惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
T
Threat Research - Cisco Blogs
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
Cyber Attacks, Cyber Crime and Cyber Security
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
T
Troy Hunt's Blog
V
V2EX - 技术
Hacker News - Newest:
Hacker News - Newest: "LLM"
H
Heimdal Security Blog
T
Tor Project blog
IT之家
IT之家
Project Zero
Project Zero
GbyAI
GbyAI
Security Latest
Security Latest
S
Security Archives - TechRepublic
人人都是产品经理
人人都是产品经理
大猫的无限游戏
大猫的无限游戏
Spread Privacy
Spread Privacy
S
Security Affairs
A
Arctic Wolf
C
Cybersecurity and Infrastructure Security Agency CISA
I
Intezer
P
Palo Alto Networks Blog
宝玉的分享
宝玉的分享
Google DeepMind News
Google DeepMind News
T
Threatpost
I
InfoQ
F
Full Disclosure
Blog — PlanetScale
Blog — PlanetScale
Last Week in AI
Last Week in AI
Cisco Talos Blog
Cisco Talos Blog
N
Netflix TechBlog - Medium
MyScale Blog
MyScale Blog
H
Help Net Security
S
Securelist
Y
Y Combinator Blog
月光博客
月光博客
博客园_首页
Engineering at Meta
Engineering at Meta
酷 壳 – CoolShell
酷 壳 – CoolShell
J
Java Code Geeks
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
A
About on SuperTechFans
K
Kaspersky official blog
Microsoft Azure Blog
Microsoft Azure Blog
Vercel News
Vercel News
阮一峰的网络日志
阮一峰的网络日志
T
The Exploit Database - CXSecurity.com
B
Blog

