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

博客园 - 聂微东
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
L
LangChain Blog
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
博客园 - 司徒正美
WordPress大学
WordPress大学
T
The Blog of Author Tim Ferriss
Blog — PlanetScale
Blog — PlanetScale
J
Java Code Geeks
Y
Y Combinator Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
GbyAI
GbyAI
Vercel News
Vercel News
大猫的无限游戏
大猫的无限游戏
T
Tailwind CSS Blog
Jina AI
Jina AI
B
Blog
Recorded Future
Recorded Future
MyScale Blog
MyScale Blog
I
InfoQ
aimingoo的专栏
aimingoo的专栏
博客园_首页
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
雷峰网
雷峰网
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
腾讯CDC
爱范儿
爱范儿
Last Week in AI
Last Week in AI
博客园 - 三生石上(FineUI控件)
博客园 - Franky
Schneier on Security
Schneier on Security
V
V2EX
TaoSecurity Blog
TaoSecurity Blog
H
Hacker News: Front Page
Cloudbric
Cloudbric
D
DataBreaches.Net
B
Blog RSS Feed
P
Palo Alto Networks Blog
云风的 BLOG
云风的 BLOG
NISL@THU
NISL@THU
I
Intezer
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Cyberwarzone
Cyberwarzone
F
Fortinet All Blogs
D
Darknet – Hacking Tools, Hacker News & Cyber Security
C
Cybersecurity and Infrastructure Security Agency CISA
C
Cisco Blogs
K
Kaspersky official blog
Forbes - Security
Forbes - 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 context usage display and active-run reload interruptions · openclaw/openclaw@fd3840c
Poo-Squirry · 2026-04-26 · via Recent Commits to openclaw:main

@@ -3,7 +3,7 @@ import os from "node:os";

33

import path from "node:path";

44

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

55

import { SessionManager } from "@mariozechner/pi-coding-agent";

6-

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

6+

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

77

import {

88

initializeGlobalHookRunner,

99

resetGlobalHookRunner,

@@ -88,6 +88,14 @@ function expectPersistedToolResultTextCapped(sm: ReturnType<typeof SessionManage

8888

expect(text).toContain("truncated");

8989

}

909091+

function expectPersistedToolResultDetailsCapped(sm: ReturnType<typeof SessionManager.inMemory>) {

92+

const toolResult = getPersistedToolResult(sm);

93+

const details = toolResult.details as Record<string, unknown>;

94+

expect(details.persistedDetailsTruncated).toBe(true);

95+

expect(details.aggregated).toBeUndefined();

96+

expect(Buffer.byteLength(JSON.stringify(details), "utf-8")).toBeLessThan(8_192);

97+

}

98+9199

afterEach(() => {

92100

resetGlobalHookRunner();

93101

if (originalBundledPluginsDir === undefined) {

@@ -109,6 +117,189 @@ describe("tool_result_persist hook", () => {

109117

expect(toolResult.details).toBeTruthy();

110118

});

111119120+

it("caps oversized toolResult details before persistence", () => {

121+

const sm = guardSessionManager(SessionManager.inMemory(), {

122+

agentId: "main",

123+

sessionKey: "main",

124+

});

125+

const appendMessage = sm.appendMessage.bind(sm) as unknown as (message: AgentMessage) => void;

126+

appendMessage({

127+

role: "assistant",

128+

content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],

129+

} as AgentMessage);

130+

appendMessage({

131+

role: "toolResult",

132+

toolCallId: "call_1",

133+

isError: false,

134+

content: [{ type: "text", text: "visible output stays small" }],

135+

details: {

136+

status: "completed",

137+

sessionId: "exec-1",

138+

aggregated: "x".repeat(120_000),

139+

tail: "t".repeat(6_000),

140+

sessions: [

141+

{

142+

sessionId: "proc-1",

143+

status: "completed",

144+

command: "node noisy-script.js ".repeat(2_000),

145+

aggregated: "a".repeat(80_000),

146+

tail: "z".repeat(8_000),

147+

},

148+

],

149+

},

150+

} as any);

