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(replay-history): drop trailing stream-error placeholder before pr… · openclaw/openclaw@24bd0b2
openperf · 2026-05-05 · via Recent Commits to openclaw:main

@@ -58,12 +58,15 @@ function openclawTranscriptAssistant(model: "delivery-mirror" | "gateway-injecte

5858

}

59596060

describe("normalizeAssistantReplayContent", () => {

61-

it("converts assistant content: [] to a non-empty sentinel text block when stopReason is error", () => {

62-

const messages = [userMessage("hello"), bedrockAssistant([], "error")];

61+

it("converts mid-turn assistant content: [] to a non-empty sentinel text block when stopReason is error", () => {

62+

const messages = [userMessage("hello"), bedrockAssistant([], "error"), userMessage("retry")];

6363

const out = normalizeAssistantReplayContent(messages);

6464

expect(out).not.toBe(messages);

6565

const repaired = out[1] as AgentMessage & { content: { type: string; text: string }[] };

6666

expect(repaired.content).toEqual([{ type: "text", text: FALLBACK_TEXT }]);

67+

// Trailing user is preserved so request still ends with user.

68+

expect(out).toHaveLength(3);

69+

expect((out[2] as { role: string }).role).toBe("user");

6770

});

68716972

it("drops blank user text messages from replay", () => {

@@ -108,9 +111,9 @@ describe("normalizeAssistantReplayContent", () => {

108111

expect(out[1]).toBe(silentStop);

109112

});

110113111-

it("converts zero-usage empty stop turns to a replay sentinel", () => {

114+

it("converts mid-turn zero-usage empty stop turns to a replay sentinel", () => {

112115

const falseSuccessStop = bedrockAssistant([], "stop");

113-

const messages = [userMessage("hello"), falseSuccessStop];

116+

const messages = [userMessage("hello"), falseSuccessStop, userMessage("retry")];

114117

const out = normalizeAssistantReplayContent(messages);

115118

expect(out).not.toBe(messages);

116119

const repaired = out[1] as AgentMessage & { content: { type: string; text: string }[] };

@@ -183,4 +186,117 @@ describe("normalizeAssistantReplayContent", () => {

183186

const out = normalizeAssistantReplayContent(messages);

184187

expect(out).toBe(messages);

185188

});

189+190+

it("drops a trailing assistant turn whose content: [] would have been rewritten to the sentinel (#77228)", () => {

191+

// The sentinel was synthesized to satisfy Bedrock's non-empty-content

192+

// rule for *non-trailing* error turns. As the trailing message it would

193+

// make prefill-strict providers (e.g. github-copilot/claude-opus-4.6)

194+

// 400 with "conversation must end with a user message". The original

195+

// turn carried content:[] and zero usage — drop is lossless.

196+

const messages = [userMessage("hello"), bedrockAssistant([], "error")];

197+

const out = normalizeAssistantReplayContent(messages);

198+

expect(out).not.toBe(messages);

199+

expect(out).toHaveLength(1);

200+

expect(out[0]).toBe(messages[0]);

201+

});

202+203+

it("drops a trailing zero-usage empty stop assistant turn (#77228)", () => {

204+

const falseSuccessStop = bedrockAssistant([], "stop");

205+

const messages = [userMessage("hello"), falseSuccessStop];

206+

const out = normalizeAssistantReplayContent(messages);

207+

expect(out).toHaveLength(1);

208+

expect(out[0]).toBe(messages[0]);

209+

});

210+211+

it("drops a trailing assistant turn that already carries the persisted sentinel content (#77228)", () => {

212+

// Covers the case where session-file-repair persisted the sentinel to

213+

// disk; on the next turn the loaded transcript ends with a non-empty

214+

// assistant turn whose only content is the sentinel text. Provider

215+

// request must still end with user.