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4 test: trim doctor command hotspots · openclaw/openclaw@c66f16a test: isolate agent auth and spawn hotspots · openclaw/openclaw@9285935 test: stabilize MCP startup disposal race · openclaw/openclaw@dd9d2eb test: merge browser contract server suites · openclaw/openclaw@5817a76 test: narrow ollama provider discovery setup · openclaw/openclaw@a0d9598 build: declare qa-lab aimock runtime dependency · openclaw/openclaw@24431e5 test: speed up safe-bins exec harness · openclaw/openclaw@ee856ab test: preserve tool helpers in embedded runner mocks · openclaw/openclaw@acd86a0 refactor: move memory embeddings into provider plugins · openclaw/openclaw@77e6e4c test: reuse system-run temp fixtures · openclaw/openclaw@7e9ff0f test: trim hotspot wait overhead · openclaw/openclaw@12a59b0 Check: avoid duplicate boundary prep · openclaw/openclaw@baf11b8 test: reduce hotspot fixture overhead · openclaw/openclaw@3a59edd feat(ui): overhaul settings and slash command UX (#67819) thanks @Bun… · openclaw/openclaw@2cfb660 QA Matrix: exit cleanly on failure · openclaw/openclaw@42805d2 QA Matrix: isolate scenario coverage · openclaw/openclaw@7e659e1 Matrix: refresh crypto bootstrap state · openclaw/openclaw@94081d8 QA Lab: add provider registry · openclaw/openclaw@bb7e982 Matrix: add plugin changelog · openclaw/openclaw@4acab55 test: trim more hotspot overhead · openclaw/openclaw@f485311 test: trim remaining hotspot tests · openclaw/openclaw@6ba8626 test: narrow hotspot mocks · openclaw/openclaw@dbc8179 test: isolate gemini embedding request helpers · openclaw/openclaw@cd330f5 test: trim memory and mcp hotspots · openclaw/openclaw@fd48dfa test: slim provider registry mocks · openclaw/openclaw@2e08c77 test: harden Parallels update smoke · openclaw/openclaw@1a98090 feat: default Anthropic to Opus 4.7 · openclaw/openclaw@628b454 fix: harden node-host shell payload mutability checks · openclaw/openclaw@75c551e fix: land node-host approval binding for native binaries (#66731) (th… · openclaw/openclaw@29919bb CI: add daily schedule to CodeQL workflow (#67645) fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… fix: restrict HTML timeout short-circuit to transient statuses fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) Gateway/skills: dedupe skills prefix-match + drop dead fallback on log Extensions/lmstudio: back off inference preload after consecutive fai… TUI/streaming: add watchdog that resets the activity indicator after … Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write fix: classify HTML provider error pages correctly (#67642) (thanks @s… fix(skills): remove unused model-usage import (#67641) · openclaw/openclaw@55f05df docs(changelog): credit codex fix superseded PRs · openclaw/openclaw@e485f24 fix(openai-codex): normalize stale transport metadata in resolution a… · openclaw/openclaw@90801ba CI: pin Docker-related GitHub Actions (#67632) · openclaw/openclaw@f697b01 Android: modernize WebView and discovery API usage (#67627) · openclaw/openclaw@44a6e50 fix(deps): bump hono to 4.12.14 and @hono/node-server to 1.19.14 (GHS… fix(deps): bump dompurify to 3.4.0 (#67614) CI: add explicit permissions to all workflow jobs (fixes code-scannin… fix: register bundled TTS providers and route overrides correctly (#6… fix: align host tilde paths with OS home (#62804) (thanks @stainlu) fix: flush creds queue before reconnect socket open (#67464) (thanks … · openclaw/openclaw@405c63f fix: strip standalone <function> tool call tags from visible text (#6… · openclaw/openclaw@78df859 fix(agents): preserve cli session metadata before transcript persist … · openclaw/openclaw@898fd04 docs(changelog): move cli transcript entry · openclaw/openclaw@c1817c6 fix(agents): normalize cli transcript api field · openclaw/openclaw@3a3fae0 docs(changelog): note cli transcript persistence · openclaw/openclaw@6c343f1 fix(agents): persist cli transcript turns · openclaw/openclaw@b8ef507 fix(msteams): harden security-sensitive flows (#65841) · openclaw/openclaw@c56b56e [Dashboard] Fix exec approval modal overflow for long command content… · openclaw/openclaw@053c5b0 Docs: remove QA changelog entry · openclaw/openclaw@7fd5771 QA: fix private runtime source loading (#67428) · openclaw/openclaw@d5933af docs(gateway): correct protocol.md schema path, hello-ok example, aut… · openclaw/openclaw@489404d CI: pin Node 22 runners to 22.18.0 · openclaw/openclaw@4ffa621 models.authStatus: normalize provider ids + tighten env-backed escape… · openclaw/openclaw@f2fdb9d Update CHANGELOG.md · openclaw/openclaw@7694a92 test(parallels): clean up npm update guard jobs · openclaw/openclaw@045ea7b Plugins: prefer scanDir override paths · openclaw/openclaw@b2974da fix(dreaming): default storage.mode to "separate" so phase blocks sto… · openclaw/openclaw@8c392f0 fix(memory-core): skip dreaming transcript ingestion via session stor… · openclaw/openclaw@a1b01f0 fix: dedupe replayed exec.finished node events (#67281) · openclaw/openclaw@5dcf526
feat(codex): add llm lifecycle hooks (#70312) · openclaw/openclaw@34e45ec
vincentkoc · 2026-04-23 · via Recent Commits to openclaw:main

@@ -114,6 +114,9 @@ function createAppServerHarness(

114114

},

115115

});

116116

},

117+

async notify(notification: CodexServerNotification) {

118+

await notify(notification);

119+

},

117120

};

118121

}

119122

@@ -238,6 +241,209 @@ describe("runCodexAppServerAttempt", () => {

238241

);

239242

});

240243244+

it("fires llm_input, llm_output, and agent_end hooks for codex turns", async () => {

245+

const llmInput = vi.fn();

246+

const llmOutput = vi.fn();

247+

const agentEnd = vi.fn();

