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

S
Schneier on Security
博客园 - 聂微东
美团技术团队
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
Tor Project blog
N
Netflix TechBlog - Medium
G
Google Developers Blog
L
LINUX DO - 最新话题
Recent Announcements
Recent Announcements
爱范儿
爱范儿
P
Privacy & Cybersecurity Law Blog
F
Fortinet All Blogs
The GitHub Blog
The GitHub Blog
Spread Privacy
Spread Privacy
TaoSecurity Blog
TaoSecurity Blog
T
Tailwind CSS Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
S
SegmentFault 最新的问题
AWS News Blog
AWS News Blog
P
Proofpoint News Feed
D
DataBreaches.Net
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
Hacker News: Ask HN
Hacker News: Ask HN
V
V2EX
www.infosecurity-magazine.com
www.infosecurity-magazine.com
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
K
Kaspersky official blog
博客园 - 司徒正美
U
Unit 42
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Blog — PlanetScale
Blog — PlanetScale
云风的 BLOG
云风的 BLOG
Schneier on Security
Schneier on Security
H
Hackread – Cybersecurity News, Data Breaches, AI and More
T
Threatpost
Vercel News
Vercel News
Engineering at Meta
Engineering at Meta
Attack and Defense Labs
Attack and Defense Labs
L
Lohrmann on Cybersecurity
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Hugging Face - Blog
Hugging Face - Blog
PCI Perspectives
PCI Perspectives
S
Secure Thoughts
The Cloudflare Blog
L
LangChain Blog
T
The Exploit Database - CXSecurity.com
C
Check Point Blog
Microsoft Azure Blog
Microsoft Azure Blog
I
InfoQ
博客园 - 三生石上(FineUI控件)

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(anthropic): quarantine invalid direct tool schemas (#92896) · openclaw/openclaw@a028131
steipete · 2026-06-14 · via Recent Commits to openclaw:main
1+

import { projectRuntimeToolInputSchema } from "./tool-schema-json-projection.js";

2+3+

type AnthropicToolDescriptor = {

4+

readonly name: string;

5+

readonly description: string;

6+

readonly parameters: unknown;

7+

};

8+9+

export type AnthropicProjectedTool = {

10+

readonly originalName: string;

11+

readonly wireName: string;

12+

readonly description?: string;

13+

readonly inputSchema: {

14+

readonly type: "object";

15+

readonly properties: Record<string, unknown>;

16+

readonly required: string[];

17+

};

18+

};

19+20+

export type AnthropicToolProjection = {

21+

readonly inputToolCount: number;

22+

readonly unavailableOriginalNames: ReadonlySet<string>;

23+

readonly tools: readonly AnthropicProjectedTool[];

24+

};

25+26+

type AnthropicParallelToolChoice = {

27+

readonly disable_parallel_tool_use?: boolean;

28+

};

29+30+

export type AnthropicProjectedToolChoice =

31+

| ({ readonly type: "auto" } & AnthropicParallelToolChoice)

32+

| ({ readonly type: "any" } & AnthropicParallelToolChoice)

33+

| { readonly type: "none" }

34+

| ({ readonly type: "tool"; readonly name: string } & AnthropicParallelToolChoice);

35+36+

function isRecord(value: unknown): value is Record<string, unknown> {

37+

return Boolean(value) && typeof value === "object" && !Array.isArray(value);

38+

}

39+40+

function isProviderSupportedViolation(violation: string): boolean {

41+

return violation.endsWith(".$dynamicRef") || violation.endsWith(".$dynamicAnchor");

42+

}

43+44+

/** Snapshots direct/custom tool descriptors before Anthropic payload construction. */

45+

export function projectAnthropicTools(

46+

tools: readonly AnthropicToolDescriptor[],

47+

toWireName: (name: string) => string,

48+

): AnthropicToolProjection {

49+

const projectedTools: AnthropicProjectedTool[] = [];

50+

const unavailableOriginalNames = new Set<string>();

51+

for (const tool of tools) {

52+

let projectedTool: AnthropicProjectedTool;

53+

let originalName: string | undefined;

54+

try {

55+

const name = tool.name;

56+

originalName = name;

