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

L
LINUX DO - 热门话题
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
S
Security @ Cisco Blogs
W
WeLiveSecurity
N
News and Events Feed by Topic
Security Archives - TechRepublic
Security Archives - TechRepublic
V2EX - 技术
V2EX - 技术
TaoSecurity Blog
TaoSecurity Blog
L
LINUX DO - 最新话题
Cloudbric
Cloudbric
S
Secure Thoughts
Recent Commits to openclaw:main
Recent Commits to openclaw:main
C
CXSECURITY Database RSS Feed - CXSecurity.com
Forbes - Security
Forbes - Security
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
The Blog of Author Tim Ferriss
博客园 - 【当耐特】
NISL@THU
NISL@THU
F
Full Disclosure
博客园_首页
Blog — PlanetScale
Blog — PlanetScale
腾讯CDC
B
Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
B
Blog RSS Feed
Jina AI
Jina AI
N
News | PayPal Newsroom
G
Google Developers Blog
P
Proofpoint News Feed
雷峰网
雷峰网
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
P
Proofpoint News Feed
PCI Perspectives
PCI Perspectives
H
Heimdal Security Blog
GbyAI
GbyAI
Project Zero
Project Zero
Hacker News - Newest:
Hacker News - Newest: "LLM"
Y
Y Combinator Blog
S
Schneier on Security
Hacker News: Ask HN
Hacker News: Ask HN
S
Security Affairs
P
Privacy & Cybersecurity Law Blog
Attack and Defense Labs
Attack and Defense Labs
美团技术团队
T
Threat Research - Cisco Blogs
T
Threatpost
The Hacker News
The Hacker News
C
Cisco Blogs
Last Week in AI
Last Week in AI
Google DeepMind News
Google DeepMind News

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) · openclaw/openclaw@69d25f5 fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… · openclaw/openclaw@c3c7a99 fix: restrict HTML timeout short-circuit to transient statuses · openclaw/openclaw@de129a6 fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) · openclaw/openclaw@3525273 Gateway/skills: dedupe skills prefix-match + drop dead fallback on log · openclaw/openclaw@d7f489f Extensions/lmstudio: back off inference preload after consecutive fai… · openclaw/openclaw@b555214 TUI/streaming: add watchdog that resets the activity indicator after … · openclaw/openclaw@f44ab20 Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write · openclaw/openclaw@b23d59a fix: classify HTML provider error pages correctly (#67642) (thanks @s… · openclaw/openclaw@e588e90 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… · openclaw/openclaw@fbccc18 fix(deps): bump dompurify to 3.4.0 (#67614) · openclaw/openclaw@2c2dc00 CI: add explicit permissions to all workflow jobs (fixes code-scannin… · openclaw/openclaw@01b7516 fix: register bundled TTS providers and route overrides correctly (#6… · openclaw/openclaw@6ea3cdd fix: align host tilde paths with OS home (#62804) (thanks @stainlu) · openclaw/openclaw@ecfaf64 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
test(ci): stabilize timeout-sensitive shards · openclaw/openclaw@2c49975
vincentkoc · 2026-06-19 · via Recent Commits to openclaw:main

@@ -2,13 +2,8 @@

22

import path from "node:path";

33

import {

44

onAgentEvent,

5-

wrapToolWithBeforeToolCallHook,

65

type AgentEventPayload,

76

} from "openclaw/plugin-sdk/agent-harness-runtime";

8-

import {

9-

createTerminalPresentationContractTool,

10-

textToolResult,

11-

} from "openclaw/plugin-sdk/agent-runtime-test-contracts";

127

import {

138

emitTrustedDiagnosticEvent,

149

onInternalDiagnosticEvent,

@@ -23,14 +18,9 @@ import {

2318

emitDynamicToolTerminalDiagnostic,

2419

} from "./dynamic-tool-diagnostics.js";

2520

import { createCodexDynamicToolBridge } from "./dynamic-tools.js";

26-

import {

27-

flattenCodexDynamicToolFunctions,

28-

type CodexDynamicToolCallParams,

29-

type CodexDynamicToolSpec,

30-

} from "./protocol.js";

21+

import type { CodexDynamicToolCallParams } from "./protocol.js";