248+

initializeGlobalHookRunner(

249+

createMockPluginRegistry([

250+

{ hookName: "llm_input", handler: llmInput },

251+

{ hookName: "llm_output", handler: llmOutput },

252+

{ hookName: "agent_end", handler: agentEnd },

253+

]),

254+

);

255+

const sessionFile = path.join(tempDir, "session.jsonl");

256+

const workspaceDir = path.join(tempDir, "workspace");

257+

const sessionManager = SessionManager.open(sessionFile);

258+

sessionManager.appendMessage(assistantMessage("existing context", Date.now()));

259+

const harness = createStartedThreadHarness();

260+261+

const run = runCodexAppServerAttempt(createParams(sessionFile, workspaceDir));

262+

await harness.waitForMethod("turn/start");

263+

await vi.waitFor(() => expect(llmInput).toHaveBeenCalledTimes(1), { interval: 1 });

264+265+

expect(llmInput).toHaveBeenCalledWith(

266+

expect.objectContaining({

267+

runId: "run-1",

268+

sessionId: "session-1",

269+

provider: "codex",

270+

model: "gpt-5.4-codex",

271+

prompt: "hello",

272+

imagesCount: 0,

273+

historyMessages: [expect.objectContaining({ role: "assistant" })],

274+

systemPrompt: expect.stringContaining(CODEX_GPT5_BEHAVIOR_CONTRACT),

275+

}),

276+

expect.objectContaining({

277+

runId: "run-1",

278+

sessionId: "session-1",

279+

sessionKey: "agent:main:session-1",

280+

}),

281+

);

282+283+

await harness.notify({

284+

method: "item/agentMessage/delta",

285+

params: {

286+

threadId: "thread-1",

287+

turnId: "turn-1",

288+

itemId: "msg-1",

289+

delta: "hello back",

290+

},

291+

});

292+

await harness.completeTurn({ threadId: "thread-1", turnId: "turn-1" });

293+

const result = await run;

294+295+

expect(result.assistantTexts).toEqual(["hello back"]);

296+

await vi.waitFor(() => expect(llmOutput).toHaveBeenCalledTimes(1), { interval: 1 });

297+

await vi.waitFor(() => expect(agentEnd).toHaveBeenCalledTimes(1), { interval: 1 });

298+299+

expect(llmOutput).toHaveBeenCalledWith(

300+

expect.objectContaining({

301+

runId: "run-1",

302+

sessionId: "session-1",

303+

provider: "codex",

304+

model: "gpt-5.4-codex",

305+

assistantTexts: ["hello back"],

306+

lastAssistant: expect.objectContaining({

307+

role: "assistant",

308+

}),

309+

}),

310+

expect.objectContaining({

311+

runId: "run-1",

312+

sessionId: "session-1",

313+

}),

314+

);

315+

expect(agentEnd).toHaveBeenCalledWith(

316+

expect.objectContaining({

317+

success: true,

318+

messages: expect.arrayContaining([

319+

expect.objectContaining({ role: "user" }),

320+

expect.objectContaining({ role: "assistant" }),

321+

]),

322+

}),

323+

expect.objectContaining({

324+

runId: "run-1",

325+

sessionId: "session-1",

326+

}),

327+

);

328+

});

329+330+

it("fires agent_end with failure metadata when the codex turn fails", async () => {

331+

const agentEnd = vi.fn();

332+

initializeGlobalHookRunner(

333+

createMockPluginRegistry([{ hookName: "agent_end", handler: agentEnd }]),

334+

);

335+

const sessionFile = path.join(tempDir, "session.jsonl");

336+

const workspaceDir = path.join(tempDir, "workspace");

337+

const harness = createStartedThreadHarness();

338+339+

const run = runCodexAppServerAttempt(createParams(sessionFile, workspaceDir));

340+

await harness.waitForMethod("turn/start");

341+

await harness.notify({

342+

method: "turn/completed",

343+

params: {

344+

threadId: "thread-1",

345+

turnId: "turn-1",

346+

turn: {

347+

id: "turn-1",

348+

status: "failed",

349+

error: { message: "codex exploded" },

350+

},

351+

},

352+

});

