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

人人都是产品经理
人人都是产品经理
Microsoft Azure Blog
Microsoft Azure Blog
V
V2EX
阮一峰的网络日志
阮一峰的网络日志
宝玉的分享
宝玉的分享
Hugging Face - Blog
Hugging Face - Blog
Y
Y Combinator Blog
Recorded Future
Recorded Future
博客园 - Franky
F
Fortinet All Blogs
The Register - Security
The Register - Security
雷峰网
雷峰网
博客园 - 【当耐特】
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
WordPress大学
WordPress大学
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Recent Announcements
Recent Announcements
S
Schneier on Security
Latest news
Latest news
S
Securelist
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Blog — PlanetScale
Blog — PlanetScale
L
Lohrmann on Cybersecurity
V
Visual Studio Blog
NISL@THU
NISL@THU
Cyberwarzone
Cyberwarzone
H
Hackread – Cybersecurity News, Data Breaches, AI and More
腾讯CDC
Spread Privacy
Spread Privacy
酷 壳 – CoolShell
酷 壳 – CoolShell
Security Latest
Security Latest
A
About on SuperTechFans
大猫的无限游戏
大猫的无限游戏
SecWiki News
SecWiki News
N
News and Events Feed by Topic
T
Threatpost
The GitHub Blog
The GitHub Blog
博客园_首页
F
Full Disclosure
爱范儿
爱范儿
The Hacker News
The Hacker News
T
The Blog of Author Tim Ferriss
Stack Overflow Blog
Stack Overflow Blog
Last Week in AI
Last Week in AI
月光博客
月光博客
C
Check Point Blog
G
Google Developers Blog
M
MIT News - Artificial intelligence
博客园 - 司徒正美

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(qa-lab): add runtime tool fixtures · openclaw/openclaw@d217fd7
vincentkoc · 2026-05-17 · via Recent Commits to openclaw:main

@@ -173,6 +173,7 @@ const QA_SKILL_WORKSHOP_GIF_PROMPT_RE =

173173

const QA_SKILL_WORKSHOP_REVIEW_PROMPT_RE = /Review transcript for durable skill updates/i;

174174

const QA_RELEASE_AUDIT_PROMPT_RE = /release readiness audit for the small project/i;

175175

const QA_TOOL_SEARCH_PROMPT_RE = /tool search qa check/i;

176+

const QA_TOOL_SEARCH_FAILURE_PROMPT_RE = /tool search qa failure/i;

176177177178

type MockScenarioState = {

178179

subagentFanoutPhase: number;

@@ -678,6 +679,69 @@ function extractToolSearchTarget(text: string): string | null {

678679

return match?.[1]?.trim() || null;

679680

}

680681682+

function buildQaToolSearchArgs(targetTool: string, failureMode: boolean): Record<string, unknown> {

683+

if (failureMode) {

684+

return { __qaFailureMode: "denied-input" };

685+

}

686+

if (targetTool === "exec") {

687+

return { command: "echo runtime-tool-fixture", timeout: 5 };

688+

}

689+

if (targetTool === "read") {

690+

return { path: "QA_KICKOFF_TASK.md" };

691+

}

692+

if (targetTool === "write") {

693+

return { path: "runtime-tool-fixture-write.txt", content: "runtime tool fixture\n" };

694+

}

695+

if (targetTool === "edit") {

696+

return {

697+

path: "runtime-tool-fixture-edit.txt",

698+

edits: [{ oldText: "before edit\n", newText: "after edit\n" }],

699+

};

700+

}

701+

if (targetTool === "apply_patch") {

702+

return {

703+

input: [

704+

"*** Begin Patch",

705+

"*** Add File: runtime-tool-fixture-patch.txt",

706+

"+runtime patch",

707+

"*** End Patch",

708+

"",

709+

].join("\n"),

710+

};

711+

}

712+

if (targetTool === "web_search") {

713+

return { query: "OpenClaw runtime parity fixed query", count: 1 };

