Merge remote-tracking branch 'origin/master' into codex/enforce-tool-cancellation

# Conflicts:
#	docs/cookbook/adding-a-tool.i18n.yaml
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
#	packages/bash/tool-bash/src/index.ts
#	packages/core/agent-loop/README.md
#	packages/core/tools/README.md
#	packages/core/tools/tests/scoped.spec.ts
#	packages/fs/tool-fs-search/tests/tools.spec.ts
#	website/zh-CN/api/harness/events.md
#	website/zh-CN/api/harness/tools.md
This commit is contained in:
Tianyi Cui
2026-07-20 23:00:21 +08:00
736 changed files with 22158 additions and 13229 deletions

View File

@@ -3,11 +3,14 @@ import { existsSync } from 'node:fs'
import { mkdtemp, mkdir, readFile, readdir, rm, symlink, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { promisify } from 'node:util'
import { fileURLToPath } from 'node:url'
import { zstdDecompress } from 'node:zlib'
import { afterEach, describe, expect, it } from 'vitest'
const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url))
const cliBin = join(repoRoot, 'packages/examples/cli-demo/lib/bin.js')
const decompress = promisify(zstdDecompress)
const dshPackages = [
'examples/agent-spine-demo', 'examples/cli-demo', 'core/agent', 'core/session',
'core/system-prompt', 'core/tools', 'core/agent-loop', 'llm/llm', 'bash/bash',
@@ -140,8 +143,13 @@ describe.skipIf(!existsSync(cliBin))('dsh-cli-demo BUILT bin', () => {
const lines = stream.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record<string, unknown>)
expect(lines[0]).toMatchObject({ type: 'session_event', event: { type: 'turn/start' } })
expect(lines.at(-1)).toMatchObject({ type: 'result', success: true, result: 'BUILT: stream task' })
const files = await readdir(join(consumer, '.sessions'), { recursive: true })
expect(files.filter(file => file.endsWith('.jsonl'))).toHaveLength(3)
const sessionsRoot = join(consumer, '.sessions')
const files = await readdir(sessionsRoot, { recursive: true })
const logs = files.filter(file => file.endsWith('.jsonl.zstd'))
expect(logs).toHaveLength(3)
const compressed = await readFile(join(sessionsRoot, logs[0]!))
expect(compressed.subarray(0, 4).toString('hex')).toBe('28b52ffd')
expect(JSON.parse((await decompress(compressed)).toString())).toMatchObject({ type: 'session' })
}, 30_000)
it('keeps stdout empty for invalid argv and missing config', async () => {

View File

@@ -53,12 +53,14 @@ describe('dsh-cli-demo app composition', () => {
persona: 'Headless.',
tools: { mode: 'native' },
persistenceRoot: root,
persistenceCompression: 'none',
skills: await skillConfig(),
workspaceContext: false,
})
const [agent] = ctx.get('agents')?.roots() ?? []
expect(ctx.get('agentLoop')).toBeDefined()
expect(ctx.get('sessionPersistence')).toBeDefined()
expect((ctx.get('sessionPersistence') as unknown as { config: { compression?: string } }).config.compression).toBe('none')
expect(agent?.session.header.cwd).toBe(process.cwd())
expect(ctx.get('userInteraction')).toBeUndefined()
expect(ctx.get('tools')?.get('ask_user_question')).toBeUndefined()

View File

@@ -70,6 +70,15 @@ function toolResponse(usage: TokenUsage): StreamChunk[] {
]
}
function failedResponse(usage: TokenUsage): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'text' },
{ type: 'text-delta', index: 0, text: 'discarded' },
{ type: 'usage', usage },
{ type: 'finish', reason: { kind: 'error', failure: { message: 'temporary', code: 'SERVER' } } },
]
}
function reasoningResponse(text: string): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'reasoning' },
@@ -98,6 +107,7 @@ async function harness(script: readonly ScriptEntry[]): Promise<Harness> {
persistenceRoot: root,
skills: { local: { dshHome: join(skillHome, '.dsh'), agentsHome: join(skillHome, '.agents') } },
workspaceContext: false,
llmRetry: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
})
await new Promise(resolve => setTimeout(resolve, 80))
ctx.llm.registerAdapter(['mock'], new ScriptedAdapter(script))
@@ -303,7 +313,7 @@ describe('runOneShot and executeCli', () => {
expect(output).toEqual({ code: 0, stdout: 'final answer\n', stderr: '' })
expect(agent.status).toBe('disposed')
const files = await readdir(persistenceRoot, { recursive: true })
expect(files.some(file => file.endsWith('.jsonl'))).toBe(true)
expect(files.some(file => file.endsWith('.jsonl.zstd'))).toBe(true)
})
it('sums usage across tool steps and selects the last text-bearing assistant message', async () => {
@@ -323,6 +333,21 @@ describe('runOneShot and executeCli', () => {
})
})
it('counts a failed retry attempt once even though it has no assistant message', async () => {
const failed = { inputTokens: 11, outputTokens: 2, cacheReadTokens: 3 }
const recovered = { inputTokens: 7, outputTokens: 5, reasoningTokens: 4 }
const { ctx } = await harness([failedResponse(failed), textResponse('done', recovered)])
const result = await runOneShot(ctx, { task: 'task' })
expect(result.usage).toEqual({
inputTokens: 18,
outputTokens: 7,
cacheReadTokens: 3,
reasoningTokens: 4,
})
})
it('keeps the prior text when a later assistant message has no text blocks', async () => {
const { ctx } = await harness([
toolResponse({ inputTokens: 1, outputTokens: 1 }),
@@ -463,6 +488,7 @@ describe('formatTurnFailure', () => {
[{ kind: 'aborted' }, 'was aborted'],
[{ kind: 'aborted', reason: 'stop' }, 'was aborted: stop'],
[{ kind: 'error', step: 2, message: 'bad' }, 'failed at step 2: bad'],
[{ kind: 'error', step: 3, failure: { message: 'provider bad', code: 'SERVER' } }, 'failed at step 3: provider bad'],
[{ kind: 'disposed' }, 'was disposed'],
[{ kind: 'max-tokens' }, 'output-token limit'],
[{ kind: 'rejected', reason: 'policy' }, 'was rejected: policy'],