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

I
Intezer
D
DataBreaches.Net
罗磊的独立博客
P
Proofpoint News Feed
大猫的无限游戏
大猫的无限游戏
博客园 - 聂微东
A
Arctic Wolf
C
Cyber Attacks, Cyber Crime and Cyber Security
Security Latest
Security Latest
Stack Overflow Blog
Stack Overflow Blog
S
Security @ Cisco Blogs
博客园 - Franky
L
LangChain Blog
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
LINUX DO - 最新话题
SecWiki News
SecWiki News
H
Help Net Security
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Vercel News
Vercel News
G
Google Developers Blog
TaoSecurity Blog
TaoSecurity Blog
B
Blog
I
InfoQ
V
Visual Studio Blog
S
Security Affairs
Help Net Security
Help Net Security
腾讯CDC
Apple Machine Learning Research
Apple Machine Learning Research
N
News | PayPal Newsroom
Application and Cybersecurity Blog
Application and Cybersecurity Blog
T
Threatpost
Engineering at Meta
Engineering at Meta
PCI Perspectives
PCI Perspectives
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
美团技术团队
S
Secure Thoughts
F
Fortinet All Blogs
Google DeepMind News
Google DeepMind News
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
V
V2EX
人人都是产品经理
人人都是产品经理
V
Vulnerabilities – Threatpost
aimingoo的专栏
aimingoo的专栏
A
About on SuperTechFans
MongoDB | Blog
MongoDB | Blog
Cloudbric
Cloudbric
T
Threat Research - Cisco Blogs
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
宝玉的分享
宝玉的分享
F
Full Disclosure

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(agents): keep runtime context before active user turns · openclaw/openclaw@0503853
SYU8384 · 2026-05-27 · via Recent Commits to openclaw:main

@@ -429,46 +429,148 @@ describe("normalizeMessagesForLlmBoundary", () => {

429429

expect(input[0]).toHaveProperty("details");

430430

});

431431432-

it("keeps historical runtime-context transcript entries out of the LLM boundary", () => {

432+

it("keeps only pre-user current-turn runtime context at the LLM boundary", () => {

433433

const input = [

434+

{

435+

role: "user",

436+

content: [{ type: "text", text: "old ask" }],

437+

timestamp: 0,

438+

},

439+

{

440+

role: "assistant",

441+

content: [{ type: "text", text: "old answer" }],

442+

timestamp: 1,

443+

},

434444

{

435445

role: "custom",

436446

customType: "openclaw.runtime-context",

437-

content: "old secret runtime context",

447+

content: "current secret runtime context",

438448

display: false,

439-

timestamp: 0,

449+

timestamp: 2,

440450

},

441451

{

442452

role: "user",

443453

content: [{ type: "text", text: "visible ask" }],

444-

timestamp: 1,

454+

timestamp: 3,

445455

},

446456

{

447457

role: "custom",

448458

customType: "openclaw.runtime-context",

449-

content: "secret runtime context",

459+

content: "post-user stale runtime context",

450460

display: false,

451-

timestamp: 2,

461+

timestamp: 4,

452462

},

453463

{

454464

role: "custom",

455465

customType: "other-extension-context",

456466

content: "normal custom context",

457467

display: false,

458-

timestamp: 3,

468+

timestamp: 5,

459469

},

460470

];

461471462472

const output = normalizeMessagesForLlmBoundary(

463473

input as Parameters<typeof normalizeMessagesForLlmBoundary>[0],

464474

) as unknown as Array<Record<string, unknown>>;

465475466-

expect(output).toHaveLength(3);

467-

expect(output.some((item) => item.content === "old secret runtime context")).toBe(false);

468-

expect(output.some((item) => item.content === "secret runtime context")).toBe(true);

476+

expect(output).toHaveLength(5);

477+

expect(output.some((item) => item.content === "current secret runtime context")).toBe(true);

478+

expect(output.some((item) => item.content === "post-user stale runtime context")).toBe(false);

469479

expect(output.some((item) => item.customType === "other-extension-context")).toBe(true);

470480

});

471481482+

it("keeps overflow retry runtime context immediately before the active user", () => {

483+

const rebuiltAfterOverflow = [

484+

{

485+

role: "user",

486+

content: [{ type: "text", text: "old ask" }],

487+

timestamp: 0,

488+

},

489+

{

490+

role: "assistant",

491+

content: [{ type: "text", text: "old answer" }],

492+

timestamp: 1,

493+

},

494+

{

495+

role: "user",

496+

content: [{ type: "text", text: "retry ask" }],

497+

timestamp: 2,

498+

},

499+

];

500+

const runtimeContext = {

501+

role: "custom",

502+

customType: "openclaw.runtime-context",

503+

content: "retry runtime context",

504+

display: false,

505+

timestamp: 3,

506+

};

507+508+

const retryMessages = attemptTesting.insertRuntimeContextMessageForPrompt({

509+

message: runtimeContext as Parameters<

510+

typeof attemptTesting.insertRuntimeContextMessageForPrompt

511+

>[0]["message"],

512+

messages: rebuiltAfterOverflow as Parameters<typeof normalizeMessagesForLlmBoundary>[0],

513+

});

514+

const retryInput = normalizeMessagesForLlmBoundary(retryMessages) as unknown as Array<

515+

Record<string, unknown>

516+

>;

517+518+

expect(retryInput.map((message) => message.role)).toEqual([

519+

"user",

520+

"assistant",

521+

"custom",

522+

"user",

523+

]);

524+

expect(retryInput[2]).toMatchObject({

525+

customType: "openclaw.runtime-context",

526+

content: "retry runtime context",

527+

});

528+

expect(retryInput[3]?.content).toEqual([{ type: "text", text: "retry ask" }]);

529+

});

530+531+

it("keeps prompt-local runtime context before the active user in existing sessions", () => {

532+

const promptInput = [

533+

{

534+

role: "user",

535+

content: [{ type: "text", text: "old ask" }],

536+

timestamp: 0,

537+

},

538+

{

539+

role: "assistant",

540+

content: [{ type: "text", text: "old answer" }],

541+

timestamp: 1,

542+

},

543+

{

544+

role: "custom",

545+

customType: "openclaw.runtime-context",

546+

content: "current runtime context",

547+

display: false,

548+

timestamp: 2,

549+

},

550+

{

551+

role: "user",

552+

content: [{ type: "text", text: "visible ask" }],

553+

timestamp: 3,

554+

},

555+

];

556+557+

const modelInput = normalizeMessagesForLlmBoundary(

558+

promptInput as Parameters<typeof normalizeMessagesForLlmBoundary>[0],

559+

) as unknown as Array<Record<string, unknown>>;

560+561+

expect(modelInput.map((message) => message.role)).toEqual([

562+

"user",

563+

"assistant",

564+

"custom",

565+

"user",

566+

]);

567+

expect(modelInput[2]).toMatchObject({

568+

customType: "openclaw.runtime-context",

569+

content: "current runtime context",

570+

});

571+

expect(modelInput[3]?.content).toEqual([{ type: "text", text: "visible ask" }]);

572+

});

573+472574

it("keeps only safe blocked metadata at the LLM boundary", () => {

473575

const input = [

474576

{