151+152+

const toolResult = getPersistedToolResult(sm);

153+

expect(toolResult.content[0]?.text).toBe("visible output stays small");

154+

expectPersistedToolResultDetailsCapped(sm);

155+

});

156+157+

it("caps oversized toolResult details without serializing the original payload", () => {

158+

const sm = guardSessionManager(SessionManager.inMemory(), {

159+

agentId: "main",

160+

sessionKey: "main",

161+

});

162+

const appendMessage = sm.appendMessage.bind(sm) as unknown as (message: AgentMessage) => void;

163+

const oversizedDetails = {

164+

status: "completed",

165+

sessionId: "exec-large",

166+

aggregated: "x".repeat(200_000),

167+

sessions: [

168+

{

169+

sessionId: "proc-large",

170+

command: "node noisy-script.js ".repeat(2_000),

171+

tail: "z".repeat(20_000),

172+

},

173+

],

174+

};

175+

const originalStringify = JSON.stringify;

176+

const stringifySpy = vi.spyOn(JSON, "stringify").mockImplementation((value, ...args) => {

177+

if (value === oversizedDetails) {

178+

throw new Error("unbounded original details stringify");

179+

}

180+

return originalStringify(value, ...args);

181+

});

182+183+

try {

184+

appendMessage({

185+

role: "assistant",

186+

content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],

187+

} as AgentMessage);

188+

appendMessage({

189+

role: "toolResult",

190+

toolCallId: "call_1",

191+

isError: false,

192+

content: [{ type: "text", text: "visible output stays small" }],

193+

details: oversizedDetails,

194+

} as any);

195+

} finally {

196+

stringifySpy.mockRestore();

197+

}

198+199+

const toolResult = getPersistedToolResult(sm);

200+

expect(toolResult.content[0]?.text).toBe("visible output stays small");

201+

expectPersistedToolResultDetailsCapped(sm);

202+

expect(stringifySpy).not.toHaveBeenCalledWith(oversizedDetails);

203+

});

204+205+

it("caps wide toolResult details without materializing every entry up front", () => {

206+

const sm = guardSessionManager(SessionManager.inMemory(), {

207+

agentId: "main",

208+

sessionKey: "main",

209+

});

210+

const appendMessage = sm.appendMessage.bind(sm) as unknown as (message: AgentMessage) => void;

211+

const wideDetails: Record<string, unknown> = {

212+

status: "completed",

213+

sessionId: "exec-wide",

214+

};

215+

for (let index = 0; index < 20_000; index += 1) {

216+

wideDetails[`debug_${index}`] = `value-${index}`;

217+

}

218+

const originalEntries = Object.entries;

219+

const originalKeys = Object.keys;

220+

const entriesSpy = vi.spyOn(Object, "entries").mockImplementation((value) => {

221+

if (value === wideDetails) {

222+

throw new Error("wide details entries materialized");

223+

}

224+

return originalEntries(value);

225+

});

226+

const keysSpy = vi.spyOn(Object, "keys").mockImplementation((value) => {

227+

if (value === wideDetails) {

228+

throw new Error("wide details keys materialized");

229+

}

230+

return originalKeys(value);

231+

});

232+233+

try {

234+

appendMessage({

235+

role: "assistant",

236+

content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],

237+

} as AgentMessage);

238+

appendMessage({

239+

role: "toolResult",

240+

toolCallId: "call_1",

241+

isError: false,

242+

content: [{ type: "text", text: "visible output stays small" }],

243+

details: wideDetails,

244+

} as any);

245+

} finally {

246+

entriesSpy.mockRestore();

247+

keysSpy.mockRestore();

248+

}

249+250+

const toolResult = getPersistedToolResult(sm);

251+

const details = toolResult.details as Record<string, unknown>;

