Merge remote-tracking branch 'origin/master' into feat/tui-package

# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/coding-agent/cordis.yml
#	examples/echo-agent/cordis.yml
#	knip.json
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/tests/config-session-id.spec.ts
#	packages/examples/README.md
#	packages/examples/stdio-demo/README.md
#	packages/examples/stdio-demo/tests/stdio-agent.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-18 21:17:10 +08:00
724 changed files with 40896 additions and 9028 deletions

View File

@@ -1,10 +1,10 @@
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'
@@ -14,6 +14,9 @@ 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 +26,7 @@ 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
@@ -45,13 +49,29 @@ 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
}
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: ReactLoopAgent): Promise<void> {
return new Promise((resolve) => {
const dispose = harness.on('agent/status', (subject, status) => {
@@ -67,7 +87,7 @@ 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(AgentId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',
@@ -107,4 +127,43 @@ 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({
agentId: AgentId('e2e-code-mode-workspace'),
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 as ReactLoopAgent)
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)
})

View File

@@ -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(AgentId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',

View File

@@ -33,17 +33,20 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
// Reasoning tokens require a larger generation cap than the retained checkpoint.
ctx = await codingHarness(workdir, {
persona: SYSTEM_PROMPT,
compact: {
tokenMeter: {
contextWindow: 2000,
},
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(AgentId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
type: 'text',

View File

@@ -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(AgentId('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)

View File

@@ -1,15 +1,13 @@
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 { 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'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
@@ -46,23 +44,26 @@ export interface CodingHarnessOptions {
* compaction plugin (the default suites run without it).
*/
compact?: BasicCompactConfig
/** Optional token-meter capacity loaded before compact-basic. */
tokenMeter?: TokenMeterConfig
}
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)
// Compaction is opt-in: only the compaction e2e loads it, with a lowered
// contextWindow/retainTokens so a short real session crosses the threshold.
if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact)
// Compaction is opt-in: only the compaction e2e loads the reusable meter and
// backend, with a lower context window so a short real session crosses the threshold.
if (options.compact !== undefined) {
await ctx.plugin(TokenMeterService, options.tokenMeter)
await ctx.plugin(BasicCompactService, options.compact)
}
// Durable JSONL persistence is opt-in: only the resume e2e needs it, and the
// other suites stay file-free. Loaded last so a resume's deferred
// `ctx.inject(['sessionPersistence'])` resolves once this is present.

View File

@@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
const first = (await ctx.agents.create({
agentId: AgentId('resume-1'),
sessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
@@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
const resumed = (await ctx.agents.resume({
agentId: AgentId('resume-2'),
resumeSessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
expect(resumed.session.id).toBe(SESSION_ID)
// The prior user turn is in the rehydrated log before the model is asked.

View File

@@ -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(AgentId('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 '