From 9c78a7df33eace02b29e5539f8c5df107b18f8c3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 28 Jul 2026 17:26:03 +0800 Subject: [PATCH] test(snapshot): share identical header sidecars --- .../2026-06-19-acp-snapshot-tests.i18n.yaml | 6 +- .../testing/2026-06-19-acp-snapshot-tests.md | 5 +- .../2026-06-19-acp-snapshot-tests.zh.md | 5 +- examples/acp-agent/tests/acp.snapshot.ts | 28 +- .../both-mode-turn/system-prompt.expected.md | 401 --------------- .../system-prompt.expected.md | 401 --------------- .../tool-schemas.expected.json | 26 - .../tool-schemas.expected.json | 473 ------------------ .../skill-load/system-prompt.expected.md | 25 - .../skill-load/tool-schemas.expected.json | 473 ------------------ .../tool-schemas.expected.json | 473 ------------------ .../support/acp-snapshot/README.i18n.yaml | 4 +- packages/support/acp-snapshot/README.md | 6 +- packages/support/acp-snapshot/README.zh.md | 6 +- packages/support/acp-snapshot/src/suite.ts | 240 +++++++-- .../fixtures/suite/shared-pin/behavior.json | 12 + .../fixtures/suite/shared-pin/input.json | 1 + .../fixtures/suite/shared-pin/session.jsonl | 4 + .../suite/shared-pin/stdout.expected.jsonl | 4 + .../support/acp-snapshot/tests/suite.spec.ts | 165 ++++++ 20 files changed, 433 insertions(+), 2325 deletions(-) delete mode 100644 examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md delete mode 100644 examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md delete mode 100644 examples/acp-agent/tests/snapshots/code-mode-workspace-context/tool-schemas.expected.json delete mode 100644 examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json delete mode 100644 examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md delete mode 100644 examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json delete mode 100644 examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/behavior.json create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/input.json create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/session.jsonl create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/stdout.expected.jsonl diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml index 13d4b4e495..48850b2a53 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml @@ -1,6 +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 -2026-06-19-acp-snapshot-tests.md: 430441e633af1e487f19272900360a8ed2f595c9 -2026-06-19-acp-snapshot-tests.zh.md: 243e431567b45d69e1fe16dda5d07ec058403b7c +# pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md +2026-06-19-acp-snapshot-tests.md: ba46682b3087e3d2ff4c52d2ad22f54b7dac31db +2026-06-19-acp-snapshot-tests.zh.md: 58195c47889edb31d5122116328928f916ad09a9 diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md index 430441e633..ba46682b30 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -53,7 +53,7 @@ Replay uses a `cordis.snapshot.yml` overlay that replaces the real adapter with A snapshot run asserts **two** normalized surfaces, because the harness's external surfaces are distinct: 1. The **stdout transcript** — the framed ACP JSON-RPC responses and committed-message updates an automation client receives. It catches regressions in the transport contract and is compared against a committed `stdout.expected.jsonl`. -2. The **re-persisted session JSONL**, normalized and compared with `session.jsonl`. The same fixture is both replay source and expected log. Prompt text is scrubbed; one scenario per header class pins readable prompt and tool content as described in the [header-pinning Agent Note](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md). Override scenarios derive model behavior solely from their sidecar. +2. The **re-persisted session JSONL**, normalized and compared with `session.jsonl`. The same fixture is both replay source and expected log. Prompt and tool bulk are scrubbed; one scenario per header class pins the remaining header sequence. The pin owns readable prompt and tool-schema sidecars by default, or names another pin as either source when the complete sequence is identical, so each distinct sidecar version is committed once. Fixture guards reject duplicate sidecar content, and record/refresh rejects shared claimants that generate different bytes. The original header-pinning rationale is preserved in the [header-pinning Agent Note](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md). Override scenarios derive model behavior solely from their sidecar. The surfaces are complementary: stdout covers the minimal automation wire, while JSONL covers loop, tool, and boundary structure that the wire intentionally omits. @@ -76,9 +76,10 @@ Tool determinism comes from a generated cwd, scrubbed environment, fresh non-log - **A hand-authored `llm.json` of model chunks** — the earlier draft; reusing the real session log makes the fixture a genuine product of the system rather than a hand-built mock, and doubles it as a behavioral expected output. - **A byte-level HTTP-record library (Polly/nock/MSW)** — rejected: adapter-specific, awkward with streaming SSE, and lower-level than the thing under test. - **Synthesizing throw/cancel entries from `turn/end {kind:'error'|'aborted'}`** — rejected: it couples `llm-replay` to loop-internal turn-closing semantics, and the `turn/end` reason is lossy (it cannot distinguish a thrown 401 from a finish-error); the explicit `replay.override.json` sidecar is the cleaner seam. +- **Copying both request-header sidecars beside every class pin** — rejected: prompt and tool-schema composition vary independently, so a change to one shared component would churn byte-identical files across unrelated class pins. Explicit per-component sources retain one structural pin per class without duplicating content. ## Consequences -The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here and defers any move to a transport-neutral headless suite as an independent testing change (the suite-level FIXME marks it). +The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here and defers any move to a transport-neutral headless suite as an independent testing change (the suite-level FIXME marks it). This Agent Note relates to but does not supersede the [proposed determinism Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas these snapshots pin assembled behavior plus the external automation output. They are complementary until the backend corpus moves off ACP. diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md index 243e431567..58195c4788 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md @@ -53,7 +53,7 @@ Status: implemented 快照运行断言**两个**归一化后的表面，因为 harness 的外部表面是不同的： 1. **stdout transcript**——自动化客户端收到的、经过 framing 的 ACP JSON-RPC 响应与已提交的消息更新。它捕获传输契约的回归，与已提交的 `stdout.expected.jsonl` 比较。 -2. **重新持久化的会话 JSONL**，经过规范化后与 `session.jsonl` 比较。同一 fixture 同时作为重放来源和预期日志。提示词文本会被清理；按照[请求头固定 Agent Note](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)所述，每种请求头类别由一个场景固定可读提示词与工具内容。Override 场景仅从其 sidecar 派生模型行为。 +2. **重新持久化的会话 JSONL**，经过规范化后与 `session.jsonl` 比较。同一 fixture 同时作为重放来源和预期日志。提示词与工具的主体内容会被清理；每种请求头类别由一个场景固定余下的请求头序列。该 pin 默认拥有可读的提示词与工具 schema sidecar；当完整的对应序列相同时，也可将另一个 pin 指定为其中任一来源，因此每个不同的 sidecar 版本只提交一次。fixture 保护会拒绝重复的 sidecar 内容，录制/刷新会拒绝生成不同字节的共享引用方。最初的请求头固定理由保留在[请求头固定 Agent Note](../../archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)中。Override 场景仅从其 sidecar 派生模型行为。 两个表面互补：stdout 覆盖精简的自动化线协议，JSONL 覆盖线协议有意省略的 loop、工具和 boundary 结构。 @@ -76,9 +76,10 @@ Status: implemented - **手工编写包含模型分片的 `llm.json`**——早期草案；复用真实会话日志，使 fixture 成为系统的真实产物而非手工构建的 mock，并让它同时充当行为预期输出。 - **字节级 HTTP 录制库（Polly/nock/MSW）**：否决。与适配器耦合，处理流式 SSE（Server-Sent Events）时笨拙，且层级低于被测对象。 - **从 `turn/end {kind:'error'|'aborted'}` 合成抛错/取消条目**：否决。这会将 `llm-replay` 耦合到 loop 内部的轮次关闭语义，且 `turn/end` 原因是有损的（无法区分抛出的 401 与 finish-error）；显式的 `replay.override.json` 伴随文件是更清晰的 seam。 +- **在每个类别 pin 旁复制两个请求头 sidecar**：否决。提示词与工具 schema 的组合各自独立变化，因此一个共享组件发生变更，就会使不相关类别 pin 中字节完全相同的文件产生无意义改动。显式的分组件来源可在不重复内容的情况下，为每个类别保留一个结构性 pin。 ## 后果 -该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture。记录与重放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，并把向传输无关 headless 套件的任何迁移推迟为一项独立的测试变更（套件级 FIXME 标记了这一点）。 +该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与重放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，并把向传输无关 headless 套件的任何迁移推迟为一项独立的测试变更（套件级 FIXME 标记了这一点）。 本 Agent Note 与[拟议的确定性 Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md)相关，但不取代它：该提案的“通用重放 fixture”在每次测试后重新派生会话*消息历史*（内部一致性不变量），而这些快照固定组装后的行为与外部自动化输出。在后端语料迁出 ACP 之前，两者相互补充。 diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 9987679607..6ac82baf3a 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -73,8 +73,8 @@ function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['m const SCENARIOS: Scenario[] = [ { name: 'handshake', hasModelTurn: false, recorded: false }, { name: 'reject-extra-dirs', hasModelTurn: false, recorded: false }, - // text-turn is the pinned-header scenario: the minimal single text turn. - // Its prompt and tool-schema sidecars pin the composed header. + // text-turn is the default header pin and owns the prompt and tool-schema + // sidecars reused by alternate classes with identical component sequences. { name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true }, { name: 'session-title-after-turn', @@ -116,7 +116,15 @@ const SCENARIOS: Scenario[] = [ }, { name: 'bash-tool-turn', hasModelTurn: true, recorded: true }, { name: 'todo-write', hasModelTurn: true, recorded: true }, - { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' }, + { + name: 'skill-load', + hasModelTurn: true, + recorded: false, + pinsHeader: true, + headerClass: 'skill', + systemPromptSource: 'text-turn', + toolSchemasSource: 'text-turn', + }, { name: 'lsp-definition', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'lsp', configPath: LSP_CONFIG }, // web_fetch markdown rendering end to end: the overlay's loopback fixture // server supplies deterministic HTML (entities, a GFM table, nesting), the @@ -164,6 +172,7 @@ const SCENARIOS: Scenario[] = [ overridden: true, pinsHeader: true, headerClass: 'workspace-context', + toolSchemasSource: 