353+354+

const result = await run;

355+356+

expect(result.promptError).toBe("codex exploded");

357+

await vi.waitFor(() => expect(agentEnd).toHaveBeenCalledTimes(1), { interval: 1 });

358+

expect(agentEnd).toHaveBeenCalledWith(

359+

expect.objectContaining({

360+

success: false,

361+

error: "codex exploded",

362+

}),

363+

expect.objectContaining({

364+

runId: "run-1",

365+

sessionId: "session-1",

366+

}),

367+

);

368+

});

369+370+

it("fires llm_output and agent_end when turn/start fails", async () => {

371+

const llmInput = vi.fn();

372+

const llmOutput = vi.fn();

373+

const agentEnd = vi.fn();

374+

initializeGlobalHookRunner(

375+

createMockPluginRegistry([

376+

{ hookName: "llm_input", handler: llmInput },

377+

{ hookName: "llm_output", handler: llmOutput },

378+

{ hookName: "agent_end", handler: agentEnd },

379+

]),

380+

);

381+

const sessionFile = path.join(tempDir, "session.jsonl");

382+

const workspaceDir = path.join(tempDir, "workspace");

383+

SessionManager.open(sessionFile).appendMessage(

384+

assistantMessage("existing context", Date.now()),

385+

);

386+

createStartedThreadHarness(async (method) => {

387+

if (method === "turn/start") {

388+

throw new Error("turn start exploded");

389+

}

390+

return undefined;

391+

});

392+393+

await expect(runCodexAppServerAttempt(createParams(sessionFile, workspaceDir))).rejects.toThrow(

394+

"turn start exploded",

395+

);

396+397+

await vi.waitFor(() => expect(llmInput).toHaveBeenCalledTimes(1), { interval: 1 });

398+

await vi.waitFor(() => expect(llmOutput).toHaveBeenCalledTimes(1), { interval: 1 });

399+

await vi.waitFor(() => expect(agentEnd).toHaveBeenCalledTimes(1), { interval: 1 });

400+

expect(llmOutput).toHaveBeenCalledWith(

401+

expect.objectContaining({

402+

assistantTexts: [],

403+

model: "gpt-5.4-codex",

404+

provider: "codex",

405+

runId: "run-1",

406+

sessionId: "session-1",

407+

}),

408+

expect.any(Object),

409+

);

410+

expect(agentEnd).toHaveBeenCalledWith(

411+

expect.objectContaining({

412+

success: false,

413+

error: "turn start exploded",

414+

messages: expect.arrayContaining([

415+

expect.objectContaining({ role: "assistant" }),

416+

expect.objectContaining({ role: "user" }),

417+

]),

418+

}),

419+

expect.any(Object),

420+

);

421+

});

422+423+

it("fires agent_end with success false when the codex turn is aborted", async () => {

424+

const agentEnd = vi.fn();

425+

initializeGlobalHookRunner(

426+

createMockPluginRegistry([{ hookName: "agent_end", handler: agentEnd }]),

427+

);

428+

const { waitForMethod } = createStartedThreadHarness();

429+

const run = runCodexAppServerAttempt(

430+

createParams(path.join(tempDir, "session.jsonl"), path.join(tempDir, "workspace")),

431+

);

432+433+

await waitForMethod("turn/start");

434+

expect(abortAgentHarnessRun("session-1")).toBe(true);

435+436+

const result = await run;

437+

expect(result.aborted).toBe(true);

438+

await vi.waitFor(() => expect(agentEnd).toHaveBeenCalledTimes(1), { interval: 1 });

439+

expect(agentEnd).toHaveBeenCalledWith(

440+

expect.objectContaining({

441+

success: false,

442+

}),

443+

expect.any(Object),

444+

);

445+

});

446+241447

it("forwards queued user input and aborts the active app-server turn", async () => {

242448

const { requests, waitForMethod } = createStartedThreadHarness();

243449