57+

if (!name) {

58+

continue;

59+

}

60+

const schemaProjection = projectRuntimeToolInputSchema(tool.parameters, `${name}.parameters`);

61+

if (

62+

!isRecord(schemaProjection.schema) ||

63+

schemaProjection.violations.some((violation) => !isProviderSupportedViolation(violation))

64+

) {

65+

unavailableOriginalNames.add(name);

66+

continue;

67+

}

68+

const properties = schemaProjection.schema.properties;

69+

const required = schemaProjection.schema.required;

70+

if (

71+

(properties !== undefined && properties !== null && !isRecord(properties)) ||

72+

(required !== undefined &&

73+

required !== null &&

74+

(!Array.isArray(required) || required.some((entry) => typeof entry !== "string")))

75+

) {

76+

unavailableOriginalNames.add(name);

77+

continue;

78+

}

79+

let description: string | undefined;

80+

try {

81+

description = typeof tool.description === "string" ? tool.description : undefined;

82+

} catch {

83+

// Description is optional; keep the usable tool schema.

84+

}

85+

const wireName = toWireName(name);

86+

projectedTool = {

87+

originalName: name,

88+

wireName,

89+

...(description ? { description } : {}),

90+

inputSchema: {

91+

type: "object",

92+

properties: (properties ?? {}) as Record<string, unknown>,

93+

required: (required ?? []) as string[],

94+

},

95+

};

96+

} catch {

97+

// Direct/custom tool arrays can bypass the runtime quarantine.

98+

if (originalName) {

99+

unavailableOriginalNames.add(originalName);

100+

}

101+

continue;

102+

}

103+

const conflictingTool = projectedTools.find(

104+

(entry) => entry.wireName === projectedTool.wireName,

105+

);

106+

if (conflictingTool && conflictingTool.originalName !== projectedTool.originalName) {

107+

throw new Error(

108+

`Anthropic tool names "${conflictingTool.originalName}" and "${projectedTool.originalName}" both map to "${projectedTool.wireName}"`,

109+

);

110+

}

111+

projectedTools.push(projectedTool);

112+

}

113+

return {

114+

inputToolCount: tools.length,

115+

unavailableOriginalNames,

116+

tools: projectedTools,

117+

};

118+

}

119+120+

/** Keeps forced Anthropic tool choices aligned with the projected wire names. */

121+

export function reconcileAnthropicToolChoice(

122+

choice: AnthropicProjectedToolChoice,

123+

projection: AnthropicToolProjection,

124+

): AnthropicProjectedToolChoice | undefined {

125+

if (projection.inputToolCount === 0) {

126+

return choice;

127+

}

128+

if (choice.type === "tool") {

129+

const requestedName = choice.name;

130+

const originalMatch = projection.tools.find((tool) => tool.originalName === requestedName);

131+

if (originalMatch) {

132+

return { ...choice, name: originalMatch.wireName };

133+

}

134+

if (projection.unavailableOriginalNames.has(requestedName)) {

135+

throw new Error(

136+

`Anthropic tool_choice requested unavailable tool "${requestedName}" after schema conversion`,

137+

);

138+

}

139+

const matchedTool = projection.tools.find((tool) => tool.wireName === requestedName);

140+

if (!matchedTool) {

141+

throw new Error(

142+

`Anthropic tool_choice requested unavailable tool "${requestedName}" after schema conversion`,

143+

);

144+

}

145+

return { ...choice, name: matchedTool.wireName };

146+

}

147+

if (projection.tools.length === 0) {

148+

if (choice.type === "auto") {

149+

return undefined;

150+

}

151+

if (choice.type === "any") {

152+

throw new Error(

153+

"Anthropic tool_choice requires a tool, but no tools survived schema conversion",

154+

);

155+

}

156+

}

157+

return choice;

158+

}

159+160+

/** Maps Claude Code wire names without trusting every direct/custom descriptor. */

161+

export function resolveOriginalAnthropicToolName(

162+

name: string,

163+

projection: AnthropicToolProjection | undefined,

164+

): string {

165+

return projection?.tools.find((tool) => tool.wireName === name)?.originalName ?? name;

166+

}