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

WordPress大学
WordPress大学
Cyberwarzone
Cyberwarzone
The GitHub Blog
The GitHub Blog
云风的 BLOG
云风的 BLOG
P
Proofpoint News Feed
小众软件
小众软件
Recent Announcements
Recent Announcements
博客园 - 三生石上(FineUI控件)
Security Archives - TechRepublic
Security Archives - TechRepublic
W
WeLiveSecurity
Cloudbric
Cloudbric
博客园 - 司徒正美
美团技术团队
N
News and Events Feed by Topic
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
PCI Perspectives
PCI Perspectives
宝玉的分享
宝玉的分享
H
Help Net Security
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Google DeepMind News
Google DeepMind News
Help Net Security
Help Net Security
Last Week in AI
Last Week in AI
S
Schneier on Security
N
News | PayPal Newsroom
B
Blog RSS Feed
L
LINUX DO - 最新话题
T
Troy Hunt's Blog
S
Secure Thoughts
雷峰网
雷峰网
aimingoo的专栏
aimingoo的专栏
L
Lohrmann on Cybersecurity
G
Google Developers Blog
Microsoft Azure Blog
Microsoft Azure Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
Tenable Blog
S
Securelist
L
LangChain Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
I
InfoQ
H
Heimdal Security Blog
Cisco Talos Blog
Cisco Talos Blog
F
Full Disclosure
Y
Y Combinator Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
K
Kaspersky official blog
T
Tailwind CSS Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
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
阮一峰的网络日志
阮一峰的网络日志
C
Cisco Blogs

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): dedupe subagent startup task · openclaw/openclaw@735890d
steipete · 2026-04-27 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -40,6 +40,7 @@ Docs: https://docs.openclaw.ai

4040

- Cron/Telegram: preserve direct-chat thread IDs and optional account IDs when inferring reminder delivery from Telegram direct-thread session keys. Fixes #44270; carries forward #44325, #44351, #44412, and #72657. Thanks @RunMintOn, @arkyu2077, @0xsline, and @vincentkoc.

4141

- Cron: omit synthetic `delivery.resolved` errors from `--no-deliver` run records while preserving explicit no-deliver target traces for agent-initiated messages. Fixes #72210; carries forward #72219. Thanks @hatemclawbot-collab and @xydigit-sj.

4242

- Cron: classify isolated runs as errors from structured embedded-run execution-denial metadata, with final-output marker fallback for `SYSTEM_RUN_DENIED`, `INVALID_REQUEST`, and approval-binding refusals, so blocked commands no longer appear green in cron history. Fixes #67172; carries forward #67186. Thanks @oc-gh-dr, @hclsys, and @1yihui.

43+

- Subagents: keep the delegated task only in the subagent system prompt and send a short initial kickoff message, avoiding duplicate task tokens while preserving multiline task formatting. Fixes #72019; carries forward #72053. Thanks @Wizongod and @ly85206559.

4344

- Onboarding/GitHub Copilot: add manifest-owned `--github-copilot-token` support for non-interactive setup, including env fallback, tokenRef storage in ref mode, saved-profile reuse, and current Copilot default-model wiring. Refs #50002 and supersedes #50003. Thanks @scottgl9.

4445

- Gateway/install: add a validated `--wrapper`/`OPENCLAW_WRAPPER` service install path that persists executable LaunchAgent/systemd wrappers across forced reinstalls, updates, and doctor repairs instead of falling back to raw node/bun `ProgramArguments`. Fixes #69400. (#72445) Thanks @willtmc.

4546

- Plugins: fail plugin registration when loader-owned acceptance gates reject missing hook names or memory-only capability registration from non-memory plugins, surfacing the issue through plugin status and doctor instead of silently dropping the registration. Fixes #72459. Thanks @1fanwang and @amknight.

Original file line numberDiff line numberDiff line change

@@ -0,0 +1,46 @@

1+

import { describe, expect, it } from "vitest";

2+

import { buildSubagentInitialUserMessage } from "./subagent-initial-user-message.js";

3+

import { buildSubagentSystemPrompt } from "./subagent-system-prompt.js";

4+
5+

describe("buildSubagentInitialUserMessage", () => {

6+

it("does not embed a task string already present in the system prompt (#72019)", () => {

7+

const msg = buildSubagentInitialUserMessage({

8+

childDepth: 1,

9+

maxSpawnDepth: 3,

10+

persistentSession: false,

11+

});

12+
13+

expect(msg).not.toContain("[Subagent Task]:");

14+

expect(msg).toContain("**Your Role**");

15+

expect(msg).toContain("depth 1/3");

16+

});

