 +0800 Subject: [PATCH 091/140] Keep root instructions within budget --- AGENTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 0c5272b105..4209b0f95c 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,7 +59,7 @@ pnpm run demo:cordis # self-referential demo: the agent modifies its own runt pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` -### Run the CI gates locally before marking a PR ready +### Run CI gates locally before marking a PR ready Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`: From d25a56b431d98a6df3ff242df6386975acce05d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:23:39 +0800 Subject: [PATCH 092/140] Restore CompactionResult diagnostics --- packages/compact/compact-basic/src/index.ts | 6 +++++- .../compact-basic/tests/compact-basic.spec.ts | 4 +++- packages/compact/compact/src/index.ts | 2 +- packages/compact/compact/src/types.ts | 8 ++++++++ packages/compact/compact/tests/compact.spec.ts | 16 ++++++++++++---- 5 files changed, 29 insertions(+), 7 deletions(-) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 9449fc84f9..8bc21ddf5b 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -426,9 +426,13 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - session.append('compact/end', { turn: openTurn }) + const endEvent = session.append('compact/end', { turn: openTurn }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 7cb872f274..4b06b321b7 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -346,6 +346,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) + expect(result.summary).toEqual(svc.mockSummary) expect(result.shadowedTokenCount).toBe(20) const events = session.events @@ -1057,7 +1058,8 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index e4baec6551..680f684ac6 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -73,7 +73,7 @@ export abstract class CompactService extends Service { * @param agent - context whose session is mutated and whose routing options guide summarization. * @param signal - optional cancellation; model-backed implementations must forward it. * @throws when compaction is active or the range is missing, reversed, or unbalanced. - * @returns the replaced range and token accounting; the durable event owns the summary. + * @returns the appended event seqs, summary, replaced range, and token accounting. */ abstract compactRegion( start: number, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index 0d3d35ace8..10a5eabfcc 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -41,6 +41,14 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index e34c8420d9..3d95c12249 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -34,17 +34,22 @@ class StubCompactService extends CompactService { ): Promise { this.lastSignal = signal const session = agent.session + const summary = [{ type: 'text' as const, text: 'stub' }] // Minimal stub honoring the lock + log-only event contract. - session.append('compact/start', { turn: 0 }) - session.append('compact/summary', { - summary: [{ type: 'text', text: 'stub' }], + const startEvent = session.append('compact/start', { turn: 0 }) + const summaryEvent = session.append('compact/summary', { + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - session.append('compact/end', { turn: 0 }) + const endEvent = session.append('compact/end', { turn: 0 }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -92,6 +97,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() + expect(result.summary).toEqual([{ type: 'text', text: 'stub' }]) + expect(result.summarySeq).toBeGreaterThan(result.startSeq) + expect(result.endSeq).toBeGreaterThan(result.summarySeq) expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) .toEqual(['compact/start', 'compact/summary', 'compact/end']) From 8eccd5416e58d1ea63f6dfb411a247ff6c272ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:25:39 +0800 Subject: [PATCH 093/140] Document restored compaction result fields --- docs/core-data-structures/compaction.md | 10 +++++++++- packages/cordis/tool-cordis/src/api-catalog.ts | 2 +- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index d253166fcf..1075f3c985 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -20,10 +20,18 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. +What a successful compaction returns to its caller: the bookkeeping-event seqs, raw summary, shadowed range and seqs, and estimated token count. ```ts type-equiv interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8e6477258e..bfa494f829 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -631,7 +631,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From cdeec6fc1d984adfdbd645d1a481dd0a2a9fdba8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:36:51 +0800 Subject: [PATCH 094/140] Update built JSON-RPC probe path --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index bc6642263e..ed4dfbb9db 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -33,7 +33,7 @@ const [ { SessionId }, ] = await Promise.all([ load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), + load("packages/examples/agent-spine-demo/lib/index.js"), load("packages/subagent/subagent/lib/index.js"), load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), load("packages/ui/jsonrpc/lib/index.js"), From 87c900dfb2a8b73f153828a01c9fbd90cd962311 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:55:48 +0800 Subject: [PATCH 095/140] Document compaction result diagnostics --- packages/compact/compact/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 51ba50382f..0e0b63d765 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -21,6 +21,8 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | | `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +`CompactionResult` keeps the raw summary and bookkeeping-event seqs available to callers alongside the shadowed range and token accounting; its drift-checked shape lives in the [compaction data-structure reference](../../../docs/core-data-structures/compaction.md#compactionresult). + `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. ## Surface contract From 54fb96ef04df12bf59c69b14de24bcba8ada98d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:46:35 +0800 Subject: [PATCH 096/140] refactor: name front door defaults --- packages/examples/acp-demo/src/index.ts | 7 +++---- packages/examples/stdio-demo/src/index.ts | 12 ++++++------ 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index 0439363301..a26220dbf7 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -18,6 +18,7 @@ import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' export const name = 'acp-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' /** * App config: the swappable per-deployment values. `model` configures the @@ -54,9 +55,7 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share this schema default and the defensive - // apply() fallback through one named constant while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), skills: agentCore.SkillConfigSchema, }) /* jscpd:ignore-end */ @@ -76,6 +75,6 @@ export function apply(ctx: Context, config: Config): void { ...config.skills !== undefined ? { skills: config.skills } : {}, }) ctx.plugin(UserInteractionService) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(acp, { model: config.model }) } diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 742371ecd5..c54f9499c6 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -23,6 +23,8 @@ import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user' import * as uiStdio from '@deepseek-ai/dsh-stdio' export const name = 'stdio-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' +const DEFAULT_WELCOME = 'ready.' /** * App config: the swappable per-demo values, each routed to where the app wires @@ -65,10 +67,8 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share these schema defaults and defensive - // apply() fallbacks through named constants while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), - welcome: z.string().default('ready.'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), + welcome: z.string().default(DEFAULT_WELCOME), skills: agentCore.SkillConfigSchema, resumeSessionId: z.string(), }) @@ -85,10 +85,10 @@ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(UserInteractionService) ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', + welcome: config.welcome ?? DEFAULT_WELCOME, sessionId, }) ctx.plugin(agentCore, { From 732735b27fb23fe90ee7f6c9853c7953b8879fdc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:32:15 +0800 Subject: [PATCH 097/140] docs: align default fallback test comments --- packages/examples/acp-demo/tests/acp-agent.spec.ts | 2 +- packages/examples/stdio-demo/tests/stdio-agent.spec.ts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index f3495c827c..ab36aa56c8 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -82,7 +82,7 @@ describe('dsh-acp-demo composition', () => { }) it('defaults the persistence root when omitted', async () => { - // Exercises the `?? './.sessions'` fallback for a direct-apply caller that + // Exercises the `DEFAULT_PERSISTENCE_ROOT` fallback for a direct-apply caller that // bypasses the schema's `.default(...)`: call `apply` directly (not via // `ctx.plugin`, which validates+defaults the config first) with no // persistenceRoot, so the runtime fallback is the one that fires. diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 79681fd954..b2398fea7c 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -100,7 +100,7 @@ describe('dsh-stdio-demo app', () => { it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config - // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on + // first) so the runtime `DEFAULT_PERSISTENCE_ROOT` / `DEFAULT_WELCOME` fallbacks on // apply()'s last two lines are the ones that fire — covering a // schema-bypassing direct-mount caller. const ctx = new Context() From 29d545eb212e88f9589134be420eff3ed8673b81 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 19:52:45 +0800 Subject: [PATCH 098/140] Refresh front-door config catalog --- docs/config-catalog.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 29be66bbbe..5bbdbe5fd3 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -63,7 +63,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts) +Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` @@ -722,7 +722,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:39`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` From bb1c8fa27da12f2432afaf3d5c04fd8299df73e9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:09:14 +0800 Subject: [PATCH 099/140] fix(llm): restore pruned status contract --- docs/cordis-catalog/services.md | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 6 +++--- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 +------ packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++---- packages/llm/llm/tests/service.spec.ts | 5 +++-- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 9 files changed, 19 insertions(+), 25 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 18e00b7904..48fb887d27 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -128,7 +128,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..978dec65c8 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -73,10 +73,10 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Only swallow error-body parsing: status and code are already captured, - // so malformed gateway JSON must not mask the actionable HTTP failure. + // Only swallow error-body parsing: the stable code and status-line message + // are already captured, so malformed gateway JSON must not mask the failure. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index dd1cb5b48c..281a4f13be 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -55,6 +55,6 @@ Unit suites run against a local `node:http` mock SSE server (pi-ai's openai SDK - **`tool_choice` is not mapped** — same MVP contract as llm-deepseek. - **In-history `system`-role messages fold into `user`-role wire messages** — pi-ai exposes a single `systemPrompt` slot, diverging from the hand-rolled twin's `role: 'system'` passthrough. -- **`LlmError.status` is never set** — pi-ai reports failures as in-stream events with no HTTP status, so error codes are regex-classified from the error text. +- **Provider HTTP status is unavailable** — pi-ai reports failures as in-stream events, so stable error codes are regex-classified from the error text. - **`buildModel` hardcodes descriptor metadata** — `contextWindow: 128000`, `maxTokens: 64000`, zero cost, identically for every registered model name; not configurable. - **pi-ai's built-in retries are disabled (`maxRetries: 0`)** — failures surface immediately; retry policy belongs to `llm/stream` listeners. diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 296fd0c3d3..c8f2002f9f 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 08f3f54c51..8f2c9b4f39 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 2e509973e5..b7e4e30a46 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index ac52ec11c9..aa3fea20d5 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From f8cc1af99b9b8a5681f93e8939bf8e93f98a4011 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:36:57 +0800 Subject: [PATCH 100/140] test(tasks): align tool fixtures with unified identity --- .../tasks/tool-tasks/tests/tool-tasks.spec.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts index 1b5e221a3c..0a2d89431e 100644 --- a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts +++ b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts @@ -5,6 +5,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import TaskService from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -23,17 +24,17 @@ async function setup(config: ToolTasks.Config = {}) { } /** - * A fake agent whose session token is `sessionId`, registered in `ctx.agents`. - * The agent id is deliberately different so session authorization and exact - * lifecycle ownership cannot be confused in tests. + * A fake agent with the shared agent/session identity, registered in + * `ctx.agents` with a dedicated lifecycle scope. */ function fakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void = () => {}): Agent { const scopeFiber = ctx.plugin(() => {}) + const id = SessionId(sessionId) const agent = { - id: `agent-${sessionId}`, + id, ctx: scopeFiber.ctx, inject, - session: { header: { version: 0, id: sessionId, createdAt: 0 } }, + session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent agentRegistryDisposers.set(agent, ctx.agents.register(agent)) return agent @@ -276,7 +277,7 @@ describe('completion notices', () => { await tick() // Disposed owner: inject throws the disposed message — contained. - const inject = vi.fn(() => { throw new Error('agent "agent-sess-1" is disposed') }) + const inject = vi.fn(() => { throw new Error('agent "sess-1" is disposed') }) const owner = fakeAgent(ctx, 'sess-1', inject) const p = producer({ owner }) ctx.tasks.start(p.spec) @@ -287,7 +288,7 @@ describe('completion notices', () => { it('does not route an old owner completion notice to a same-session replacement', async () => { const { ctx } = await setup() - const oldInject = vi.fn(() => { throw new Error('agent "agent-shared" is disposed') }) + const oldInject = vi.fn(() => { throw new Error('agent "shared" is disposed') }) const oldOwner = fakeAgent(ctx, 'shared', oldInject) const p = producer({ owner: oldOwner }) ctx.tasks.start(p.spec) From 8e37abb6c9dffa1fa2d5a24d05aa9eef4dde88e3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:50:33 +0800 Subject: [PATCH 101/140] docs: refresh module graph for unified identity --- docs/module-graph.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 199f11e8d3..baa714bad1 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -205,6 +205,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -219,10 +220,6 @@ flowchart TD pkg_permission --> pkg_sandbox pkg_permission --> pkg_session pkg_permission --> pkg_user_approval - pkg_stdio --> pkg_agent - pkg_stdio --> pkg_llm - pkg_stdio --> pkg_session - pkg_stdio --> pkg_user_interaction pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope @@ -250,6 +247,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -296,6 +294,7 @@ flowchart TD pkg_tool_workflow --> pkg_workflow pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -317,12 +316,18 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent + pkg_stdio --> pkg_agent + pkg_stdio --> pkg_agent_loop + pkg_stdio --> pkg_llm + pkg_stdio --> pkg_session + pkg_stdio --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_invariants @@ -356,6 +361,7 @@ flowchart TD pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction pkg_stdio_demo --> pkg_agent + pkg_stdio_demo --> pkg_agent_loop pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot pkg_stdio_demo --> pkg_llm @@ -412,16 +418,15 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | -| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -433,15 +438,16 @@ flowchart TD | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | From 419b0bcf7dfd9c0e88bc15ecf303c9576a92b43f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:51:45 +0800 Subject: [PATCH 102/140] docs: refresh module graph for UI identity --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index baa714bad1..83f98d734e 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -321,6 +321,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_stdio --> pkg_agent @@ -443,7 +444,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | From 828d6004ba35737a5887def0ce3c32b1c84b77ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:12 +0800 Subject: [PATCH 103/140] fix(sdk): share generated session identity --- packages/sdk/create-sdk/tests/create.spec.ts | 1 + packages/sdk/helper/src/features/builtin/app.ts | 7 ++++--- .../sdk/helper/src/templates/assets/index.ts.tpl | 14 +++++++------- packages/sdk/helper/tests/project.spec.ts | 15 +++++++++++++-- 4 files changed, 25 insertions(+), 12 deletions(-) diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 9d75700bb9..04a251351d 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -257,6 +257,7 @@ describe('CreateWizard and scaffolder', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('ctx.agents.create') expect(index).toContain('agentOptions: { model: "deepseek-v4-flash" }') + expect(index).not.toContain('AgentId') const tsconfig = parseGeneratedTsConfig(await readFile(join(target, 'tsconfig.base.json'), 'utf8')) const manifest = parseGeneratedPackageManifest(await readFile(join(target, 'package.json'), 'utf8')) expect(tsconfig.compilerOptions.types).toEqual(['node']) diff --git a/packages/sdk/helper/src/features/builtin/app.ts b/packages/sdk/helper/src/features/builtin/app.ts index a89f2c84ae..e4ff11af20 100644 --- a/packages/sdk/helper/src/features/builtin/app.ts +++ b/packages/sdk/helper/src/features/builtin/app.ts @@ -4,6 +4,7 @@ * @module @deepseek-ai/dsh-helper/features/builtin/app */ +import { JsExpression } from '../../documents/cordis-yaml-file.ts' import { featureId } from '../../ids.ts' import type { ProjectProfile } from '../../project/types.ts' import { @@ -94,11 +95,11 @@ class AppOption extends FeatureOption { name: '@deepseek-ai/dsh-stdio', config: { welcome: 'agent REPL ready. Give it a coding task.', - agent: 'main', + sessionId: new JsExpression('process.env.DSH_SDK_SESSION_ID'), }, - }, ['welcome', 'agent'], config => [ + }, ['welcome', 'sessionId'], config => [ ...optionalString(config, 'welcome'), - ...requiredString(config, 'agent'), + ...config.sessionId instanceof JsExpression ? [] : requiredString(config, 'sessionId'), ]), ]) case 'embed': diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index d0315db80c..4c3099199c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -2,14 +2,12 @@ import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{else}} import { randomUUID } from 'node:crypto' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{/if}} /** Boot this project's cordis.yml when invoked by dsh-scripts. */ export async function main(boot: SdkBootContext) { - const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} const model = boot.args.model if (typeof model !== 'string' || model.length === 0) throw new Error('stdio startup requires --model=') @@ -17,24 +15,26 @@ export async function main(boot: SdkBootContext) { if (resume !== undefined && (typeof resume !