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

The GitHub Blog
The GitHub Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Microsoft Security Blog
Microsoft Security Blog
J
Java Code Geeks
S
SegmentFault 最新的问题
Apple Machine Learning Research
Apple Machine Learning Research
N
Netflix TechBlog - Medium
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园_首页
宝玉的分享
宝玉的分享
Google DeepMind News
Google DeepMind News
B
Blog RSS Feed
Hugging Face - Blog
Hugging Face - Blog
量子位
Blog — PlanetScale
Blog — PlanetScale
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
阮一峰的网络日志
阮一峰的网络日志
D
Docker
罗磊的独立博客
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
云风的 BLOG
云风的 BLOG
IT之家
IT之家
MyScale Blog
MyScale Blog
Microsoft Azure Blog
Microsoft Azure 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
docs: document subagent registry helpers · openclaw/openc...
steipete · 2026-06-05 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -1,3 +1,5 @@

1+

// Subagent initial-user-message tests ensure the delegated task appears once in

2+

// the first user turn instead of being duplicated into the system prompt.

13

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

24

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

35

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

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,5 @@

1+

// Subagent list tests cover active/recent formatting, usage summaries, and

2+

// stale-run filtering for the user-visible subagent status command.

13

import fs from "node:fs/promises";

24

import os from "node:os";

35

import path from "node:path";

@@ -108,6 +110,8 @@ describe("buildSubagentList", () => {

108110

});

109111
110112

it("keeps ended orchestrators active while descendants remain pending", () => {

113+

// Parent orchestrators can finish their own turn before child workers do;

114+

// list output should keep them active until descendants settle.

111115

const now = Date.now();

112116

const orchestratorRun = {

113117

runId: "run-orchestrator-ended",

@@ -218,6 +222,8 @@ describe("buildSubagentList", () => {

218222

channels: { whatsapp: { allowFrom: ["*"] } },

219223

session: { store: storePath },

220224

} as OpenClawConfig;

225+

// Prompt/cache usage is separate from visible IO so operators can spot

226+

// cache-heavy sessions without misreading it as assistant output.

221227

const list = buildSubagentList({

222228

cfg,

223229

runs: [run],

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,5 @@

1+

// Subagent orphan-recovery tests cover restart recovery for child sessions whose

2+

// embedded run was interrupted while the registry still considers them active.

13

import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";

24

import * as sessions from "../config/sessions.js";

35

import * as gateway from "../gateway/call.js";

@@ -11,7 +13,8 @@ import {

1113

import * as subagentRegistrySteerRuntime from "./subagent-registry-steer-runtime.js";

1214

import type { SubagentRunRecord } from "./subagent-registry.types.js";

1315
14-

// Mock dependencies before importing the module under test

16+

// Mocks are installed before importing the recovery module so registry/runtime

17+

// helpers resolve to deterministic restart fixtures.

1518

vi.mock("../config/config.js", () => ({

1619

getRuntimeConfig: vi.fn(() => ({

1720

session: { store: undefined },

@@ -157,7 +160,8 @@ describe("subagent-orphan-recovery", () => {

157160

expect(result.failed).toBe(0);

158161

expect(result.skipped).toBe(0);

159162
160-

// Should have called callGateway to resume the session

163+

// Recovery resumes through the gateway and records the new run id so the

164+

// registry follows the resumed transcript instead of the idempotency key.

161165

expect(gateway.callGateway).toHaveBeenCalledOnce();

162166

const opts = requireRecord(

163167

firstCallParam(vi.mocked(gateway.callGateway).mock.calls, "gateway resume"),

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,5 @@

1+

// Subagent registry cleanup tests cover deferred cleanup decisions while

2+

// completion delivery, descendants, and retry windows are still unresolved.

13

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

24

import { resolveDeferredCleanupDecision } from "./subagent-registry-cleanup.js";

35

import type { SubagentRunRecord } from "./subagent-registry.types.js";

@@ -28,6 +30,8 @@ describe("resolveDeferredCleanupDecision", () => {

2830

Pick<Parameters<typeof resolveDeferredCleanupDecision>[0], "resolveAnnounceRetryDelayMs">

2931

>,

3032

) {

33+

// Fixed timing keeps expiry and backoff decisions independent from wall

34+

// clock drift while still exercising production thresholds.

3135

return resolveDeferredCleanupDecision({

3236

now,

3337

announceExpiryMs: 5 * 60_000,

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,5 @@

1+

// Subagent registry helper tests cover orphan reconciliation and compact logging

2+

// for announce delivery give-up paths.

13

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

24

import { defaultRuntime } from "../runtime.js";

35

import { logAnnounceGiveUp, reconcileOrphanedRun } from "./subagent-registry-helpers.js";

@@ -81,6 +83,8 @@ describe("logAnnounceGiveUp", () => {

8183

});

8284
8385

it("normalizes multiline delivery errors onto one gateway log line", () => {

86+

// Gateway logs are line-oriented; multiline provider errors must be

87+

// collapsed before they enter warning text.

8488

const logSpy = vi.spyOn(defaultRuntime, "log").mockImplementation(() => {});

8589

const entry = createRunEntry({

8690

delivery: {