714+

}

715+

if (targetTool === "web_fetch") {

716+

return { url: "https://example.com/", maxChars: 500 };

717+

}

718+

if (targetTool === "image_generate") {

719+

return { prompt: "QA lighthouse runtime parity fixture", filename: "runtime-tool-fixture" };

720+

}

721+

if (targetTool === "tts") {

722+

return { text: "Runtime parity voice fixture." };

723+

}

724+

if (targetTool === "message") {

725+

return { action: "send", message: "runtime parity message fixture" };

726+

}

727+

if (targetTool === "session_status") {

728+

return { sessionKey: "current" };

729+

}

730+

if (targetTool === "sessions_spawn") {

731+

return {

732+

task: "Runtime tool fixture subagent: reply exactly RUNTIME-TOOL-FIXTURE.",

733+

label: "runtime-tool-fixture",

734+

mode: "run",

735+

thread: false,

736+

runTimeoutSeconds: 30,

737+

};

738+

}

739+

if (targetTool === "memory_recall") {

740+

return { query: "runtime parity memory fixture" };

741+

}

742+

return { marker: "normal" };

743+

}

744+681745

function isActiveMemorySubagentPrompt(text: string) {

682746

return text.includes("You are a memory search agent.");

683747

}

@@ -765,19 +829,42 @@ function extractBareToolArg(text: string, name: string) {

765829766830

function hasDeclaredTool(body: Record<string, unknown>, name: string) {

767831

const tools = Array.isArray(body.tools) ? body.tools : [];

768-

return tools.some((tool) => {

769-

if (!tool || typeof tool !== "object") {

770-

return false;

771-

}

772-

const record = tool as Record<string, unknown>;

773-

if (record.name === name) {

832+

const dynamicTools = Array.isArray(body.dynamicTools) ? body.dynamicTools : [];

833+

if (

834+

[...tools, ...dynamicTools].some((tool) => toolDefinitionMentionsName(tool, name)) ||

835+

instructionTextMentionsToolName(extractInstructionsText(body), name)

836+

) {

837+

return true;

838+

}

839+

return false;

840+

}

841+842+

function toolDefinitionMentionsName(value: unknown, name: string, depth = 0): boolean {

843+

if (depth > 6 || !value || typeof value !== "object") {

844+

return false;

845+

}

846+

if (Array.isArray(value)) {

847+

return value.some((item) => toolDefinitionMentionsName(item, name, depth + 1));

848+

}

849+

const record = value as Record<string, unknown>;

850+

for (const key of ["name", "tool", "functionName"]) {

851+

if (record[key] === name) {

774852

return true;

775853

}

776-

const nested = record.function;

777-

return Boolean(

778-

nested && typeof nested === "object" && (nested as { name?: unknown }).name === name,

779-

);

780-

});

854+

}

855+

return Object.values(record).some((item) => toolDefinitionMentionsName(item, name, depth + 1));

856+

}

857+858+

function instructionTextMentionsToolName(text: string, name: string) {

859+

if (!text) {

860+

return false;

861+

}

862+

const escapedName = escapeRegExp(name);

863+

return new RegExp(`(^|[^A-Za-z0-9_])${escapedName}([^A-Za-z0-9_]|$)`).test(text);

864+

}

865+866+

function isQaToolSearchFixture(text: string) {

867+

return QA_TOOL_SEARCH_PROMPT_RE.test(text) || QA_TOOL_SEARCH_FAILURE_PROMPT_RE.test(text);

781868

}

782869783870

function buildExplicitSessionsSpawnArgs(text: string): Record<string, unknown> | null {

@@ -1416,26 +1503,36 @@ async function buildResponsesPayload(

14161503

const hasEmptyResponseRetryInstruction = allInputText.includes(QA_EMPTY_RESPONSE_RETRY_NEEDLE);

14171504

const canCallSessionsSpawn = hasDeclaredTool(body, "sessions_spawn");

14181505

const canCallSessionsYield = hasDeclaredTool(body, "sessions_yield");