== 'string' || resume.length === 0)) { throw new Error('stdio startup requires --resume=') } + const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`) + process.env.DSH_SDK_SESSION_ID = sessionId +{{/if}} + const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) +{{#if isStdio}} if (resume === undefined) { await ctx.agents.create({ - agentId: AgentId('main'), - sessionId: SessionId(`main-session-${randomUUID()}`), + sessionId, meta: { cwd: boot.cwd }, agentOptions: { model }, }) } else { await ctx.agents.resume({ - agentId: AgentId('main'), - resumeSessionId: SessionId(resume), + resumeSessionId: sessionId, agentOptions: { model }, }) } {{else}} {{#if isEmbed}} await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId(`main-session-${randomUUID()}`), meta: { cwd: boot.cwd }, agentOptions: { model: {{modelLiteral}} }, diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index d55bb16be9..13fc046a04 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -167,6 +167,10 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('agents.create') expect(index).toContain('boot.args.resume') + expect(index).not.toContain('AgentId') + expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') + expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') + expect(index).toContain('resumeSessionId: sessionId') expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', @@ -175,7 +179,11 @@ describe('SdkProject and ProjectEditSession', () => { config: 'dsh-sdk config', }) expect(await readFile(join(project.root, '.env.example'), 'utf8')).toContain('EXA_API_KEY=') - expect(project.cordis.entry('stdio')?.config).toMatchObject({ agent: 'main' }) + expect(project.cordis.entry('stdio')?.config?.sessionId).toMatchObject({ + source: 'process.env.DSH_SDK_SESSION_ID', + }) + expect(await readFile(join(project.root, 'cordis.yml'), 'utf8')) + .toContain('sessionId: !!js process.env.DSH_SDK_SESSION_ID') expect(project.cordis.entry('stdio')?.config).not.toHaveProperty('model') expect(project.cordis.entry('agent-loop')?.config).toEqual({ agents: [] }) expect(project.cordis.entry('system-prompt')?.config?.persona).toContain('{{cwd}}') @@ -286,7 +294,10 @@ describe('SdkProject and ProjectEditSession', () => { const embed = (await embedEdit.commit()).project expect(embed.profile.runInterface).toBe('embed') expect(await readFile(join(embed.root, 'README.md'), 'utf8')).toContain('Embed the harness') - expect(await readFile(join(embed.root, 'index.ts'), 'utf8')).toContain('agents.create') + const embedIndex = await readFile(join(embed.root, 'index.ts'), 'utf8') + expect(embedIndex).toContain('agents.create') + expect(embedIndex).toContain("import { SessionId } from '@deepseek-ai/dsh-session'") + expect(embedIndex).not.toContain('AgentId') await writeFile(join(embed.root, 'README.md'), '# Custom README\n') const modified = await SdkProject.open(embed.root) From 336f4e51ba0b7fe0c79abbd7d617f6597f0fd7fb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:52 +0800 Subject: [PATCH 104/140] docs(acp): align identity routing contract --- packages/ui/acp/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..923c0178fa 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. +The plugin injects `agents`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -Forward and reverse indexes route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). +One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). ## Session config options From 2a6fef66ef3d55aff250f31f3d728f15e15f5269 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:52:49 +0800 Subject: [PATCH 105/140] test(agent-loop): remove review bookkeeping --- packages/core/agent-loop/tests/agent.spec.ts | 3 +-- .../tests/contract-regressions.spec.ts | 18 +++++++++--------- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7969d18200..91fc1a891d 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -401,8 +401,7 @@ describe('Agent', () => { // The waiter is internal agent state, NOT an effect-scoped ctx.on listener: // disposing the OWNING fiber runs the agent's listener disposers, which would // have dropped a ctx.on-based waiter before the 'disposed' transition and - // hung the promise. With internal waiters, the fiber disposer still settles - // it. Regression for the round-3 whenIdle finding. + // hung the promise. With internal waiters, the fiber disposer still settles it. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) let agent!: Agent diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index ec2412aff5..00eafa18cb 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -44,7 +44,7 @@ function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('HIGH: session log records what agent/step-result actually produced', () => { +describe('session log records what agent/step-result actually produced', () => { it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => { const adapter = new MockAdapter([textResponse('original'), textResponse('done')]) const ctx = await harness(adapter) @@ -94,7 +94,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( }) }) -describe('HIGH: abort during tool execution ends the turn', () => { +describe('abort during tool execution ends the turn', () => { it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { const adapter = new MockAdapter([ // model asks for two tool calls in one step @@ -146,7 +146,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { }) }) -describe('HIGH: steering from late extension points is never stranded', () => { +describe('steering from late extension points is never stranded', () => { it('steer() from an agent/turn-continuation listener overrides a stop decision', async () => { const adapter = new MockAdapter([ textResponse('no tools, would stop here'), @@ -268,7 +268,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { }) }) -describe('HIGH: plugin exceptions are contained', () => { +describe('plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) @@ -323,7 +323,7 @@ describe('HIGH: plugin exceptions are contained', () => { }) }) -describe('MEDIUM: disposed status is part of the agent/status contract', () => { +describe('disposed status is part of the agent/status contract', () => { it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) @@ -370,7 +370,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { }) }) -describe('MEDIUM: misc registry and config fixes', () => { +describe('misc registry and config fixes', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -529,7 +529,7 @@ describe('MEDIUM: misc registry and config fixes', () => { }) }) -describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () => { +describe('turn numbering continues across seeded (forked) sessions', () => { it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) @@ -567,7 +567,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () }) }) -describe('LOW: discriminated SessionEvent narrows without casts', () => { +describe('discriminated SessionEvent narrows without casts', () => { it('narrows event.data from event.type', () => { const session = new Session(SessionId('s')) const appended: SessionEvent = session.append('tool/call', { @@ -585,7 +585,7 @@ describe('LOW: discriminated SessionEvent narrows without casts', () => { }) }) -describe('HIGH: a finish-error stream chunk ends the turn as error, not completed', () => { +describe('a finish-error stream chunk ends the turn as error, not completed', () => { it('translates finish {kind:error} into a turn error with a logged error event', async () => { // The second sanctioned adapter error path (besides throwing): an // adapter that cannot throw mid-stream ends the stream with a From 60c4d523d1a868d6766b828a2e5a0771f7c42205 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:59:24 +0800 Subject: [PATCH 106/140] docs(tools): align schema default contract --- packages/core/tools/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 0f7974e0f9..00bbb67ff5 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -142,7 +142,7 @@ The available tools: - **Native tool calls execute sequentially** — `ToolDefinition` carries no concurrency-safety metadata; adding it (and parallel execution in the loop) waits on the deferred tool-shapes review (`TODO(review)`). - **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md). -- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and never applies `default` (`XXX(unused-default)` flags removing that field); raw-registered JSON-Schema tools validate their own input. +- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input. - **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper. - **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only. - **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[ content]` placeholders. From c148090961bf8de680f6b210e5d0532b23c174b8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:07:59 +0800 Subject: [PATCH 107/140] test(sdk): cover invalid generated session ids --- packages/sdk/helper/tests/project.spec.ts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index 13fc046a04..bfaa8cbf77 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -873,6 +873,12 @@ describe('extension points', () => { resource.kind === 'cordis-config-entry' && resource.entry.id === 'acp') expect(acpEntry?.entry.id).toBe('acp') expect(acpEntry?.validateConfig?.({ model: '' })).toHaveLength(1) + const stdioEntry = builtins.get(featureId('app')).contribution(selection('app', ['stdio']), profile).resources + .find((resource): resource is CordisConfigEntryResource => + resource.kind === 'cordis-config-entry' && resource.entry.id === 'stdio') + expect(stdioEntry?.validateConfig?.({ welcome: 'ready', sessionId: 1 })).toEqual([ + 'sessionId must be a non-empty string', + ]) const embedOption = app.options.find(option => option.id === 'embed') expect(embedOption?.markerConfigEntries(profile)).toEqual([]) expect(embedOption?.contribution(profile, {}).resources.map(resource => resource.kind)).toEqual([ From a6e406a7782303ea5838007e8e85401e95ce4e01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:16:52 +0800 Subject: [PATCH 108/140] docs(agent-loop): correct identity limitations --- packages/core/agent-loop/README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 9a165fd66a..6028b2f97f 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -126,7 +126,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`). -- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent. +- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. -- **`runLoop`/`Inbox`/`InboxMessage` stay exported with no outside consumer** — [removal is proposed](../../../docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md). From 1a111654ae13b9dd448cc7166499c45247e20731 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:26 +0800 Subject: [PATCH 109/140] docs(subagent): restore local run identity contract --- packages/subagent/subagent/src/types.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 67fcc99600..b0f228da96 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -134,9 +134,9 @@ export interface SubagentResult { */ export interface SubagentRun { /** - * Parent-scoped run id. A local run publishes a child session whose - * `parentSession` records `request.parent`; a remote provider mints an id - * unique in the parent namespace. + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent`; a remote + * provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 90220b235fcbdc506c6106a4c33cddd3faebacb1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:46 +0800 Subject: [PATCH 110/140] docs(core): describe the public loop contract --- packages/core/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/README.md b/packages/core/README.md index 921591d85e..fdd8e3669e 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | Concrete plugin implementing the public `Agent` contract and owning the loop driver | `ctx.agentLoop` | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. From d56cc8d42417c45c835c2f7576d16bab980eb428 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:00:56 +0800 Subject: [PATCH 111/140] fix(stdio): close startup failure gaps --- .../helper/src/templates/assets/index.ts.tpl | 31 ++++++++++++------- packages/sdk/helper/tests/project.spec.ts | 2 ++ packages/ui/stdio/README.md | 6 ++-- packages/ui/stdio/package.json | 5 +++ 4 files changed, 30 insertions(+), 14 deletions(-) diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index 4c3099199c..a79818908c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -20,17 +20,26 @@ export async function main(boot: SdkBootContext) { {{/if}} const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} - if (resume === undefined) { - await ctx.agents.create({ - sessionId, - meta: { cwd: boot.cwd }, - agentOptions: { model }, - }) - } else { - await ctx.agents.resume({ - resumeSessionId: sessionId, - agentOptions: { model }, - }) + try { + if (resume === undefined) { + await ctx.agents.create({ + sessionId, + meta: { cwd: boot.cwd }, + agentOptions: { model }, + }) + } else { + await ctx.agents.resume({ + resumeSessionId: sessionId, + agentOptions: { model }, + }) + } + } catch (error) { + try { + await ctx.fiber.dispose() + } catch (disposeError) { + throw new AggregateError([error, disposeError], 'stdio startup and cleanup failed') + } + throw error } {{else}} {{#if isEmbed}} diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index bfaa8cbf77..655b308911 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -171,6 +171,8 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') expect(index).toContain('resumeSessionId: sessionId') + expect(index).toContain('await ctx.fiber.dispose()') + expect(index).toContain("new AggregateError([error, disposeError], 'stdio startup and cleanup failed')") expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..f9cebe11e6 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -9,7 +9,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera | Key | Default | Meaning | |---|---|---| | `welcome` | `ready.` | Banner printed before the first prompt | -| `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown | +| `sessionId` | `main` | Exact agent/session identity driven by stdin and observed for EOF shutdown | The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects. @@ -18,7 +18,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent name: '@deepseek-ai/dsh-stdio' config: welcome: 'agent REPL ready. Give it a coding task.' - agent: main + sessionId: main ``` ## Model Experience @@ -37,6 +37,6 @@ The plugin seeds display labels from the live agent registry, then tracks `agent ## Known Limitations and Deferred Work -- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label. +- **One configured session receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `sessionId` rather than routing by the visible label. - **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews. - **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process. diff --git a/packages/ui/stdio/package.json b/packages/ui/stdio/package.json index 1c7311d0cb..e1bffdf171 100644 --- a/packages/ui/stdio/package.json +++ b/packages/ui/stdio/package.json @@ -29,6 +29,11 @@ "@deepseek-ai/dsh-user-interaction": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-agent-loop": { + "optional": true + } + }, "dependencies": { "schemastery": "^3.18.0" }, From 3855a77e7d8b779c74c53cbbe7736a6a29563ba2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 112/140] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 3befcfc566b4deec276d600df993949f6e49facc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:47 +0800 Subject: [PATCH 113/140] Revert "docs(approval): qualify audit guarantees" This reverts commit 14439a93c2bb915441e7b59f505d94a79b22d4af. --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..9f4968c3a4 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. +- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. +- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 70c6c0ac39aacf14ab0b627319b192fd1ca6f03b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 114/140] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From c2cf2cbbd846f477e6b3674b095a87e5ed0aa2c0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:05:44 +0800 Subject: [PATCH 115/140] test(agent-loop): name regression contracts --- packages/core/agent-loop/tests/contract-regressions.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 00eafa18cb..098a53261c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -370,7 +370,7 @@ describe('disposed status is part of the agent/status contract', () => { }) }) -describe('misc registry and config fixes', () => { +describe('registration, request routing, and queued-input ownership contracts', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) From b2064cba10f3a0c19ca24472f0ee7d7f81c1816f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 116/140] fix(agent-loop): reject duplicate configured identities --- packages/core/agent-loop/src/index.ts | 22 ++++++++++++++++--- .../tests/config-session-id.spec.ts | 19 ++++++++++++++++ 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 325ba7b92d..7144ae8dfb 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -369,6 +369,24 @@ export interface Config { })[] } +/** Reject self-contained identity conflicts before any configured agent starts. */ +function validateConfiguredAgents(agents: Config['agents']): void { + const exactIdentities = new Map() + for (const { id, sessionId, resumeSessionId } of agents) { + const hasResumeId = resumeSessionId !== undefined && resumeSessionId !== '' + if (sessionId !== undefined && hasResumeId) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } + const exactIdentity = hasResumeId ? resumeSessionId : sessionId + if (exactIdentity === undefined) continue + const firstId = exactIdentities.get(exactIdentity) + if (firstId !== undefined) { + throw new Error(`agents "${firstId}" and "${id}" use duplicate exact session identity "${exactIdentity}"`) + } + exactIdentities.set(exactIdentity, id) + } +} + /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -390,6 +408,7 @@ export class AgentLoop extends Service implements AgentFactory { constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + validateConfiguredAgents(config.agents) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') @@ -412,9 +431,6 @@ export class AgentLoop extends Service implements AgentFactory { } continue } - if (sessionId !== undefined) { - throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) - } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index bd2a5522df..56cc0bee40 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -64,6 +64,25 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('rejects duplicate exact ids before asynchronous configured startup', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + + const outcome = await ctx.plugin(AgentLoop, { + agents: [ + { id: 'first', sessionId: SessionId('shared'), model: 'mock' }, + { id: 'second', sessionId: SessionId('shared'), model: 'mock' }, + ], + }).then(() => undefined, (error: unknown) => error) + const published = ctx.agents.get(SessionId('shared')) + await ctx.fiber.dispose() + + expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"')) + expect(published).toBeUndefined() + }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) dirs.push(root) From 042d752fd2ca7f8699011275b03a952935a0a54a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 117/140] docs(repeat-guard): trim module orientation --- packages/guard/repeat-tool-guard/src/index.ts | 37 ++----------------- 1 file changed, 4 insertions(+), 33 deletions(-) diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index d51df1d829..bd6c5a4404 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -1,37 +1,8 @@ /** - * Repeat-tool-call guard: advisory loop-breaker for agents stuck re-issuing - * the same tool call with identical arguments. - * - * Not a model-facing tool — it registers no tool, never vetoes or rewrites a - * call, and adds exactly one behavior: watch each agent's stream of tool calls - * through the `tools/post-execute` waterfall, count runs of consecutive calls - * to the same tool with identical canonicalized arguments, and at configured - * run lengths fold an escalating advisory reminder onto the decision's - * `additionalContext`. The loop appends that context as a logged - * `context/message` after the step's tool results, so the reminder is - * model-visible, source-attributed, and reconstructable from the session log - * with no new session event. Decision record: - * docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md. - * - * ```yaml - * - id: repeat-tool-guard - * name: '@deepseek-ai/dsh-repeat-tool-guard' - * config: - * thresholds: [3, 5, 8] # consecutive counts that trigger a reminder - * include: [] # tool-name patterns to track; empty = all tools - * exclude: [todo_write] # tool-name patterns transparent to the chain - * ``` - * - * Chain state is keyed by the live agent object — the tool registry is a - * context-level singleton whose waterfalls interleave every agent's calls, so - * a shared counter would let one agent's repetition trip another's reminder. - * State is in-memory only: a session resumed from persistence starts with a - * fresh chain (the guard is a heuristic nudge, not a logged invariant). - * - * Plugin export shape: named exports, NO default. The cordis Loader's - * `unwrapExports` does `exports.default ?? exports`, so a stray default would - * collapse the module to the bare `apply` (see docs/postmortem/0001). - * + * Advisory per-agent repeat-call detector. It enriches post-execute decisions + * with logged model context without vetoing or rewriting calls. Configuration + * and chain semantics live in the package README; rationale lives in the + * repeat-tool-guard RFC. * @module @deepseek-ai/dsh-repeat-tool-guard */ From 68b5c716b1265590f5f2936c33f9760b12c8d1db Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:08 +0800 Subject: [PATCH 118/140] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 85e07f8191..f83f2bf616 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:373`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From b77cfd64a1cba70c1c2168d370aeab3108989a12 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:32 +0800 Subject: [PATCH 119/140] docs(catalog): refresh repeat guard source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 46645b0575..29d37dd6db 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -548,7 +548,7 @@ export interface Config { } ``` -Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts) +Source: [`packages/guard/repeat-tool-guard/src/index.ts:26`](../packages/guard/repeat-tool-guard/src/index.ts) ## `@deepseek-ai/dsh-sandbox-local` From 69c36e4fb5a6bceff4f44a8ba81ee8deb68fc1e8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:20 +0800 Subject: [PATCH 120/140] docs(subagent): name parent session lineage --- packages/subagent/subagent/src/types.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index b0f228da96..e5ba8fd84d 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -135,8 +135,8 @@ export interface SubagentResult { export interface SubagentRun { /** * Parent-scoped run id. For a local run, this MUST equal the published child - * session id, whose `parentSession` records `request.parent`; a remote - * provider mints an id unique in the parent namespace. + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 9366baf39fd84f169e1df7f42048088b5cc0c790 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:26 +0800 Subject: [PATCH 121/140] docs(acp): describe session terminal rendering --- packages/ui/acp/src/index.