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

月光博客
月光博客
H
Hackread – Cybersecurity News, Data Breaches, AI and More
V
Vulnerabilities – Threatpost
L
LangChain Blog
Stack Overflow Blog
Stack Overflow Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
云风的 BLOG
云风的 BLOG
C
Cisco Blogs
V
Visual Studio Blog
L
Lohrmann on Cybersecurity
Latest news
Latest news
S
Securelist
The Last Watchdog
The Last Watchdog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
The Register - Security
The Register - Security
Webroot Blog
Webroot Blog
The Cloudflare Blog
S
Secure Thoughts
Y
Y Combinator Blog
aimingoo的专栏
aimingoo的专栏
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
N
News and Events Feed by Topic
S
Security Affairs
Attack and Defense Labs
Attack and Defense Labs
Microsoft Azure Blog
Microsoft Azure Blog
T
Tailwind CSS Blog
V2EX - 技术
V2EX - 技术
GbyAI
GbyAI
L
LINUX DO - 热门话题
PCI Perspectives
PCI Perspectives
Schneier on Security
Schneier on Security
V
V2EX
K
Kaspersky official blog
Hugging Face - Blog
Hugging Face - Blog
AWS News Blog
AWS News Blog
T
The Exploit Database - CXSecurity.com
C
CERT Recently Published Vulnerability Notes
C
Cyber Attacks, Cyber Crime and Cyber Security
P
Proofpoint News Feed
T
Threatpost
WordPress大学
WordPress大学
SecWiki News
SecWiki News
B
Blog RSS Feed
Blog — PlanetScale
Blog — PlanetScale
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
A
Arctic Wolf
酷 壳 – CoolShell
酷 壳 – CoolShell
W
WeLiveSecurity
Jina AI
Jina AI
D
Darknet – Hacking Tools, Hacker News & Cyber Security

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(openai): normalize responses replay tool ids · openclaw/openclaw@ef77428
yetval · 2026-05-27 · via Recent Commits to openclaw:main
1+

import { createHash } from "node:crypto";

12

import type { AgentMessage } from "@earendil-works/pi-agent-core";

2334

type OpenAIThinkingBlock = {

@@ -20,6 +21,10 @@ type DowngradeOpenAIReasoningBlocksOptions = {

2021

dropReplayableReasoning?: boolean;

2122

};

222324+

const OPENAI_RESPONSES_ID_MAX_LENGTH = 64;

25+

const OPENAI_RESPONSES_CALL_ID_RE = /^call_[A-Za-z0-9_-]{1,59}$/;

26+

const OPENAI_RESPONSES_FUNCTION_CALL_ITEM_ID_RE = /^fc_[A-Za-z0-9_-]{1,61}$/;

27+2328

function parseOpenAIReasoningSignature(value: unknown): OpenAIReasoningSignature | null {

2429

if (!value) {

2530

return null;

@@ -86,6 +91,193 @@ function isOpenAIToolCallType(type: unknown): boolean {

8691

return type === "toolCall" || type === "toolUse" || type === "functionCall";

8792

}

889394+

function shortOpenAIResponsesIdHash(id: string): string {

95+

return createHash("sha256").update(id).digest("hex").slice(0, 10);

96+

}

97+98+

function sanitizeOpenAIResponsesIdTail(value: string): string {

99+

return value.replace(/[^A-Za-z0-9_-]/g, "_").replace(/^_+|_+$/g, "");

100+

}

101+102+

function normalizeOpenAIResponsesIdPart(params: {

103+

value: string;

104+

prefix: "call_" | "fc_";

105+

isValid: (value: string) => boolean;

106+

}): string {

107+

const trimmed = params.value.trim();

108+

if (params.isValid(trimmed)) {

109+

return trimmed;

110+

}

111+112+

const rawTail = trimmed.startsWith(params.prefix) ? trimmed.slice(params.prefix.length) : trimmed;

113+

const hash = shortOpenAIResponsesIdHash(trimmed || params.prefix);

114+

const maxTailLength = OPENAI_RESPONSES_ID_MAX_LENGTH - params.prefix.length;

115+

const hashSuffix = `_${hash}`;

116+

const safeTail = sanitizeOpenAIResponsesIdTail(rawTail);

117+

const clippedBase = safeTail.slice(0, Math.max(1, maxTailLength - hashSuffix.length));

118+

const tail = `${clippedBase || "id"}${hashSuffix}`.slice(0, maxTailLength);

119+

return `${params.prefix}${tail}`;

120+

}

121+122+

function normalizeOpenAIResponsesFunctionCallId(id: string): string {

123+

const { callId, itemId } = splitOpenAIFunctionCallPairing(id);

124+

const normalizedCallId = normalizeOpenAIResponsesIdPart({

125+

value: callId,

126+

prefix: "call_",

127+

isValid: (value) => OPENAI_RESPONSES_CALL_ID_RE.test(value),

128+

});

129+130+

if (!itemId) {

131+

return normalizedCallId;

132+

}

133+134+

const normalizedItemId = normalizeOpenAIResponsesIdPart({

135+

value: itemId,

136+

prefix: "fc_",

137+

isValid: (value) => OPENAI_RESPONSES_FUNCTION_CALL_ITEM_ID_RE.test(value),

138+

});

139+

return `${normalizedCallId}|${normalizedItemId}`;