17+
18+

it("includes the persistent session note when requested", () => {

19+

const msg = buildSubagentInitialUserMessage({

20+

childDepth: 2,

21+

maxSpawnDepth: 4,

22+

persistentSession: true,

23+

});

24+
25+

expect(msg).toContain("persistent and remains available");

26+

});

27+
28+

it("keeps the delegated task single-sourced across system and first user text", () => {

29+

const task = "UNIQUE_SUBAGENT_TASK_TOKEN\n preserve indentation";

30+

const system = buildSubagentSystemPrompt({

31+

childSessionKey: "agent:main:subagent:test",

32+

task,

33+

childDepth: 1,

34+

maxSpawnDepth: 2,

35+

});

36+

const user = buildSubagentInitialUserMessage({

37+

childDepth: 1,

38+

maxSpawnDepth: 2,

39+

persistentSession: false,

40+

});

41+
42+

expect(system).toContain("UNIQUE_SUBAGENT_TASK_TOKEN");

43+

expect(user).not.toContain("UNIQUE_SUBAGENT_TASK_TOKEN");

44+

expect(`${system}\n${user}`.match(/UNIQUE_SUBAGENT_TASK_TOKEN/g)).toHaveLength(1);

45+

});

46+

});

Original file line numberDiff line numberDiff line change

@@ -0,0 +1,26 @@

1+

/**

2+

* First user turn for a native `sessions_spawn` / subagent run.

3+

*

4+

* Keep the full task out of this message: `buildSubagentSystemPrompt` already

5+

* places it under **Your Role**, and repeating it here doubles first-request

6+

* input tokens (#72019).

7+

*/

8+

export function buildSubagentInitialUserMessage(params: {

9+

childDepth: number;

10+

maxSpawnDepth: number;

11+

/** When true, this subagent uses a persistent session for follow-up messages. */

12+

persistentSession: boolean;

13+

}): string {

14+

const lines = [

15+

`[Subagent Context] You are running as a subagent (depth ${params.childDepth}/${params.maxSpawnDepth}). Results auto-announce to your requester; do not busy-poll for status.`,

16+

];

17+

if (params.persistentSession) {

18+

lines.push(

19+

"[Subagent Context] This subagent session is persistent and remains available for thread follow-up messages.",

20+

);

21+

}

22+

lines.push(

23+

"Begin. Your assigned task is in the system prompt under **Your Role**; execute it to completion.",

24+

);

25+

return lines.join("\n\n");

26+

}

Original file line numberDiff line numberDiff line change

@@ -288,6 +288,42 @@ describe("spawnSubagentDirect seam flow", () => {

288288

});

289289

});

290290
291+

it("does not duplicate long subagent task text in the initial user message (#72019)", async () => {

292+

const calls: Array<{ method?: string; params?: unknown }> = [];

293+

hoisted.callGatewayMock.mockImplementation(

294+

async (request: { method?: string; params?: unknown }) => {

295+

calls.push(request);

296+

if (request.method === "agent") {

297+

return { runId: "run-no-dup", status: "accepted", acceptedAt: 1000 };

298+

}

299+

if (request.method?.startsWith("sessions.")) {

300+

return { ok: true };

301+

}

302+

return {};

303+

},

304+

);

305+

installSessionStoreCaptureMock(hoisted.updateSessionStoreMock);

306+
307+

const task = "UNIQUE_LONG_SUBAGENT_TASK_TOKEN\n keep indentation";

308+

const result = await spawnSubagentDirect(

309+

{

310+

task,

311+

},

312+

{

313+

agentSessionKey: "agent:main:main",

314+

agentChannel: "discord",

315+

},

316+

);

317+
318+

expect(result.status).toBe("accepted");

319+

const agentCall = calls.find((call) => call.method === "agent");

320+

const params = agentCall?.params as { message?: string; extraSystemPrompt?: string };

321+

expect(params.message).not.toContain("UNIQUE_LONG_SUBAGENT_TASK_TOKEN");

322+

expect(params.message).not.toContain("[Subagent Task]:");

323+

expect(params.message).toContain("**Your Role**");

324+

expect(params.extraSystemPrompt).toBe("system-prompt");

325+

});

326+
291327

it("returns an error when the initial child session patch is rejected", async () => {

292328

hoisted.callGatewayMock.mockImplementation(

293329

async (request: { method?: string; params?: unknown }) => {

Original file line numberDiff line numberDiff line change

@@ -26,6 +26,7 @@ import {

2626

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

2727

import { resolveSubagentCapabilities } from "./subagent-capabilities.js";

2828

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

29+

import { buildSubagentInitialUserMessage } from "./subagent-initial-user-message.js";

2930

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

3031

import { resolveSubagentSpawnAcceptedNote } from "./subagent-spawn-accepted-note.js";

3132

export {

@@ -974,15 +975,11 @@ export async function spawnSubagentDirect(

974975

? "lightweight"

975976

: undefined;

976977
977-

const childTaskMessage = [

978-

`[Subagent Context] You are running as a subagent (depth ${childDepth}/${maxSpawnDepth}). Results auto-announce to your requester; do not busy-poll for status.`,

979-

spawnMode === "session"

980-

? "[Subagent Context] This subagent session is persistent and remains available for thread follow-up messages."