'text-turn', configPath: WORKSPACE_CONTEXT_CONFIG, }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, @@ -236,9 +245,19 @@ const SCENARIOS: Scenario[] = [ recorded: true, pinsHeader: true, headerClass: 'code-workspace-context', + systemPromptSource: 'code-mode-turn', + toolSchemasSource: 'code-mode-turn', configPath: CODE_MODE_WORKSPACE_CONTEXT_CONFIG, }, - { name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG }, + { + name: 'both-mode-turn', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + headerClass: 'both', + systemPromptSource: 'code-mode-turn', + configPath: BOTH_MODE_CONFIG, + }, // Machine permission scenarios use an explicit deployment policy; there is // no session-scoped UI picker on the automation protocol. { @@ -247,6 +266,7 @@ const SCENARIOS: Scenario[] = [ recorded: true, pinsHeader: true, headerClass: 'sandbox', + toolSchemasSource: 'text-turn', env: { DSH_PERMISSION_MODE: 'workspace-write' }, }, { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md deleted file mode 100644 index 0cee2a6517..0000000000 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ /dev/null @@ -1,401 +0,0 @@ -You are an AI agent powered by the DeepSeek Harness SDK. - -You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. - -Verify your work by running the code or tests. Keep answers brief and factual. - - -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - -Check the [exit code: N] marker on every bash result; investigate failures before moving on. - -Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. - -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. - -Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). - - -Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. - -Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out. - -## Writing code for run_code - -Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program: - -- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON. -- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue. -- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`. -- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need. - -The available tools: - -```ts -type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } - -interface ToolArgsMap { - /** 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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_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: { - /** The bash command to execute. */ - command: string; - /** 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". */ - description: string; - /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */ - timeoutMs?: number; - /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */ - workdir?: string; - /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */ - run_in_background?: boolean; - /** 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. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ - justification?: string; - } & Record; - /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ - create_goal: { - /** The concrete completion objective inferred from the direct human request. */ - objective: string; - /** Optional positive safe-integer limit on automatic continuation rounds. */ - max_goal_rounds?: number; - } & Record; - /** Edit an existing UTF-8 text file by replacing literal text. */ - edit: { - /** Path to edit, resolved by the filesystem backend. */ - file_path: string; - /** Literal text to replace. Must match exactly. */ - old_string: string; - /** Literal replacement text. Use an empty string to delete the match. */ - new_string: string; - /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ - replace_all?: boolean; - /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ - justification?: string; - } & Record; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ - get_goal: Record; - /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */ - ralph: { - /** The immutable completion objective for every fresh Ralph round. */ - objective: string; - /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */ - maxRounds?: number; - } & Record; - /** Read a UTF-8 text file and return line-numbered content. */ - read: { - /** Path to read, resolved by the filesystem backend. */ - file_path: string; - /** 1-based first line to return. Defaults to 1. */ - offset?: number; - /** Maximum number of lines to return. Defaults to 2000. */ - limit?: number; - } & Record; - /** 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. */ - skill: { - /** The exact skill name from the available skills list. */ - name: string; - } & Record; - /** 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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ - subagent: { - /** A short (3-5 word) description of the delegated task, for display. */ - description: string; - /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */ - prompt: string; - /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ - run_in_background?: boolean; - } & Record; - /** 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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ - subagent_fork: { - /** A short (3-5 word) description of the delegated task, for display. */ - description: string; - /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */ - prompt: string; - /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ - run_in_background?: boolean; - } & Record; - /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */ - task_kill: { - /** Task id returned by the tool that started the background work. */ - task_id: string; - /** Optional short reason, recorded in the log and forwarded to the task. */ - reason?: string; - } & Record; - /** List your background tasks (running and finished) with their ids, kinds, and statuses. */ - task_list: Record; - /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */ - task_output: { - /** Task id returned by the tool that started the background work. */ - task_id: string; - /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */ - wait?: boolean; - /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */ - timeout_ms?: number; - } & Record; - /** 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). */ - todo_write: { - /** The COMPLETE task list, replacing any previous list. */ - todos: ({ - /** What the task is — a short imperative line. */ - content: string; - /** pending (not started) | in_progress (now) | completed (done). */ - status: "pending" | "in_progress" | "completed"; - })[]; - } & Record; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ - update_goal: { - /** Exact id returned by get_goal. */ - goal_id: string; - /** Exact positive revision returned by get_goal. */ - revision: number; - /** edit | pause | resume | complete | blocked */ - action: "edit" | "pause" | "resume" | "complete" | "blocked"; - /** Replacement objective; valid only with action edit. */ - objective?: string; - /** Replacement cap; valid only with action edit. */ - max_goal_rounds?: number; - /** Concrete blocking condition; required only with action blocked. */ - blocked_reason?: string; - } & Record; - /** 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. The 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?, provider?, 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. Script-body hooks: - `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/oneOf — no 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */ - workflow: { - /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ - script: string; - /** The workflow identity block (plain JSON — never code). */ - meta: { - /** Short kebab-case workflow name. */ - name: string; - /** One-line description of what the workflow does. */ - description: string; - /** Optional guidance on when this workflow applies. */ - whenToUse?: string; - /** Optional phase declarations matched by phase() calls. */ - phases?: ({ - /** The phase title phase() calls match by exact string. */ - title: string; - /** Optional one-line description of the phase. */ - detail?: string; - /** Optional provider override this phase is expected to use. */ - provider?: string; - /** Optional model override this phase is expected to use. */ - model?: string; - } & Record)[]; - } & Record; - /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ - args?: Record; - } & Record; - /** Create or fully replace a UTF-8 text file. */ - write: { - /** Path to write, resolved by the filesystem backend. */ - file_path: string; - /** Full UTF-8 text content to write. */ - content: string; - /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ - justification?: string; - } & Record; -} - -interface ToolOutputMap { - bash: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - exitCode: number | null; - signal: string | null; - timedOut: boolean; - aborted: boolean; - timeoutMs: number; - stdout: { - text: string; - truncated: boolean; - spillPath?: string; - }; - stderr: { - text: string; - truncated: boolean; - spillPath?: string; - }; - sandbox?: { - mode: string; - denied: boolean; - enforcement?: string; - runnerFailed?: boolean; - }; - }; - create_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - edit: { - path: string; - before: string; - after: string; - }; - get_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - ralph: { - runId: string; - agentsStarted: number; - result: JsonValue; - }; - read: { - path: string; - offset: number; - lines: { - number: number; - text: string; - }[]; - totalLines: number; - }; - skill: { - name: string; - provider: string; - resourceBase?: { - kind: "directory"; - path: string; - } | { - kind: "url"; - url: string; - } | { - kind: "opaque"; - description: string; - }; - content: string; - }; - subagent: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - runId: string; - output: JsonValue[]; - }; - subagent_fork: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - runId: string; - output: JsonValue[]; - }; - task_kill: { - outcome: "cancellation-requested" | "already-finished"; - task: { - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - }; - }; - task_list: ({ - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - })[]; - task_output: { - text: string; - task: { - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - }; - }; - todo_write: { - todos: ({ - content: string; - status: "pending" | "in_progress" | "completed"; - })[]; - counts: { - pending: number; - inProgress: number; - completed: number; - }; - }; - update_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - workflow: { - runId: string; - agentsStarted: number; - result: JsonValue; - }; - write: { - path: string; - operation: "create" | "update"; - before: string | null; - after: string; - }; -} - -type ToolName = keyof ToolOutputMap - -declare class ToolCallError extends Error { - readonly name: "ToolCallError"; - readonly toolName: ToolName; -} - -declare const tools: { - [K in ToolName]: (args: ToolArgsMap[K]) => Promise; -} -``` diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md deleted file mode 100644 index 0cee2a6517..0000000000 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ /dev/null @@ -1,401 +0,0 @@ -You are an AI agent powered by the DeepSeek Harness SDK. - -You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. - -Verify your work by running the code or tests. Keep answers brief and factual. - - -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - -Check the [exit code: N] marker on every bash result; investigate failures before moving on. - -Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. - -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. - -Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). - - -Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. - -Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out. - -## Writing code for run_code - -Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program: - -- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON. -- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue. -- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`. -- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need. - -The available tools: - -```ts -type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } - -interface ToolArgsMap { - /** 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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_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: { - /** The bash command to execute. */ - command: string; - /** 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". */ - description: string; - /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */ - timeoutMs?: number; - /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */ - workdir?: string; - /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */ - run_in_background?: boolean; - /** 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. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ - justification?: string; - } & Record; - /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ - create_goal: { - /** The concrete completion objective inferred from the direct human request. */ - objective: string; - /** Optional positive safe-integer limit on automatic continuation rounds. */ - max_goal_rounds?: number; - } & Record; - /** Edit an existing UTF-8 text file by replacing literal text. */ - edit: { - /** Path to edit, resolved by the filesystem backend. */ - file_path: string; - /** Literal text to replace. Must match exactly. */ - old_string: string; - /** Literal replacement text. Use an empty string to delete the match. */ - new_string: string; - /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ - replace_all?: boolean; - /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ - justification?: string; - } & Record; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ - get_goal: Record; - /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */ - ralph: { - /** The immutable completion objective for every fresh Ralph round. */ - objective: string; - /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */ - maxRounds?: number; - } & Record; - /** Read a UTF-8 text file and return line-numbered content. */ - read: { - /** Path to read, resolved by the filesystem backend. */ - file_path: string; - /** 1-based first line to return. Defaults to 1. */ - offset?: number; - /** Maximum number of lines to return. Defaults to 2000. */ - limit?: number; - } & Record; - /** 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. */ - skill: { - /** The exact skill name from the available skills list. */ - name: string; - } & Record; - /** 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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ - subagent: { - /** A short (3-5 word) description of the delegated task, for display. */ - description: string; - /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */ - prompt: string; - /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ - run_in_background?: boolean; - } & Record; - /** 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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ - subagent_fork: { - /** A short (3-5 word) description of the delegated task, for display. */ - description: string; - /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */ - prompt: string; - /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ - run_in_background?: boolean; - } & Record; - /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */ - task_kill: { - /** Task id returned by the tool that started the background work. */ - task_id: string; - /** Optional short reason, recorded in the log and forwarded to the task. */ - reason?: string; - } & Record; - /** List your background tasks (running and finished) with their ids, kinds, and statuses. */ - task_list: Record; - /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */ - task_output: { - /** Task id returned by the tool that started the background work. */ - task_id: string; - /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */ - wait?: boolean; - /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */ - timeout_ms?: number; - } & Record; - /** 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). */ - todo_write: { - /** The COMPLETE task list, replacing any previous list. */ - todos: ({ - /** What the task is — a short imperative line. */ - content: string; - /** pending (not started) | in_progress (now) | completed (done). */ - status: "pending" | "in_progress" | "completed"; - })[]; - } & Record; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ - update_goal: { - /** Exact id returned by get_goal. */ - goal_id: string; - /** Exact positive revision returned by get_goal. */ - revision: number; - /** edit | pause | resume | complete | blocked */ - action: "edit" | "pause" | "resume" | "complete" | "blocked"; - /** Replacement objective; valid only with action edit. */ - objective?: string; - /** Replacement cap; valid only with action edit. */ - max_goal_rounds?: number; - /** Concrete blocking condition; required only with action blocked. */ - blocked_reason?: string; - } & Record; - /** 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. The 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?, provider?, 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. Script-body hooks: - `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/oneOf — no 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */ - workflow: { - /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ - script: string; - /** The workflow identity block (plain JSON — never code). */ - meta: { - /** Short kebab-case workflow name. */ - name: string; - /** One-line description of what the workflow does. */ - description: string; - /** Optional guidance on when this workflow applies. */ - whenToUse?: string; - /** Optional phase declarations matched by phase() calls. */ - phases?: ({ - /** The phase title phase() calls match by exact string. */ - title: string; - /** Optional one-line description of the phase. */ - detail?: string; - /** Optional provider override this phase is expected to use. */ - provider?: string; - /** Optional model override this phase is expected to use. */ - model?: string; - } & Record)[]; - } & Record; - /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ - args?: Record; - } & Record; - /** Create or fully replace a UTF-8 text file. */ - write: { - /** Path to write, resolved by the filesystem backend. */ - file_path: string; - /** Full UTF-8 text content to write. */ - content: string; - /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ - justification?: string; - } & Record; -} - -interface ToolOutputMap { - bash: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - exitCode: number | null; - signal: string | null; - timedOut: boolean; - aborted: boolean; - timeoutMs: number; - stdout: { - text: string; - truncated: boolean; - spillPath?: string; - }; - stderr: { - text: string; - truncated: boolean; - spillPath?: string; - }; - sandbox?: { - mode: string; - denied: boolean; - enforcement?: string; - runnerFailed?: boolean; - }; - }; - create_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - edit: { - path: string; - before: string; - after: string; - }; - get_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - ralph: { - runId: string; - agentsStarted: number; - result: JsonValue; - }; - read: { - path: string; - offset: number; - lines: { - number: number; - text: string; - }[]; - totalLines: number; - }; - skill: { - name: string; - provider: string; - resourceBase?: { - kind: "directory"; - path: string; - } | { - kind: "url"; - url: string; - } | { - kind: "opaque"; - description: string; - }; - content: string; - }; - subagent: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - runId: string; - output: JsonValue[]; - }; - subagent_fork: { - kind: "background"; - taskId: string; - } | { - kind: "foreground"; - runId: string; - output: JsonValue[]; - }; - task_kill: { - outcome: "cancellation-requested" | "already-finished"; - task: { - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - }; - }; - task_list: ({ - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - })[]; - task_output: { - text: string; - task: { - id: string; - kind: string; - label: string; - status: "running" | "stopping" | "completed" | "killed" | "failed"; - detail?: string; - startedAt: number; - finishedAt?: number; - }; - }; - todo_write: { - todos: ({ - content: string; - status: "pending" | "in_progress" | "completed"; - })[]; - counts: { - pending: number; - inProgress: number; - completed: number; - }; - }; - update_goal: { - goal: null; - } | { - goal: { - id: string; - revision: number; - objective: string; - phase: "active" | "paused" | "blocked" | "complete"; - roundsStarted: number; - maxGoalRounds: number; - blockedReason?: { - code: string; - message: string; - }; - }; - activation: "armed" | "disarmed"; - }; - workflow: { - runId: string; - agentsStarted: number; - result: JsonValue; - }; - write: { - path: string; - operation: "create" | "update"; - before: string | null; - after: string; - }; -} - -type ToolName = keyof ToolOutputMap - -declare class ToolCallError extends Error { - readonly name: "ToolCallError"; - readonly toolName: ToolName; -} - -declare const tools: { - [K in ToolName]: (args: ToolArgsMap[K]) => Promise; -} -``` diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/tool-schemas.expected.json deleted file mode 100644 index a9ee29aa7a..0000000000 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/tool-schemas.expected.json +++ /dev/null @@ -1,26 +0,0 @@ -{ - "initial": [ - { - "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." - }, - "description": { - "type": "string", - "description": "Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"." - } - }, - "required": [ - "code", - "description" - ] - } - } - ], - "changes": [] -} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json deleted file mode 100644 index 01ac777a42..0000000000 --- a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json +++ /dev/null @@ -1,473 +0,0 @@ -{ - "initial": [ - { - "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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_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 (collect with task_output, stop with task_kill). 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": "create_goal", - "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace. Must match exactly." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "ralph", - "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The immutable completion objective for every fresh Ralph round." - }, - "maxRounds": { - "type": "number", - "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "task_kill", - "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the task." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "name": "task_list", - "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "task_output", - "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "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", - "additionalProperties": false, - "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": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit | pause | resume | complete | blocked", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Concrete blocking condition; required only with action blocked." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "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?, provider?, 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/oneOf — no 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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).", - "additionalProperties": true, - "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", - "additionalProperties": true, - "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." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "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\": [...]}).", - "additionalProperties": true - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - "changes": [] -} diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md deleted file mode 100644 index 17e6773a03..0000000000 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ /dev/null @@ -1,25 +0,0 @@ -You are an AI agent powered by the DeepSeek Harness SDK. - -You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. - -Verify your work by running the code or tests. Keep answers brief and factual. - - -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - -Check the [exit code: N] marker on every bash result; investigate failures before moving on. - -Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. - -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. - -Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). - - -Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. - -Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out. diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json deleted file mode 100644 index 01ac777a42..0000000000 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ /dev/null @@ -1,473 +0,0 @@ -{ - "initial": [ - { - "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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_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 (collect with task_output, stop with task_kill). 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": "create_goal", - "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace. Must match exactly." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "ralph", - "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The immutable completion objective for every fresh Ralph round." - }, - "maxRounds": { - "type": "number", - "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "task_kill", - "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the task." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "name": "task_list", - "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "task_output", - "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "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", - "additionalProperties": false, - "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": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit | pause | resume | complete | blocked", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Concrete blocking condition; required only with action blocked." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "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?, provider?, 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/oneOf — no 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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).", - "additionalProperties": true, - "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", - "additionalProperties": true, - "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." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "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\": [...]}).", - "additionalProperties": true - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - "changes": [] -} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json deleted file mode 100644 index 01ac777a42..0000000000 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ /dev/null @@ -1,473 +0,0 @@ -{ - "initial": [ - { - "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]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. 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. 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; read its output with `task_output` and stop it with `task_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 (collect with task_output, stop with task_kill). 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": "create_goal", - "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace. Must match exactly." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "ralph", - "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The immutable completion objective for every fresh Ralph round." - }, - "maxRounds": { - "type": "number", - "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", - "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." - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background task and return its id; collect with task_output or stop with task_kill." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "task_kill", - "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the task." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "name": "task_list", - "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "task_output", - "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", - "parameters": { - "type": "object", - "properties": { - "task_id": { - "type": "string", - "description": "Task id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." - } - }, - "required": [ - "task_id" - ] - } - }, - { - "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", - "additionalProperties": false, - "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": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit | pause | resume | complete | blocked", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Concrete blocking condition; required only with action blocked." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "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?, provider?, 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/oneOf — no 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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).", - "additionalProperties": true, - "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", - "additionalProperties": true, - "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." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "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\": [...]}).", - "additionalProperties": true - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation 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 file operation needs the wider access." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - "changes": [] -} diff --git a/packages/support/acp-snapshot/README.i18n.yaml b/packages/support/acp-snapshot/README.i18n.yaml index b7f09e888d..d30a2fb2a7 100644 --- a/packages/support/acp-snapshot/README.i18n.yaml +++ b/packages/support/acp-snapshot/README.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 packages/support/acp-snapshot/README.md -README.md: afbb23e2251932d41ac5d5d5b7d966f2750857fe -README.zh.md: 67ebbff395881c811819bb9e3dcfa4faa4d39914 +README.md: d0d2ae794caa35744b999ecad96d09e226ecc7ca +README.zh.md: de1e5d370e4c58cc565ec4a12fc20467a89cbed8 diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index afbb23e225..d0d2ae794c 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -9,7 +9,7 @@ Four layers, importable separately: - **`launchAcpTestAgent` (launcher)** — boots a source agent under tsx or a built `lib` agent under plain Node from a supplied cwd, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through startup, 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. When Windows accepts forced termination but publishes its exit marker asynchronously, shutdown gives that marker a bounded grace before treating fallback refusal as a second failure. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — drives ACP JSON-RPC stdio from a deterministic `input.json` script through the launcher, tees raw stdout for the expected-output and purity checks, and harvests every persisted raw JSONL session log (parent and subagent children, primary-first) after graceful stdin EOF. `AgentUnderTest` supplies absolute `binScript`, optional `libBinScript`, `configPath`, and `tsconfigPath` paths because the subprocess cwd is outside the repo; `workspaceParent` may move the generated child cwd from the platform temp directory when that grant is itself under test. Startup failures preserve captured agent stderr in the rejected diagnostic. - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs and every native/JavaScript filesystem spelling of the generated cwd → tokens, longest-first; cwd-rooted separators selected as canonical `/` or host-native; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept, the same cwd-path policy), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/archived/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 expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.json`) 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/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Refresh evaluates fresh leaves with the harvested run's ids, cwd, and every cwd alias, then reuses normalized-equivalent leaves only when the complete logical-record layout aligns and volatile string replacements form a bijection; ambiguous logs keep fresh strings, and fresh semantic values remain authoritative. It also expands packed timing envelopes before aligning event times, so switching between packed and unpacked layouts cannot shift later records. A newly inserted `session/title` receives its preceding event's time so feature-driven insertions do not churn the remainder of a fixture. 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. +- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, a tokenized pin per header class composed with independently shared `system-prompt.expected.md` and `tool-schemas.expected.json` sidecars, and a live uniformity guard. Its fixture guards reject orphan scenario dirs, missing files, multiple pins for one class, duplicate sidecar content, unscrubbed JSONL headers, and malformed pinning headers. Refresh evaluates fresh leaves with the harvested run's ids, cwd, and every cwd alias, then reuses normalized-equivalent leaves only when the complete logical-record layout aligns and volatile string replacements form a bijection; ambiguous logs keep fresh strings, and fresh semantic values remain authoritative. It also expands packed timing envelopes before aligning event times, so switching between packed and unpacked layouts cannot shift later records. A newly inserted `session/title` receives its preceding event's time so feature-driven insertions do not churn the remainder of a fixture. 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. Committed session fixtures use canonical packed rows. An in-flight branch that merges this contract runs the [temporary repository migrator](../../../scripts/migrate-packed-session-fixtures.ts) with `pnpm run migrate:packed-session-fixtures`; its [removal proposal](../../../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md) owns deletion after affected branches converge. @@ -51,11 +51,11 @@ defineAcpSnapshotSuite({ }) ``` -A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode and filesystem scenarios are templates. `workspaceParent` moves the generated cwd outside the platform temp area when temporary-directory grants are themselves under test; the harness still owns and removes only the generated child. Each pinning directory stores the normalized full prompt sequence in generated `system-prompt.expected.md` and the corresponding full tool-schema sequence in generated `tool-schemas.expected.json`; `session.jsonl` stores `"system":"{{system}}","tools":"{{tools}}"` while retaining config, reason, and any model-visible prefix. A pin with legitimate mid-run header changes declares `expectedHeaderChanges`, which fixes the length of both sidecar sequences. +A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode and filesystem scenarios are templates. `workspaceParent` moves the generated cwd outside the platform temp area when temporary-directory grants are themselves under test; the harness still owns and removes only the generated child. A pin owns its generated `system-prompt.expected.md` or `tool-schemas.expected.json` by default; `systemPromptSource` and `toolSchemasSource` name another pin when the complete corresponding sequence is identical, so each distinct version is committed once. The pin's `session.jsonl` stores `"system":"{{system}}","tools":"{{tools}}"` while retaining config, reason, and any model-visible prefix. A pin with legitimate mid-run header changes declares `expectedHeaderChanges`; a shared source must declare the same count, and record/refresh rejects claimants that generate different bytes. Every scenario compares `stdout.expected.jsonl` with cwd-rooted separators canonicalized to `/`. On Windows, `pinsNativeWindowsStdout` additionally compares the complete `stdout.expected.windows.jsonl` after the shared expected output and requires that sidecar exactly when enabled. A scenario whose driven behavior needs POSIX process semantics (e.g. cancelling a live bash call kills a detached process group) declares `posixOnly`, which skips its run test on Windows while the fixture guards keep covering its committed files everywhere. -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 Agent Note](../../../.agents/notes/archived/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 expected outputs, and each pin's prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md). +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 Agent Note](../../../.agents/notes/archived/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 expected outputs, and owned prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md). Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the TUI snapshot suite and the web browser e2e lane. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run. diff --git a/packages/support/acp-snapshot/README.zh.md b/packages/support/acp-snapshot/README.zh.md index 67ebbff395..de1e5d370e 100644 --- a/packages/support/acp-snapshot/README.zh.md +++ b/packages/support/acp-snapshot/README.zh.md @@ -9,7 +9,7 @@ ACP 快照套件工具包：无密钥快照层（`pnpm run test:snapshot`，见[ - **`launchAcpTestAgent`（启动器）**：从指定 cwd 在 tsx 下启动源 agent，或在普通 Node 下启动已构建 `lib` agent；通过原始字节 stdout tee 连接 SDK 客户端，收集会话更新和 stderr，在启动过程中公开异步 spawn 失败，对未处理权限请求快速失败，并负责优雅或带信号关闭。关闭会等待进程退出、继承 stdio 关闭和 ACP parser 耗尽，然后才解析或传播子级错误，使捕获内容完整，且调用方可在任一结果后移除自有路径。当 Windows 接受强制终止但异步发布退出标记时，关闭会给该标记有界宽限，然后才将回退拒绝视为第二次失败。快照和普通 e2e 套件共享该进程边界；测试只需提供 agent 路径、cwd、环境覆盖和任何权限策略。 - **`runScenario`（harness）**：通过启动器从确定性 `input.json` 脚本驱动 ACP JSON-RPC stdio，将原始 stdout tee 给预期输出和纯度检查，并在优雅 stdin EOF 后收集每个持久化原始 JSONL 会话日志（父级和 subagent 子级，主级优先）。`AgentUnderTest` 提供绝对 `binScript`、可选 `libBinScript`、`configPath` 和 `tsconfigPath` 路径，因为子进程 cwd 位于仓库外。当生成子级 cwd 自身位于待测授权中时，`workspaceParent` 可以将它从平台临时目录移出。启动失败会在拒绝诊断中保留已捕获 agent stderr。 - **规范化器**：将两个已捕获接口转换为稳定文本的纯函数：`normalizeStdout`（JSON-RPC id → 首次出现序列；UUID 以及生成 cwd 的每个原生/JavaScript 文件系统写法 → token，按最长优先；根据 cwd 的分隔符选择规范 `/` 或宿主原生形式；同时作为 stdout 纯度检查）、`normalizeSessionLog`（时间归零、保留 `seq`、使用同一 cwd 路径策略）、`scrubSystemPrompts`（提示词文本 → `{{system}}`）、`scrubToolSchemas`（schema bulk → `{{tools}}`）和 `scrubRequestHeaders`（每个 pin 之外的所有 header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}`，保留结构；见[header 固定 Agent Note](../../../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)）。 -- **`defineAcpSnapshotSuite`（工厂）**：为场景表注册完整 describe/it 树：每场景预期输出与重新持久化日志比较、录制/刷新 fixture 回写、拒绝结构化 `UNKNOWN_TOOL` 结果、每 header 类别 pin（`system-prompt.expected.md` 加 `tool-schemas.expected.json`）及其实时一致性保护，以及 fixture 保护块（无遗留场景目录、必需文件存在、每类别恰好一个 pin、每个 JSONL 的提示词/schema 已擦除、非 pin fixture 的 header 已完全擦除）。刷新会使用收集所得本次运行的 id、cwd 及全部 cwd 别名评估本次生成的叶值；只有完整逻辑记录布局对齐且易变字符串替换形成双射时，才会复用规范化后等价的叶值；有歧义的日志保留本次生成的字符串，而本次生成的语义值仍为权威数据。它还会在对齐事件时间前展开打包时序 envelope，因此切换打包/非打包布局无法移动后续记录。新插入的 `session/title` 使用前一个事件的时间，因此功能驱动的插入不会扰动 fixture 余下部分。每个场景目录的 `session.jsonl` 和连续 `session..jsonl` 同级文件是有序主级/子级清单；场景表不重复其数量。必须在 vitest 收集时调用。 +- **`defineAcpSnapshotSuite`（工厂）**：为场景表注册完整 describe/it 树：每场景预期输出与重新持久化日志比较、录制/刷新 fixture 回写、拒绝结构化 `UNKNOWN_TOOL` 结果、每个 header 类别一个 token 化 pin（由可独立共享的 `system-prompt.expected.md` 和 `tool-schemas.expected.json` sidecar 组合而成），以及实时一致性保护。其 fixture 保护会拒绝遗留场景目录、缺失文件、一个类别包含多个 pin、重复的 sidecar 内容、未擦除的 JSONL header，以及格式错误的 pin header。刷新会使用收集所得本次运行的 id、cwd 及全部 cwd 别名评估本次生成的叶值；只有完整逻辑记录布局对齐且易变字符串替换形成双射时，才会复用规范化后等价的叶值；有歧义的日志保留本次生成的字符串，而本次生成的语义值仍为权威数据。它还会在对齐事件时间前展开打包时序 envelope，因此切换打包/非打包布局无法移动后续记录。新插入的 `session/title` 使用前一个事件的时间，因此功能驱动的插入不会扰动 fixture 余下部分。每个场景目录的 `session.jsonl` 和连续 `session..jsonl` 同级文件是有序主级/子级清单；场景表不重复其数量。