Merge latest origin/master into compact-post-step-overflow-recovery

# Conflicts:
#	docs/agent-lifecycle.md
#	docs/architecture.md
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/rfc/INDEX.md
#	docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md
#	docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md
#	docs/rfc/implemented/feature/2026-07-07-session-prefix.md
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/src/config.ts
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/src/summarizer.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/compact/compact/README.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-pi-ai/README.md
#	packages/llm/llm-pi-ai/src/stream.ts
#	packages/llm/llm-pi-ai/tests/convert.spec.ts
#	packages/llm/llm/README.md
#	packages/llm/llm/src/index.ts
#	packages/llm/llm/tests/service.spec.ts
#	scripts/gen-doc-graphs.ts
This commit is contained in:
Tianyi Cui
2026-07-19 12:06:23 +08:00
814 files changed
+42348 -10067

No files matched your search

@@ -11,9 +11,12 @@
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
config:
provider: deepseek
model: deepseek-v4-flash
resumeSessionId: !!js process.env.RESUME_SESSION_ID
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
tools:
mode: code
welcome: 'code-mode agent ready. Give it a multi-tool task.'
+12
View File
@@ -49,6 +49,14 @@ flowchart LR
cfg --> plugin_coding_fs_policy
plugin_coding_tool_fs["tool-fs<br/>@deepseek-ai/dsh-tool-fs"]
cfg --> plugin_coding_tool_fs
plugin_coding_tool_fs_search["tool-fs-search<br/>@deepseek-ai/dsh-tool-fs-search"]
cfg --> plugin_coding_tool_fs_search
plugin_coding_timeout_policy["timeout-policy<br/>@deepseek-ai/dsh-timeout-policy"]
cfg --> plugin_coding_timeout_policy
plugin_coding_spill_local["spill-local<br/>@deepseek-ai/dsh-spill-local"]
cfg --> plugin_coding_spill_local
plugin_coding_spill_policy["spill-policy<br/>@deepseek-ai/dsh-spill-policy"]
cfg --> plugin_coding_spill_policy
```
| Plugin id | Package / module |
@@ -70,6 +78,10 @@ flowchart LR
| `fs-local` | `@deepseek-ai/dsh-fs-local` |
| `fs-policy` | `@deepseek-ai/dsh-fs-policy` |
| `tool-fs` | `@deepseek-ai/dsh-tool-fs` |
| `tool-fs-search` | `@deepseek-ai/dsh-tool-fs-search` |
| `timeout-policy` | `@deepseek-ai/dsh-timeout-policy` |
| `spill-local` | `@deepseek-ai/dsh-spill-local` |
| `spill-policy` | `@deepseek-ai/dsh-spill-policy` |
Source config: [`examples/coding-agent/cordis.yml`](cordis.yml).
+32 -7
View File
@@ -1,6 +1,6 @@
# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo`
# supplies the agent spine, generic task controls, logging, JSONL persistence,
# readline UI, and `main` agent.
# supplies the agent spine, workspace instructions, generic task controls,
# logging, JSONL persistence, readline UI, and `main` agent.
# HMR remains a leaf because it requires Loader internals; `demo:repl` passes
# `--expose-internals`. The app bin loads the gitignored root `.env`; this file
# reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`.
@@ -11,16 +11,12 @@
config:
root: ['.']
# The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed
# twin (same config shape; `reasoning: high` replaces thinking/reasoningEffort).
# The native DeepSeek adapter.
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY
baseURL: !!js process.env.DEEPSEEK_BASE_URL
models:
- deepseek-v4-pro
- deepseek-v4-flash
# Local executor for the app bundle's bash tool.
- id: bash
@@ -32,11 +28,14 @@
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
config:
provider: deepseek
model: deepseek-v4-flash
# Set RESUME_SESSION_ID to continue a prior persisted session (the ids live
# under ./.sessions); unset starts a fresh session each run.
resumeSessionId: !!js process.env.RESUME_SESSION_ID
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
welcome: 'agent REPL ready. Give it a coding task.'
# Keep the persona to identity and behavior; tool plugins own tool guidance.
# The loop resolves {{model}} from this agent's configuration.
@@ -109,3 +108,29 @@
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
# Bash-backed discovery tools (glob/grep): fixed ripgrep commands through the
# local bash executor above — not ctx.fs. Capped results save the complete
# formatted list through the spill backend below (ctx.spillStore, optional).
- id: tool-fs-search
name: '@deepseek-ai/dsh-tool-fs-search'
# The tool-call timeout enforcer: arms each declared ToolDefinition.timeoutMs
# (the search tools above declare 30s) as a deadline on exec.signal. Without
# it a declared budget is advisory and only the bash executor's own timeout
# backstop applies.
- id: timeout-policy
name: '@deepseek-ai/dsh-timeout-policy'
# Tool-output spill stack: a local backend that saves oversized tool text under
# a private session-scoped dir, and the tools/post-execute policy that replaces
# an over-budget plain-text result with a preview + the spill locator/retrieval
# hint. A leaf pair after the app (needs ctx.tools). The policy is a no-op until
# a tool returns more than maxInlineBytes of plain text.
- id: spill-local
name: '@deepseek-ai/dsh-spill-local'
- id: spill-policy
name: '@deepseek-ai/dsh-spill-policy'
config:
maxInlineBytes: 50000
+66 -7
View File
@@ -1,19 +1,23 @@
import { mkdtemp, readFile, rm } from 'node:fs/promises'
import { mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
/**
* With-key Code Mode proof: a real model receives only `run_code`, composes two
@@ -23,6 +27,7 @@ import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '
+ 'batch related tool work into one program and print or return ONLY the findings that matter.'
const WORKSPACE_PROBE = 'dragonfruit-8675309'
let ctx: Context | undefined
let workdir: string | undefined
@@ -45,14 +50,30 @@ async function codeModeHarness(cwd: string): Promise<Context> {
await harness.plugin(ToolRegistry, { mode: 'code' })
await harness.plugin(AgentRegistry)
await harness.plugin(AgentLoop, { agents: [] })
await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
await harness.plugin(LlmDeepSeek)
await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
await harness.plugin(ToolBash)