252+

expect(details.persistedDetailsTruncated).toBe(true);

253+

expect(details.originalDetailKeys).toEqual(

254+

expect.arrayContaining(["status", "sessionId", "debug_0"]),

255+

);

256+

});

257+258+

it("falls back to a compact summary when sanitized details still exceed the cap", () => {

259+

const sm = guardSessionManager(SessionManager.inMemory(), {

260+

agentId: "main",

261+

sessionKey: "main",

262+

});

263+

const appendMessage = sm.appendMessage.bind(sm) as unknown as (message: AgentMessage) => void;

264+

appendMessage({

265+

role: "assistant",

266+

content: [{ type: "toolCall", id: "call_1", name: "exec", arguments: {} }],

267+

} as AgentMessage);

268+

appendMessage({

269+

role: "toolResult",

270+

toolCallId: "call_1",

271+

isError: false,

272+

content: [{ type: "text", text: "visible output stays small" }],

273+

details: {

274+

status: "completed".repeat(250),

275+

sessionId: "exec-oversized",

276+

cwd: "/tmp/very-long-working-directory".repeat(250),

277+

name: "noisy process".repeat(250),

278+

fullOutputPath: "/tmp/output.log".repeat(250),

279+

truncation: "truncated".repeat(250),

280+

tail: "t".repeat(20_000),

281+

aggregated: "a".repeat(120_000),

282+

sessions: Array.from({ length: 10 }, (_, index) => ({

283+

sessionId: `proc-${index}`,

284+

status: "completed".repeat(100),

285+

cwd: "/tmp/session".repeat(100),

286+

name: "child process".repeat(100),

287+

command: "node noisy-script.js ".repeat(200),

288+

aggregated: "x".repeat(50_000),

289+

tail: "z".repeat(10_000),

290+

})),

291+

},

292+

} as any);

293+294+

const toolResult = getPersistedToolResult(sm);

295+

const details = toolResult.details as Record<string, unknown>;

296+

expect(details.persistedDetailsTruncated).toBe(true);

297+

expect(details.finalDetailsTruncated).toBe(true);

298+

expect(details.aggregated).toBeUndefined();

299+

expect(details.tail).toBeUndefined();

300+

expect(Buffer.byteLength(JSON.stringify(details), "utf-8")).toBeLessThan(8_192);

301+

});

302+112303

it("loads tool_result_persist hooks without breaking persistence", () => {

113304

const tmp = fs.mkdtempSync(path.join(os.tmpdir(), "openclaw-toolpersist-"));

114305

process.env.OPENCLAW_BUNDLED_PLUGINS_DIR = "/nonexistent/bundled/plugins";

@@ -189,6 +380,35 @@ describe("tool_result_persist hook", () => {

189380

appendToolCallAndResult(sm);

190381

expectPersistedToolResultTextCapped(sm);

191382

});

383+384+

it("reapplies the details cap after tool_result_persist expands details", () => {

385+

initializeTempPlugin({

386+

tmpPrefix: "openclaw-toolpersist-details-expand-",

387+

id: "persist-details-expand",

388+

body: `export default { id: "persist-details-expand", register(api) {

389+

api.on("tool_result_persist", (event) => {

390+

return {

391+

message: {

392+

...event.message,

393+

details: {

394+

status: "completed",

395+

aggregated: "x".repeat(150000),

396+

sessions: [{ sessionId: "proc-1", command: "y".repeat(50000), tail: "z".repeat(10000) }],

397+

},

398+

},

399+

};

400+

}, { priority: 10 });

401+

} };`,

402+

});

403+404+

const sm = guardSessionManager(SessionManager.inMemory(), {

405+

agentId: "main",

406+

sessionKey: "main",

407+

});

408+409+

appendToolCallAndResult(sm);

410+

expectPersistedToolResultDetailsCapped(sm);

411+

});

192412

});

193413194414

describe("before_message_write hook", () => {