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

C
Cybersecurity and Infrastructure Security Agency CISA
WordPress大学
WordPress大学
人人都是产品经理
人人都是产品经理
小众软件
小众软件
博客园 - 【当耐特】
爱范儿
爱范儿
美团技术团队
Jina AI
Jina AI
Hugging Face - Blog
Hugging Face - Blog
博客园 - 聂微东
月光博客
月光博客
宝玉的分享
宝玉的分享
V
V2EX
Blog — PlanetScale
Blog — PlanetScale
Spread Privacy
Spread Privacy
博客园 - 叶小钗
量子位
Security Archives - TechRepublic
Security Archives - TechRepublic
Google DeepMind News
Google DeepMind News
L
LINUX DO - 热门话题
Hacker News - Newest:
Hacker News - Newest: "LLM"
P
Privacy International News Feed
Y
Y Combinator Blog
P
Proofpoint News Feed
NISL@THU
NISL@THU
The Last Watchdog
The Last Watchdog
S
Secure Thoughts
G
Google Developers Blog
Hacker News: Ask HN
Hacker News: Ask HN
Help Net Security
Help Net Security
I
InfoQ
Cisco Talos Blog
Cisco Talos Blog
Google Online Security Blog
Google Online Security 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
Recent Announcements
Recent Announcements
Simon Willison's Weblog
Simon Willison's Weblog
Vercel News
Vercel News
Recent Commits to openclaw:main
Recent Commits to openclaw:main
T
Threat Research - Cisco Blogs
GbyAI
GbyAI
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
C
CXSECURITY Database RSS Feed - CXSecurity.com
V
Vulnerabilities – Threatpost
B
Blog
Stack Overflow Blog
Stack Overflow Blog
Microsoft Azure Blog
Microsoft Azure Blog
N
News | PayPal Newsroom
J
Java Code Geeks
Latest news
Latest news
H
Hackread – Cybersecurity News, Data Breaches, AI and More

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(codex): bound turn/start text when context budget is non-positive… · openclaw/openclaw@fb25f29
Nas01010101 · 2026-06-19 · via Recent Commits to openclaw:main

@@ -2,6 +2,7 @@

22

import type { AgentMessage } from "openclaw/plugin-sdk/agent-core";

33

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

44

import {

5+

CODEX_TURN_START_TEXT_INPUT_MAX_CHARS,

56

fitCodexProjectedContextForTurnStart,

67

projectContextEngineAssemblyForCodex,

78

resolveCodexContextEngineProjectionMaxChars,

@@ -226,6 +227,92 @@ describe("projectContextEngineAssemblyForCodex", () => {

226227

expect(fitted).not.toContain("old context");

227228

});

228229230+

it("bounds output when the non-context text alone exceeds the turn limit", () => {

231+

// A large older-context header prefix pushes before + after over maxChars

232+

// while the trailing user request stays small enough to keep its label.

233+

const before = `OpenClaw assembled context for this turn:\n${"prefix ".repeat(120)}`;

234+

const context = "older context ".repeat(40);

235+

const prompt = `urgent request ${"q".repeat(120)}`;

236+

const after = `\n</conversation_context>\n\nCurrent user request:\n${prompt}`;

237+

const promptText = `${before}${context}${after}`;

238+

const maxChars = 420;

239+

// before + after already exceed maxChars, so the context budget is non-positive.

240+

expect(before.length + after.length).toBeGreaterThan(maxChars);

241+242+

const fitted = fitCodexProjectedContextForTurnStart({

243+

promptText,

244+

contextRange: { start: before.length, end: before.length + context.length },

245+

maxChars,

246+

});

247+248+

expect(fitted.length).toBeLessThanOrEqual(maxChars);

249+

// The user's actual request is the priority tail and must survive truncation.

250+

expect(fitted).toContain("Current user request:");

251+

expect(fitted.endsWith("q".repeat(40))).toBe(true);

252+

// The dropped older context is reported, not silently lost.