216+

const persistedSentinel = bedrockAssistant([{ type: "text", text: FALLBACK_TEXT }], "error");

217+

const messages = [userMessage("hello"), persistedSentinel];

218+

const out = normalizeAssistantReplayContent(messages);

219+

expect(out).toHaveLength(1);

220+

expect(out[0]).toBe(messages[0]);

221+

});

222+223+

it("drops several consecutive trailing sentinel/empty-error turns at the tail", () => {

224+

const messages = [

225+

userMessage("hi"),

226+

bedrockAssistant([{ type: "text", text: "real" }]),

227+

userMessage("again"),

228+

bedrockAssistant([], "error"),

229+

bedrockAssistant([{ type: "text", text: FALLBACK_TEXT }], "error"),

230+

];

231+

const out = normalizeAssistantReplayContent(messages);

232+

expect(out).toHaveLength(3);

233+

expect((out.at(-1) as { role: string }).role).toBe("user");

234+

});

235+236+

it("does not drop a trailing assistant turn that has real content", () => {

237+

const realReply = bedrockAssistant([{ type: "text", text: "hello back" }], "stop", {

238+

input: 1,

239+

output: 1,

240+

totalTokens: 2,

241+

});

242+

const messages = [userMessage("hi"), realReply];

243+

const out = normalizeAssistantReplayContent(messages);

244+

expect(out).toBe(messages);

245+

expect(out).toHaveLength(2);

246+

});

247+248+

it("does not drop a trailing assistant turn with non-error empty content (toolUse / length)", () => {

249+

// Boundary lock: only error/zero-usage-empty-stop and the sentinel

250+

// shape are droppable. toolUse/length empty turns are real provider

251+

// states and must be preserved on the wire.

252+

const toolUse = bedrockAssistant([], "toolUse");

253+

const messages = [userMessage("hi"), toolUse];

254+

const out = normalizeAssistantReplayContent(messages);

255+

expect(out).toBe(messages);

256+

expect(out).toHaveLength(2);

257+

});

258+259+

it("preserves a trailing real model reply whose only content happens to be the sentinel text (clawsweeper review on #77287)", () => {

260+

// Defensive boundary: even if a model legitimately replies with the

261+

// exact sentinel string, the trim must require synthetic provenance

262+

// (stopReason: "error" or zero-usage stop) before dropping. Without

263+

// this guard the trim would silently delete a real reply on next

264+

// replay.

265+

const realReplyAsStop = bedrockAssistant([{ type: "text", text: FALLBACK_TEXT }], "stop", {

266+

input: 1,

267+

output: 1,

268+

totalTokens: 2,

269+

});

270+

const messages = [userMessage("hi"), realReplyAsStop];

271+

const out = normalizeAssistantReplayContent(messages);

272+

expect(out).toBe(messages);

273+

expect(out).toHaveLength(2);

274+

expect((out[1] as { content: unknown[] }).content).toEqual([

275+

{ type: "text", text: FALLBACK_TEXT },

276+

]);

277+

});

278+279+

it("preserves a trailing turn whose sentinel content is paired with stopReason: toolUse (real provider state, not synthetic)", () => {

280+

const toolUseSentinel = bedrockAssistant([{ type: "text", text: FALLBACK_TEXT }], "toolUse");

281+

const messages = [userMessage("hi"), toolUseSentinel];

282+

const out = normalizeAssistantReplayContent(messages);

283+

expect(out).toBe(messages);

284+

expect(out).toHaveLength(2);

285+

});

286+287+

it("still drops a trailing zero-usage stop turn whose content was already lifted to the sentinel block (post-rewrite shape)", () => {

288+

// Confirms the sentinel-content branch still recognizes the post-rewrite

289+

// shape produced by the in-memory rewrite earlier in the same loop:

290+

// stopReason: "stop" + zero usage + sentinel content. Only the synthetic

291+

// provenance (zero usage + stop) makes this droppable; a non-zero-usage

292+

// version is preserved by the regression test above.

293+

const persistedZeroUsageSentinel = bedrockAssistant(

294+

[{ type: "text", text: FALLBACK_TEXT }],

295+

"stop",

296+

);

297+

const messages = [userMessage("hi"), persistedZeroUsageSentinel];

298+

const out = normalizeAssistantReplayContent(messages);

299+

expect(out).toHaveLength(1);

300+

expect(out[0]).toBe(messages[0]);

301+

});

186302

});