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

雷峰网
雷峰网
宝玉的分享
宝玉的分享
I
InfoQ
P
Privacy International News Feed
V
V2EX
IT之家
IT之家
S
SegmentFault 最新的问题
D
Darknet – Hacking Tools, Hacker News & Cyber Security
V2EX - 技术
V2EX - 技术
C
CERT Recently Published Vulnerability Notes
C
Check Point Blog
The Register - Security
The Register - Security
爱范儿
爱范儿
博客园 - 三生石上(FineUI控件)
AWS News Blog
AWS News Blog
M
MIT News - Artificial intelligence
C
Cyber Attacks, Cyber Crime and Cyber Security
F
Fortinet All Blogs
B
Blog
N
Netflix TechBlog - Medium
B
Blog RSS Feed
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Last Week in AI
Last Week in AI
T
Threatpost
Forbes - Security
Forbes - Security
U
Unit 42
A
Arctic Wolf
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
P
Palo Alto Networks Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Recorded Future
Recorded Future
L
Lohrmann on Cybersecurity
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
P
Proofpoint News Feed
月光博客
月光博客
Spread Privacy
Spread Privacy
MongoDB | Blog
MongoDB | Blog
Jina AI
Jina AI
I
Intezer
V
Visual Studio Blog
阮一峰的网络日志
阮一峰的网络日志
The Hacker News
The Hacker News
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
L
LangChain Blog
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
博客园_首页
MyScale Blog
MyScale Blog
腾讯CDC
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
量子位

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
refactor: centralize context prompt token resolution · openclaw/openclaw@bb6cf75
steipete · 2026-04-26 · via Recent Commits to openclaw:main

@@ -239,66 +239,12 @@ describe("runReplyAgent auto-compaction token update", () => {

239239

return { typing, sessionCtx, resolvedQueue, followupRun };

240240

}

241241242-

it("updates totalTokens from lastCallUsage even without compaction", async () => {

243-

const tmp = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-usage-last-"));

244-

const storePath = path.join(tmp, "sessions.json");

245-

const sessionKey = "main";

246-

const sessionEntry = {

247-

sessionId: "session",

248-

updatedAt: Date.now(),

249-

totalTokens: 50_000,

250-

};

251-252-

await seedSessionStore({ storePath, sessionKey, entry: sessionEntry });

253-254-

runEmbeddedPiAgentMock.mockResolvedValue({

255-

payloads: [{ text: "ok" }],

256-

meta: {

257-

agentMeta: {

258-

// Tool-use loop: accumulated input is higher than last call's input

259-

usage: { input: 75_000, output: 5_000, total: 80_000 },

260-

lastCallUsage: { input: 55_000, output: 2_000, total: 57_000 },

261-

},

262-

},

263-

});

264-265-

const { typing, sessionCtx, resolvedQueue, followupRun } = createBaseRun({

266-

storePath,

267-

sessionEntry,

268-

});

269-270-

await runReplyAgent({

271-

commandBody: "hello",

272-

followupRun,

273-

queueKey: "main",

274-

resolvedQueue,

275-

shouldSteer: false,

276-

shouldFollowup: false,

277-

isActive: false,

278-

isStreaming: false,

279-

typing,

280-

sessionCtx,

281-

sessionEntry,

282-

sessionStore: { [sessionKey]: sessionEntry },

283-

sessionKey,

284-

storePath,

285-

defaultModel: "anthropic/claude-opus-4-6",

286-

agentCfgContextTokens: 200_000,

287-

resolvedVerboseLevel: "off",

288-

isNewSession: false,

289-

blockStreamingEnabled: false,

290-

resolvedBlockStreamingBreak: "message_end",

291-

shouldInjectGroupIntro: false,

292-

typingMode: "instant",

293-

});

294-295-

const stored = JSON.parse(await fs.readFile(storePath, "utf-8"));

296-

// totalTokens should use lastCallUsage (55k), not accumulated (75k)

297-

expect(stored[sessionKey].totalTokens).toBe(55_000);

298-

});

299-300-

it("reports live diagnostic context from promptTokens, not provider usage totals", async () => {

301-

const tmp = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-usage-diagnostic-"));

242+

async function runBaseReplyWithAgentMeta(params: {

243+

agentMeta: Record<string, unknown>;

244+

collectDiagnostics?: boolean;

245+

tmpPrefix: string;

246+

}) {

247+

const tmp = await fs.mkdtemp(path.join(os.tmpdir(), params.tmpPrefix));

302248

const storePath = path.join(tmp, "sessions.json");

303249

const sessionKey = "main";

304250

const sessionEntry = {

@@ -312,18 +258,16 @@ describe("runReplyAgent auto-compaction token update", () => {

312258

runEmbeddedPiAgentMock.mockResolvedValue({

313259

payloads: [{ text: "ok" }],

314260

meta: {

315-

agentMeta: {

316-

usage: { input: 75_000, output: 5_000, cacheRead: 25_000, total: 105_000 },

317-

lastCallUsage: { input: 55_000, output: 2_000, cacheRead: 25_000, total: 82_000 },

318-

promptTokens: 44_000,

319-

},

261+

agentMeta: params.agentMeta,

320262

},

321263

});

322264323265

const diagnostics: DiagnosticEventPayload[] = [];

