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 - 最新话题
I
InfoQ
V
V2EX
博客园 - 叶小钗
博客园 - 三生石上(FineUI控件)
爱范儿
爱范儿
T
Tailwind CSS Blog
大猫的无限游戏
大猫的无限游戏
IT之家
IT之家
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
阮一峰的网络日志
阮一峰的网络日志
博客园 - 聂微东
月光博客
月光博客
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Last Week in AI
Last Week in AI
量子位
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
G
Google Developers Blog
MongoDB | Blog
MongoDB | Blog
博客园 - 司徒正美
腾讯CDC
罗磊的独立博客
有赞技术团队
有赞技术团队
Jina AI
Jina AI
T
The Exploit Database - CXSecurity.com
C
CERT Recently Published Vulnerability Notes
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
V
Visual Studio Blog
H
Help Net Security
AWS News Blog
AWS News Blog
C
Cybersecurity and Infrastructure Security Agency CISA
Recorded Future
Recorded Future
GbyAI
GbyAI
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Attack and Defense Labs
Attack and Defense Labs
Webroot Blog
Webroot Blog
S
SegmentFault 最新的问题
Know Your Adversary
Know Your Adversary
The GitHub Blog
The GitHub Blog
I
Intezer
博客园 - Franky
云风的 BLOG
云风的 BLOG
N
News and Events Feed by Topic
P
Proofpoint News Feed
D
DataBreaches.Net
Google DeepMind News
Google DeepMind News
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
G
GRAHAM CLULEY

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
fix(agents): clean Gemini tool schemas by model id (#91559) · openclaw/openclaw@1f89d6d
Pick-cat · 2026-06-23 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -29,13 +29,17 @@ function resolveToolParameterSchemaCacheKey(

2929

): string {

3030

const normalizedProvider = normalizeLowercaseStringOrEmpty(options?.modelProvider);

3131

const normalizedModelId = normalizeLowercaseStringOrEmpty(options?.modelId);

32+

const toolSchemaProfile = normalizeLowercaseStringOrEmpty(

33+

options?.modelCompat?.toolSchemaProfile,

34+

);

3235

const unsupportedKeywords = Array.from(

3336

resolveUnsupportedToolSchemaKeywords(options?.modelCompat),

3437

).toSorted();

3538

const omitEmptyArrayItems = shouldOmitEmptyArrayItems(options?.modelCompat);

3639

return JSON.stringify([

3740

normalizedProvider,

3841

normalizedModelId,

42+

toolSchemaProfile,

3943

unsupportedKeywords,

4044

omitEmptyArrayItems,

4145

]);

@@ -57,6 +61,10 @@ function rememberCachedToolParameterSchema(schema: object, key: string, value: T

5761

return value;

5862

}

5963
64+

function isGeminiModelId(modelId: string): boolean {

65+

return /(?:^|[/:])gemini(?:$|[-/:.])/.test(modelId);

66+

}

67+
6068

function extractEnumValues(schema: unknown): unknown[] | undefined {

6169

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

6270

return undefined;

@@ -769,8 +777,15 @@ function normalizeToolParameterSchemaUncached(

769777

//

770778

// Normalize once here so callers can always pass `tools` through unchanged.

771779

const normalizedProvider = normalizeLowercaseStringOrEmpty(options?.modelProvider);

780+

const normalizedModelId = normalizeLowercaseStringOrEmpty(options?.modelId);

781+

const normalizedToolSchemaProfile = normalizeLowercaseStringOrEmpty(

782+

options?.modelCompat?.toolSchemaProfile,

783+

);

772784

const isGeminiProvider =

773-

normalizedProvider.includes("google") || normalizedProvider.includes("gemini");

785+

normalizedProvider.includes("google") ||

786+

normalizedProvider.includes("gemini") ||

787+

isGeminiModelId(normalizedModelId) ||

788+

normalizedToolSchemaProfile === "gemini";

774789

const isAnthropicProvider = normalizedProvider.includes("anthropic");

775790

const unsupportedToolSchemaKeywords = resolveUnsupportedToolSchemaKeywords(options?.modelCompat);

776791

const omitEmptyArrayItems = shouldOmitEmptyArrayItems(options?.modelCompat);

@@ -781,7 +796,13 @@ function normalizeToolParameterSchemaUncached(

781796

? stripEmptyArrayItemsFromArraySchemas(normalizedSchema)

782797

: normalizedSchema;

783798

if (isGeminiProvider && !isAnthropicProvider) {

784-

return cleanSchemaForGemini(arrayItemsCompatibleSchema);

799+

const geminiCompatibleSchema = cleanSchemaForGemini(arrayItemsCompatibleSchema);

800+

return unsupportedToolSchemaKeywords.size > 0

801+

? (stripUnsupportedSchemaKeywords(

802+

geminiCompatibleSchema,

803+

unsupportedToolSchemaKeywords,

804+

) as TSchema)

805+

: geminiCompatibleSchema;

