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

Martin Fowler
Martin Fowler
V
Visual Studio Blog
有赞技术团队
有赞技术团队
T
Tailwind CSS Blog
B
Blog
I
InfoQ
博客园 - 三生石上(FineUI控件)
阮一峰的网络日志
阮一峰的网络日志
F
Fortinet All Blogs
H
Help Net Security
博客园 - Franky
宝玉的分享
宝玉的分享
博客园 - 司徒正美
C
Check Point Blog
G
Google Developers Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Jina AI
Jina AI
T
The Blog of Author Tim Ferriss
MongoDB | Blog
MongoDB | Blog
云风的 BLOG
云风的 BLOG
A
About on SuperTechFans
罗磊的独立博客
大猫的无限游戏
大猫的无限游戏
IT之家
IT之家

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
fix(agents): split embedded attempt dispatch timing · ope...
galiniliev · 2026-05-17 · via Recent Commits to openclaw:main

@@ -114,6 +114,7 @@ import { createEmbeddedRunReplayState, observeReplayMetadata } from "./replay-st

114114

import { handleAssistantFailover } from "./run/assistant-failover.js";

115115

import {

116116

createEmbeddedRunStageTracker,

117+

EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE,

117118

formatEmbeddedRunStageSummary,

118119

shouldWarnEmbeddedRunStageSummary,

119120

} from "./run/attempt-stage-timing.js";

@@ -194,6 +195,16 @@ const COMPACTION_CONTINUATION_RETRY_INSTRUCTION =

194195

"The previous attempt compacted the conversation context before producing a final user-visible answer. Continue from the compacted transcript and produce the final answer now. Do not restart from scratch, do not repeat completed work, and do not rerun tools unless the transcript clearly lacks required evidence.";

195196

type EmbeddedRunAttemptForRunner = Awaited<ReturnType<typeof runEmbeddedAttemptWithBackend>>;

196197198+

function resolveAttemptDispatchApiKey(params: {

199+

apiKeyInfo: ApiKeyInfo | null;

200+

runtimeAuthState: RuntimeAuthState | null;

201+

}): string | undefined {

202+

if (params.runtimeAuthState) {

203+

return undefined;

204+

}

205+

return params.apiKeyInfo?.apiKey;

206+

}

207+197208

function resolveEmbeddedRunLaneTimeoutMs(timeoutMs: number): number | undefined {

198209

if (!Number.isFinite(timeoutMs) || timeoutMs <= 0) {

199210

return undefined;

@@ -1271,6 +1282,9 @@ export async function runEmbeddedPiAgent(

12711282

authRetryPending = false;

12721283

attemptedThinking.add(thinkLevel);

12731284

await fs.mkdir(resolvedWorkspace, { recursive: true });

1285+

if (!startupStagesEmitted) {

1286+

startupStages.mark(EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE.workspace);

1287+

}

1274128812751289

const basePrompt =

12761290

nextAttemptPromptOverride ??

@@ -1289,9 +1303,12 @@ export async function runEmbeddedPiAgent(

12891303

promptAdditions.length > 0

12901304

? `${basePrompt}\n\n${promptAdditions.join("\n\n")}`

12911305

: basePrompt;

1292-

let resolvedStreamApiKey: string | undefined;

1293-

if (!runtimeAuthState && apiKeyInfo) {

1294-

resolvedStreamApiKey = (apiKeyInfo as ApiKeyInfo).apiKey;

1306+

const resolvedStreamApiKey = resolveAttemptDispatchApiKey({

1307+

apiKeyInfo,

1308+

runtimeAuthState,

1309+

});

1310+

if (!startupStagesEmitted) {

1311+

startupStages.mark(EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE.prompt);

12951312

}

12961313

const runtimePlan = buildAgentRuntimePlan({

12971314

provider,

@@ -1323,9 +1340,10 @@ export async function runEmbeddedPiAgent(

13231340

},

13241341

});

13251342

if (!startupStagesEmitted) {

1326-

startupStages.mark("attempt-dispatch");

1343+

startupStages.mark(EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE.runtimePlan);

1344+

startupStages.mark(EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE.dispatch);

13271345

notifyExecutionPhase("attempt_dispatch", { provider, model: modelId });

1328-

emitStartupStageSummary("attempt-dispatch");

1346+

emitStartupStageSummary(EMBEDDED_RUN_ATTEMPT_DISPATCH_STAGE.dispatch);

13291347

startupStagesEmitted = true;

13301348

}

13311349