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 8bb25df579..d9c53cebf0 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1049,7 +1049,7 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * zero or more times per event (best-effort UI feed, never load-bearing). * @param presenter - resolves tool-owned render intent for tool events; * defaults to the generic-fallback {@link nullToolPresenter}. - * @param terminal - the connection's terminal-rendering context; defaults to + * @param terminal - the session's terminal-rendering context; defaults to * disabled (the plain-text console-block fallback). * @param options - `includeUserMessages` (default `true`): live streaming * passes `false` so a prompt the client just sent is not echoed back. @@ -1122,7 +1122,7 @@ export function todosToPlan(todos: TodoItem[]): Plan { } /** - * Per-connection terminal-rendering context threaded into + * Per-session terminal-rendering context threaded into * {@link streamSessionEventUpdate}: whether the client advertised the * `_meta.terminal_output` capability, and the session's workspace cwd (the * default terminal-card header when a tool doesn't supply its own). Kept out of From 2f1a40d9381aea67badc63f7c1d30e5cda5c0f02 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:35:31 +0800 Subject: [PATCH 122/140] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 7cc00a407a..44490c39f0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,9 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:390`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 4c08629b58ef493da1a02e0dcff9eed4d4eb1980 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:56:12 +0800 Subject: [PATCH 123/140] docs(acp): describe concurrent update routing --- packages/ui/acp/src/index.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index d9c53cebf0..7b5cb11324 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -20,11 +20,12 @@ * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts use the same identity: the - * bridge answers `approval/request` for its own agents over - * `session/request_permission` (see the approval answerer below) — whether a - * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. + * session record, and each `session/update` carries that id. Concurrent updates + * may alternate on the shared connection without crossing session attribution. + * Permission prompts use the same identity: the bridge answers + * `approval/request` for its own agents over `session/request_permission` (see + * the approval answerer below) — whether a call ASKS is policy (a hook or + * plugin returning `ask`), not the bridge's. * * stdout is the protocol: this plugin must run in an example that loads NO * stdout logger (the console logger writes to stdout and would corrupt the @@ -483,8 +484,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // whose end arrives late is ignored (see // SessionRecord.inflight). A turn that ends `error` REJECTS the prompt (ACP // has no error stop reason); other reasons resolve via the codec. Demux - // strictly by session id: a `session/event` is routed to its own record, so - // two sessions streaming at once never cross-settle or interleave updates. + // strictly by session id: concurrent updates may alternate on the shared + // connection, but they retain the owning id and never cross-settle. ctx.on('session/event', (session, event: SessionEvent) => { const rec = sessions.get(session.header.id) if (rec === undefined) return From 486362d2f8a6de1aee998cee320046d5c3db1a8d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:57:32 +0800 Subject: [PATCH 124/140] docs(catalog): refresh ACP config source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4300404cfb..cb5aebbdf8 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:244`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:245`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` From f7af6a87dcf06397bb66b91fd851572e31385815 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 03:25:21 +0800 Subject: [PATCH 125/140] docs(acp): describe terminal capability lifetime --- packages/ui/acp/src/index.ts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 7b5cb11324..a12249d0b5 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -359,10 +359,10 @@ export function apply(ctx: Context, config: AcpConfig): void { // await and NOT install a record (which would resurrect a live agent/listeners // after the bridge closed). Checked after every load await. let closed = false - // Whether the client advertised the Zed `_meta.terminal_output` capability in - // `initialize`. When true, a tool's terminal presentation is rendered as a - // terminal card (content + `_meta.terminal_*`); when false, the bridge uses - // the tool's text fallback. Set once in `initialize`, read on every tool event. + // Connection-level terminal capability from the latest `initialize`; false + // before initialization. Each `session/new` or `session/load` snapshots it in + // `SessionRecord.terminalEnabled`, so later initialization affects only future + // sessions. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only From 9a25e44fbb4c192ad1912fa504d9b71e19820f36 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 12:54:45 +0800 Subject: [PATCH 126/140] test(agent-spine-demo): wait for exact agent identity --- .../examples/agent-spine-demo/tests/agent-core.spec.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index 6081fff1a1..fb74e11b7d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -86,10 +86,10 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { } } -function waitForMainIdle(ctx: Context): Promise { +function waitForIdle(ctx: Context, target: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (agent, status) => { - if (agent.id === 'main' && status === 'idle') { + if (agent === target && status === 'idle') { dispose() resolve() } @@ -177,7 +177,7 @@ describe('dsh-agent-spine-demo bundle', () => { const agent = handle.agent agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, agent) const sentText = adapter.requests[0]?.messages.map(messageText).join('\n') expect(sentText).toContain('hi') @@ -206,7 +206,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(adapter.requests[0]?.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }]) await handle.dispose() @@ -295,7 +295,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(messageText(adapter.requests[0]?.messages[0])).toContain('workspace rule before skills') expect(messageText(adapter.requests[0]?.messages[1])).toContain('prefix-order-skill') From e846a115f29fd4fdfe7d6fc7ac303688a093a715 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:51:44 +0800 Subject: [PATCH 127/140] test(acp-snapshot): cover pre-spawn launch failure --- .../support/acp-snapshot/tests/harness.spec.ts | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 3436f32f96..2b9d6e032f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -244,6 +244,23 @@ describe('runScenario', () => { )).rejects.toThrow(/agent stderr:\nfake agent requested startup failure/) }) + it('preserves launch-resolution errors when no child process exists', async () => { + const { dir, fixtureFile } = await scenario({}) + vi.stubEnv('DSH_EXAMPLE_MODE', 'lib') + try { + await expect(runScenario( + { steps: [] }, + { + agent: { ...AGENT, binScript: join(dir, 'outside-src.ts'), libBinScript: undefined }, + mode: 'replay', + fixtureFile, + }, + )).rejects.toThrow(/expected a "\/src\/" segment/) + } finally { + vi.unstubAllEnvs() + } + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 1815095579a28d5eb46ba7329f508d31b3a79d56 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:54:24 +0800 Subject: [PATCH 128/140] docs(api): refresh compact reference --- website/zh-CN/api/harness/compact.md | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/website/zh-CN/api/harness/compact.md b/website/zh-CN/api/harness/compact.md index 8be3b4287a..67f17cc941 100644 --- a/website/zh-CN/api/harness/compact.md +++ b/website/zh-CN/api/harness/compact.md @@ -25,20 +25,19 @@ Check token pressure and compact if the conversation is too large. Estimate the [Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L58) -### ctx.compact.compactRegion(session, start, end, agent, signal?) +### ctx.compact.compactRegion(start, end, agent, signal?) ```ts website-api -abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` -Forcibly compact a range of surface nodes into a single summary node. `start` and `end` name an inclusive span by surface position, not numeric seq order; replacements can make visible seqs non-monotonic. Both edges must be balanced so assistant tool calls remain paired with their results. A model- backed implementation forwards cancellation. The agent must own the exact target session object; implementations reject an ownership mismatch before model resolution, lock acquisition, summarization, or log mutation, and reject active, missing, reversed, or unbalanced ranges. Use toolPairingBalancedBefore and toolPairingBalancedAfter for the edge checks. +Forcibly compact a range of surface nodes into a single summary node. `start` and `end` name an inclusive span by surface position, not numeric seq order; replacements can make visible seqs non-monotonic. Both edges must be balanced so assistant tool calls remain paired with their results. A model- backed implementation forwards cancellation and rejects active, missing, reversed, or unbalanced ranges. The target session is `agent.session`. Use toolPairingBalancedBefore and toolPairingBalancedAfter for the edge checks. -- `session` — session to mutate; must be identical to `agent.session`. - `start` — first surface seq, inclusive. - `end` — last surface seq, inclusive. -- `agent` — owner of the target session and summarizer context. +- `agent` — context whose session is mutated and whose routing options guide summarization. - `signal` — optional cancellation; model-backed implementations must forward it. -**Returns** the replaced range and summary. +**Returns** the appended event seqs, summary, replaced range, and token accounting. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L85) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L82) From 9d0066440311c928a23e925fcdc34ba9da5bd184 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:54:48 +0800 Subject: [PATCH 129/140] docs(api): refresh agent reference --- website/zh-CN/api/harness/agents.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index f6c9565d37..ef20c585d7 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -20,7 +20,7 @@ Register the effect-scoped creation factory, rejecting a duplicate. Service fact **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L152) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L149) ### ctx.agents.create(options) @@ -34,7 +34,7 @@ Create and publish an owned agent and session through the active factory. Reject **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L177) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L174) ### ctx.agents.resume(options) @@ -48,7 +48,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L193) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L190) ### ctx.agents.register(agent) @@ -62,7 +62,7 @@ Register a live agent in the calling effect scope, with scope-filtered creation **Returns** the exact Cordis effect disposer for nested teardown ordering. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L207) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L204) ### ctx.agents.enter(agent) @@ -76,7 +76,7 @@ Insert an unpublished agent for an ordered factory transaction. **Returns** an idempotent closure that removes this exact entry and emits the paired disposal edge; detachment during creation dispatch is deferred. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L222) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L219) ### ctx.agents.announce(agent) @@ -88,7 +88,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L290) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L286) ### ctx.agents.get(id) @@ -102,7 +102,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L324) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L320) ### ctx.agents.list() @@ -114,4 +114,4 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L332) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L328) From 0f85ae0a9df15ad0a356087715afebba12ff41b4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:14 +0800 Subject: [PATCH 130/140] fix(subagent): identify lifecycle runs explicitly --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 8 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/subagent.md | 5 +- docs/event-producer-consumer.md | 8 +- docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 7 +- .../hooks-claude/tests/coverage-cases.ts | 9 +- packages/subagent/subagent-acp/src/run.ts | 1 + .../subagent/subagent-inprocess/src/index.ts | 1 + packages/subagent/subagent/README.md | 4 +- packages/subagent/subagent/package.json | 2 + packages/subagent/subagent/src/index.ts | 25 +++- packages/subagent/subagent/src/types.ts | 19 +++ .../subagent/subagent/tests/service.spec.ts | 25 +++- .../tool-subagent/tests/tool-subagent.spec.ts | 15 ++ packages/support/subagent-mock/src/index.ts | 1 + packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +----- .../jsonrpc/tests/built-scope-carrier.e2e.ts | 1 + packages/ui/jsonrpc/tests/server.spec.ts | 130 ++++++++++++++++-- .../tests/workflow-workerthread.spec.ts | 8 ++ pnpm-lock.yaml | 3 + website/zh-CN/api/harness/events.md | 8 +- website/zh-CN/api/harness/subagents.md | 10 +- 26 files changed, 253 insertions(+), 93 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a0cbac6789..f07dfcf18a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -918,7 +918,7 @@ export interface Config { Depends on: [`SubagentCapabilities`](../packages/subagent/subagent/src/index.ts) · [`SubagentStopReason`](../packages/subagent/subagent/src/index.ts) -Source: [`packages/support/subagent-mock/src/index.ts:86`](../packages/support/subagent-mock/src/index.ts) +Source: [`packages/support/subagent-mock/src/index.ts:87`](../packages/support/subagent-mock/src/index.ts) ## `@deepseek-ai/dsh-subagent-spawn` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 820a453ceb..d0ff7002b0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -301,7 +301,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:109`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -311,7 +311,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -321,7 +321,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:89`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -331,7 +331,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:100`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 52f9cdf131..ee953e37c7 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -264,7 +264,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:142`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 18cb22c32d..815438f215 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -69,6 +69,7 @@ interface SubagentStopReasonMap { ```ts type-equiv interface SubagentRun { readonly id: SessionId + readonly localAgent: Agent | undefined readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void @@ -76,7 +77,7 @@ interface SubagentRun { } ``` -A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, expose the exact child as `localAgent`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope. A remote provider instead returns a parent-scoped lifecycle id and `localAgent: undefined`. ## The provider seam: `SubagentProvider` @@ -91,7 +92,7 @@ interface SubagentProvider { } ``` -`start()` fulfills only with a ready run. The service observes its result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. In-process children are discoverable through `ctx.agents`, while remote children need not be. `subagent/end` reports final output or infrastructure failure. Both events are observe-only and contain listener exceptions. +`start()` fulfills only with a ready run. The service mints a unique `runId`, snapshots `local` from the provider's exact `localAgent`, observes the result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. The paired `subagent/end` carries the same identity and the final output or infrastructure failure. Both events are observe-only and contain listener exceptions. ## In-process backends: depth and seed diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 6d75d54f3d..49e8d778cf 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -30,10 +30,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:109`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:89`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:100`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:86`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:103`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 604aa7cf7f..f49092f99d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -279,6 +279,7 @@ flowchart TD pkg_tool_skill --> pkg_skill pkg_tool_skill --> pkg_tools pkg_subagent --> pkg_agent + pkg_subagent --> pkg_brand pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope pkg_subagent --> pkg_session @@ -493,7 +494,7 @@ flowchart TD | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 71640498c9..ed5c0babe9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1028,7 +1028,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly localAgent: Agent | undefined;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 136ee893c6..7bb4c0b4ea 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -288,8 +289,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -324,7 +325,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts index 9d4004c1ff..0431486d57 100644 --- a/packages/hooks/hooks-claude/tests/coverage-cases.ts +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -231,7 +232,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const injected: string[] = [] const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { id: SessionId('child-x'), header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-x'), provider: 'p', id: SessionId('child-x'), local: true }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -247,7 +248,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const warn = vi.fn(); ctx.logger.warn = warn as never const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { id: SessionId('child-y'), header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-y'), provider: 'p', id: SessionId('child-y'), local: true }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -291,7 +292,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-z'), provider: 'p', id: SessionId('child-z'), local: false, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -691,7 +692,7 @@ export function defineCoverageCases(group: CoverageGroup): void { // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { provider: 'mock', model: 'mock' } }) - ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-stop'), provider: 'inproc', id: childHandle.agent.id, local: true, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index b7b10ecb97..a10a87a940 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -294,6 +294,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { id, + localAgent: undefined, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 018f93051f..c5c85ec232 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -175,6 +175,7 @@ export async function startInProcessRun( return { id: childId, + localAgent: child, result, dispose(): Promise { request.signal.removeEventListener('abort', onAbort) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 45e0976ed7..17edd0e3c7 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,9 +50,9 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. -A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, exposes the exact child as `SubagentRun.localAgent`, and records `request.parent.session.id` in the child's `parentSession` header. Remote providers instead mint a parent-scoped lifecycle id and return `localAgent: undefined`. -The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. +The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. The pair shares a service-minted `runId`; its `local` flag is snapshotted from the provider's exact `localAgent`, so observers never infer run identity or locality from reusable provider/session names. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index 84d2c963d5..aea05553e4 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -31,6 +32,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 00762cc413..8f3549ac7c 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -28,6 +28,7 @@ * @module @deepseek-ai/dsh-subagent */ +import { randomUUID } from 'node:crypto' import { Context, Service } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' @@ -43,7 +44,9 @@ import type { SubagentRun, SubagentStartRequest, } from './types.ts' +import { SubagentRunId } from './types.ts' +export { SubagentRunId } from './types.ts' export type { SubagentCapabilities, SubagentProvider, @@ -112,18 +115,26 @@ declare module 'cordis' { /** Observe-only identifying detail for a ready subagent run. */ export interface SubagentRunInfo { + /** Unique identity shared with the paired terminal event. */ + readonly runId: SubagentRunId /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean } /** Observe-only outcome detail for a settled subagent run. */ export interface SubagentRunEndInfo { + /** Unique identity shared with the paired start event. */ + readonly runId: SubagentRunId /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ @@ -208,22 +219,28 @@ export class SubagentService extends Service { const parent = request.parent const run = await provider.start(request) + const runId = SubagentRunId(randomUUID()) + const lifecycleIdentity = { + runId, + provider: name, + id: run.id, + local: run.localAgent !