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

T
Threatpost
G
Google Developers Blog
Latest news
Latest news
Know Your Adversary
Know Your Adversary
O
OpenAI News
腾讯CDC
月光博客
月光博客
P
Privacy International News Feed
Google Online Security Blog
Google Online Security Blog
Help Net Security
Help Net Security
L
LINUX DO - 最新话题
雷峰网
雷峰网
AI
AI
Hacker News - Newest:
Hacker News - Newest: "LLM"
有赞技术团队
有赞技术团队
N
News and Events Feed by Topic
V
Vulnerabilities – Threatpost
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
D
Docker
Google DeepMind News
Google DeepMind News
T
Tor Project blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Hacker News: Ask HN
Hacker News: Ask HN
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
H
Heimdal Security Blog
I
Intezer
WordPress大学
WordPress大学
C
CERT Recently Published Vulnerability Notes
Attack and Defense Labs
Attack and Defense Labs
www.infosecurity-magazine.com
www.infosecurity-magazine.com
P
Privacy & Cybersecurity Law Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
V
V2EX
博客园 - 三生石上(FineUI控件)
G
GRAHAM CLULEY
Security Archives - TechRepublic
Security Archives - TechRepublic
F
Fortinet All Blogs
L
LangChain Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
Spread Privacy
Spread Privacy
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
V2EX - 技术
V2EX - 技术
Stack Overflow Blog
Stack Overflow Blog
Recent Announcements
Recent Announcements
T
Tenable Blog
Microsoft Azure Blog
Microsoft Azure Blog
V
Visual Studio Blog
SecWiki News
SecWiki News
Cisco Talos Blog
Cisco Talos Blog

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: apply ACP spawn model defaults · openclaw/openclaw@ff22b1e
steipete · 2026-05-31 · via Recent Commits to openclaw:main

@@ -17,6 +17,7 @@ import {

1717

} from "../acp/control-plane/spawn.js";

1818

import { isAcpEnabledByPolicy, resolveAcpAgentPolicyError } from "../acp/policy.js";

1919

import { DEFAULT_HEARTBEAT_EVERY } from "../auto-reply/heartbeat.js";

20+

import { formatThinkingLevels } from "../auto-reply/thinking.js";

2021

import {

2122

resolveChannelDefaultBindingPlacement,

2223

resolveInboundConversationResolution,

@@ -82,6 +83,10 @@ import {

8283

inheritedToolDenyPatch,

8384

} from "./inherited-tool-deny.js";

8485

import { AGENT_LANE_SUBAGENT } from "./lanes.js";

86+

import {

87+

resolveConfiguredSubagentSpawnModelSelection,

88+

resolveThinkingDefault,

89+

} from "./model-selection.js";

8590

import { resolveSandboxRuntimeStatus } from "./sandbox/runtime-status.js";

8691

import { resolveRequesterOriginForChild } from "./spawn-requester-origin.js";

8792

import { resolveSpawnedWorkspaceInheritance } from "./spawned-context.js";

@@ -93,6 +98,8 @@ import {

9398

} from "./subagent-capabilities.js";

9499

import { getSubagentDepthFromSessionStore } from "./subagent-depth.js";

95100

import { countActiveRunsForSession, getSubagentRunByChildSessionKey } from "./subagent-registry.js";

101+

import { splitModelRef } from "./subagent-spawn-plan.js";

102+

import { resolveSubagentThinkingOverride } from "./subagent-spawn-thinking.js";

96103

import { resolveSubagentTargetPolicy } from "./subagent-target-policy.js";

97104

import { resolveInternalSessionKey, resolveMainSessionAlias } from "./tools/sessions-helpers.js";

98105

@@ -437,7 +444,7 @@ function hasSessionLocalHeartbeatRelayRoute(params: {

437444

function resolveTargetAcpAgentId(params: {

438445

requestedAgentId?: string;

439446

cfg: OpenClawConfig;

440-

}): { ok: true; agentId: string } | { ok: false; error: string } {

447+

}): { ok: true; agentId: string; configAgentId?: string } | { ok: false; error: string } {

441448

const requested = normalizeOptionalAgentId(params.requestedAgentId);

442449

if (requested) {

443450

const configuredAgent = params.cfg.agents?.list?.find(

@@ -447,6 +454,7 @@ function resolveTargetAcpAgentId(params: {

447454

return {

448455

ok: true,

449456

agentId: normalizeOptionalAgentId(configuredAgent.runtime.acp?.agent) ?? requested,

457+

configAgentId: requested,

450458

};

451459

}

452460

if (configuredAgent && !isExplicitlyAllowedAcpAgent(params.cfg, requested)) {

@@ -458,7 +466,11 @@ function resolveTargetAcpAgentId(params: {

458466

'Use runtime="acp" only with external ACP harness ids such as codex, claude, droid, gemini, or opencode, or configure agents.list[].runtime.type="acp" with runtime.acp.agent.',

459467

};

460468

}

461-

return { ok: true, agentId: requested };

469+

return {

470+

ok: true,

471+

agentId: requested,

472+

...(configuredAgent ? { configAgentId: requested } : {}),

473+

};

462474

}

463475464476

const configuredDefault = normalizeOptionalAgentId(params.cfg.acp?.defaultAgent);

@@ -975,15 +987,71 @@ function validateAcpResumeSessionOwnership(params: {

975987

};