await harness.plugin(WorkerCodeRuntime, {})
return harness
}
function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise<void> {
async function workspaceCodeModeHarness(): Promise<Context> {
const harness = new Context()
await harness.plugin(LlmService)
await harness.plugin(SessionStore)
await harness.plugin(SystemPrompt, { persona: PERSONA })
await harness.plugin(ToolRegistry, { mode: 'code' })
await harness.plugin(AgentRegistry)
await harness.plugin(LocalFileSystem, { cwd: '/' })
await harness.plugin(ToolFs)
await harness.plugin(WorkspaceContext, { maxBytes: 65536 })
await harness.plugin(AgentLoop, { agents: [] })
await harness.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] })
await harness.plugin(WorkerCodeRuntime, {})
return harness
}
function waitForIdle(harness: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = harness.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -67,7 +88,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-'))
ctx = await codeModeHarness(workdir)
const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
@@ -107,4 +128,42 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
expect(finalText).toContain('alpha-7')
expect(finalText).toContain('beta-9')
}, 180_000)
it('delivers nested workspace instructions discovered by an fs sub-call after the outer result', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-workspace-e2e-'))
await mkdir(join(workdir, '.git'), { recursive: true })
await mkdir(join(workdir, 'pkg/deep'), { recursive: true })
await writeFile(join(workdir, 'pkg/AGENTS.md'), `If asked for the Code Mode workspace handshake, reply with exactly ${WORKSPACE_PROBE} and nothing else.\n`)
await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n')
ctx = await workspaceCodeModeHarness()
const handle = await ctx.agents.create({
sessionId: SessionId('e2e-code-mode-workspace-session'),
meta: { cwd: workdir },
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})
handle.agent.send([{
type: 'text',
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
}])
await waitForIdle(ctx, handle.agent)
const events: SessionEvent[] = [...handle.agent.session.events]
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
const outerResult = events.find(event => event.type === 'tool/result')
const workspaceContext = events.find(event => event.type === 'context/message'
&& typeof event.data.meta === 'object'
&& event.data.meta !== null
&& !Array.isArray(event.data.meta)
&& event.data.meta.kind === 'workspace-instructions')
expect(dispatch).toBeDefined()
expect(outerResult).toBeDefined()
expect(workspaceContext).toBeDefined()
expect(workspaceContext!.seq).toBeGreaterThan(outerResult!.seq)
const finalMessage = events.findLast(event => event.type === 'assistant/message')
const answer = finalMessage?.type === 'assistant/message'
? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
: ''
expect(answer).toContain(WORKSPACE_PROBE)
}, 180_000)
})
@@ -4,8 +4,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* The swebench-style smoke test: a real model fixes a real bug in a temp
@@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
expect(before.status).not.toBe(0)
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* Key-gated smoke for mid-session compaction. It verifies the compact event
@@ -39,13 +39,14 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
compact: {
thresholdRatio: 0.5,
retainTokens: 400,
summarizationProvider: '',
summarizationModel: '',
maxTokens: 1024,
compactionRetries: 1,
},
persistenceRoot: join(workdir, '.sessions'),
})
const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
+2 -2
View File
@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* The first place a REAL model meets the REAL bash tool: the cheap canary
@@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
it('runs a bash command on request and reports its output', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-'))
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
await waitForIdle(ctx, agent)
+8 -13
View File
@@ -1,11 +1,8 @@
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import type { Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
@@ -54,13 +51,11 @@ export interface CodingHarnessOptions {
export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await mountAgentLoopTestDependencies(ctx, {
systemPrompt: { persona: options.persona ?? '' },
})
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
await ctx.plugin(LlmDeepSeek)
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
await ctx.plugin(ToolBash)
await ctx.plugin(ToolTodo)
@@ -77,7 +72,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
return ctx
}
export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
export function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
+4 -8
View File
@@ -3,8 +3,6 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
@@ -40,10 +38,9 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// log on disk survives.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const first = (await ctx.agents.create({
agentId: AgentId('resume-1'),
sessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
@@ -54,10 +51,9 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// run 1's exchange as conversation history.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const resumed = (await ctx.agents.resume({
agentId: AgentId('resume-2'),
resumeSessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent
expect(resumed.session.id).toBe(SESSION_ID)
// The prior user turn is in the rehydrated log before the model is asked.
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
@@ -3,8 +3,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* A REAL model drives the REAL todo_write tool: verify the WORLD (the session
@@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
it('appends a todo/write event with the model-produced task list', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-'))
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text:
'Use the todo_write tool to record a plan of exactly two steps: first '