3122

import {

3223

createParams,

33-

createCodexRuntimePlanFixture,

3424

createRuntimeDynamicTool,

3525

createStartedThreadHarness,

3626

runCodexAppServerAttempt,

@@ -43,10 +33,6 @@ function flushDiagnosticEvents() {

4333

return waitForDiagnosticEventsDrained();

4434

}

453546-

function specNames(specs: readonly CodexDynamicToolSpec[]): string[] {

47-

return flattenCodexDynamicToolFunctions(specs).map((tool) => tool.name);

48-

}

49-5036

function activeDiagnosticToolKeys(events: DiagnosticEventPayload[]): Set<string> {

5137

const active = new Set<string>();

5238

for (const event of events) {

@@ -70,246 +56,6 @@ function activeDiagnosticToolKeys(events: DiagnosticEventPayload[]): Set<string>

7056

setupRunAttemptTestHooks();

71577258

describe("runCodexAppServerAttempt dynamic tools", () => {

73-

it("preserves model order across queued native and dynamic tools", async () => {

74-

let rejectSlowTool!: (error: Error) => void;

75-

const slowToolResult = new Promise<never>((_resolve, reject) => {

76-

rejectSlowTool = reject;

77-

});

78-

const slowTool = createRuntimeDynamicTool("slow_failure");

79-

slowTool.execute = vi.fn(() => slowToolResult);

80-

const laterTool = createTerminalPresentationContractTool({

81-

name: "fast_summary",

82-

result: textToolResult("fast result"),

83-

format: () => "later dynamic summary",

84-

});

85-

const harness = createStartedThreadHarness();

86-

const params = createParams(

87-

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

88-

path.join(tempDir, "workspace"),

89-

);

90-

let terminalPresentation: string | undefined;

91-

let latestOrdinal = -1;

92-

let nextOrdinal = 0;

93-

const onExecutionPhase = vi.fn();

94-

params.disableTools = false;

95-

params.runtimePlan = createCodexRuntimePlanFixture();

96-

params.allocateToolOutcomeOrdinal = () => nextOrdinal++;

97-

params.onExecutionPhase = onExecutionPhase;

98-

params.onToolOutcome = (observation) => {

99-

const ordinal = observation.toolCallOrdinal ?? latestOrdinal + 1;

100-

if (ordinal >= latestOrdinal) {

101-

latestOrdinal = ordinal;

102-

terminalPresentation = observation.terminalPresentation;

103-

}

104-

};

105-

testing.setOpenClawCodingToolsFactoryForTests((options) =>

106-

[slowTool, laterTool].map((tool) =>

107-

wrapToolWithBeforeToolCallHook(tool, {

108-

runId: options?.runId,

109-

sessionId: options?.sessionId,

110-

sessionKey: options?.sessionKey,

111-

onToolOutcome: options?.onToolOutcome,

112-

allocateToolOutcomeOrdinal: options?.allocateToolOutcomeOrdinal,

113-

}),

114-

),

115-

);

116-117-

const run = runCodexAppServerAttempt(params);

118-

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

119-

await vi.waitFor(() =>

120-

expect(onExecutionPhase).toHaveBeenCalledWith(

121-

expect.objectContaining({ phase: "turn_accepted" }),

122-

),

123-

);

124-

for (const item of [

125-

{

126-

type: "function_call",

127-

name: "slow_failure",

128-

arguments: "{}",

129-

call_id: "call-slow",

130-

},

131-

{

132-

type: "function_call",

133-

name: "shell_command",

134-

arguments: '{"command":"git status --short"}',

135-

call_id: "command-before-dynamic",

136-

},

137-

]) {

138-

await harness.notify({

139-

method: "rawResponseItem/completed",

140-

params: { threadId: "thread-1", turnId: "turn-1", item },

141-

});

142-

}

143-

const webSearchItem = {

144-

type: "webSearch",

145-

id: "web-search-before-dynamic",

146-

query: "OpenClaw",

147-

status: "completed",

148-

durationMs: 1,

149-

};

150-

const webSearchStarted = harness.notify({

151-

method: "item/started",

152-

params: { threadId: "thread-1", turnId: "turn-1", item: webSearchItem },

153-

});