785806

}

786807

if (unsupportedToolSchemaKeywords.size > 0) {

787808

return stripUnsupportedSchemaKeywords(

Original file line numberDiff line numberDiff line change

@@ -43,6 +43,93 @@ describe("normalizeToolParameterSchema", () => {

4343

expect(providerSpecific).toEqual(first);

4444

});

4545
46+

it("uses Gemini cleanup for OpenAI-compatible providers when the model id is Gemini", () => {

47+

const schema = {

48+

type: "object",

49+

properties: {

50+

sessionKey: {

51+

description: "Explicit session key, or null to clear it",

52+

anyOf: [{ type: "string" }, { type: "null" }],

53+

},

54+

},

55+

};

56+
57+

expect(

58+

normalizeToolParameterSchema(schema, {

59+

modelProvider: "jjcc",

60+

modelId: "gemini-3.1-pro-preview",

61+

}),

62+

).toEqual({

63+

type: "object",

64+

properties: {

65+

sessionKey: {

66+

type: "string",

67+

description: "Explicit session key, or null to clear it",

68+

},

69+

},

70+

});

71+

expect(

72+

normalizeToolParameterSchema(schema, {

73+

modelProvider: "stepfun",

74+

modelId: "step-router-v1",

75+

}),

76+

).toEqual(schema);

77+

});

78+
79+

it("keeps normalized tool-schema profile behavior aligned with the cache key", () => {

80+

const schema = {

81+

type: "object",

82+

properties: {

83+

sessionKey: {

84+

anyOf: [{ type: "string" }, { type: "null" }],

85+

},

86+

},

87+

};

88+
89+

const defaultSchema = normalizeToolParameterSchema(schema, {

90+

modelProvider: "openai-compatible",

91+

modelId: "custom-model",

92+

});

93+

const mixedCaseGeminiProfileSchema = normalizeToolParameterSchema(schema, {

94+

modelProvider: "openai-compatible",

95+

modelId: "custom-model",

96+

modelCompat: { toolSchemaProfile: "Gemini" },

97+

});

98+
99+

expect(defaultSchema).toEqual(schema);

100+

expect(mixedCaseGeminiProfileSchema).toEqual({

101+

type: "object",

102+

properties: {

103+

sessionKey: { type: "string" },

104+

},

105+

});

106+

});

107+
108+

it("applies explicit unsupported keyword stripping after Gemini cleanup", () => {

109+

expect(

110+

normalizeToolParameterSchema(

111+

{

112+

type: "object",

113+

properties: {

114+

count: {

115+

anyOf: [{ type: "integer", vendorOnly: true }, { type: "null" }],

116+

},

117+

},

118+

},

119+

{

120+

modelProvider: "jjcc",

121+

modelId: "gemini-3.1-pro-preview",

122+

modelCompat: { unsupportedToolSchemaKeywords: ["vendorOnly"] },

123+

},

124+

),

125+

).toEqual({

126+

type: "object",

127+

properties: {

128+

count: { type: "integer" },

129+

},

130+

});

131+

});

132+
46133

it("normalizes truly empty schemas to type:object with properties:{}", () => {

47134

expect(normalizeToolParameterSchema({})).toEqual({

48135

type: "object",

Original file line numberDiff line numberDiff line change

@@ -33,6 +33,10 @@ describe("createCronToolSchema", () => {

3333

const providerSchemaRecord = normalizeToolParameterSchema(createCronToolSchema(), {

3434

modelProvider: "gemini",

3535

}) as unknown as Record<string, unknown>;

36+

const jjccGeminiSchemaRecord = normalizeToolParameterSchema(createCronToolSchema(), {

37+

modelProvider: "jjcc",

38+

modelId: "gemini-3.1-pro-preview",

39+

}) as unknown as Record<string, unknown>;

3640
3741

// Regression: models like GPT-5.4 rely on these fields to populate job/patch.

3842

// If a field is removed from this list the test must be updated intentionally.

@@ -254,6 +258,22 @@ describe("createCronToolSchema", () => {

254258

expect(patchProps?.payload?.properties?.model?.description).toMatch(/null to clear/i);

255259

});

256260
261+

it("projects nullable cron fields for Gemini models behind OpenAI-compatible providers", () => {

262+

expect(propertyAt(jjccGeminiSchemaRecord, "job.agentId")).toMatchObject({

263+

type: "string",

264+

});

265+

expect(propertyAt(jjccGeminiSchemaRecord, "job.sessionKey")).toMatchObject({

266+

type: "string",

267+

});

268+

expect(propertyAt(jjccGeminiSchemaRecord, "patch.payload.toolsAllow")).toMatchObject({

269+

type: "array",

270+

});

271+

expect(propertyAt(jjccGeminiSchemaRecord, "patch.delivery.channel")).toMatchObject({

272+

type: "string",

273+

});

274+

expect(JSON.stringify(jjccGeminiSchemaRecord)).not.toContain('"anyOf"');

275+

});

276+
257277

// Regression guard: ensure no OpenAPI 3.0 incompatible keywords leak into the

258278

// serialized provider-facing cron tool schema.

259279

it("serialized provider schema contains no type-array or not/const keywords", () => {