必须在 vitest 收集时调用。 签入仓库的会话 fixture 使用规范打包行。合并此契约的在途分支通过 `pnpm run migrate:packed-session-fixtures` 运行[临时仓库迁移器](../../../scripts/migrate-packed-session-fixtures.ts)；待受影响分支收敛后，由其[移除提案](../../../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md)负责删除该迁移器。 @@ -51,11 +51,11 @@ defineAcpSnapshotSuite({ }) ``` -启动不同组合树的场景会设置自己的 `configPath`（一个 basename 仍以 `cordis.yml` 结尾的 overlay，使 bin 的回放交换可找到同级 `*cordis.snapshot.yml`）；当该组合改变请求 header 时，还会设置自己的 `headerClass` 和 pin 场景，acp-agent 示例的 Code Mode 与文件系统场景是模板。当临时目录授权自身待测时，`workspaceParent` 将生成 cwd 移出平台临时区域；harness 仍只拥有并移除生成的子级。每个 pin 目录将规范化的完整提示词序列存入生成的 `system-prompt.expected.md`，将对应完整工具 schema 序列存入生成的 `tool-schemas.expected.json`；`session.jsonl` 存储 `"system":"{{system}}","tools":"{{tools}}"`，同时保留配置、原因和任何模型可见前缀。具有合法运行中 header 变更的 pin 声明 `expectedHeaderChanges`，用于固定两个 sidecar 序列的长度。 +启动不同组合树的场景会设置自己的 `configPath`（一个 basename 仍以 `cordis.yml` 结尾的 overlay，使 bin 的回放交换可找到同级 `*cordis.snapshot.yml`）；当该组合改变请求 header 时，还会设置自己的 `headerClass` 和 pin 场景，acp-agent 示例的 Code Mode 与文件系统场景是模板。当临时目录授权自身待测时，`workspaceParent` 将生成 cwd 移出平台临时区域；harness 仍只拥有并移除生成的子级。每个 pin 默认拥有其生成的 `system-prompt.expected.md` 或 `tool-schemas.expected.json`；当完整的对应序列相同时，`systemPromptSource` 和 `toolSchemasSource` 指定另一个 pin 作为来源，因此每个不同版本只提交一次。该 pin 的 `session.jsonl` 存储 `"system":"{{system}}","tools":"{{tools}}"`，同时保留配置、原因和任何模型可见前缀。具有合法运行中 header 变更的 pin 声明 `expectedHeaderChanges`；共享来源必须声明相同的 header 变更数量，录制/刷新会拒绝生成不同字节的共享引用方。 每个场景都比较 `stdout.expected.jsonl`，其中以 cwd 为根的分隔符规范化为 `/`。在 Windows 上，`pinsNativeWindowsStdout` 还会在共享预期输出之后比较完整 `stdout.expected.windows.jsonl`，并在启用时精确要求该 sidecar。驱动行为需要 POSIX 进程语义的场景（例如取消实时 bash 调用会终止脱离进程组）声明 `posixOnly`，在 Windows 上跳过运行测试，但 fixture 保护仍在所有平台覆盖其已提交文件。 -示例还发布 `cordis.snapshot.yml` 回放 overlay，位于 `cordis.yml` 旁边（bin 在 `DSH_SNAPSHOT=replay` 下交换它们，见[单源回放配置 Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)）；回放 fixture 由 [`dsh-llm-replay`](../llm-replay/README.md) 提供，该包通过对子级设置的 `DSH_SNAPSHOT_*` env var 指向它。`pnpm run test:snapshot:record` 调用实时 LLM，并重写已记录场景的模型 fixture；`pnpm run test:snapshot:refresh` 保持无密钥，运行回放 overlay，并从已提交模型脚本重写 stdout、可比较会话日志预期输出，以及每个 pin 的提示词与工具 schema sidecar。Fixture 角色、录制/回放/刷新语义和场景表字段记录在 `Scenario` 以及[快照 Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) 中。 +示例还发布 `cordis.snapshot.yml` 回放 overlay，位于 `cordis.yml` 旁边（bin 在 `DSH_SNAPSHOT=replay` 下交换它们，见[单源回放配置 Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)）；回放 fixture 由 [`dsh-llm-replay`](../llm-replay/README.md) 提供，该包通过对子级设置的 `DSH_SNAPSHOT_*` env var 指向它。`pnpm run test:snapshot:record` 调用实时 LLM，并重写已记录场景的模型 fixture；`pnpm run test:snapshot:refresh` 保持无密钥，运行回放 overlay，并从已提交模型脚本重写 stdout、可比较会话日志预期输出，以及各 pin 自有的提示词与工具 schema sidecar。Fixture 角色、录制/回放/刷新语义和场景表字段记录在 `Scenario` 以及[快照 Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) 中。 约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 TUI 快照套件和 web 浏览器 e2e lane 消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once`等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。 diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 9eb74a529a..026702844e 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -8,10 +8,12 @@ * cwd and persistence roots and reads only committed fixtures. Record and * refresh stay serial while writing. * - * Exactly one scenario per header-composition class pins the full prompt and - * tool-schema sequences in dedicated sidecars. Every live header is checked - * against that pin, so session-dependent composition must declare a separate - * class instead of escaping coverage. + * Exactly one scenario per header-composition class pins the tokenized header + * sequence. Its prompt and tool-schema sequences live in independent + * sidecars, each of which may be shared with another class pin when the bytes + * are identical. Every live header is checked against the composed pin, so + * session-dependent composition must declare a separate class instead of + * escaping coverage. * @module @deepseek-ai/dsh-acp-snapshot/suite */ @@ -31,10 +33,10 @@ import { scrubToolSchemas, } from './normalize.ts' -/** The readable system-prompt snapshot beside each header-pinning fixture. */ +/** The readable system-prompt snapshot beside its owning header pin. */ const SYSTEM_PROMPT_SNAPSHOT = 'system-prompt.expected.md' -/** The structured tool-schema snapshot beside each header-pinning fixture. */ +/** The structured tool-schema snapshot beside its owning header pin. */ const TOOL_SCHEMAS_SNAPSHOT = 'tool-schemas.expected.json' /** The optional full Windows-native stdout transcript. */ @@ -80,10 +82,23 @@ export interface Scenario { */ overridden?: boolean /** - * Whether this scenario is its header class's sole request-header pin. Dedicated sidecars own - * the prompt and tool schemas, while every classmate is checked for equality. + * Whether this scenario is its header class's sole tokenized request-header + * pin. Prompt and tool-schema sidecars are selected independently, while + * every classmate is checked for equality with the reconstructed header. */ pinsHeader?: boolean + /** + * Header-pinning scenario whose `system-prompt.expected.md` this pin reuses. + * Defaults to this scenario. The source must own its prompt sidecar and + * declare the same {@link expectedHeaderChanges}; meaningless off a pin. + */ + systemPromptSource?: string + /** + * Header-pinning scenario whose `tool-schemas.expected.json` this pin reuses. + * Defaults to this scenario. The source must own its schema sidecar and + * declare the same {@link expectedHeaderChanges}; meaningless off a pin. + */ + toolSchemasSource?: string /** * How many changed `request/header` snapshots this PINNING scenario's primary * fixture legitimately carries (default 0). Their full prompt text is kept in @@ -189,6 +204,71 @@ export interface SnapshotSuiteOptions { mode: 'replay' | 'record' | 'refresh' } +/** One scenario's generated claim on a shared snapshot file. */ +export interface SharedSnapshotClaim { + /** Scenario that first generated the snapshot in this suite run. */ + scenario: string + /** Complete generated file content. */ + content: string +} + +/** One committed snapshot file and its complete content. */ +export interface NamedSnapshotContent { + /** Diagnostic path of the committed file. */ + path: string + /** Complete committed file content. */ + content: string +} + +/** + * Record one scenario's generated content for a shared snapshot source. + * A later claimant must generate identical bytes; otherwise record/refresh + * would make the final file depend on scenario order. + * + * @param claims Claims already made in this suite run, keyed by source path. + * @param source The shared snapshot path being claimed. + * @param scenario The scenario generating the content. + * @param content The complete content the scenario generated. + * @returns Nothing. + */ +export function claimSharedSnapshot( + claims: Map, + source: string, + scenario: string, + content: string, +): void { + const previous = claims.get(source) + if (previous !== undefined && previous.content !== content) { + throw new Error( + `acp-snapshot: shared snapshot ${source} diverged between ${previous.scenario} and ${scenario}`, + ) + } + if (previous === undefined) claims.set(source, { scenario, content }) +} + +/** + * Reject byte-identical committed snapshots stored under different paths. + * + * @param kind Human-readable snapshot kind for the diagnostic. + * @param snapshots The committed files to compare. + * @returns Nothing. + */ +export function assertUniqueSnapshotContents( + kind: string, + snapshots: readonly NamedSnapshotContent[], +): void { + const firstPathByContent = new Map() + for (const snapshot of snapshots) { + const firstPath = firstPathByContent.get(snapshot.content) + if (firstPath !== undefined) { + throw new Error( + `acp-snapshot: identical ${kind} snapshots appear in ${firstPath} and ${snapshot.path}; reuse one source`, + ) + } + firstPathByContent.set(snapshot.content, snapshot.path) + } +} + /** * Validate and order a scenario directory's session-fixture filenames. * @@ -783,8 +863,8 @@ export function stabilizeRefreshLog( * Register the suite: one test per scenario (the expected-output and log comparisons and * the header-uniformity guard) plus the fixture guard block (no orphan * scenario dirs, required files present, exactly one pin per header class, - * pinning fixtures well-formed, every JSONL prompt-scrubbed, non-pinning - * fixtures fully header-scrubbed). Must + * shared sidecars unique and well-formed, every JSONL prompt-scrubbed, + * non-pinning fixtures fully header-scrubbed). Must * run at vitest collection time — it calls `describe`/`it`. Throws * immediately if any header class lacks a pinning scenario or carries two * (the uniformity guard needs exactly one comparison anchor per class). @@ -801,6 +881,19 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { /** The class a scenario's header composition belongs to (see {@link Scenario.headerClass}). */ const classOf = (scenario: Scenario): string => scenario.headerClass ?? 'default' + const scenariosByName = new Map() + for (const scenario of scenarios) { + if (scenariosByName.has(scenario.name)) { + throw new Error(`acp-snapshot: duplicate scenario name "${scenario.name}"`) + } + scenariosByName.set(scenario.name, scenario) + for (const field of ['systemPromptSource', 'toolSchemasSource'] as const) { + if (scenario[field] !== undefined && scenario.pinsHeader !== true) { + throw new Error(`acp-snapshot: ${scenario.name}.${field} is only valid on a header-pinning scenario`) + } + } + } + /** Each header class's single pinning scenario. Guarded here (and by meta-tests) so a pin cannot silently vanish or split. */ const pinningByClass = new Map() for (const scenario of scenarios) { @@ -816,6 +909,43 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { } } + const sourceFor = ( + pinningScenario: Scenario, + field: 'systemPromptSource' | 'toolSchemasSource', + label: string, + ): Scenario => { + const sourceName = pinningScenario[field] ?? pinningScenario.name + const source = scenariosByName.get(sourceName) + if (source === undefined) { + throw new Error(`acp-snapshot: ${pinningScenario.name} names unknown ${label} source "${sourceName}"`) + } + if (source.pinsHeader !