== undefined, + } // Attach the terminal observer before dispatching start. Promise reactions // still run after this synchronous start emission, preserving start → end. void run.result.then( (result) => { this.emitLifecycle('subagent/end', { - provider: name, - id: run.id, + ...lifecycleIdentity, stopReason: result.stopReason, lastAssistantMessage: result.output, }, parent) }, () => { - this.emitLifecycle('subagent/end', { provider: name, id: run.id, stopReason: 'error' }, parent) + this.emitLifecycle('subagent/end', { ...lifecycleIdentity, stopReason: 'error' }, parent) }, ) - this.emitLifecycle('subagent/start', { provider: name, id: run.id }, parent) + this.emitLifecycle('subagent/start', lifecycleIdentity, parent) return run } diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index e5ba8fd84d..1b1645d89b 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -7,10 +7,23 @@ */ import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Branded } from '@deepseek-ai/dsh-brand' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' +/** Identifies one accepted subagent run across its lifecycle event pair. */ +export type SubagentRunId = Branded<'SubagentRunId'> + +/** + * Brand a string as a {@link SubagentRunId}. + * @param id - the raw id string (the service mints UUIDs; tests may pass fixtures). + * @returns the same string, branded. + */ +export function SubagentRunId(id: string): SubagentRunId { + return id as SubagentRunId +} + /** * Which START-TIME features a provider supports. Checked by the service before delegating to * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks @@ -139,6 +152,12 @@ export interface SubagentRun { * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId + /** + * The exact published in-process child, or `undefined` for a remote run. + * When present, its id is {@link id}; the provider retains no ownership + * implication beyond the run's ordinary {@link dispose} contract. + */ + readonly localAgent: Agent | undefined /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index ad7dbaafff..66008a923b 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -48,6 +48,7 @@ class StubProvider implements SubagentProvider { this.startCount += 1 return { id: SessionId(`child:${this.name}:${request.parent.id}`), + localAgent: undefined, result: Promise.resolve(this.outcome), async dispose() {}, } @@ -137,13 +138,14 @@ describe('SubagentService', () => { const parent = fakeParent('delegator') const events: string[] = [] const keys: unknown[] = [] - ctx.on('subagent/start', function () { events.push('start'); keys.push(carrierKeyOf(this)) }) - ctx.on('subagent/end', function () { events.push('end'); keys.push(carrierKeyOf(this)) }) + const runIds: string[] = [] + ctx.on('subagent/start', function (info) { events.push('start'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) + ctx.on('subagent/end', function (info) { events.push('end'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), localAgent: undefined, result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -151,6 +153,21 @@ describe('SubagentService', () => { await Promise.resolve() expect(events).toEqual(['start', 'end']) expect(keys).toEqual([parent, parent]) + expect(runIds[0]).toBe(runIds[1]) + }) + + it('mints distinct lifecycle identities when provider and child ids repeat', async () => { + const { ctx, subagents } = await service() + subagents.registerProvider(new StubProvider('reused')) + const runIds: string[] = [] + ctx.on('subagent/start', info => void runIds.push(info.runId)) + + const first = await subagents.start('reused', baseRequest()) + const second = await subagents.start('reused', baseRequest()) + await Promise.all([first.result, second.result]) + + expect(runIds).toHaveLength(2) + expect(new Set(runIds).size).toBe(2) }) it('emits no run lifecycle when provider startup rejects', async () => { @@ -192,7 +209,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), localAgent: undefined, result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 27a603049e..dbb78812d4 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -144,6 +144,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('weird-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -171,6 +172,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -200,6 +202,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('bare-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -327,6 +330,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -349,6 +353,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -380,6 +385,7 @@ describe('dsh-tool-subagent', () => { }, { once: true }) return { id: SessionId('spy-child'), + localAgent: undefined, result, dispose: async () => {}, } @@ -472,6 +478,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture2-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -529,6 +536,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture3-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -558,6 +566,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture4-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -732,6 +741,7 @@ describe('dsh-tool-subagent background mode', () => { }, { once: true }) return { id, + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -771,6 +781,7 @@ describe('dsh-tool-subagent background mode', () => { const order: string[] = [] const completed = await settleRun({ id: SessionId('child-1'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text' as const, text: 'ok' }], stopReason: 'completed' as const }), dispose() { order.push('dispose'); return Promise.resolve() }, }) @@ -782,6 +793,7 @@ describe('dsh-tool-subagent background mode', () => { let disposed = false const failed = await settleRun({ id: SessionId('child-2'), + localAgent: undefined, result: Promise.reject(new Error('transport gone')), dispose() { disposed = true; return Promise.resolve() }, }) @@ -790,6 +802,7 @@ describe('dsh-tool-subagent background mode', () => { const disposeFailed = await settleRun({ id: SessionId('child-3'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' }), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -797,6 +810,7 @@ describe('dsh-tool-subagent background mode', () => { const bothFailed = await settleRun({ id: SessionId('child-4'), + localAgent: undefined, result: Promise.reject(new Error('result failed')), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -832,6 +846,7 @@ describe('background preflight failure (no orphaned child, by construction)', () starts += 1 return { id: SessionId('probe-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' as const }), dispose: () => Promise.resolve(), } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index c2e94c521f..4ea30d166a 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -69,6 +69,7 @@ class MockSubagentProvider implements SubagentProvider { }) return { id, + localAgent: undefined, result, dispose(): Promise { flags.cancelled = true diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 6d9f007e66..3d19b601c4 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It classifies subagent completions through live parent ownership or durable parent lineage and retains parent-scoped provider/id counts after child disposal. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 91cc49571a..5246795a31 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -19,7 +19,7 @@ import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type SubagentService from '@deepseek-ai/dsh-subagent' -import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -68,15 +68,6 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } -/** Whether the live id names a local child related to this exact delegating parent. */ -function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { - const child = ctx.agents.get(id) - return child !== undefined && ( - ctx.agents.isOwnedBy(id, parent) - || child.session.header.parentSession === parent.session.id - ) -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -92,7 +83,6 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -116,36 +106,12 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count starts related - // by exact runtime ownership or durable parent lineage so provider-owned - // roots remain local, completions survive child disposal, and reused ids - // need no settlement-order assumption. - const localRuns = this.localRuns - this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - const parent = subagentParentOf(this) - if (!isLocalChild(ctx, info.id, parent)) return - const providerRuns = localRuns.get(info.provider) ?? new Map>() - const parentRuns = providerRuns.get(info.id) ?? new Map() - parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) - providerRuns.set(info.id, parentRuns) - localRuns.set(info.provider, providerRuns) - })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { const parent = subagentParentOf(this) - const providerRuns = localRuns.get(info.provider) - const parentRuns = providerRuns?.get(info.id) - const pendingCount = parentRuns?.get(parent) - if (pendingCount !== undefined) { - if (pendingCount === 1) parentRuns?.delete(parent) - else parentRuns?.set(parent, pendingCount - 1) - if (parentRuns?.size === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) localRuns.delete(info.provider) - } - // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above. A remote run - // has neither a cached local start nor a live child related to this - // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return + // This protocol reports only in-process child sessions. The service + // snapshots the provider's exact run provenance through child disposal; + // matching ids or parent lineage alone never establishes locality. + if (!info.local) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -223,7 +189,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index ed4dfbb9db..54727f571b 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -71,6 +71,7 @@ try { start() { return Promise.resolve({ id: child.agent.id, + localAgent: child.agent, result: result.promise, dispose() { return Promise.resolve(); }, }); diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 3fe73c904e..5b9259dd85 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -70,7 +70,7 @@ async function makeHarness(storageDir: string) { async function settleSubagent( ctx: Context, parent: Agent, - info: SubagentRunEndInfo, + info: Omit & { localAgent: Agent | undefined }, beforeSettle?: () => Promise, ): Promise { const result = Promise.withResolvers() @@ -81,6 +81,7 @@ async function settleSubagent( async start() { return { id: info.id, + localAgent: info.localAgent, result: result.promise, dispose: () => Promise.resolve(), } @@ -294,12 +295,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), + localAgent: handle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), + localAgent: parentlessHandle.agent, stopReason: 'error', }, () => parentlessHandle.dispose()) @@ -335,7 +338,7 @@ describe('HarnessSdkServer', () => { } }) - it('ignores a remote run id that collides with an unrelated local agent', async () => { + it('ignores a remote run id that collides with a local child of the same parent', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) const ctx = await makeHarness(storageDir) try { @@ -346,24 +349,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const unrelatedHandle = await ctx.agents.create({ + const collidingChild = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('remote-run-id'), - meta: { cwd: storageDir }, + meta: { cwd: storageDir, parentSession: SessionId('collision-parent') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'remote', id: SessionId('remote-run-id'), + localAgent: undefined, stopReason: 'completed', lastAssistantMessage: [], - }, () => unrelatedHandle.dispose()) + }) expect(transport.notifications.some(notification => notification.method === 'subagent.finished' && notification.params?.agentId === 'remote-run-id', )).toBe(false) + await collidingChild.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -392,12 +397,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'first' }], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'second' }], }, () => childHandle.dispose()) @@ -436,6 +443,7 @@ describe('HarnessSdkServer', () => { const replacement = Promise.withResolvers() const results = [first.promise, sameLifetime.promise, replacement.promise] let starts = 0 + let currentLocalAgent = oldChild.agent const disposeProvider = ctx.subagents.registerProvider({ name: 'reused', capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -444,7 +452,7 @@ describe('HarnessSdkServer', () => { const result = results[starts] starts += 1 if (result === undefined) throw new Error('unexpected fourth reused-id run') - return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + return Promise.resolve({ id: SessionId('reused-child'), localAgent: currentLocalAgent, result, dispose: () => Promise.resolve() }) }, }) @@ -471,6 +479,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, }) + currentLocalAgent = newChild.agent const secondRun = await ctx.subagents.start('reused', { parent: newParent.agent, prompt: [], @@ -512,7 +521,99 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and ignores runs without a local child session', async () => { + it('keeps locality bound to the accepted run across provider re-registration', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-provider-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parent = await ctx.agents.create({ + sessionId: SessionId('provider-reuse-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const child = await parent.agent.ctx.agents.create({ + sessionId: SessionId('provider-reuse-child'), + meta: { cwd: storageDir, parentSession: SessionId('provider-reuse-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const localResult = Promise.withResolvers() + const remoteResult = Promise.withResolvers() + const unregisterLocal = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: child.agent, + result: localResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const localRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + unregisterLocal() + + const unregisterRemote = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: undefined, + result: remoteResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const remoteRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + remoteResult.resolve({ output: [{ type: 'text', text: 'remote' }], stopReason: 'completed' }) + await remoteRun.result + await Promise.resolve() + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.lastAssistantMessage !== undefined, + )).toBe(false) + + await child.dispose() + localResult.resolve({ output: [{ type: 'text', text: 'local' }], stopReason: 'completed' }) + await localRun.result + await Promise.resolve() + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'provider-reuse-child', + )).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'reused-provider', + agentId: 'provider-reuse-child', + parentSessionId: 'provider-reuse-parent', + childSessionId: 'provider-reuse-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'local' }], + }, + }]) + + await localRun.dispose() + await remoteRun.dispose() + unregisterRemote() + await parent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + + it('uses explicit local provenance when start was missed and ignores remote runs', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -529,6 +630,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) + const fallbackChild = handle.agent failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, @@ -541,12 +643,13 @@ describe('HarnessSdkServer', () => { inheritsParentContext: true, start: () => Promise.resolve({ id: SessionId('fallback-child-session'), + localAgent: fallbackChild, result: missedStartResult.promise, dispose: () => Promise.resolve(), }), }) - // Start before the server subscribes, so the terminal fallback must use - // the still-live registry entry rather than a cached start record. + // Start before the server subscribes. The terminal payload still carries + // this run's exact local child without reconstructing it from ids. const missedStartRun = await ctx.subagents.start('fork', { parent: parentHandle.agent, prompt: [], @@ -560,22 +663,25 @@ describe('HarnessSdkServer', () => { await Promise.resolve() await missedStartRun.dispose() disposeMissedStartProvider() - // The server also missed this agent's creation, but observes the start; - // recover its lineage from the still-live registry entry. + // The server also missed this agent's creation but sees the exact child + // on the run lifecycle payload. await settleSubagent(ctx, parentHandle.agent, { provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), + localAgent: fallbackChild, stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('failed-child-session'), + localAgent: failedHandle.agent, stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('missing-child-agent'), + localAgent: undefined, stopReason: 'error', }) @@ -800,6 +906,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(3) }) }) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 5905161e6a..2f52cd7b6b 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -105,6 +105,7 @@ class StubProvider implements SubagentProvider { if (request.signal.aborted) throw new Error('child start aborted before publication') return { id: SessionId(`stub-child-${index}`), + localAgent: undefined, result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -362,6 +363,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('reject-child'), + localAgent: undefined, result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -396,6 +398,7 @@ describe('dsh-workflow-workerthread', () => { } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ id: SessionId('raw-invalid-child'), + localAgent: undefined, result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -419,6 +422,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('bad-dispose-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -440,6 +444,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('trap-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -767,6 +772,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('signal-only-child'), + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -1088,6 +1094,7 @@ describe('dsh-workflow-workerthread', () => { ready.resolve({ id: SessionId('late-ready-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1124,6 +1131,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('doomed-child'), + localAgent: undefined, result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d7b3ab2b95..47d998fedc 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1441,6 +1441,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index aafaf28484..1301a6a508 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -383,7 +383,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c - `info` — the run identity and terminal outcome. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L109) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L112) ### subagent/provider-added @@ -397,7 +397,7 @@ A provider became resolvable in the registry. - `provider` — the registered provider. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L83) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L86) ### subagent/provider-removed @@ -411,7 +411,7 @@ A provider left the registry. Accepted runs remain holder-owned. - `name` — the provider name that no longer resolves. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L89) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L92) ### subagent/start @@ -425,7 +425,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( - `info` — the provider and ready child identity. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L100) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L103) ## system-prompt/* diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index 54fe5aa76e..52632e820d 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -6,7 +6,7 @@ Named provider registry and capability-checked start surface. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L153) ### ctx.subagents.registerProvider(provider) @@ -20,7 +20,7 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L156) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L167) ### ctx.subagents.getProvider(name) @@ -34,7 +34,7 @@ Look up a provider by name. **Returns** the provider, or undefined when absent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L179) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L190) ### ctx.subagents.list() @@ -46,7 +46,7 @@ List registered provider names in insertion order. **Returns** the registered names. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L187) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L198) ### ctx.subagents.start(name, request) @@ -61,4 +61,4 @@ Establish a ready child on the named provider. Capability and semantic checks ru **Returns** the ready holder-owned run. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L200) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L211) From 1febeb8428d1c1dd4d24f812567b792d3d3f79ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:48 +0800 Subject: [PATCH 131/140] test(jsonrpc): configure built scope probe --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 54727f571b..051b0eef20 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -43,7 +43,7 @@ const [ const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); const ctx = new Context(); try { - await ctx.plugin(agentCore); + await ctx.plugin(agentCore, { workspaceContext: false }); await ctx.plugin(SubagentService); await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); await new Promise((ready) => setTimeout(ready, 50)); From 546143048c011b30380fc135efbbde12afc8b465 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:29:29 +0800 Subject: [PATCH 132/140] docs(api): refresh llm reference --- website/zh-CN/api/harness/llm.