253+

expect(fitted).toContain("[truncated ");

254+

});

255+256+

it("bounds output for a large request under the default Codex turn limit", () => {

257+

const maxChars = CODEX_TURN_START_TEXT_INPUT_MAX_CHARS;

258+

// A large assembled header prefix already over the cap forces the

259+

// non-positive context budget on the real default limit (1 << 20).

260+

const before = `header\n${"older history ".repeat(90_000)}`;

261+

const context = "x".repeat(2_000);

262+

const prompt = `urgent request ${"u".repeat(2_000)}`;

263+

const after = `\n</conversation_context>\n\nCurrent user request:\n${prompt}`;

264+

const promptText = `${before}${context}${after}`;

265+

expect(before.length + after.length).toBeGreaterThan(maxChars);

266+267+

const fitted = fitCodexProjectedContextForTurnStart({

268+

promptText,

269+

contextRange: { start: before.length, end: before.length + context.length },

270+

// maxChars omitted -> defaults to CODEX_TURN_START_TEXT_INPUT_MAX_CHARS.

271+

});

272+273+

expect(fitted.length).toBeLessThanOrEqual(maxChars);

274+

// The user request is the priority tail and survives even though the older

275+

// header text is truncated to satisfy the limit.

276+

expect(fitted).toContain("Current user request:");

277+

expect(fitted.endsWith("u".repeat(1_000))).toBe(true);

278+

});

279+280+

it("never splits a UTF-16 surrogate pair at the truncation boundary", () => {

281+

// Drive the non-positive-budget path with an emoji (surrogate pair) sitting

282+

// across the kept-tail cut. A naive code-unit slice would orphan the low

283+

// surrogate into U+FFFD; the boundary must stay on a whole code point.

284+

const before = `OpenClaw assembled context for this turn:\n${"H".repeat(300)}`;

285+

const context = "older context ".repeat(20);

286+

// Emoji immediately before the user text so the cut can fall mid-pair.

287+

const prompt = `\u{1F600}${"U".repeat(60)}`;

288+

const after = `\n</conversation_context>\n\nCurrent user request:\n${prompt}`;

289+

const promptText = `${before}${context}${after}`;

290+

const contextRange = { start: before.length, end: before.length + context.length };

291+292+

// Sweep cap sizes around the cut so the test is not brittle to marker length;

293+

// at least one value lands the boundary inside the surrogate pair.

294+

for (let maxChars = 90; maxChars <= 140; maxChars += 1) {

295+

const fitted = fitCodexProjectedContextForTurnStart({ promptText, contextRange, maxChars });

296+

expect(fitted.length).toBeLessThanOrEqual(maxChars);

297+

// U+FFFD only appears when a lone surrogate is rendered, i.e. a split pair.

298+

expect(fitted).not.toContain("�");

299+

// Any surviving emoji must be the complete pair, not a lone low surrogate.

300+

for (let i = 0; i < fitted.length; i += 1) {

301+

const code = fitted.charCodeAt(i);

302+

const isLowSurrogate = code >= 0xdc00 && code <= 0xdfff;

303+

const isHighSurrogate = code >= 0xd800 && code <= 0xdbff;

304+

if (isLowSurrogate) {

305+

const prev = fitted.charCodeAt(i - 1);

306+

expect(prev >= 0xd800 && prev <= 0xdbff).toBe(true);

307+

}

308+

if (isHighSurrogate) {

309+

const next = fitted.charCodeAt(i + 1);

310+

expect(next >= 0xdc00 && next <= 0xdfff).toBe(true);

311+

}

312+

}

313+

}

314+

});

315+229316

it("keeps the old conservative cap when no runtime budget is available", () => {

230317

expect(resolveCodexContextEngineProjectionMaxChars({})).toBe(24_000);

231318

expect(resolveCodexContextEngineProjectionMaxChars({ contextTokenBudget: 0 })).toBe(24_000);