== true) { + throw new Error(`acp-snapshot: ${pinningScenario.name} names non-pinning ${label} source "${sourceName}"`) + } + if (source[field] !== undefined && source[field] !== source.name) { + throw new Error(`acp-snapshot: ${pinningScenario.name} names ${label} source "${sourceName}", which does not own its sidecar`) + } + const expectedChanges = pinningScenario.expectedHeaderChanges ?? 0 + const sourceChanges = source.expectedHeaderChanges ?? 0 + if (sourceChanges !== expectedChanges) { + throw new Error( + `acp-snapshot: ${pinningScenario.name} and ${sourceName} declare different header-change counts for shared ${label}`, + ) + } + return source + } + + const promptSourceByClass = new Map() + const schemaSourceByClass = new Map() + for (const [cls, pinningScenario] of pinningByClass) { + promptSourceByClass.set(cls, sourceFor(pinningScenario, 'systemPromptSource', 'system-prompt snapshot')) + schemaSourceByClass.set(cls, sourceFor(pinningScenario, 'toolSchemasSource', 'tool-schema snapshot')) + } + const promptOwners = new Set([...promptSourceByClass.values()].map(source => source.name)) + const schemaOwners = new Set([...schemaSourceByClass.values()].map(source => source.name)) + const promptClaims = new Map() + const schemaClaims = new Map() + scenarioSuite('snapshot scenarios', () => { for (const scenario of scenarios) { // In RECORD mode, only re-run the `recorded` (live-API) scenarios; the `authored` ones @@ -914,17 +1044,26 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const primary = result.sessionLogs[0] as HarvestedLog const prompts = normalizedSystemPrompts(primary.content, ctx) expect(prompts.length, `${mode} produced no system prompt to snapshot`).toBeGreaterThan(0) - const snapshot = formatSystemPromptSnapshot(prompts[0] as string, prompts.slice(1)) - await writeFile(join(dir, SYSTEM_PROMPT_SNAPSHOT), snapshot) + const promptSnapshot = formatSystemPromptSnapshot(prompts[0] as string, prompts.slice(1)) + /* v8 ignore next -- registration guarantees every scenario class has resolved sources. */ + const promptSource = promptSourceByClass.get(classOf(scenario)) ?? scenario + const promptPath = join(snapshotsDir, promptSource.name, SYSTEM_PROMPT_SNAPSHOT) + claimSharedSnapshot(promptClaims, promptPath, scenario.name, promptSnapshot) + await writeFile(promptPath, promptSnapshot) const schemaSets = normalizedToolSchemas(primary.content, ctx) expect(schemaSets.length, `${mode} produced no tool schemas to snapshot`).toBeGreaterThan(0) expect(schemaSets.length, `${mode} produced a tool-schema sequence that differs from its prompt sequence`) .toBe(prompts.length) - await writeFile(join(dir, TOOL_SCHEMAS_SNAPSHOT), formatToolSchemasSnapshot( + const toolSchemasSnapshot = formatToolSchemasSnapshot( schemaSets[0] as unknown[], schemaSets.slice(1), - )) + ) + /* v8 ignore next -- registration guarantees every scenario class has resolved sources. */ + const schemaSource = schemaSourceByClass.get(classOf(scenario)) ?? scenario + const schemaPath = join(snapshotsDir, schemaSource.name, TOOL_SCHEMAS_SNAPSHOT) + claimSharedSnapshot(schemaClaims, schemaPath, scenario.name, toolSchemasSnapshot) + await writeFile(schemaPath, toolSchemasSnapshot) } } @@ -953,17 +1092,27 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // tokenized JSONL plus readable prompt and structured schema sidecars. /* v8 ignore next -- construction guarantees the pin exists; a miss would fail the one-header assertion loudly. */ const pinningScenario = pinningByClass.get(classOf(scenario)) ?? scenario + /* v8 ignore next -- registration guarantees every scenario class has resolved sources. */ + const promptSource = promptSourceByClass.get(classOf(scenario)) ?? pinningScenario + /* v8 ignore next -- registration guarantees every scenario class has resolved sources. */ + const schemaSource = schemaSourceByClass.get(classOf(scenario)) ?? pinningScenario const pinningDir = join(snapshotsDir, pinningScenario.name) const pinnedFixture = await readFile(join(pinningDir, 'session.jsonl'), 'utf8') const pinned = normalizedHeaders(pinnedFixture, fixtureContext(pinnedFixture)) - const promptSnapshot = await readFile(join(pinningDir, SYSTEM_PROMPT_SNAPSHOT), 'utf8') + const promptSnapshot = await readFile( + join(snapshotsDir, promptSource.name, SYSTEM_PROMPT_SNAPSHOT), + 'utf8', + ) const initialPromptSnapshot = initialSystemPromptSnapshot(promptSnapshot) expect(pinned.length, `the pinning fixture (${pinningScenario.name}) has an unexpected request/header count`) .toBe(1 + (pinningScenario.expectedHeaderChanges ?? 0)) - const toolSchemasSnapshot = await readFile(join(pinningDir, TOOL_SCHEMAS_SNAPSHOT), 'utf8') + const toolSchemasSnapshot = await readFile( + join(snapshotsDir, schemaSource.name, TOOL_SCHEMAS_SNAPSHOT), + 'utf8', + ) const toolSchemas = parseToolSchemasSnapshot(toolSchemasSnapshot) const pinnedSchemaSets = [toolSchemas.initial, ...toolSchemas.changes] - expect(pinnedSchemaSets.length, `the pinning fixture (${pinningScenario.name}) has an unexpected tool-schema count`) + expect(pinnedSchemaSets.length, `the schema source (${schemaSource.name}) has an unexpected tool-schema count`) .toBe(pinned.length) const pinnedHeaders = pinned.map((header, index) => restorePinnedToolSchemas( header, @@ -987,7 +1136,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(header, `session ${log.id}: request/header #${k + 1} diverged from the pinned (${pinningScenario.name}) header`) .toEqual(expected) if (expectedChanges === 0) { - expect(formatSystemPromptSnapshot(prompts[k] as string), `session ${log.id}: initial system prompt #${k + 1} diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`) + expect(formatSystemPromptSnapshot(prompts[k] as string), `session ${log.id}: initial system prompt #${k + 1} diverged from ${promptSource.name}/${SYSTEM_PROMPT_SNAPSHOT}`) .toEqual(initialPromptSnapshot) } } @@ -995,12 +1144,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(formatSystemPromptSnapshot( prompts[0] as string, prompts.slice(1), - ), `session ${log.id}: changed system prompts diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`) + ), `session ${log.id}: changed system prompts diverged from ${promptSource.name}/${SYSTEM_PROMPT_SNAPSHOT}`) .toEqual(promptSnapshot) expect(formatToolSchemasSnapshot( schemaSets[0] as unknown[], schemaSets.slice(1), - ), `session ${log.id}: changed tool schemas diverged from ${pinningScenario.name}/${TOOL_SCHEMAS_SNAPSHOT}`) + ), `session ${log.id}: changed tool schemas diverged from ${schemaSource.name}/${TOOL_SCHEMAS_SNAPSHOT}`) .toEqual(toolSchemasSnapshot) } } @@ -1021,7 +1170,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { it('every registered scenario has its required fixture files', async () => { // Every scenario needs input, stdout, a primary session fixture, and matching optional sidecars. - for (const { name, overridden, pinsHeader, pinsNativeWindowsStdout } of scenarios) { + for (const { name, overridden, pinsNativeWindowsStdout } of scenarios) { const dir = join(snapshotsDir, name) expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true) expect(existsSync(join(dir, 'stdout.expected.jsonl')), `${name}/stdout.expected.jsonl`).toBe(true) @@ -1032,17 +1181,17 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(existsSync(join(dir, 'session.jsonl')), `${name}/session.jsonl`).toBe(true) expect(existsSync(join(dir, 'replay.override.json')), `${name}/replay.override.json presence must match \`overridden\``) .toBe(overridden === true) - expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``) - .toBe(pinsHeader === true) - expect(existsSync(join(dir, TOOL_SCHEMAS_SNAPSHOT)), `${name}/${TOOL_SCHEMAS_SNAPSHOT} presence must match \`pinsHeader\``) - .toBe(pinsHeader === true) + expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match snapshot-source ownership`) + .toBe(promptOwners.has(name)) + expect(existsSync(join(dir, TOOL_SCHEMAS_SNAPSHOT)), `${name}/${TOOL_SCHEMAS_SNAPSHOT} presence must match snapshot-source ownership`) + .toBe(schemaOwners.has(name)) await expect(sessionFixtures(dir), `${name}: session fixture inventory`).resolves.toBeDefined() } }) it('exactly one scenario pins the request-header content of each header class', () => { - // Zero pins would drop a class's prompt/schema surface from the suite entirely; two would - // split it. + // Zero pins would drop a class's structural header surface from the suite entirely; two + // would split it. const pins = new Map() for (const scenario of scenarios.filter(s => s.pinsHeader === true)) { const cls = classOf(scenario) @@ -1055,33 +1204,56 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { } }) - it('every pinning fixture carries one tokenized header sequence and two sidecars', async () => { + it('every pinning fixture composes one tokenized header sequence with its referenced sidecars', async () => { // Assert the committed pin directly because a class containing only its // pinning scenario has no non-pinning live run to catch undeclared changes. for (const scenario of pinningByClass.values()) { + /* v8 ignore next -- registration guarantees every pin has resolved sources. */ + const promptSource = promptSourceByClass.get(classOf(scenario)) ?? scenario + /* v8 ignore next -- registration guarantees every pin has resolved sources. */ + const schemaSource = schemaSourceByClass.get(classOf(scenario)) ?? scenario const fixture = await readFile(join(snapshotsDir, scenario.name, 'session.jsonl'), 'utf8') const headers = normalizedHeaders(fixture, fixtureContext(fixture)) - const promptSnapshot = await readFile(join(snapshotsDir, scenario.name, SYSTEM_PROMPT_SNAPSHOT), 'utf8') + const promptSnapshot = await readFile( + join(snapshotsDir, promptSource.name, SYSTEM_PROMPT_SNAPSHOT), + 'utf8', + ) expect(headers.length, `${scenario.name}: unexpected request/header count`) .toBe(1 + (scenario.expectedHeaderChanges ?? 