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index 200e926d15..a70d5bd478 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -6,7 +6,7 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L96) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L94) ### ctx.llm.registerAdapter(providers, adapter) @@ -21,7 +21,7 @@ Register an adapter for the given provider routes. Throws `LlmError` with code ` **Returns** the disposer that unregisters all of them. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L109) ### ctx.llm.listProviders() @@ -33,7 +33,7 @@ Describe provider routes with a registered adapter. **Returns** detached provider metadata in registration order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L140) ### ctx.llm.listModels(provider) @@ -47,7 +47,7 @@ Discover models advertised by one registered provider. Catalog membership is adv **Returns** detached model metadata in adapter-preferred order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L152) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L150) ### ctx.llm.stream(options) @@ -61,4 +61,4 @@ Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with **Returns** the chunk stream, possibly wrapped by `llm/stream` listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L210) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L208) From 39b9c25b8992bbb9623a58820a7a8a3bab6d3175 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 01:59:54 +0800 Subject: [PATCH 133/140] test: refresh parallel tool call permission snapshot --- .../tests/snapshots/parallel-tool-calls/stdout.golden.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl index 6d7bc199e8..8680db3d30 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} From 3d19252e9643df4875b43669e7e22a32865ba857 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:03:35 +0800 Subject: [PATCH 134/140] test: refresh parallel tool call permission snapshot --- .../tests/snapshots/parallel-tool-calls/stdout.golden.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl index 6d7bc199e8..8680db3d30 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} From 9f1a69366bb4644f781df1508cd2879d205f343e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:18:59 +0800 Subject: [PATCH 135/140] docs: tighten identity bridge prose --- docs/config-catalog.md | 10 +- .../feature/2026-07-06-approval-seam.md | 32 +-- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/subagent/subagent/src/index.ts | 4 +- packages/ui/acp/src/index.ts | 267 +++--------------- packages/ui/jsonrpc/README.md | 12 +- packages/ui/jsonrpc/src/server.ts | 59 ++-- 7 files changed, 86 insertions(+), 300 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3b3e034601..c8e1a04036 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -20,20 +20,14 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } ``` Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:247`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:206`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..81e60a726f 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -49,39 +49,39 @@ The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothin #### The seam: mechanism and policy split -After request validation and a successful `approval/asked` append, the answerer phase always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable`. `ApprovalRequest` is a readonly same-process contract, so the service borrows its routing identity and cancellation signal instead of copying the record or capturing a parallel callback bundle. It dispatches the `approval/request` waterfall, races the request signal (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the request agent's session log. Request acceptance and either pre-commit audit append may still reject; returning a decision that could not be logged would violate the pair. Session owns post-commit observer containment, so a callback failure cannot turn an authoritative audit append into a rejected request or suppress the matching event. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. `request()` also throws before appending anything when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every ask path runs mid-turn already, and idle asks are a deferred design. +After validation and a successful `approval/asked` append, the service resolves the `approval/request` waterfall to `allowed-once`, `rejected`, `cancelled`, or `unavailable`. It borrows the readonly request identity and signal, treats abort as `cancelled`, contains answerer failures and invalid returns as `unavailable`, discards late answers, and appends the paired `approval/decided` event. Pre-commit audit failures reject; post-append observer failures cannot undo an authoritative event. `allowed-once` authorizes only the asked action, and `request()` rejects outside an open turn so the audit pair remains inside the durable commit boundary. -Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates. +Answerers are `approval/request` waterfall listeners. Zero listeners fall through to `unavailable`; a recognizing listener occupies the first-wins decision slot, while an unrecognized agent must delegate with `next()`. Listeners dispose with their fibers, so an unloaded channel fails closed. Because sibling registration order is not deterministic, a deployment composes one terminal answerer and reserves `prepend` for decide-or-delegate gates. -`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The caller retains ownership and honors the readonly contract for the duration of `request()`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call. +`ApprovalRequest` carries the asking `agent`, `toolName`, optional exact `callId`, human-readable `reason`, and optional `signal`. It uses the `CallId` brand without importing `dsh-tools`, which depends on this seam. Tool arguments stay on the already-streamed call that a UI references by `callId`. #### Ask routing in dsh-tools -`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to guards and dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: with no ApprovalService, or after one unmounts, the next ask fails closed without gating the registry's fiber. An agent-less execution also fails closed — without an agent there is no session to audit to and no UI to route to. +`ToolRegistry.execute()` resolves `ask` before dispatch: `allowed-once` proceeds, while rejection, cancellation, and channel absence produce distinct deny reasons. Opportunistic `ctx.get('approval')` consumption lets an absent or unmounted service fail closed without gating the registry fiber. Agent-less execution also fails closed because it has neither an audit session nor a UI owner. #### The per-session policy tier -The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged and falls through to fail-closed `'unavailable'` when nobody answers. Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections. +The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox RFC](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The ACP bridge answers only for an exact agent object owned by its forward session map. It attaches `session/request_permission` to the existing `callId`, advertises one-shot allow/reject options, maps cancellation separately, and never grants an unknown option. Foreign or call-less requests delegate; a failed client RPC becomes `unavailable`. Hooks and `tools/pre-execute` decide whether a call asks at all. The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` and `approval/decided` are durable log-only events; the model sees only the ordinary tool result derived from the outcome. Successful completion commits one `decided` per `asked`, including cancellation and contained answerer failure. Idle requests append neither event; a pre-commit failure rejects, while failure of the second append can leave an already-committed `asked` unmatched. #### Entities and dependencies -One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (event-map merge + append), `dsh-agent` (the `Agent` type), `dsh-llm` (`CallId`, via `dsh-brand`). `dsh-tools` and `dsh-acp` each peer on it; the escalation phase's asker lives in `dsh-tool-bash` (see [the sandbox RFC](2026-07-06-sandbox.md) § Escalation), so the sandbox family keeps its ZERO-edge relation (the executor contributes the per-call override mechanism, and transport seams never ask humans questions). The seam is one package, not the capability-seam three: the service body (dispatch + audit) has no replaceable implementation — the replaceable part is the answerer listeners, and those live with their owners (the bridge; future terminal UIs; test scripts). `@cordisjs/plugin-capability` stays orthogonal (a static grant registry answers "is this already authorized", not "ask the user now"), and `subagent-acp`'s child-side `permission` auto-answer is untouched — routing a child's approvals to the parent session is deferred (§ Deferred). +`dsh-user-approval` depends on Cordis plus the session, agent, and branded-call contracts; `dsh-tools` and `dsh-acp` consume it. The sandbox executor stays independent because `dsh-tool-bash` owns escalation requests. The fixed dispatch-and-audit service remains one package; replaceable answerers live with their channel owners. Static capability grants and `subagent-acp` child-side permission answers remain separate concerns. ### Testing -Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation), scoped routing, post-append observer throws on both audit events, and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`. +Unit tests pin outcomes, first-wins delegation, containment, cancellation, scoped routing, audit pairing, the unbypassable `'never'` policy, tool deny reasons, and ACP ownership/outcome mapping through a real scripted bridge. -Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing). +Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the `'never'` prompt and policy-switch notice. Unscripted permission prompts cancel and fail closed. ## Deferred @@ -102,12 +102,10 @@ Snapshot tier: the harness accepts scripted permission answers (`permissionAnswe The implemented contract is pinned by the suites in Testing: -- With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. -- A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). -- Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. -- Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. -- A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. +- `allowed-once` dispatches one action; every other outcome denies with a distinct reason, and `'never'` rejects before prompting. +- Missing, foreign, agent-less, throwing, invalid, and disconnected answer paths fail closed. +- Successful requests route by exact agent ownership and append one replayable, model-invisible audit pair; idle and pre-commit failures reject. +- ACP ownership keeps prompts inside their session, while a deployment without the service emits no prompt or audit events. Costs and accepted limits: @@ -117,8 +115,6 @@ Costs and accepted limits: ## FAQ -Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that. - - **What happens in a deployment with no answerer at all (headless, CI)?** Every ask falls through the empty waterfall to `unavailable` and the tool call denies with the "no approval channel is available" reason. Fail-closed is the zero-listener default, not a configuration. - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 896e019779..9084befad5 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC forwards only lifecycle events whose service-snapshotted `local` flag is true, obtains the delegating parent from the scoped event carrier, and keeps no child identity or lineage cache. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 8f3549ac7c..19779f9137 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -121,7 +121,7 @@ export interface SubagentRunInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean } @@ -133,7 +133,7 @@ export interface SubagentRunEndInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 95c5abb0d6..e20cd40f10 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1,36 +1,7 @@ /** - * The Agent Client Protocol (ACP) bridge: a client-driver / UI plugin that - * exposes the harness agent as an ACP server over JSON-RPC stdio, so editors - * (Zed and other ACP clients) can drive it. The structured analogue of the - * readline `stdio-chat` plugin. - * - * This is NOT a loop change and NOT an ADR-0009 capability seam: it consumes - * the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, - * and `dsh-session-persistence` (for `session/load`). It maps: - * - * - `initialize` → protocol-version negotiation, text-only capabilities - * - `session/new` → `ctx.agents.create({ sessionId, meta:{cwd} })` - * - `session/load` → `ctx.agents.resume(...)` then replay the event log - * - `session/prompt` → `agent.send()`, settle on the owning turn's end (a turn - * that ends in `error` rejects the RPC) - * - `session/cancel` → `agent.cancel()` (the queue-aware cancel: aborts a - * running step, clears queued + steering work, and drops a - * turn about to start) + settle the in-flight prompt - * - * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; - * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, and each `session/update` carries that id. Concurrent updates - * may alternate on the shared connection without crossing session attribution. - * Permission prompts use the same identity: the bridge answers - * `approval/request` for its own agents over `session/request_permission` (see - * the approval answerer below) — whether a call ASKS is policy (a hook or - * plugin returning `ask`), not the bridge's. - * - * stdout is the protocol: this plugin must run in an example that loads NO - * stdout logger (the console logger writes to stdout and would corrupt the - * JSON-RPC frames). The guarantee is config-only — see the package README and - * RFC 010 § Risks. + * Multi-session ACP bridge over JSON-RPC stdio. Creates or resumes agents, + * routes session-scoped events and approvals, and settles prompts by turn. + * Stdout is reserved for protocol frames. * * @module @deepseek-ai/dsh-acp */ @@ -104,27 +75,15 @@ import { } from './codec.ts' export const name = 'acp' -// Interface services back advertised loading, tool-owned presentation with a generic fallback, and interaction. -// TODO(acp-session-inject): remove `sessions`; the bridge never reads it, and ownership is already behind `agents`. +// Interface services back loading, presentation, interaction, and prompt assembly. export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt'] -/** - * Build an ACP "invalid params" error whose human detail rides in the message. - * `RequestError.invalidParams(data, additionalMessage)` keeps the standard - * "Invalid params" message and appends `additionalMessage`, so we pass the - * detail as `additionalMessage` (and no structured `data`). - */ +/** Preserve invalid-parameter detail in the SDK wire error message. */ function invalidParams(detail: string): RequestError { return RequestError.invalidParams(undefined, detail) } -/** - * Build an ACP "internal error" whose human detail rides in the message. Used - * to reject a `session/prompt` whose turn ended in failure: a plain `Error` - * thrown from a method handler is flattened to a generic "Internal error" on - * the wire, so we wrap the detail in the SDK's `RequestError.internalError` - * (which appends `additionalMessage`) to surface *why* the turn failed. - */ +/** Preserve failed-turn detail; plain handler errors become a generic wire internal error. */ function internalError(detail: string): RequestError { return RequestError.internalError(undefined, detail) } @@ -249,13 +208,7 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } @@ -292,30 +245,11 @@ interface ModelCatalogEntry { /** Per-session bridge state keyed by ACP session id. */ interface SessionRecord { agent: Agent - /** - * The owned-agent disposer (from the {@link AgentHandle} the factory returned). - * Teardown calls it to unregister this ONE agent, stop its loop, await - * quiescence, and remove its session — instead of leaving it for the bridge - * fiber to reclaim. - */ + /** Exact owned-agent disposer; resolves after registry, loop, and session teardown. */ dispose: () => Promise - /** - * Resolves tool-owned presentation for THIS session's tool calls and remembers - * each in-flight call's `(name, args)` so the matching `tool/result` can find - * its tool. Per-session so two concurrent sessions never cross their in-flight - * tool state. - */ + /** Per-session tool presentation and call/result correlation. */ presenter: ToolPresenter - /** - * Whether THIS session renders shell tools as terminal cards — snapshotted - * from the client's `_meta.terminal_output` capability at session creation - * (`session/new`/`session/load`), NOT re-read live. A capability snapshot per - * session means the `tool_call` (which registers the terminal) and the matching - * `tool_call_update` (which streams its output) ALWAYS agree, even if a later - * `initialize` mutates the connection-level capability between them — otherwise - * a re-`initialize` mid-call could orphan a `terminal_output` (call non-terminal, - * result terminal) or clobber the card (call terminal, result non-terminal). - */ + /** Terminal capability snapshot shared by matching call and result updates. */ terminalEnabled: boolean /** Session-local provider/model selection and the current step snapshot. */ target: LlmTargetRef @@ -325,18 +259,7 @@ interface SessionRecord { reject: (error: Error) => void turn: number | undefined } | undefined - /** - * Config switches accepted while the session was IDLE, not yet anchored in - * its log. The turn-enclosure contract makes a bare between-turns append - * invalid (the JSONL backend treats a post-`turn/end` tail as crash - * garbage, and dev invariants throw), so an idle switch waits here and is - * anchored at the next turn's prompt-submit — before anything in that - * turn assembles a prompt or runs a call, and last write - * per knob wins (an idle flip-flop anchors as one event). Until anchored, - * the switch lives only in bridge memory: the set/new/load responses - * overlay it truthfully, and a restart before the next turn reverts it — - * which `session/load` then reports honestly from the log's fold. - */ + /** Last idle switch per knob, anchored before the next prompt assembles. */ pendingSwitches: { preset?: string } } @@ -347,21 +270,15 @@ interface SessionRecord { * correlation in a `finally` so presentation failure cannot starve settlement. */ export function apply(ctx: Context, config: AcpConfig): void { - // Capture the injected services NOW, during apply(), while we are inside this - // plugin's fiber (where `inject` grants access). The ACP method handlers run - // LATER, from the AgentSideConnection's JSON-RPC read loop — a context that is - // NOT this fiber's injection scope — so reading `ctx.agents` / `ctx.logger` / - // `ctx.sessionPersistence` lazily inside a handler throws "cannot get property - // … without inject". Resolving the references here and closing over them keeps - // the handlers working regardless of which fiber later invokes them. + // ACP handlers execute outside this plugin's injection scope, so capture + // injected services during apply(); lazy service reads in a handler fail. const agents = ctx.agents const llm = ctx.llm const sessionPersistence = ctx.sessionPersistence const logger = ctx.logger const tools = ctx.tools const userInteraction = ctx.userInteraction - // A new ToolPresenter per session (and a throwaway per load replay), each given - // this warn sink so a throwing tool presenter is logged, not propagated. + // Presenter callbacks are contained so display failures cannot break protocol handling. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) /** Resolve a complete target only; partial config remains available to other request listeners. */ @@ -459,23 +376,12 @@ export function apply(ctx: Context, config: AcpConfig): void { } } - // TODO(derive-acp-session-id): derive event ids from `agent.session`, verify ownership, then remove the reverse map. - // Agent events currently carry only the Agent, so retain `SessionRecord.sessionId` and update both indexes together. - // Dropping the forward record lets the weak reverse entry expire. const sessions = new Map() - // Session ids whose `session/load` is mid-`resume()` (the slot is reserved - // before the async resume so a pipelined load/new for the SAME id can't create - // two agents). Distinct ids load concurrently; a given id loads once at a time. + // Reserve an id before resume so pipelined load/new requests cannot duplicate it. const loadingIds = new Set() - // Set once the bridge has torn down (disposal or client disconnect). An async - // `session/load` mid-`resume()` when teardown ran must observe this after its - // await and NOT install a record (which would resurrect a live agent/listeners - // after the bridge closed). Checked after every load await. + // Async creation checks this after awaits to avoid publishing after teardown. let closed = false - // Connection-level terminal capability from the latest `initialize`; false - // before initialization. Each `session/new` or `session/load` snapshots it in - // `SessionRecord.terminalEnabled`, so later initialization affects only future - // sessions. + // Each new or loaded session snapshots the latest connection capability. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only @@ -674,22 +580,13 @@ export function apply(ctx: Context, config: AcpConfig): void { currentValue, options: [ ...presets.names.map((name: string) => presets.optionOf(name)), - // The derived not-a-preset state: visible exactly while it IS the - // current value (a knob state outside the table), switchable FROM, - // never a target — set() below rejects it like any unknown name. + // `custom` echoes the current derived state but is never a target. ...currentValue === 'custom' ? [presets.optionOf('custom')] : [], ], }] } - /** - * Whether the session's log currently has an open turn — the last boundary - * event is a `turn/start`. Decides whether a config switch may append NOW - * (enclosed) or must wait for the next turn (see - * {@link SessionRecord.pendingSwitches}). Read from the LOG, not - * `agent.status`: status stays `running` across the gap between two queued - * turns, where a bare append would still land outside any turn. - */ + /** Whether the log has an open turn in which a config switch can be enclosed. */ const isTurnOpen = (agent: Agent): boolean => { const events = agent.session.events for (let index = events.length - 1; index >= 0; index -= 1) { @@ -700,12 +597,7 @@ export function apply(ctx: Context, config: AcpConfig): void { return false } - /** - * Anchor a record's pending switches into its (just-opened) turn, last - * write per knob — skipping a value the session already effectively has, - * so a net-zero idle flip-flop anchors NOTHING (the log records switches, - * not select clicks). - */ + /** Anchor last-write-wins idle switches into a just-opened turn. */ const flushPendingSwitches = (rec: SessionRecord): void => { const pending = rec.pendingSwitches rec.pendingSwitches = {} @@ -717,15 +609,8 @@ export function apply(ctx: Context, config: AcpConfig): void { presets.set(rec.agent.session, pending.preset) } - // Idle-accepted switches anchor at the next turn's prompt-submit: the turn - // is open (the seam fires inside it, per drained message — the first flush - // empties the slot, later ones no-op), the loop has not yet assembled - // anything for it, and — unlike appending from inside a `session/event` - // listener — this seam fires OUTSIDE any log emit, so peer listeners - // (the dev invariants, persistence) observe the anchored events in strict - // log order. A turn with no prompt (an idle inject's one-shot injection - // turn) leaves the switch pending — it runs no step, so nothing executes - // or assembles under a stale value. + // Prompt-submit is inside the new turn but before prompt assembly. Promptless + // injection turns leave the switch pending because they execute no request. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) @@ -780,10 +665,8 @@ export function apply(ctx: Context, config: AcpConfig): void { agentOptions: agentOptions(config), setup: (agentCtx) => { installTarget(agentCtx, target) }, }) - // Creation is now asynchronous because it awaits the unpublished setup - // transaction. A client disconnect can therefore close this bridge - // after the entry check but before the handle resolves; never install a - // post-close record that quiesce() could not have seen. + // Agent creation may resolve after the bridge closes; dispose the handle + // instead of publishing a record that teardown could not observe. /* v8 ignore next 4 -- the in-memory transport rejects the in-flight RPC immediately on close; real stdio may let the handler resume */ if (closed) { @@ -991,10 +874,7 @@ export function apply(ctx: Context, config: AcpConfig): void { if (presets === undefined) { throw invalidParams(`unknown permission value ${JSON.stringify(params.value)}`) } - // A no-op switch (the value the session already shows — pending, - // else derived) is acknowledged FIRST and records nothing: - // clients re-push current selections on session start, and the - // derived 'custom' current is only ever valid as such an echo. + // A current-value echo is acknowledged without recording a switch. const current = rec.pendingSwitches.preset ?? presets.current(rec.agent.session.events) if (params.value === current) break if (!presets.names.includes(params.value)) { @@ -1236,27 +1116,16 @@ export function streamSessionEventUpdate( } /** - * Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires - * `content` + `priority` + `status`, but a {@link TodoItem} carries no priority, - * so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the - * harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole - * plan on each `plan` update, matching the harness's whole-list-replace - * semantics, so no per-entry diffing is needed. - * @param todos - the harness todo list (the whole list, not a diff). - * @returns the ACP plan body, one entry per todo. + * Map a whole harness todo list to an ACP replacement plan, using medium + * priority because harness todos do not carry one. + * @param todos - complete harness todo list. + * @returns one ACP plan entry per todo. */ export function todosToPlan(todos: TodoItem[]): Plan { return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) } } -/** - * Per-session terminal-rendering context threaded into - * {@link streamSessionEventUpdate}: whether the client advertised the - * `_meta.terminal_output` capability, and the session's workspace cwd (the - * default terminal-card header when a tool doesn't supply its own). Kept out of - * the pure translator's required params so the no-capability / no-presenter - * tests stay terse. - */ +/** Per-session terminal capability and workspace used while translating updates. */ export interface TerminalRendering { enabled: boolean /** The session workspace cwd (terminal-card header default); `undefined` when the session has none. */ @@ -1267,47 +1136,21 @@ export interface TerminalRendering { const noTerminalRendering: TerminalRendering = { enabled: false, cwd: undefined } /** - * Resolves tool-owned presentation for a session's tool-call events. A tool - * declares `presentCall`/`presentResult` (see `dsh-tools`) returning a - * `card`-tagged {@link ToolCallView}/{@link ToolResultView}; this looks them up - * by name in the registry and applies a generic fallback when a tool defines - * neither. The returned view is what {@link streamSessionEventUpdate} switches on. - * - * The `tool/result` session event does NOT carry the tool name or args — so to - * call a tool's `presentResult` (which needs both), the presenter remembers each - * `tool/call`'s `{ name, args, card }` keyed by callId and looks it up on the - * matching result. The map is bridge-LOCAL (not a change to the event schema or a - * core service): one presenter per live session - * (and a throwaway per `session/load` replay), and each entry is removed when its - * result arrives. In the normal loop a `tool/call` is always followed by a - * `tool/result` (the registry turns even a thrown tool into an isError result), - * so the map holds only currently-in-flight calls. The one exception is a step - * torn down mid-tool (an abort between `tool/call` and `tool/result`), which can - * leave a single stale entry per such call; this is bounded by the session - * lifetime (the whole presenter is dropped on teardown) and never affects - * correctness — a later result for a different callId is unaffected, and the - * stale entry's only cost is one map slot until the session ends. + * Resolve tool-owned call/result views with a generic fallback. Per-session + * state correlates results with call arguments; interrupted calls may retain an + * entry only until that session's presenter is discarded. */ export class ToolPresenter { private readonly pending = new Map() /** - * @param tools the registry to resolve tool definitions by name. - * @param onError invoked when a tool's `presentCall`/`presentResult` THROWS; - * the presenter swallows the error and falls back to the generic - * presentation so a buggy display callback can never fail a live turn or a - * `session/load` replay (docs/defensive-patterns.md "contain callback exceptions at the - * boundary"). Defaults to a no-op for callers that don't supply a logger. + * @param tools - registry used to resolve executing definitions. + * @param onError - contained presenter-error sink before generic fallback. + * @param agent - optional scoped registry view for the executing agent. */ constructor( private readonly tools: Pick, private readonly onError: (message: string) => void = () => {}, - /** - * The agent whose view resolves tool presentations: a scoped/shadowed - * tool presents with ITS OWN presentCall/presentResult — the same - * definition that executed — not a same-named global's. Absent (a replay - * with no live agent) the global view presents. - */ private readonly agent?: Agent, ) {} @@ -1316,10 +1159,8 @@ export class ToolPresenter { * for the matching result. * @param callId - the call id the matching `tool/result` will look up. * @param name - the tool name, resolved against the registry for `presentCall`. - * @param argsJson - the raw arguments JSON from the event; parsed for the view - * (a non-JSON string is surfaced raw). - * @returns the tool-owned view, or the generic fallback (title = tool name, - * kind `other`, parsed args as raw input) when the tool defines none or threw. + * @param argsJson - raw event arguments parsed for presentation. + * @returns the tool-owned view or generic fallback. */ call(callId: CallId, name: string, argsJson: string): ToolCallView { const args = parseToolArguments(argsJson) @@ -1331,10 +1172,7 @@ export class ToolPresenter { this.onError(`acp: tool "${name}" presentCall threw, using generic presentation: ${String(error)}`) present = undefined } - // No tool-owned presentation: fall back to the tool name as the title, the - // full parsed args as the raw input, and kind `other` (the generic card). - // The kind is never sniffed from the name — the bridge does not special-case - // tool names; a tool that wants a richer kind declares `presentCall`. + // Tool names never imply presentation kind; richer cards are tool-owned. const view: ToolCallView = present ?? { card: 'generic', title: name, kind: 'other', rawInput: args } this.pending.set(callId, { name, args, card: view.card }) return view @@ -1343,14 +1181,11 @@ export class ToolPresenter { /** * Completed-state render intent for a `tool/result`; consumes the remembered * `(name, args, card)`. - * @param callId - the id of the matching `tool/call`; an unknown or late id - * falls back to the raw content. - * @param content - the result's content blocks (the fallback and fill-in body). + * @param callId - matching call id; unknown or late ids use raw content. + * @param content - result content used by the fallback and fill-in body. * @param isError - whether the result is an error, forwarded to `presentResult`. * @param meta - the result's machine-readable meta, forwarded when present. - * @returns the tool-owned view — an orphaned `terminal` result (no terminal - * call side) and a content-less `generic` are normalized — or the raw-content - * generic card when the tool defines no `presentResult` or threw. + * @returns a normalized tool-owned view or raw-content fallback. */ result(callId: CallId, content: ContentBlock[], isError: boolean, meta?: unknown): ToolResultView { const call = this.pending.get(callId) @@ -1420,25 +1255,11 @@ type AcpToolCallContent = | { type: 'diff'; path: string; oldText: string | null; newText: string } | { type: 'terminal'; terminalId: string } -/** - * Relativize a file card's TITLE path against the session workspace cwd, so a - * card reads `Read src/foo.ts` rather than `/abs/proj/src/foo.ts` — matching the - * reference ACP adapter's `toDisplayPath`. Only the TITLE is relativized; the - * card's `locations`/`diff` paths stay RAW (the editor opens the real path). The - * pure tool presenter can't see the session cwd, so this happens here where the - * bridge knows it. The rewrite is an exact substring replace of the known raw - * path (a card carries the same path in `locations[0]`/`diffs[0]`), never a - * heuristic. A path outside the workspace, or an absent/relative session cwd, is - * left unchanged. - */ +/** Relativize only in-workspace title text; location and diff paths stay raw. */ function displayTitle(title: string, rawPath: string | undefined, sessionCwd: string | undefined): string { if (rawPath === undefined || sessionCwd === undefined || !isAbsolute(rawPath) || !isAbsolute(sessionCwd)) return title const rel = relativePath(sessionCwd, rawPath) - // Only relativize a target that stays INSIDE the workspace. `relative` prefixes - // a `..` SEGMENT for a target above the cwd — test for the segment (`..` alone - // or `..…`), NOT a bare `..` char prefix, so a sibling like `..cache/x` - // (a real in-workspace name) still relativizes. Never relativize to the empty - // string (rawPath === cwd — a non-file target). + // Test the `..` segment, not a character prefix: `..cache/x` is in-workspace. if (rel.length === 0 || rel === '..' || rel.startsWith(`..${pathSep}`)) return title return title.split(rawPath).join(rel) } diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 3d19b601c4..6666867598 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -1,26 +1,26 @@ # @deepseek-ai/dsh-jsonrpc -The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC server that lets an out-of-process SDK client (e.g. the Python `deepseek_harness` package) drive DeepSeek Harness agents without touching Cordis. The client speaks newline-delimited JSON-RPC on the process stdin/stdout ([`HarnessSdkServer`](src/server.ts): `initialize` → `session/prompt` → `shutdown`, with `session.event` / `session.finished` / `subagent.*` notifications over [`JsonRpcLineTransport`](src/transport.ts)). The SDK-client analogue of the [`acp`](../acp/README.md) bridge, split the same way: this package is the protocol plugin, while [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) is the app bin that boots a `cordis.yml` around it — which process serves this protocol is a config decision, not a hardcoded bin. This plugin is the serving face of the [single-executable distribution plan](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). +The `jsonrpc` plugin serves newline-delimited JSON-RPC over stdio so out-of-process SDK clients can drive harness agents. [`HarnessSdkServer`](src/server.ts) owns the protocol methods and notifications; [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) supplies the surrounding `cordis.yml` application. ## Wiring -`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId`. It forwards subagent completions only when the service-snapshotted lifecycle `local` flag is true; provider names, child ids, and durable lineage never establish locality. A registered adapter wins, an unowned `deepseek` route mounts `dsh-llm-deepseek`, and any other unowned provider fails initialization. Other capabilities come from the surrounding `cordis.yml`. ## Config -No `cordis.yml`-settable keys. The `JsonRpcConfig` fields (`input`, `output`, `exit`) are runtime-only test seams so a spec can drive the server over in-memory streams without a subprocess or a killed test process; production always serves the process stdio and exits via `process.exit`. +There are no `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are runtime-only transport seams; production uses process stdio and `process.exit`. ## stdout is the protocol -The process stdout this plugin runs in carries only JSON-RPC frames. The tree that loads it must load NO stdout logger (a console logger corrupts the frames) — the guarantee is config-only, same as the ACP bridge. Diagnostics go to stderr. +Stdout carries only JSON-RPC frames. The deployment must not compose a stdout logger; diagnostics belong on stderr. ## Shutdown and exit semantics -The plugin owns the PROTOCOL-level exit: a `shutdown` request is answered first (the response frame flushes), then the plugin disposes its own fiber — running the effect disposer: an idempotent `server.shutdown()` (every SDK-created agent disposed to quiescence, event subscriptions detached) plus `transport.close()` — and exits the process with code 0. Own-fiber disposal is deliberate: the request's `server.shutdown()` already flushed all SDK-owned session state, and the process exit that follows is the teardown of the rest of the tree. Process-level exits (stdin EOF → 0, SIGTERM → 0, SIGINT → 130) belong to the app bin, which disposes the whole root context. Fiber disposal WITHOUT a `shutdown` request (HMR-style unload) just stops serving — it never exits the process. +The plugin answers `shutdown`, disposes SDK-owned agents and subscriptions to quiescence, closes the transport, then exits with code 0. EOF and signal exits belong to the app bin, which disposes the root context. Unloading only this plugin stops serving without exiting the process. ## Wire notes -`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime` (SDK clients key on it, independent of this package's name). A session accepts at most one in-flight `session/prompt`; an overlapping prompt for the same `sessionId` fails immediately through the standard handler-error response, while other sessions remain independent and the same session can be reused after the active prompt settles. Persistence roots and the deployment persona come from `cordis.yml`; the wire exposes only parameters the server applies. +`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. A session accepts one in-flight prompt; overlap fails immediately, other sessions remain independent, and the session is reusable after settlement. Persistence roots and persona come from `cordis.yml`. ## Model Experience diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 5246795a31..8949ccb06a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -1,13 +1,6 @@ /** - * `HarnessSdkServer`: the JSON-RPC method surface the `dsh-jsonrpc` plugin - * serves to out-of-process SDK clients (e.g. the Python `deepseek_harness` - * package). Requests: `initialize` → `session/prompt`* → `shutdown`. - * Notifications pushed to the host: `session.event` (every durable session - * event, verbatim), `session.finished` (per prompt turn settle), - * `subagent.started` / `subagent.finished` (child-session lineage and run - * outcomes). The server owns only the SDK-facing session map — the harness - * itself is the context the plugin mounts in; plugins, persistence, and - * the LLM adapter set all come from the external `cordis.yml`. + * JSON-RPC method and notification surface for out-of-process harness SDKs. + * The surrounding context owns plugins, persistence, and configured adapters. * * @module @deepseek-ai/dsh-jsonrpc/server */ @@ -23,7 +16,7 @@ import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' -/** Parameters of the `initialize` request (once per process, before any prompt). */ +/** Parameters for the process-wide SDK handshake. */ export interface InitializeParams { /** Working directory recorded on every SDK-created session's header. */ cwd: string @@ -33,16 +26,13 @@ export interface InitializeParams { model: string } -/** Result of the `initialize` request: the server's identity for the SDK handshake. */ +/** Wire-stable server identity returned by initialization. */ export interface InitializeResult { /** Wire-stable server identity (`deepseek-harness-sdk-runtime`) and version. */ serverInfo: { name: string; version: string } } -/** - * Parameters of a `session/prompt` request: one user turn on one SDK session, - * with at most one in flight per session. - */ +/** One user turn on one SDK session. */ export interface SessionPromptParams { /** The SDK-side session id; an unknown id lazily creates the agent+session pair. */ sessionId: string @@ -50,7 +40,7 @@ export interface SessionPromptParams { contentBlocks: ContentBlock[] } -/** Result of a `session/prompt` request: the prompt ran to turn settle (outcome rides on `session.finished`). */ +/** Prompt acceptance after turn settlement; outcome rides on `session.finished`. */ export interface SessionPromptResult { /** Always `true`; the turn outcome is the paired `session.finished` notification. */ accepted: true @@ -62,20 +52,12 @@ interface SessionRecord { activePrompt: boolean } -/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +/** Recover the delegating parent from the service-owned scoped carrier. */ function subagentParentOf(carrier: Scoped): Agent { - // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } -/** - * The SDK server over a booted harness context. Constructing it subscribes to - * session and subagent lifecycle events, forwarding durable session - * events and SDK-facing completion notifications while retaining local-run - * identity across child disposal. The subscriptions live until - * {@link shutdown}. One instance serves one transport peer for the process - * lifetime — there is no re-`initialize`. - */ +/** SDK server whose subscriptions and created agents live until {@link shutdown}. */ export class HarnessSdkServer { private cwd = process.cwd() private provider = 'deepseek' @@ -125,10 +107,9 @@ export class HarnessSdkServer { } /** - * Record cwd and provider/model, mounting the DeepSeek adapter only when the - * `deepseek` provider route has no configured owner. - * @param params - the SDK handshake parameters. - * @returns the server identity for the handshake. + * Configure the SDK route, mounting the DeepSeek fallback only when unowned. + * @param params - SDK handshake parameters. + * @returns server identity for the handshake. */ async initialize(params: InitializeParams): Promise { this.cwd = resolve(params.cwd) @@ -142,13 +123,9 @@ export class HarnessSdkServer { } /** - * Handle `session/prompt`: get-or-create the session's agent, send the - * content as the user message, await turn settle (quiescence), then notify - * `session.finished` with the settled turn's outcome. A session accepts at - * most one prompt at a time; an overlapping request fails immediately while - * other sessions remain independent. - * @param params - the target session id and prompt content. - * @returns `{ accepted: true }` after the turn settled. + * Run one prompt to settlement; overlap on the same session fails. + * @param params - target session and user content. + * @returns acceptance after the turn settled. */ async prompt(params: SessionPromptParams): Promise { const rec = await this.getOrCreateSession(params.sessionId) @@ -171,11 +148,9 @@ export class HarnessSdkServer { } /** - * Handle `shutdown`: dispose every SDK-created agent handle (awaiting loop - * quiescence), unmount the adapter fiber this server mounted (if any), and - * detach the event subscriptions. The CONTEXT stays up — the bin disposes it - * as part of process exit. - * @returns an empty object (the JSON-RPC result). + * Dispose server-owned agents, adapter, and subscriptions to quiescence. + * The surrounding context remains running. + * @returns empty JSON-RPC result. */ shutdown(): Promise> { this.shutdownTask ??