140+

}

141+142+

function shouldNormalizeOpenAIResponsesToolCallId(id: string): boolean {

143+

const pairing = splitOpenAIFunctionCallPairing(id);

144+

if (!OPENAI_RESPONSES_CALL_ID_RE.test(pairing.callId)) {

145+

return true;

146+

}

147+

if (pairing.itemId === undefined) {

148+

return false;

149+

}

150+

return !OPENAI_RESPONSES_FUNCTION_CALL_ITEM_ID_RE.test(pairing.itemId);

151+

}

152+153+

function createOpenAIResponsesToolCallIdResolver(): {

154+

resolveAssistantId: (id: string) => string;

155+

resolveToolResultId: (id: string) => string;

156+

} {

157+

const rewrittenByOriginalId = new Map<string, string>();

158+159+

return {

160+

resolveAssistantId(id: string): string {

161+

const rewritten = rewrittenByOriginalId.get(id);

162+

if (rewritten) {

163+

return rewritten;

164+

}

165+

if (!shouldNormalizeOpenAIResponsesToolCallId(id)) {

166+

return id;

167+

}

168+

const normalized = normalizeOpenAIResponsesFunctionCallId(id);

169+

rewrittenByOriginalId.set(id, normalized);

170+

return normalized;

171+

},

172+

resolveToolResultId(id: string): string {

173+

const rewritten = rewrittenByOriginalId.get(id);

174+

if (rewritten) {

175+

return rewritten;

176+

}

177+

if (!shouldNormalizeOpenAIResponsesToolCallId(id)) {

178+

return id;

179+

}

180+

const normalized = normalizeOpenAIResponsesFunctionCallId(id);

181+

rewrittenByOriginalId.set(id, normalized);

182+

return normalized;

183+

},

184+

};

185+

}

186+187+

/**

188+

* OpenAI Responses rejects replayed `function_call.call_id`,

189+

* `function_call.id`, and matching `function_call_output.call_id` values

190+

* that exceed its 64-char `call_*` / `fc_*` shape. pi-ai skips its own

191+

* normalizer for same-model replay, then splits persisted `call_id|fc_id`

192+

* pairs directly into the provider payload, so OpenClaw must normalize here.

193+

*/

194+

export function normalizeOpenAIResponsesToolCallIds(messages: AgentMessage[]): AgentMessage[] {

195+

let changed = false;

196+

const resolver = createOpenAIResponsesToolCallIdResolver();

197+

const rewrittenMessages: AgentMessage[] = [];

198+199+

for (const msg of messages) {

200+

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

201+

rewrittenMessages.push(msg);

202+

continue;

203+

}

204+205+

const role = (msg as { role?: unknown }).role;

206+

if (role === "assistant") {

207+

const assistantMsg = msg as Extract<AgentMessage, { role: "assistant" }>;

208+

if (!Array.isArray(assistantMsg.content)) {

209+

rewrittenMessages.push(msg);

210+

continue;

211+

}

212+213+

let assistantChanged = false;

214+

const nextContent = assistantMsg.content.map((block) => {

215+

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

216+

return block;

217+

}

218+

const toolCallBlock = block as OpenAIToolCallBlock;

219+

if (!isOpenAIToolCallType(toolCallBlock.type) || typeof toolCallBlock.id !== "string") {

220+

return block;

221+

}

222+223+

const nextId = resolver.resolveAssistantId(toolCallBlock.id);

224+

if (nextId === toolCallBlock.id) {

225+

return block;

226+

}

227+

assistantChanged = true;

228+

return {

229+

...(block as unknown as Record<string, unknown>),

230+

id: nextId,

231+

} as typeof block;

232+

});

233+234+

if (!assistantChanged) {

235+

rewrittenMessages.push(msg);

236+

continue;

237+

}

238+

changed = true;

239+

rewrittenMessages.push({ ...assistantMsg, content: nextContent } as AgentMessage);

240+

continue;

241+

}

242+243+

if (role === "toolResult") {

244+

const toolResult = msg as Extract<AgentMessage, { role: "toolResult" }> & {

245+

toolUseId?: unknown;

246+

};

247+

let toolResultChanged = false;

248+

const updates: Record<string, string> = {};

249+250+

if (typeof toolResult.toolCallId === "string") {

251+

const nextToolCallId = resolver.resolveToolResultId(toolResult.toolCallId);

252+

if (nextToolCallId !== toolResult.toolCallId) {

253+

updates.toolCallId = nextToolCallId;

254+

toolResultChanged = true;

255+

}

256+

}

257+258+

if (typeof toolResult.toolUseId === "string") {

259+

const nextToolUseId = resolver.resolveToolResultId(toolResult.toolUseId);

260+

if (nextToolUseId !== toolResult.toolUseId) {

261+

updates.toolUseId = nextToolUseId;

262+

toolResultChanged = true;

263+

}

264+

}

265+266+

if (!toolResultChanged) {

267+

rewrittenMessages.push(msg);

268+

continue;

269+

}

270+

changed = true;

271+

rewrittenMessages.push({ ...toolResult, ...updates } as AgentMessage);

272+

continue;

273+

}

274+275+

rewrittenMessages.push(msg);

276+

}

277+278+

return changed ? rewrittenMessages : messages;

279+

}

280+89281

/**

90282

* OpenAI can reject replayed `function_call` items with an `fc_*` id if the

91283

* matching `reasoning` item is absent in the same assistant turn.