154-

const rawWebSearch = harness.notify({

155-

method: "rawResponseItem/completed",

156-

params: {

157-

threadId: "thread-1",

158-

turnId: "turn-1",

159-

item: {

160-

type: "web_search_call",

161-

status: "completed",

162-

action: { type: "search", query: "OpenClaw" },

163-

},

164-

},

165-

});

166-

await harness.notify({

167-

method: "rawResponseItem/completed",

168-

params: {

169-

threadId: "thread-1",

170-

turnId: "turn-1",

171-

item: {

172-

type: "function_call",

173-

name: "fast_summary",

174-

arguments: "{}",

175-

call_id: "call-later",

176-

},

177-

},

178-

});

179-

await rawWebSearch;

180-

const slowCall = harness.handleServerRequest({

181-

id: "request-slow",

182-

method: "item/tool/call",

183-

params: {

184-

threadId: "thread-1",

185-

turnId: "turn-1",

186-

callId: "call-slow",

187-

namespace: null,

188-

tool: "slow_failure",

189-

arguments: {},

190-

},

191-

});

192-

const nativeItem = {

193-

type: "commandExecution",

194-

id: "command-before-dynamic",

195-

command: "git status --short",

196-

cwd: "/workspace",

197-

processId: null,

198-

source: "agent",

199-

status: "completed",

200-

commandActions: [{ type: "unknown", command: "git status --short" }],

201-

aggregatedOutput: "",

202-

exitCode: 0,

203-

durationMs: 1,

204-

};

205-

const nativeStarted = harness.notify({

206-

method: "item/started",

207-

params: { threadId: "thread-1", turnId: "turn-1", item: nativeItem },

208-

});

209-

await harness.handleServerRequest({

210-

id: "request-later",

211-

method: "item/tool/call",

212-

params: {

213-

threadId: "thread-1",

214-

turnId: "turn-1",

215-

callId: "call-later",

216-

namespace: null,

217-

tool: "fast_summary",

218-

arguments: {},

219-

},

220-

});

221-

await nativeStarted;

222-

await webSearchStarted;

223-

await harness.notify({

224-

method: "item/completed",

225-

params: { threadId: "thread-1", turnId: "turn-1", item: nativeItem },

226-

});

227-

await harness.notify({

228-

method: "item/completed",

229-

params: { threadId: "thread-1", turnId: "turn-1", item: webSearchItem },

230-

});

231-

rejectSlowTool(new Error("slow failure"));

232-

await slowCall;

233-

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

234-

await run;

235-236-

expect(terminalPresentation).toBe("later dynamic summary");

237-

});

238-239-

it("suppresses a late dynamic tool presentation after its timeout response", async () => {

240-

let resolveSlowTool!: (result: ReturnType<typeof textToolResult>) => void;

241-

const slowToolResult = new Promise<ReturnType<typeof textToolResult>>((resolve) => {

242-

resolveSlowTool = resolve;

243-

});

244-

const formatTerminalPresentation = vi.fn(() => "late success summary");

245-

const slowTool = createTerminalPresentationContractTool({

246-

name: "slow_summary",

247-

result: textToolResult("unused"),

248-

format: formatTerminalPresentation,

249-

});

250-

slowTool.execute = vi.fn(() => slowToolResult);

251-

const harness = createStartedThreadHarness();

252-

const params = createParams(

253-

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

254-

path.join(tempDir, "workspace"),

255-

);

256-

let terminalPresentation: string | undefined = "previous summary";

257-

let latestOrdinal = -1;

258-

let nextOrdinal = 0;

259-

const onExecutionPhase = vi.fn();

260-

params.disableTools = false;

261-

params.runtimePlan = createCodexRuntimePlanFixture();

262-

params.allocateToolOutcomeOrdinal = () => nextOrdinal++;

263-

params.onExecutionPhase = onExecutionPhase;

264-

params.onToolOutcome = (observation) => {

265-

const ordinal = observation.toolCallOrdinal ?? latestOrdinal + 1;

266-

if (ordinal >= latestOrdinal) {

267-

latestOrdinal = ordinal;

268-

terminalPresentation = observation.terminalPresentation;