976988

}

977989990+

type AcpSpawnRuntimeOptions = {

991+

model?: string;

992+

thinking?: string;

993+

timeoutSeconds?: number;

994+

};

995+996+

function resolveAcpSpawnRuntimeOptions(params: {

997+

cfg: OpenClawConfig;

998+

targetAgentId: string;

999+

configAgentId?: string;

1000+

model?: string;

1001+

thinking?: string;

1002+

runTimeoutSeconds?: number;

1003+

}): { ok: true; runtimeOptions?: AcpSpawnRuntimeOptions } | { ok: false; error: string } {

1004+

const policyAgentId = params.configAgentId ?? params.targetAgentId;

1005+

const model = resolveConfiguredSubagentSpawnModelSelection({

1006+

cfg: params.cfg,

1007+

agentId: policyAgentId,

1008+

modelOverride: params.model,

1009+

includeAgentPrimary: false,

1010+

});

1011+

const targetAgentConfig = resolveAgentConfig(params.cfg, policyAgentId);

1012+

const thinkingPlan = resolveSubagentThinkingOverride({

1013+

cfg: params.cfg,

1014+

targetAgentConfig,

1015+

thinkingOverrideRaw: params.thinking,

1016+

});

1017+

if (thinkingPlan.status === "error") {

1018+

const { provider, model: modelId } = splitModelRef(model);

1019+

return {

1020+

ok: false,

1021+

error: `Invalid thinking level "${thinkingPlan.thinkingCandidateRaw}". Use one of: ${formatThinkingLevels(provider, modelId)}.`,

1022+

};

1023+

}

1024+1025+

let thinking = thinkingPlan.thinkingOverride;

1026+

if (!thinking && model) {

1027+

const { provider, model: modelId } = splitModelRef(model);

1028+

if (provider && modelId) {

1029+

thinking = resolveThinkingDefault({

1030+

cfg: params.cfg,

1031+

provider,

1032+

model: modelId,

1033+

});

1034+

}

1035+

}

1036+1037+

const runtimeOptions =

1038+

model || thinking || params.runTimeoutSeconds

1039+

? {

1040+

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

1041+

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

1042+

...(params.runTimeoutSeconds ? { timeoutSeconds: params.runTimeoutSeconds } : {}),

1043+

}

1044+

: undefined;

1045+

return { ok: true, runtimeOptions };

1046+

}

1047+9781048

async function initializeAcpSpawnRuntime(params: {

9791049

cfg: OpenClawConfig;

9801050

sessionKey: string;

9811051

targetAgentId: string;

9821052

runtimeMode: AcpRuntimeSessionMode;

9831053

resumeSessionId?: string;

984-

model?: string;

985-

thinking?: string;

986-

runTimeoutSeconds?: number;

1054+

runtimeOptions?: AcpSpawnRuntimeOptions;

9871055

cwd?: string;

9881056

}): Promise<AcpSpawnInitializedRuntime> {

9891057

const storePath = resolveStorePath(params.cfg.session?.store, { agentId: params.targetAgentId });

@@ -1008,14 +1076,7 @@ async function initializeAcpSpawnRuntime(params: {

10081076

agent: params.targetAgentId,

10091077

mode: params.runtimeMode,

10101078

resumeSessionId: params.resumeSessionId,

1011-

runtimeOptions:

1012-

params.model || params.thinking || params.runTimeoutSeconds

1013-

? {

1014-

...(params.model ? { model: params.model } : {}),

1015-

...(params.thinking ? { thinking: params.thinking } : {}),

1016-

...(params.runTimeoutSeconds ? { timeoutSeconds: params.runTimeoutSeconds } : {}),

1017-

}

1018-

: undefined,

1079+

runtimeOptions: params.runtimeOptions,

10191080

cwd: params.cwd,

10201081

backendId: params.cfg.acp?.backend,

10211082

});

@@ -1320,6 +1381,21 @@ export async function spawnAcpDirect(

13201381

error: resumeAuthorization.error,

13211382

});

13221383

}

1384+

const runtimeOptionsResult = resolveAcpSpawnRuntimeOptions({

1385+

cfg,

1386+

targetAgentId,

1387+

configAgentId: targetAgentResult.configAgentId,

1388+

model: params.model,

1389+

thinking: params.thinking,

1390+

runTimeoutSeconds: params.runTimeoutSeconds,

1391+

});

1392+

if (!runtimeOptionsResult.ok) {

1393+

return createAcpSpawnFailure({

1394+

status: "error",

1395+

errorCode: "spawn_failed",

1396+

error: runtimeOptionsResult.error,

1397+

});

1398+

}

13231399

const { effectiveStreamToParent } = resolveAcpSpawnStreamPlan({

13241400

spawnMode,

13251401

requestThreadBinding,

@@ -1392,9 +1468,7 @@ export async function spawnAcpDirect(

13921468

targetAgentId,

13931469

runtimeMode,

13941470

resumeSessionId: params.resumeSessionId,

1395-

model: params.model,

1396-

thinking: params.thinking,

1397-

runTimeoutSeconds: params.runTimeoutSeconds,

1471+

runtimeOptions: runtimeOptionsResult.runtimeOptions,

13981472

cwd: runtimeCwd,

13991473

});

14001474

initializedRuntime = initializedSession.runtimeCloseHandle;