981-

: undefined,

982-

`[Subagent Task]: ${task}`,

983-

]

984-

.filter((line): line is string => Boolean(line))

985-

.join("\n\n");

978+

const childTaskMessage = buildSubagentInitialUserMessage({

979+

childDepth,

980+

maxSpawnDepth,

981+

persistentSession: spawnMode === "session",

982+

});

986983
987984

const toolSpawnMetadata = mapToolContextToSpawnedRunMetadata({

988985

agentGroupId: ctx.agentGroupId,

Original file line numberDiff line numberDiff line change

@@ -16,10 +16,9 @@ export function buildSubagentSystemPrompt(params: {

1616

/** Config value: max allowed spawn depth. */

1717

maxSpawnDepth?: number;

1818

}) {

19-

const taskText =

20-

typeof params.task === "string" && params.task.trim()

21-

? params.task.replace(/\s+/g, " ").trim()

22-

: "{{TASK_DESCRIPTION}}";

19+

const taskRaw = typeof params.task === "string" ? params.task : "";

20+

const taskBody = taskRaw.trim();

21+

const hasTask = taskBody !== "";

2322

const childDepth = typeof params.childDepth === "number" ? params.childDepth : 1;

2423

const maxSpawnDepth =

2524

typeof params.maxSpawnDepth === "number"

@@ -31,17 +30,33 @@ export function buildSubagentSystemPrompt(params: {

3130

);

3231

const canSpawn = childDepth < maxSpawnDepth;

3332

const parentLabel = childDepth >= 2 ? "parent orchestrator" : "main agent";

33+

const roleLines =

34+

hasTask && taskBody.includes("\n")

35+

? [

36+

"## Your Role",

37+

"- You were created to handle the following task (verbatim; line breaks preserved):",

38+

"",

39+

"```",

40+

taskBody,

41+

"```",

42+

"- Complete this task. That's your entire purpose.",

43+

`- You are NOT the ${parentLabel}. Don't try to be.`,

44+

"",

45+

]

46+

: [

47+

"## Your Role",

48+

`- You were created to handle: ${hasTask ? taskBody : "{{TASK_DESCRIPTION}}"}`,

49+

"- Complete this task. That's your entire purpose.",

50+

`- You are NOT the ${parentLabel}. Don't try to be.`,

51+

"",

52+

];

3453
3554

const lines = [

3655

"# Subagent Context",

3756

"",

3857

`You are a **subagent** spawned by the ${parentLabel} for a specific task.`,

3958

"",

40-

"## Your Role",

41-

`- You were created to handle: ${taskText}`,

42-

"- Complete this task. That's your entire purpose.",

43-

`- You are NOT the ${parentLabel}. Don't try to be.`,

44-

"",

59+

...roleLines,

4560

"## Rules",

4661

"1. **Stay focused** - Do your assigned task, nothing else",

4762

`2. **Complete the task** - Your final message will be automatically reported to the ${parentLabel}`,

Original file line numberDiff line numberDiff line change

@@ -988,6 +988,22 @@ describe("buildSubagentSystemPrompt", () => {

988988

expect(prompt).toContain("instead of full-file `cat`");

989989

});

990990
991+

it("keeps multiline and indented task text verbatim in the system prompt (#72019)", () => {

992+

const task = "line one\n line two\n line three";

993+

const prompt = buildSubagentSystemPrompt({

994+

childSessionKey: "agent:main:subagent:abc",

995+

task,

996+

childDepth: 1,

997+

maxSpawnDepth: 1,

998+

});

999+
1000+

expect(prompt).toContain("```");

1001+

expect(prompt).toContain("line one");

1002+

expect(prompt).toContain(" line two");

1003+

expect(prompt).toContain(" line three");

1004+

expect(prompt).not.toContain("line one line two");

1005+

});

1006+
9911007

it("omits ACP spawning guidance when ACP is disabled", () => {

9921008

const prompt = buildSubagentSystemPrompt({

9931009

childSessionKey: "agent:main:subagent:abc",