324-

const unsubscribe = onInternalDiagnosticEvent((event) => {

325-

diagnostics.push(event);

326-

});

266+

const unsubscribe = params.collectDiagnostics

267+

? onInternalDiagnosticEvent((event) => {

268+

diagnostics.push(event);

269+

})

270+

: undefined;

327271

const { typing, sessionCtx, resolvedQueue, followupRun } = createBaseRun({

328272

storePath,

329273

sessionEntry,

@@ -355,10 +299,39 @@ describe("runReplyAgent auto-compaction token update", () => {

355299

typingMode: "instant",

356300

});

357301

} finally {

358-

unsubscribe();

302+

unsubscribe?.();

359303

}

360304305+

const stored = JSON.parse(await fs.readFile(storePath, "utf-8"));

361306

const usageEvent = diagnostics.find((event) => event.type === "model.usage");

307+

return { sessionKey, stored, usageEvent };

308+

}

309+310+

it("updates totalTokens from lastCallUsage even without compaction", async () => {

311+

const { sessionKey, stored } = await runBaseReplyWithAgentMeta({

312+

tmpPrefix: "openclaw-usage-last-",

313+

agentMeta: {

314+

// Tool-use loop: accumulated input is higher than last call's input

315+

usage: { input: 75_000, output: 5_000, total: 80_000 },

316+

lastCallUsage: { input: 55_000, output: 2_000, total: 57_000 },

317+

},

318+

});

319+320+

// totalTokens should use lastCallUsage (55k), not accumulated (75k)

321+

expect(stored[sessionKey].totalTokens).toBe(55_000);

322+

});

323+324+

it("reports live diagnostic context from promptTokens, not provider usage totals", async () => {

325+

const { usageEvent } = await runBaseReplyWithAgentMeta({

326+

tmpPrefix: "openclaw-usage-diagnostic-",

327+

collectDiagnostics: true,

328+

agentMeta: {

329+

usage: { input: 75_000, output: 5_000, cacheRead: 25_000, total: 105_000 },

330+

lastCallUsage: { input: 55_000, output: 2_000, cacheRead: 25_000, total: 82_000 },

331+

promptTokens: 44_000,

332+

},

333+

});

334+362335

expect(usageEvent).toMatchObject({

363336

type: "model.usage",

364337

usage: {

@@ -376,72 +349,21 @@ describe("runReplyAgent auto-compaction token update", () => {

376349

});

377350378351

it("falls back to last-call prompt usage for live diagnostic context", async () => {

379-

const tmp = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-usage-diagnostic-last-"));

380-

const storePath = path.join(tmp, "sessions.json");

381-

const sessionKey = "main";

382-

const sessionEntry = {

383-

sessionId: "session",

384-

updatedAt: Date.now(),

385-

totalTokens: 50_000,

386-

};

387-388-

await seedSessionStore({ storePath, sessionKey, entry: sessionEntry });

389-390-

runEmbeddedPiAgentMock.mockResolvedValue({

391-

payloads: [{ text: "ok" }],

392-

meta: {

393-

agentMeta: {

394-

usage: { input: 75_000, output: 5_000, cacheRead: 25_000, total: 105_000 },

395-

lastCallUsage: {

396-

input: 55_000,

397-

output: 2_000,

398-

cacheRead: 25_000,

399-

cacheWrite: 1_000,

400-

total: 83_000,

401-

},

352+

const { usageEvent } = await runBaseReplyWithAgentMeta({

353+

tmpPrefix: "openclaw-usage-diagnostic-last-",

354+

collectDiagnostics: true,

355+

agentMeta: {

356+

usage: { input: 75_000, output: 5_000, cacheRead: 25_000, total: 105_000 },

357+

lastCallUsage: {

358+

input: 55_000,

359+

output: 2_000,

360+

cacheRead: 25_000,

361+

cacheWrite: 1_000,

362+

total: 83_000,

402363

},

403364

},

404365

});

405366406-

const diagnostics: DiagnosticEventPayload[] = [];

407-

const unsubscribe = onInternalDiagnosticEvent((event) => {

408-

diagnostics.push(event);

409-

});

410-

const { typing, sessionCtx, resolvedQueue, followupRun } = createBaseRun({

411-

storePath,

412-

sessionEntry,

413-

});

414-415-

try {

416-

await runReplyAgent({

417-

commandBody: "hello",

418-

followupRun,

419-

queueKey: "main",

420-

resolvedQueue,

421-

shouldSteer: false,

422-

shouldFollowup: false,

423-

isActive: false,

424-

isStreaming: false,

425-

typing,

426-

sessionCtx,

427-

sessionEntry,

428-

sessionStore: { [sessionKey]: sessionEntry },

429-

sessionKey,

430-

storePath,

431-

defaultModel: "anthropic/claude-opus-4-6",

432-

agentCfgContextTokens: 200_000,

433-

resolvedVerboseLevel: "off",

434-

isNewSession: false,

435-

blockStreamingEnabled: false,

436-

resolvedBlockStreamingBreak: "message_end",

437-

shouldInjectGroupIntro: false,

438-

typingMode: "instant",

439-

});

440-

} finally {

441-

unsubscribe();

442-

}

443-444-

const usageEvent = diagnostics.find((event) => event.type === "model.usage");

445367

expect(usageEvent).toMatchObject({

446368

type: "model.usage",

447369

usage: {