1506+

const canPlanQaSessionsSpawn =

1507+

canCallSessionsSpawn ||

1508+

/subagent fanout synthesis check|delegate one bounded qa task|subagent handoff/i.test(prompt);

14191509

const buildToolProgressReadEvents = (pattern: RegExp) => {

14201510

const toolProgressPrompt = extractLastMatchingUserText(extractAllUserTexts(input), pattern);

14211511

return buildToolCallEventsWithArgs("read", {

14221512

path: readTargetFromPrompt(toolProgressPrompt || prompt || allInputText),

14231513

});

14241514

};

1425-

if (QA_TOOL_SEARCH_PROMPT_RE.test(allInputText) && !toolOutput) {

1515+

if (

1516+

(QA_TOOL_SEARCH_PROMPT_RE.test(allInputText) ||

1517+

QA_TOOL_SEARCH_FAILURE_PROMPT_RE.test(allInputText)) &&

1518+

!toolOutput

1519+

) {

14261520

const targetTool = extractToolSearchTarget(allInputText);

1521+

const plannedArgs = targetTool

1522+

? buildQaToolSearchArgs(targetTool, QA_TOOL_SEARCH_FAILURE_PROMPT_RE.test(allInputText))

1523+

: {};

14271524

if (targetTool && hasDeclaredTool(body, "tool_search_code")) {

14281525

return buildToolCallEventsWithArgs("tool_search_code", {

14291526

code: [

14301527

`const hits = await openclaw.tools.search(${JSON.stringify(targetTool)}, { limit: 1 });`,

14311528

"const match = hits.find((tool) => tool.name === " + JSON.stringify(targetTool) + ");",

14321529

"if (!match) throw new Error('target tool not found');",

1433-

"return await openclaw.tools.call(match.id, { marker: 'code-mode' });",

1530+

`return await openclaw.tools.call(match.id, ${JSON.stringify(plannedArgs)});`,

14341531

].join("\n"),

14351532

});

14361533

}

1437-

if (targetTool && hasDeclaredTool(body, targetTool)) {

1438-

return buildToolCallEventsWithArgs(targetTool, { marker: "normal" });

1534+

if (targetTool && (hasDeclaredTool(body, targetTool) || isQaToolSearchFixture(allInputText))) {

1535+

return buildToolCallEventsWithArgs(targetTool, plannedArgs);

14391536

}

14401537

}

14411538

if (

@@ -1905,7 +2002,7 @@ async function buildResponsesPayload(

19052002

size: "1024x1024",

19062003

});

19072004

}

1908-

if (canCallSessionsSpawn && /subagent fanout synthesis check/i.test(prompt)) {

2005+

if (canPlanQaSessionsSpawn && /subagent fanout synthesis check/i.test(prompt)) {

19092006

if (!toolOutput && scenarioState.subagentFanoutPhase === 0) {

19102007

scenarioState.subagentFanoutPhase = 1;

19112008

return buildToolCallEventsWithArgs("sessions_spawn", {

@@ -1924,7 +2021,7 @@ async function buildResponsesPayload(

19242021

}

19252022

}

19262023

const explicitSessionsSpawnArgs = buildExplicitSessionsSpawnArgs(allInputText);

1927-

if (canCallSessionsSpawn && explicitSessionsSpawnArgs && !toolOutput) {

2024+

if (explicitSessionsSpawnArgs && !toolOutput) {

19282025

return buildToolCallEventsWithArgs("sessions_spawn", explicitSessionsSpawnArgs);

19292026

}

19302027

if (canCallSessionsSpawn && /forked subagent context qa check/i.test(prompt) && !toolOutput) {

@@ -1981,7 +2078,7 @@ async function buildResponsesPayload(

19812078

}

19822079

}

19832080

if (

1984-

canCallSessionsSpawn &&

2081+

canPlanQaSessionsSpawn &&

19852082

(/\bdelegate\b/i.test(prompt) || /subagent handoff/i.test(prompt)) &&

19862083

!toolOutput

19872084

) {