= this.performShutdown() From 1e4de0deaa5d9fbe0b725c90b098001a3fd8ecf9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 03:02:42 +0800 Subject: [PATCH 136/140] fix(sdk): pin generated project build tool --- packages/sdk/helper/src/project/npm-dependency-policy.ts | 2 +- packages/sdk/helper/tests/documents.spec.ts | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/packages/sdk/helper/src/project/npm-dependency-policy.ts b/packages/sdk/helper/src/project/npm-dependency-policy.ts index a8877826e2..727bd6648a 100644 --- a/packages/sdk/helper/src/project/npm-dependency-policy.ts +++ b/packages/sdk/helper/src/project/npm-dependency-policy.ts @@ -23,7 +23,7 @@ const EXTERNAL_NPM_DEPENDENCY_SPECS: Readonly> = { '@cordisjs/plugin-timer': '^1.1.2', '@types/node': '^22.20.0', cordis: '^4.0.0-rc.7', - tsdown: '^0.22.2', + tsdown: '0.22.2', tsx: '^4.22.4', typescript: '^6.0.3', } diff --git a/packages/sdk/helper/tests/documents.spec.ts b/packages/sdk/helper/tests/documents.spec.ts index 1ba8b9bd68..1b8050b90f 100644 --- a/packages/sdk/helper/tests/documents.spec.ts +++ b/packages/sdk/helper/tests/documents.spec.ts @@ -282,6 +282,7 @@ describe('package manager strategies', () => { section: 'devDependencies', spec: '^4.0.0-rc.7', }) expect(resolveNpmDependency('@cordisjs/plugin-hmr', 'dependencies', '0.0.1').spec).toBe('^1.0.15') + expect(resolveNpmDependency('tsdown', 'devDependencies', '0.0.1').spec).toBe('0.22.2') expect(resolveNpmDependency('@deepseek-ai/dsh-tools', 'dependencies', '1.2.3').spec).toBe('^1.2.3') expect(() => resolveNpmDependency('unknown', 'dependencies', '0.0.1')).toThrow('no generated-project') }) From 4851d9570496a8ed5573873c85d18c054a78fad3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 03:49:18 +0800 Subject: [PATCH 137/140] docs: propose follow-up simplification RFCs --- docs/rfc/INDEX.md | 4 ++ ...026-07-04-prune-dead-core-spine-surface.md | 1 + ...19-fold-compaction-package-split.i18n.yaml | 6 +++ ...026-07-19-fold-compaction-package-split.md | 37 ++++++++++++++++++ ...-07-19-fold-compaction-package-split.zh.md | 37 ++++++++++++++++++ ...6-07-19-make-jsonrpc-directional.i18n.yaml | 6 +++ .../2026-07-19-make-jsonrpc-directional.md | 38 +++++++++++++++++++ .../2026-07-19-make-jsonrpc-directional.zh.md | 38 +++++++++++++++++++ ...-19-retire-subagent-mock-package.i18n.yaml | 6 +++ ...2026-07-19-retire-subagent-mock-package.md | 35 +++++++++++++++++ ...6-07-19-retire-subagent-mock-package.zh.md | 35 +++++++++++++++++ ...-use-one-session-surface-manager.i18n.yaml | 6 +++ ...6-07-19-use-one-session-surface-manager.md | 35 +++++++++++++++++ ...7-19-use-one-session-surface-manager.zh.md | 35 +++++++++++++++++ 14 files changed, 319 insertions(+) create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index fba361469c..99ea97d16a 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -21,6 +21,10 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | +| [Fold the single compaction backend into its service package](proposed/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | +| [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | +| [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | +| [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md b/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md index cca7c57b34..f874784a6d 100644 --- a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md +++ b/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md @@ -25,6 +25,7 @@ The production corpus is `packages/*/*/src`, example sources/config, and runtime | `CompactionResult.startSeq`, `summarySeq`, `endSeq`, and `summary` | The production consumer reads only shadowed range/seq/token accounting; the durable log owns summary and event identity. | Remove the four result echoes while keeping both shared transcript renderers. | | `BasicCompactService` estimation/summarization visibility | No outside production caller invokes the five methods; the implemented RFC names only `estimateContentTokens()` and `summarize()` as subclass hooks. | Make those two `protected` and the three orchestration-only estimators private. | | `CodeLogEntry.source`/`level` and `RunCodeMeta.dispatches` | Every production consumer maps logs to text; no presenter/model path reads the other fields or the persisted dispatch count. | Make code-runtime logs strings (or text-only entries) and remove result-meta dispatch plumbing; keep the local counter that mints deterministic dispatch ids. | +| `CodeRuntime.language` and `CodeRuntime.isolation` | The worker backend supplies the only production values, while Code Mode and every other production caller invoke only `run()`. | Remove the unread descriptors while preserving the worker's language, isolation, budgets, cancellation, and disposal behavior. | | `ToolNotFoundError.toolName`, `SystemPrompt.config`, and `BashTask.command` | Each stored public value has no production reader. | Drop the unread field while retaining error messages, resolved configuration behavior, and task lifecycle. | | Backend package-root implementation helpers | The exact inventory below is called only through relative same-package imports. Production namespace imports mount the retained plugin contract without reading these properties; named root consumers are tests. | Retain each adapter/provider/service and its config/error contract; stop exporting the listed helper functions/constants at package roots. | | Consumer package-root implementation helpers | The exact inventory below has only same-package production callers. Production namespace imports mount plugin contracts without reading helper properties; named root consumers are tests. | Retain plugin contracts and stable error codes; move tests to package-local modules or public behavior and stop exporting the listed helpers at package roots. | diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml new file mode 100644 index 0000000000..2aabfdf8cc --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-fold-compaction-package-split.md: 37be6de84356549d27a8fc32b6589130eb1f27b8 +2026-07-19-fold-compaction-package-split.zh.md: f6609add00826ba472f8c82e0a67613ca201fd30 diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md new file mode 100644 index 0000000000..37be6de843 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md @@ -0,0 +1,37 @@ +# RFC: Fold the single compaction backend into its service package + +Status: proposed + +English | [中文](2026-07-19-fold-compaction-package-split.zh.md) + +## Problem + +Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. + +The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. + +## Proposal + +Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. + +Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. + +Amend the implemented compaction decision and the [recallable-compaction proposal](../feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. + +## Alternatives considered + +**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. + +**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. + +## Acceptance criteria + +- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. +- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. +- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. +- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. +- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. + +## Risks + +This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md new file mode 100644 index 0000000000..f6609add00 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md @@ -0,0 +1,37 @@ +# RFC: 将唯一的压缩后端并入服务包 + +Status: proposed + +[English](2026-07-19-fold-compaction-package-split.md) | 中文 + +## 问题 + +压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 + +该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 + +## 提案 + +把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 + +保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 + +如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 + +## 备选方案 + +**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 + +**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 + +## 验收标准 + +- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 +- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 +- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 +- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 +- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 + +## 风险 + +这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml new file mode 100644 index 0000000000..b515d611f5 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-make-jsonrpc-directional.md: 4531cb251c4d12c9f2d700c9297bdee87e284779 +2026-07-19-make-jsonrpc-directional.zh.md: fb9bd06a9817357112b1eba2f41130ce2368d0b9 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md new file mode 100644 index 0000000000..4531cb251c --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -0,0 +1,38 @@ +# RFC: Make JSON-RPC completion and transport directional + +Status: proposed + +English | [中文](2026-07-19-make-jsonrpc-directional.zh.md) + +## Problem + +The JSON-RPC bridge models both endpoints as symmetric peers although the shipped protocol is directional. The TypeScript server accepts requests and emits responses or notifications, but its transport also implements unused outbound requests and inbound notification dispatch. The Python SDK sends requests and receives responses or notifications, but it also queues unused inbound server requests and exposes response helpers. + +`session/prompt` also reports one settled turn through two protocol shapes. The server emits `session.finished` and then returns the constant `{ accepted: true }`; the Python SDK discards that response and waits for the notification to recover the status. Because the response is written only after the handler returns, the notification necessarily precedes the constant response on the same stream. + +The unused halves add pending-request maps, generated IDs, request queues, close-time rejection paths, response helpers, and a second completion waiter without serving a production caller. + +## Proposal + +Specialize each endpoint to its actual role. The TypeScript transport will retain inbound requests, outbound responses, and outbound notifications. The Python client will retain outbound requests and inbound responses or notifications. Delete the opposite-direction request machinery from each side. + +Return the settled outcome directly from `session/prompt` as `{ status, reason }` after `agent.whenIdle()`. Delete `session.finished`, the constant acceptance response, and the Python post-response completion loop. `session.event` and subagent notifications still stream before the response, and durable session events remain the source for final-response reconstruction. + +## Alternatives considered + +**Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer today. + +**Keep `session.finished` for streaming clients.** Turn settlement is not incremental data: the request response already marks the same boundary and follows all earlier notifications on the ordered stream. A second terminal notification creates two representations that clients must reconcile. + +## Acceptance criteria + +- The TypeScript endpoint cannot originate requests or consume notifications. +- The Python endpoint cannot originate notifications or consume server requests. +- `session/prompt` returns the authoritative `ok`, `error`, or `aborted` outcome and reason after turn settlement. +- Session events and subagent lifecycle notifications emitted during the turn arrive before the response. +- Same-session overlap rejection, framing, multibyte input, handler errors, flush, shutdown ordering, and final-response reconstruction retain their behavior. +- TypeScript bridge tests, Python SDK tests, built JSON-RPC coverage, snapshots, and generated API documentation pass. + +## Risks + +This deliberately narrows the pre-release wire protocol. Raw clients listening only for `session.finished`, or embedders using the unused symmetric transport methods, must move to the prompt response. A future server-initiated request requires a new typed protocol addition rather than reusing generic dormant machinery. diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md new file mode 100644 index 0000000000..fb9bd06a98 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -0,0 +1,38 @@ +# RFC: 让 JSON-RPC 完成结果与传输方向单一化 + +Status: proposed + +[English](2026-07-19-make-jsonrpc-directional.md) | 中文 + +## 问题 + +JSON-RPC 桥接层把两个端点都建模为对称的对等端，但实际协议具有固定方向。TypeScript 服务端接收请求并发出响应或通知，其传输层却还实现了未使用的出站请求和入站通知分发。Python SDK 发送请求并接收响应或通知，却还会把未使用的服务端入站请求放入队列，并公开响应辅助方法。 + +`session/prompt` 还会用两种协议结构报告同一个已结束轮次。服务端先发出 `session.finished`，再返回常量 `{ accepted: true }`；Python SDK 丢弃该响应，转而等待通知以取得状态。响应只有在处理函数返回后才会写入，因此在同一条有序流上，通知必然先于这个常量响应。 + +这些未使用的双向能力引入了待处理请求表、生成 ID、请求队列、关闭时的拒绝路径、响应辅助方法和第二套完成等待逻辑，却没有任何生产调用方使用。 + +## 提案 + +按实际角色收窄两个端点。TypeScript 传输层只保留入站请求、出站响应和出站通知。Python 客户端只保留出站请求以及入站响应或通知。删除两侧与实际方向相反的请求机制。 + +在 `agent.whenIdle()` 完成后，由 `session/prompt` 直接返回 `{ status, reason }` 作为轮次结果。删除 `session.finished`、常量接纳响应以及 Python 中响应后的完成等待循环。`session.event` 与 subagent 通知仍在响应前流式发出，持久会话事件仍是最终响应重建的真源。 + +## 备选方案 + +**为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但当前没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 + +**为流式客户端保留 `session.finished`。** 轮次结束不是增量数据：请求响应已经标识同一个边界，并且在有序流中位于先前所有通知之后。第二条终止通知会产生两种结果表示，迫使客户端进行协调。 + +## 验收标准 + +- TypeScript 端点无法发起请求，也不消费通知。 +- Python 端点无法发起通知，也不消费服务端请求。 +- 轮次结束后，`session/prompt` 返回权威的 `ok`、`error` 或 `aborted` 状态及其原因。 +- 轮次中发出的会话事件与 subagent 生命周期通知都先于响应到达。 +- 同一会话的重叠拒绝、分帧、多字节输入、处理器错误、flush、关闭顺序与最终响应重建保持原有行为。 +- TypeScript 桥接测试、Python SDK 测试、构建后 JSON-RPC 覆盖、快照和生成的 API 文档全部通过。 + +## 风险 + +本提案会刻意收窄预发布协议格式。仅监听 `session.finished` 的原始客户端，以及使用未使用对称传输方法的嵌入方，都必须改为读取请求响应。未来若需要服务端发起请求，应新增类型化协议，而不是复用休眠的通用机制。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml new file mode 100644 index 0000000000..37c3c8b508 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-retire-subagent-mock-package.md: 2731d35448cbc4dc9db4c92579c35202a53eefdd +2026-07-19-retire-subagent-mock-package.zh.md: 919c56502227157465277cc07c23fb7096763684 diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md new file mode 100644 index 0000000000..2731d35448 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md @@ -0,0 +1,35 @@ +# RFC: Retire the standalone subagent mock package + +Status: proposed + +English | [中文](2026-07-19-retire-subagent-mock-package.zh.md) + +## Problem + +`@deepseek-ai/dsh-subagent-mock` is a configurable test double packaged as a workspace plugin. Its only external consumers are the `tool-subagent` unit suite and the tool-catalog generator. No runtime package, example, snapshot configuration, or real provider loads it. + +That narrow fixture carries a manifest, exports, peer and development dependencies, project references, package README obligations, Loader composition tests, module-graph membership, and documentation-gate exceptions. The tool-catalog generator mounts it only to make the real subagent tool register its schema; it never executes a child. + +## Proposal + +Delete `packages/support/subagent-mock`. Move the scripted provider behavior actually used by `tool-subagent` into a package-local test fixture while continuing to exercise the real `SubagentService`, provider registry, and tool implementation. + +Have the tool-catalog generator register the minimal provider descriptor required before mounting `ToolSubagent`. Remove the package references, manifest dependency, graph node, README allowlists, and mock-specific Loader tests. + +## Alternatives considered + +**Keep a reusable mock package for future tests.** Reuse has not materialized outside one test file and one generator. A future second consumer can extract a fixture once its shared contract is known; packaging all configurable reply, cancellation, result, and Loader behavior today makes test infrastructure look like a supported backend. + +**Generate the subagent schema without mounting the real tool.** Hand-constructing or importing the schema would weaken the catalog's check that the production registry and tool composition expose the documented shape. The generator should keep mounting the real service and tool with only the child boundary replaced. + +## Acceptance criteria + +- `packages/support/subagent-mock` and every workspace, graph, dependency, and documentation entry for it are removed. +- `tool-subagent` tests retain every scripted reply, structured-result, cancellation, foreground/background, and task-integration case they currently exercise through the real service and tool. +- Tool-catalog generation mounts the production subagent registry and tool with a minimal local provider and produces a byte-identical catalog. +- No runtime or example package gains a dependency on test-only fixtures. +- Focused subagent tests, catalog and graph generation, module-graph verification, build, hygiene, and the full pre-push suite pass. + +## Risks + +Relocating the fixture could accidentally replace too much production composition with a stub. The local fixture must implement only the nondeterministic child boundary; capability checks, lifecycle, task handling, and tool output remain under production code. Mock Loader and HMR coverage can disappear because no deployed composition consumes the package afterward. diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md new file mode 100644 index 0000000000..919c565022 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md @@ -0,0 +1,35 @@ +# RFC: 撤销独立的 subagent mock 包 + +Status: proposed + +[English](2026-07-19-retire-subagent-mock-package.md) | 中文 + +## 问题 + +`@deepseek-ai/dsh-subagent-mock` 是一个以工作区插件形式发布的可配置测试替身。它仅有两个外部消费方：`tool-subagent` 单元测试和工具目录生成器。运行时包、示例、快照配置和真实提供方都不会加载它。 + +这个用途狭窄的 fixture（测试前置数据）需要维护 manifest（元数据清单）、导出、对等依赖（peer dependency）与开发依赖、项目引用、包（package）README 契约、Loader 组合测试、模块图成员关系以及文档门禁例外。工具目录生成器挂载它，只是为了让真实 subagent 工具注册 schema；生成器从不执行子 agent。 + +## 提案 + +删除 `packages/support/subagent-mock`。把 `tool-subagent` 实际使用的脚本化提供方行为移入该包的本地测试 fixture，同时继续测试真实的 `SubagentService`、提供方注册表和工具实现。 + +工具目录生成器在挂载 `ToolSubagent` 前，只注册所需的最小提供方描述。删除该包的项目引用、manifest 依赖、图节点、README 允许列表和 mock 专用 Loader 测试。 + +## 备选方案 + +**为未来测试保留可复用 mock 包。** 除一个测试文件和一个生成器外，复用需求并未出现。未来产生第二个消费方时，可以在共享契约明确后再提取 fixture；当前把所有可配置回复、取消、结果与 Loader 行为打包，会使测试基础设施看起来像受支持的后端。 + +**不挂载真实工具，直接生成 subagent schema。** 手工构造或直接导入 schema，会削弱目录生成器对生产注册表与工具组合是否公开文档结构的校验。生成器应继续挂载真实服务与工具，只替换不确定的子 agent 边界。 + +## 验收标准 + +- 删除 `packages/support/subagent-mock`，并移除其全部工作区、图、依赖和文档条目。 +- `tool-subagent` 测试保留当前通过真实服务与工具覆盖的全部脚本化回复、结构化结果、取消、前台与后台运行以及任务集成用例。 +- 工具目录生成器使用最小本地提供方挂载生产 subagent 注册表与工具，并生成字节级一致的目录。 +- 运行时包与示例包都不会新增对测试专用 fixture 的依赖。 +- 聚焦 subagent 测试、目录与图生成、模块图校验、构建、hygiene 和完整 pre-push 门禁全部通过。 + +## 风险 + +迁移 fixture 时，可能会误将过多生产组合替换成测试替身。本地 fixture 只能实现不确定的 subagent 边界；能力检查、生命周期、任务处理与工具输出仍由生产代码负责。由于之后不再有部署组合消费该包，可以删除 mock 的 Loader 与 HMR 覆盖。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml new file mode 100644 index 0000000000..adee0c347d --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-use-one-session-surface-manager.md: f351c05cf5cb5d408aeb22c8c3e6ac5c575fc24a +2026-07-19-use-one-session-surface-manager.zh.md: 20c1f04f7b4197549f23145aa2c6015cd44f38cc diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md new file mode 100644 index 0000000000..f351c05cf5 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md @@ -0,0 +1,35 @@ +# RFC: Use one surface manager per session + +Status: proposed + +English | [中文](2026-07-19-use-one-session-surface-manager.zh.md) + +## Problem + +`Session` maintains two `SurfaceManager` instances over the same append-only event log. `surfaceValidator` eagerly validates seed and append candidates, while the lazy `_surface` independently folds committed events for `session.surface`, derived messages, compaction, and workspace context. Once the public surface is read, every later event advances duplicate node and replacement-generation state. + +The [session surface decision](../../implemented/architecture/2026-06-18-session-surface.md) calls for one ordered surface and one representation to validate. The second manager does not create an independent authority or protect a different failure boundary; it repeats the canonical fold and gives the two views a state-drift opportunity. + +## Proposal + +Keep one `SurfaceManager` per `Session`. Seed and append acceptance continue to call `validateNext()` before committing an event, and the public surface view reads `nodes` and `replaceGeneration` from that same manager. + +Expose only the readonly surface contract from `Session.surface`; candidate validation remains owned by `Session`. Retain `foldSurface()` as the detached full-log replay function used by offline validation and reconstruction. + +## Alternatives considered + +**Keep acceptance and projection state separate.