0)) - const toolSchemasSnapshot = await readFile(join(snapshotsDir, scenario.name, TOOL_SCHEMAS_SNAPSHOT), 'utf8') + const toolSchemasSnapshot = await readFile( + join(snapshotsDir, schemaSource.name, TOOL_SCHEMAS_SNAPSHOT), + 'utf8', + ) const toolSchemas = parseToolSchemasSnapshot(toolSchemasSnapshot) const schemaSets = [toolSchemas.initial, ...toolSchemas.changes] - expect(schemaSets.length, `${scenario.name}: tool-schema sequence must match the header sequence`) + expect(schemaSets.length, `${schemaSource.name}: tool-schema sequence must match ${scenario.name}'s header sequence`) .toBe(headers.length) for (const [index, header] of headers.entries()) { expect(() => restorePinnedToolSchemas(header, schemaSets[index] as unknown[]), `${scenario.name}: tools must use the sidecar token`) .not.toThrow() } - expect(promptSnapshot.length, `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must not be empty`).toBeGreaterThan(0) - expect(promptSnapshot.endsWith('\n'), `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must end in a newline`).toBe(true) - expect(toolSchemasSnapshot, `${scenario.name}/${TOOL_SCHEMAS_SNAPSHOT} must use canonical JSON formatting`) + expect(promptSnapshot.length, `${promptSource.name}/${SYSTEM_PROMPT_SNAPSHOT} must not be empty`).toBeGreaterThan(0) + expect(promptSnapshot.endsWith('\n'), `${promptSource.name}/${SYSTEM_PROMPT_SNAPSHOT} must end in a newline`).toBe(true) + expect(toolSchemasSnapshot, `${schemaSource.name}/${TOOL_SCHEMAS_SNAPSHOT} must use canonical JSON formatting`) .toBe(formatToolSchemasSnapshot(toolSchemas.initial, toolSchemas.changes)) expect(headerChangeCount(fixture), `${scenario.name}: a pinning fixture must carry exactly its declared changed headers`) .toBe(scenario.expectedHeaderChanges ?? 0) } }) + it('stores each distinct prompt and tool-schema snapshot once', async () => { + const prompts = await Promise.all([...promptOwners].map(async (owner): Promise => ({ + path: `${owner}/${SYSTEM_PROMPT_SNAPSHOT}`, + content: await readFile(join(snapshotsDir, owner, SYSTEM_PROMPT_SNAPSHOT), 'utf8'), + }))) + const schemas = await Promise.all([...schemaOwners].map(async (owner): Promise => ({ + path: `${owner}/${TOOL_SCHEMAS_SNAPSHOT}`, + content: await readFile(join(snapshotsDir, owner, TOOL_SCHEMAS_SNAPSHOT), 'utf8'), + }))) + assertUniqueSnapshotContents('system-prompt', prompts) + assertUniqueSnapshotContents('tool-schema', schemas) + }) + it('every committed JSONL has valid tool results and canonical header storage', async () => { // Prompts and schemas always leave JSONL. Header pins retain prefixes; // every other fixture tokenizes those too. Fixed-point checks make both diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/behavior.json b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/behavior.json new file mode 100644 index 0000000000..4de8f25b7e --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/behavior.json @@ -0,0 +1,12 @@ +{ + "prompt": "respond", + "logs": [{ + "file": "b/main/session.jsonl", + "lines": [ + { "type": "session", "id": "{{SID}}", "createdAt": 100, "cwd": "{{CWD}}", "delegationDepth": 0 }, + { "type": "request/header", "seq": 0, "time": 100, "data": { "header": { "config": { "model": "fake" }, "system": "SYS PROMPT", "tools": [{ "name": "t1", "description": "D1", "parameters": { "type": "object" } }] }, "reason": "initial" } }, + { "type": "request/header", "seq": 1, "time": 100, "data": { "header": { "config": { "model": "fake" }, "system": "SYS PROMPT\n\nNEW PROMPT LINE", "tools": [{ "name": "t1", "description": "D1", "parameters": { "type": "object" } }] }, "reason": "change" } }, + { "type": "turn/start", "seq": 2, "time": 100, "data": { "turn": 1 } } + ] + }] +} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/input.json b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/input.json new file mode 100644 index 0000000000..b9e2d9bbc5 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/input.json @@ -0,0 +1 @@ +{ "steps": [{ "op": "initialize" }, { "op": "newSession" }, { "op": "prompt", "text": "pin" }] } diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/session.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/session.jsonl new file mode 100644 index 0000000000..8a9407cbc0 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/session.jsonl @@ -0,0 +1,4 @@ +{"type":"session","id":"13131313-3434-4545-8686-787878787878","createdAt":7,"cwd":"/rec/shared-pin-cwd","delegationDepth":0} +{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":1,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}} +{"type":"turn/start","seq":2,"time":7,"data":{"turn":1}} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/stdout.expected.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/stdout.expected.jsonl new file mode 100644 index 0000000000..f173b45b77 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/shared-pin/stdout.expected.jsonl @@ -0,0 +1,4 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentCapabilities":{"loadSession":false}}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"thinking about it"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index a54da894a9..d68b1335d1 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -6,6 +6,8 @@ import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts' import { + assertUniqueSnapshotContents, + claimSharedSnapshot, fixtureContext, formatSystemPromptSnapshot, headerChangeCount, @@ -18,6 +20,7 @@ import { scenarioSkipped, sessionFixtureNames, restorePinnedToolSchemas, + type SharedSnapshotClaim, stabilizeRefreshLog, stdoutExpectedVariants, unknownToolCallIds, @@ -57,6 +60,16 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. // Replay pins explicit header classes; recording covers the default fallback. const REPLAY_SCENARIOS: Scenario[] = [ { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, + { + name: 'shared-pin', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + expectedHeaderChanges: 1, + headerClass: 'shared', + systemPromptSource: 'pin-turn', + toolSchemasSource: 'pin-turn', + }, { name: 'plain-turn', hasModelTurn: true, @@ -211,6 +224,158 @@ describe('defineAcpSnapshotSuite: registration contract', () => { }) }).toThrow(/header class "default" pinned by both first-pin and second-pin/) }) + + it('throws when scenario names are duplicated', () => { + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [ + { name: 'duplicate', hasModelTurn: true, recorded: true, pinsHeader: true }, + { name: 'duplicate', hasModelTurn: true, recorded: true }, + ], + mode: 'replay', + }) + }).toThrow(/duplicate scenario name "duplicate"/) + }) + + it.each(['systemPromptSource', 'toolSchemasSource'] as const)( + 'rejects %s away from a header pin', + (field) => { + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [{ + name: 'plain', + hasModelTurn: true, + recorded: true, + [field]: 'owner', + }], + mode: 'replay', + }) + }).toThrow(new RegExp(`plain\\.${field} is only valid on a header-pinning scenario`)) + }, + ) + + it('rejects an unknown or non-pinning sidecar source', () => { + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [{ + name: 'pin', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + systemPromptSource: 'missing', + }], + mode: 'replay', + }) + }).toThrow(/pin names unknown system-prompt snapshot source "missing"/) + + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [ + { + name: 'pin', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + toolSchemasSource: 'plain', + }, + { name: 'plain', hasModelTurn: true, recorded: true }, + ], + mode: 'replay', + }) + }).toThrow(/pin names non-pinning tool-schema snapshot source "plain"/) + }) + + it('rejects a sidecar source that redirects the same artifact', () => { + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [ + { name: 'owner', hasModelTurn: true, recorded: true, pinsHeader: true }, + { + name: 'redirect', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + headerClass: 'redirect', + systemPromptSource: 'owner', + }, + { + name: 'consumer', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + headerClass: 'consumer', + systemPromptSource: 'redirect', + }, + ], + mode: 'replay', + }) + }).toThrow(/consumer names system-prompt snapshot source "redirect", which does not own its sidecar/) + }) + + it('rejects shared sidecars with different header-change counts', () => { + expect(() => { + defineAcpSnapshotSuite({ + agent: AGENT, + snapshotsDir: REPLAY_DIR, + scenarios: [ + { + name: 'owner', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + expectedHeaderChanges: 1, + }, + { + name: 'consumer', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + headerClass: 'consumer', + toolSchemasSource: 'owner', + }, + ], + mode: 'replay', + }) + }).toThrow(/consumer and owner declare different header-change counts for shared tool-schema snapshot/) + }) +}) + +describe('shared snapshot content', () => { + it('accepts identical claims and rejects order-dependent shared output', () => { + const claims = new Map() + claimSharedSnapshot(claims, 'shared/system-prompt.expected.md', 'first', 'prompt\n') + claimSharedSnapshot(claims, 'shared/system-prompt.expected.md', 'second', 'prompt\n') + expect(claims.get('shared/system-prompt.expected.md')).toEqual({ + scenario: 'first', + content: 'prompt\n', + }) + expect(() => { + claimSharedSnapshot(claims, 'shared/system-prompt.expected.md', 'third', 'different\n') + }).toThrow(/diverged between first and third/) + }) + + it('rejects identical committed content under different paths', () => { + assertUniqueSnapshotContents('prompt', [ + { path: 'one/system-prompt.expected.md', content: 'one\n' }, + { path: 'two/system-prompt.expected.md', content: 'two\n' }, + ]) + expect(() => { + assertUniqueSnapshotContents('prompt', [ + { path: 'one/system-prompt.expected.md', content: 'same\n' }, + { path: 'two/system-prompt.expected.md', content: 'same\n' }, + ]) + }).toThrow(/identical prompt snapshots appear in one\/system-prompt\.expected\.md and two\/system-prompt\.expected\.md/) + }) }) describe('sessionFixtureNames', () => {