269-

}

270-

};

271-

testing.setOpenClawCodingToolsFactoryForTests((options) => [

272-

wrapToolWithBeforeToolCallHook(slowTool, {

273-

runId: options?.runId,

274-

sessionId: options?.sessionId,

275-

sessionKey: options?.sessionKey,

276-

onToolOutcome: options?.onToolOutcome,

277-

allocateToolOutcomeOrdinal: options?.allocateToolOutcomeOrdinal,

278-

}),

279-

]);

280-281-

const run = runCodexAppServerAttempt(params);

282-

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

283-

await vi.waitFor(() =>

284-

expect(onExecutionPhase).toHaveBeenCalledWith(

285-

expect.objectContaining({ phase: "turn_accepted" }),

286-

),

287-

);

288-

const response = await harness.handleServerRequest({

289-

id: "request-timeout",

290-

method: "item/tool/call",

291-

params: {

292-

threadId: "thread-1",

293-

turnId: "turn-1",

294-

callId: "call-timeout",

295-

namespace: null,

296-

tool: "slow_summary",

297-

arguments: { timeoutMs: 1 },

298-

},

299-

});

300-

expect(response).toMatchObject({ success: false });

301-

expect(terminalPresentation).toBeUndefined();

302-303-

resolveSlowTool(textToolResult("late result"));

304-

await vi.waitFor(() => {

305-

expect(formatTerminalPresentation).toHaveBeenCalled();

306-

});

307-

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

308-

await run;

309-310-

expect(terminalPresentation).toBeUndefined();

311-

});

312-31359

it("passes the live run session key to Codex dynamic tools when sandbox policy uses another key", () => {

31460

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

31561

const params = createParams(path.join(tempDir, "session.jsonl"), workspaceDir);

@@ -331,75 +77,6 @@ describe("runCodexAppServerAttempt dynamic tools", () => {

33177

});

33278

});

33379334-

it("keeps Codex native code mode while registering node shell tools for node sessions", async () => {

335-

const harness = createStartedThreadHarness();

336-

const params = createParams(

337-

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

338-

path.join(tempDir, "workspace"),

339-

);

340-

params.disableTools = false;

341-

params.runtimePlan = createCodexRuntimePlanFixture();

342-

params.execOverrides = {

343-

host: "node",

344-

node: "mac-mini",

345-

security: "full",

346-

ask: "off",

347-

};

348-

params.config = {

349-

mcp: {

350-

servers: {

351-

local_docs: {

352-

transport: "stdio",

353-

command: "node",

354-

args: ["/opt/local-docs-mcp/dist/index.js"],

355-

},

356-

},

357-

},

358-

} as never;

359-

testing.setOpenClawCodingToolsFactoryForTests(() => [

360-

createRuntimeDynamicTool("exec"),

361-

createRuntimeDynamicTool("process"),

362-

createRuntimeDynamicTool("message"),

363-

]);

364-365-

const run = runCodexAppServerAttempt(params);

366-

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

367-

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

368-369-

const startParams = harness.requests.find((request) => request.method === "thread/start")

370-

?.params as

371-

| {

372-

config?: {

373-

"features.code_mode"?: boolean;

374-

"features.code_mode_only"?: boolean;

375-

mcp_servers?: Record<string, unknown>;

376-

};

377-

dynamicTools?: CodexDynamicToolSpec[];

378-

environments?: unknown[];

379-

}

380-

| undefined;

381-382-

expect(startParams?.config).toMatchObject({

383-

"features.code_mode": true,

384-

"features.code_mode_only": false,

385-

mcp_servers: {

386-

local_docs: {

387-

command: "node",

388-

args: ["/opt/local-docs-mcp/dist/index.js"],

389-

},

390-

},

391-

});

392-

expect(startParams?.environments).toBeUndefined();

393-

expect(specNames(startParams?.dynamicTools ?? [])).toEqual([

394-

"message",

395-

"node_exec",

396-

"node_process",

397-

]);

398-399-

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

400-

await run;

401-

});

402-40380

it("emits normalized tool progress around app-server dynamic tool requests", async () => {

40481

const harness = createStartedThreadHarness();

40582

const onRunAgentEvent = vi.fn();