** Separate instances appear to isolate public reads from validation, but ordinary callers already receive borrowed surface state and cannot mutate it through the declared readonly contract. A cast that mutates the returned node array already corrupts derived history; duplicating the manager is not a sound runtime trust boundary. + +**Recompute the public surface from the full log on every access.** This removes cached duplicate state but gives up incremental derivation and makes repeated request construction scale with complete session history. + +## Acceptance criteria + +- A live `Session` owns exactly one incremental `SurfaceManager`. +- Seed and append candidates are validated before publication with no partial surface mutation on rejection. +- `session.surface`, derived messages, compaction, and workspace context observe the same nodes and replacement generation as the acceptance path. +- `foldSurface()` remains available for detached replay and agrees with the live manager for every accepted prefix. +- Session surface, seed, request reconstruction, compaction tool-pairing, and workspace-context tests pass. + +## Risks + +Sharing one manager makes the readonly borrowed-state contract more important because a hostile cast could corrupt both validation and projection state. The implementation should return a narrowed view and keep mutation methods inaccessible through `Session.surface`; JavaScript callers that deliberately bypass the type contract remain outside the supported same-process boundary. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md new file mode 100644 index 0000000000..20c1f04f7b --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -0,0 +1,35 @@ +# RFC: 每个会话只使用一个表层管理器 + +Status: proposed + +[English](2026-07-19-use-one-session-surface-manager.md) | 中文 + +## 问题 + +`Session` 针对同一份仅追加事件日志维护两个 `SurfaceManager` 实例。`surfaceValidator` 主动校验种子事件与追加候选事件，延迟创建的 `_surface` 则独立折叠已提交事件，供 `session.surface`、派生消息、压缩（compaction）和工作区上下文使用。一旦读取公共表层，之后的每个事件都会推进两份重复的节点状态与替换代数状态。 + +[会话表层决策](../../implemented/architecture/2026-06-18-session-surface.md)要求系统只保留一个有序表层，并使用一种表示完成校验。第二个管理器既不形成独立真源，也不保护不同的失败边界；它只会重复规范折叠，并使两个视图可能出现状态偏差。 + +## 提案 + +每个 `Session` 只保留一个 `SurfaceManager`。种子事件与追加事件的接纳流程仍在提交事件之前调用 `validateNext()`，公共表层视图则从同一个管理器读取 `nodes` 与 `replaceGeneration`。 + +`Session.surface` 只公开只读表层契约，候选事件校验仍由 `Session` 负责。保留 `foldSurface()`，用于离线校验与重建时执行分离的完整日志回放。 + +## 备选方案 + +**继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但普通调用方目前取得的就是借用的表层状态，无法通过声明的只读契约修改它。通过类型断言修改返回的节点数组，本就会破坏派生历史；复制管理器并不能构成可靠的运行时信任边界。 + +**每次读取都根据完整日志重新计算公共表层。** 该方案不再缓存重复状态，但会放弃增量派生，使每次请求构造都随完整会话历史增长。 + +## 验收标准 + +- 每个活跃 `Session` 只拥有一个增量 `SurfaceManager`。 +- 种子事件与追加候选事件都在发布前完成校验，拒绝事件时不会留下只修改一半的表层状态。 +- `session.surface`、派生消息、压缩和工作区上下文观察到的节点与替换代数，和接纳路径使用的状态完全一致。 +- `foldSurface()` 仍可用于分离回放，并且对任意已接纳前缀都与活跃管理器一致。 +- 会话表层、种子、请求重建、压缩工具配对和工作区上下文测试全部通过。 + +## 风险 + +共享一个管理器会提高只读借用状态契约的重要性，因为恶意类型断言可能同时破坏校验状态和投影视图。实现应返回收窄后的视图，避免通过 `Session.surface` 暴露修改方法；刻意绕过类型契约的 JavaScript 调用方不属于受支持的同进程边界。 From 0c911172e959d16fdf54a0cd1d927f4cb23c997b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:45:04 +0800 Subject: [PATCH 138/140] docs: drop rejected compaction RFC --- docs/rfc/INDEX.md | 1 - ...19-fold-compaction-package-split.i18n.yaml | 6 --- ...026-07-19-fold-compaction-package-split.md | 37 ------------------- ...-07-19-fold-compaction-package-split.zh.md | 37 ------------------- 4 files changed, 81 deletions(-) delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 99ea97d16a..4dc9b229ff 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -21,7 +21,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | -| [Fold the single compaction backend into its service package](proposed/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | | [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | | [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | | [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml deleted file mode 100644 index 2aabfdf8cc..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-19-fold-compaction-package-split.md: 37be6de84356549d27a8fc32b6589130eb1f27b8 -2026-07-19-fold-compaction-package-split.zh.md: f6609add00826ba472f8c82e0a67613ca201fd30 diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md deleted file mode 100644 index 37be6de843..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md +++ /dev/null @@ -1,37 +0,0 @@ -# RFC: Fold the single compaction backend into its service package - -Status: proposed - -English | [中文](2026-07-19-fold-compaction-package-split.zh.md) - -## Problem - -Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. - -The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. - -## Proposal - -Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. - -Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. - -Amend the implemented compaction decision and the [recallable-compaction proposal](../feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. - -## Alternatives considered - -**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. - -**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. - -## Acceptance criteria - -- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. -- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. -- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. -- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. -- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. - -## Risks - -This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md deleted file mode 100644 index f6609add00..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md +++ /dev/null @@ -1,37 +0,0 @@ -# RFC: 将唯一的压缩后端并入服务包 - -Status: proposed - -[English](2026-07-19-fold-compaction-package-split.md) | 中文 - -## 问题 - -压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 - -该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 - -## 提案 - -把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 - -保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 - -如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 - -## 备选方案 - -**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 - -**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 - -## 验收标准 - -- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 -- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 -- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 -- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 -- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 - -## 风险 - -这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。 From 89416002736122864b0eb1530350ad78ef090b26 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:59:23 +0800 Subject: [PATCH 139/140] docs: expand simplification RFC implementation plans --- .../2026-07-19-make-jsonrpc-directional.i18n.yaml | 4 ++-- .../simplification/2026-07-19-make-jsonrpc-directional.md | 8 ++++++++ .../2026-07-19-make-jsonrpc-directional.zh.md | 8 ++++++++ .../2026-07-19-use-one-session-surface-manager.i18n.yaml | 4 ++-- .../2026-07-19-use-one-session-surface-manager.md | 8 ++++++++ .../2026-07-19-use-one-session-surface-manager.zh.md | 8 ++++++++ 6 files changed, 36 insertions(+), 4 deletions(-) diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml index b515d611f5..e04aed96a6 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-make-jsonrpc-directional.md: 4531cb251c4d12c9f2d700c9297bdee87e284779 -2026-07-19-make-jsonrpc-directional.zh.md: fb9bd06a9817357112b1eba2f41130ce2368d0b9 +2026-07-19-make-jsonrpc-directional.md: 2a9579c53c111887e9d93cf02cc832304a496795 +2026-07-19-make-jsonrpc-directional.zh.md: 4f3793f1b4de3b4f69c4219c10fe5b3b360c8692 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md index 4531cb251c..2a9579c53c 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -18,6 +18,14 @@ Specialize each endpoint to its actual role. The TypeScript transport will retai Return the settled outcome directly from `session/prompt` as `{ status, reason }` after `agent.whenIdle()`. Delete `session.finished`, the constant acceptance response, and the Python post-response completion loop. `session.event` and subagent notifications still stream before the response, and durable session events remain the source for final-response reconstruction. +## Implementation plan + +1. In `packages/ui/jsonrpc/src/server.ts`, replace `SessionPromptResult.accepted` with `status: 'ok' | 'error' | 'aborted'` and the captured `TurnEndReason`. `HarnessSdkServer.prompt()` will return `completed` as `ok`, `aborted` as `aborted`, and every other current or merge-extensible reason as `error`; reaching idle without a `turn/end` remains an invariant error. Remove only `session.finished`, leaving `session.event`, `subagent.started`, and `subagent.finished` unchanged. +2. In `packages/ui/jsonrpc/src/transport.ts`, replace `JsonRpcTransportPeer` with a server-side notification surface and retain `onRequest()`, `notify()`, `start()`, `flush()`, and `close()`. Remove generated request IDs, the pending-response map, outbound `request()`, inbound response and notification dispatch, and close-time pending-request rejection. Incoming response- and notification-shaped frames will be ignored, while request result, method-not-found, and handler-error responses retain their current behavior and remain ordered after notifications emitted by the awaited handler. +3. In `python/sdk/src/deepseek_harness/client.py`, `models.py`, and `__init__.py`, remove `IncomingRequest`, `_requests`, `notify()`, `next_request()`, `respond()`, and `respond_error()`. Add a public validated `SessionPromptResponse` carrying status and reason, return it from `session_prompt()`, and keep an explicit reader guard that ignores unexpected server-request frames instead of allowing them to match a response waiter. +4. In `python/sdk/src/deepseek_harness/api.py`, build `TurnResult.status` and a new `TurnResult.reason` from `SessionPromptResponse`, then delete the `session.finished` branch and second completion loop. Keep the subscription open during the request and preserve `_request_raw()`'s final notification drain so the last `turn/end` event and any subagent notification written before the response are collected before `Session.run()` reconstructs the final assistant message. +5. Replace the symmetric transport-pair cases in `packages/ui/jsonrpc/tests/transport.spec.ts` with raw client-input/server-output coverage, and update `server.spec.ts`, `plugin-apply.spec.ts`, and `built-scope-carrier.e2e.ts` for direct outcomes, ordering, overlap, shutdown, and the narrowed fake. Update `python/sdk/tests/test_client.py` for response-based settlement, unexpected-request-frame handling, callback and concurrency behavior, and the removed public helpers. Update the JSON-RPC and bilingual Python SDK READMEs, export JSDoc and declarations, `scripts/smoke-python-runtime.py`, and the Python single-executable snapshot. + ## Alternatives considered **Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer today. diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md index fb9bd06a98..4f3793f1b4 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -18,6 +18,14 @@ JSON-RPC 桥接层把两个端点都建模为对称的对等端，但实际协 在 `agent.whenIdle()` 完成后，由 `session/prompt` 直接返回 `{ status, reason }` 作为轮次结果。删除 `session.finished`、常量接纳响应以及 Python 中响应后的完成等待循环。`session.event` 与 subagent 通知仍在响应前流式发出，持久会话事件仍是最终响应重建的真源。 +## 实施计划 + +1. 在 `packages/ui/jsonrpc/src/server.ts` 中，用 `status: 'ok' | 'error' | 'aborted'` 和捕获的 `TurnEndReason` 替换 `SessionPromptResult.accepted`。`HarnessSdkServer.prompt()` 把 `completed` 映射为 `ok`，把 `aborted` 映射为 `aborted`，把其他当前或可合并扩展的原因映射为 `error`；进入空闲状态却没有 `turn/end` 仍视为不变量错误。只删除 `session.finished`，保持 `session.event`、`subagent.started` 和 `subagent.finished` 不变。 +2. 在 `packages/ui/jsonrpc/src/transport.ts` 中，用服务端通知接口替换 `JsonRpcTransportPeer`，并保留 `onRequest()`、`notify()`、`start()`、`flush()` 和 `close()`。删除生成的请求 ID、待处理响应表、出站 `request()`、入站响应与通知分发，以及关闭时对待处理请求的拒绝逻辑。入站响应结构和通知结构将被忽略；请求结果、方法不存在与处理器错误响应保持原有行为，并继续排在被等待处理器发出的通知之后。 +3. 在 `python/sdk/src/deepseek_harness/client.py`、`models.py` 和 `__init__.py` 中，删除 `IncomingRequest`、`_requests`、`notify()`、`next_request()`、`respond()` 和 `respond_error()`。新增公开且经过校验的 `SessionPromptResponse` 来携带状态与原因，由 `session_prompt()` 返回该对象，并保留明确的读取保护：忽略意外的服务端请求帧，避免它们命中响应等待器。 +4. 在 `python/sdk/src/deepseek_harness/api.py` 中，根据 `SessionPromptResponse` 构造 `TurnResult.status` 和新增的 `TurnResult.reason`，再删除 `session.finished` 分支与第二个完成循环。请求期间保持订阅打开，并保留 `_request_raw()` 最后的通知排空步骤，确保写在响应前的最后一条 `turn/end` 事件与任何 subagent 通知，都会在 `Session.run()` 重建最终助手消息之前被收集。 +5. 用原始客户端输入与服务端输出覆盖替换 `packages/ui/jsonrpc/tests/transport.spec.ts` 中的对称传输对用例，并更新 `server.spec.ts`、`plugin-apply.spec.ts` 和 `built-scope-carrier.e2e.ts`，覆盖直接结果、顺序、重叠、关闭和收窄后的伪实现。更新 `python/sdk/tests/test_client.py`，覆盖基于响应的结束流程、意外请求帧处理、回调与并发行为，以及已删除的公开辅助方法。同步更新 JSON-RPC README、双语 Python SDK README、导出 JSDoc 与声明、`scripts/smoke-python-runtime.py` 和 Python 单可执行文件快照。 + ## 备选方案 **为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但当前没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml index adee0c347d..185d7af4ac 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-use-one-session-surface-manager.md: f351c05cf5cb5d408aeb22c8c3e6ac5c575fc24a -2026-07-19-use-one-session-surface-manager.zh.md: 20c1f04f7b4197549f23145aa2c6015cd44f38cc +2026-07-19-use-one-session-surface-manager.md: 0e4fa14b21f5054e1ace425712506c5c060f2251 +2026-07-19-use-one-session-surface-manager.zh.md: 26126310eefaf56aa45efc428a54e65f0cf35947 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md index f351c05cf5..0e4fa14b21 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md @@ -16,6 +16,14 @@ Keep one `SurfaceManager` per `Session`. Seed and append acceptance continue to Expose only the readonly surface contract from `Session.surface`; candidate validation remains owned by `Session`. Retain `foldSurface()` as the detached full-log replay function used by offline validation and reconstruction. +## Implementation plan + +1. In `packages/core/session/src/surface.ts`, export a structural `SessionSurface` contract containing only readonly `nodes` and `replaceGeneration`, and make `SurfaceManager` implement it. Re-export that type from `packages/core/session/src/index.ts` so `Session.surface` no longer exposes `validateNext()` through its declaration. +2. In `Session`, replace `surfaceValidator` and lazy `_surface` with one eagerly constructed `surfaceManager`. Route seed and append validation through that manager and return it from `get surface(): SessionSurface`; `deriveMessages()` will read the same nodes and generation. `validateNext()` may synchronize already committed log entries, but it must only plan the uncommitted candidate. The candidate reaches manager state after `log.push()` and the next delta synchronization, so rejection by surface validation or pre-commit `internal/dispatch` cannot leave phantom state. +3. Keep `foldSurface()` and the transition functions in `surface.ts` unchanged. Compile and exercise the direct consumers in `packages/compact/compact/src/tool-pairing.ts`, `packages/compact/compact-basic/src/region.ts`, and `packages/context/workspace-context/src/state.ts`; they continue to consume only nodes and replacement generation. +4. Extend `packages/core/session/tests/surface.spec.ts` to read the public view before an invalid candidate, prove that nodes and generation remain at the accepted prefix after rejection, append a later valid event, and compare every resulting prefix with `foldSurface()`. Add an `internal/dispatch` veto case and a type-level `SessionSurface` assertion in `session.spec.ts`, while retaining the seeded replay, delta-growth, replacement, generation, and derived-cache cases. +5. Run the request-reconstruction, compaction tool-pairing, compaction range, and workspace-context regression suites that consume the surface. In the implementation PR, update `packages/core/session/README.md`, `docs/core-data-structures/session.md`, the implemented session-surface RFC and its Chinese counterpart, the translation record, `scripts/type-equiv.manifest.json`, and the generated RFC index before moving this RFC pair to `implemented/`. + ## Alternatives considered **Keep acceptance and projection state separate.** Separate instances appear to isolate public reads from validation, but ordinary callers already receive borrowed surface state and cannot mutate it through the declared readonly contract. A cast that mutates the returned node array already corrupts derived history; duplicating the manager is not a sound runtime trust boundary. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md index 20c1f04f7b..26126310ee 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -16,6 +16,14 @@ Status: proposed `Session.surface` 只公开只读表层契约，候选事件校验仍由 `Session` 负责。保留 `foldSurface()`，用于离线校验与重建时执行分离的完整日志回放。 +## 实施计划 + +1. 在 `packages/core/session/src/surface.ts` 中，导出结构化的 `SessionSurface` 契约，只包含只读的 `nodes` 与 `replaceGeneration`，并让 `SurfaceManager` 实现该契约。从 `packages/core/session/src/index.ts` 重新导出这个类型，使 `Session.surface` 的声明不再暴露 `validateNext()`。 +2. 在 `Session` 中，用一个主动创建的 `surfaceManager` 替换 `surfaceValidator` 与延迟创建的 `_surface`。种子事件与追加事件都通过该管理器校验，`get surface(): SessionSurface` 返回同一个对象，`deriveMessages()` 也读取同一份节点与代数。`validateNext()` 可以同步已提交的日志事件，但对尚未提交的候选事件只能制定变更计划。候选事件在 `log.push()` 之后、下一次增量同步时才进入管理器状态，因此表层校验拒绝或提交前 `internal/dispatch` 否决都不会留下虚假状态。 +3. 保持 `foldSurface()` 与 `surface.ts` 中的状态转换函数不变。编译并验证 `packages/compact/compact/src/tool-pairing.ts`、`packages/compact/compact-basic/src/region.ts` 和 `packages/context/workspace-context/src/state.ts` 中的直接消费方；它们仍然只读取节点与替换代数。 +4. 扩展 `packages/core/session/tests/surface.spec.ts`：先读取公共视图，再提交无效候选事件，证明拒绝后节点与代数仍停留在已接纳前缀；随后追加有效事件，并把每个结果前缀与 `foldSurface()` 比较。在 `session.spec.ts` 中新增 `internal/dispatch` 否决用例与类型层面的 `SessionSurface` 断言，同时保留种子回放、增量增长、替换、代数和派生缓存用例。 +5. 运行消费表层的请求重建、压缩工具配对、压缩范围与工作区上下文回归套件。在实现 PR 中，先更新 `packages/core/session/README.md`、`docs/core-data-structures/session.md`、已实现会话表层 RFC 及其中文对应文件、翻译记录、`scripts/type-equiv.manifest.json` 和生成的 RFC 索引，再把本 RFC 双语文件移入 `implemented/`。 + ## 备选方案 **继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但普通调用方目前取得的就是借用的表层状态，无法通过声明的只读契约修改它。通过类型断言修改返回的节点数组，本就会破坏派生历史；复制管理器并不能构成可靠的运行时信任边界。 From bca74015130ed89295d8d83f33979c491a637854 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:12:26 +0800 Subject: [PATCH 140/140] docs: retain rejected compaction RFC --- docs/rfc/INDEX.md | 1 + ...19-fold-compaction-package-split.i18n.yaml | 6 +++ ...026-07-19-fold-compaction-package-split.md | 37 +++++++++++++++++++ ...-07-19-fold-compaction-package-split.zh.md | 37 +++++++++++++++++++ 4 files changed, 81 insertions(+) create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 4dc9b229ff..ec88f76c2d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -233,6 +233,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune the unimplemented subagent seam vocabulary](rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md) | 2026-07-04 | | [Collapse workflows to the exercised foreground core](rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md) | 2026-07-12 | | [Prune unused skill registry surface](rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md) | 2026-07-12 | +| [Fold the single compaction backend into its service package](rejected/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml new file mode 100644 index 0000000000..d2a15cc2c2 --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-fold-compaction-package-split.md: 7c7a2da85beb956f8d6c24f813fc33aa350b5c0e +2026-07-19-fold-compaction-package-split.zh.md: 37d75671d57226742608a525ea711b34780e65c6 diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md new file mode 100644 index 0000000000..7c7a2da85b --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md @@ -0,0 +1,37 @@ +# RFC: Fold the single compaction backend into its service package + +Status: rejected — More compaction backends are planned, so the interface and basic implementation packages remain separate. + +English | [中文](2026-07-19-fold-compaction-package-split.zh.md) + +## Problem + +Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. + +The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. + +## Proposal + +Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. + +Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. + +Amend the implemented compaction decision and the [recallable-compaction proposal](../../proposed/feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. + +## Alternatives considered + +**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. + +**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. + +## Acceptance criteria + +- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. +- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. +- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. +- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. +- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. + +## Risks + +This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md new file mode 100644 index 0000000000..37d75671d5 --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md @@ -0,0 +1,37 @@ +# RFC: 将唯一的压缩后端并入服务包 + +Status: rejected — 计划增加更多压缩后端，因此接口包与 basic 实现包继续分离。 + +[English](2026-07-19-fold-compaction-package-split.md) | 中文 + +## 问题 + +压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 + +该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 + +## 提案 + +把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 + +保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 + +如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../../proposed/feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 + +## 备选方案 + +**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 + +**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 + +## 验收标准 + +- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 +- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 +- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 +- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 +- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 + +## 风险 + +这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。