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

H
Help Net Security
T
ThreatConnect
SecWiki News
SecWiki News
F
Future of Privacy Forum
AWS News Blog
AWS News Blog
C
Cisco Blogs
A
Arctic Wolf
Vercel News
Vercel News
The GitHub Blog
The GitHub Blog
Scott Helme
Scott Helme
V
V2EX
博客园 - 叶小钗
阮一峰的网络日志
阮一峰的网络日志
K
Kaspersky official blog
G
Google Developers Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
P
Privacy International News Feed
C
Cyber Attacks, Cyber Crime and Cyber Security
N
News | PayPal Newsroom
Schneier on Security
Schneier on Security
NISL@THU
NISL@THU
Microsoft Azure Blog
Microsoft Azure Blog
量子位
The Hacker News
The Hacker News
Stack Overflow Blog
Stack Overflow Blog
Security Latest
Security Latest
M
Microsoft Research Blog - Microsoft Research
Google Online Security Blog
Google Online Security Blog
博客园_首页
C
CXSECURITY Database RSS Feed - CXSecurity.com
I
InfoQ
Google DeepMind News
Google DeepMind News
Y
Y Combinator Blog
The Cloudflare Blog
Microsoft Security Blog
Microsoft Security Blog
Martin Fowler
Martin Fowler
Cisco Talos Blog
Cisco Talos 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
T
Troy Hunt's Blog
F
Fox-IT International blog
S
Security @ Cisco Blogs
博客园 - 司徒正美
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
C
Comments on: Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
L
LINUX DO - 最新话题
GbyAI
GbyAI
Project Zero
Project Zero
腾讯CDC
T
Tailwind CSS Blog

Recent Commits to openclaw:main

fix(ui): harden control e2e browser setup fix(telegram): keep overlapping DM replies deliverable (#85361) (than… refactor: share realtime forced consult coordination test(qa-lab): add runtime confidence reports build: refresh dependency pins (#86628) · openclaw/openclaw@cda7c30 test: port release validation stabilizers · openclaw/openclaw@9f7485e fix(cron): stop forcing message tool for delivery · openclaw/openclaw@c51fa0d fix(google): omit request config with cached content test: stabilize release validation test harnesses fix(test): bound kitchen sink command output · openclaw/openclaw@f1197ed fix(discord): stabilize realtime wake-name feedback test(config): guard legacy agentRuntime regression perf: precompute audio resample kernels fix(codex): allow env api-key app-server bootstrap · openclaw/openclaw@009b18c refactor: reuse shared coercion helpers (#86419) · openclaw/openclaw@77d9ac3 fix(cron): preserve runtime snapshot for isolated delivery · openclaw/openclaw@a98660e fix(test): model active assistant failover attempts · openclaw/openclaw@c55bee5 docs: update changelog for bug sweep landings test: fix mock signatures for tsgo · openclaw/openclaw@aa05c5c docs: document fail-closed behavior for rejected modelPatterns · openclaw/openclaw@36f269d fix(security): guard plugin modelPatterns with compileSafeRegex · openclaw/openclaw@117e082 docs(manifest): note safe-regex validation for modelPatterns · openclaw/openclaw@e7c7ee4 style: use bracket notation for __openclaw to satisfy no-underscore-d… · openclaw/openclaw@9a6c161 fix(security): escape field names in transcript regex extraction · openclaw/openclaw@fe8d99d test: tighten oversized metadata assertion to check exact id in __ope… · openclaw/openclaw@aff8e64 fix(logging): exit on stdout/stderr EPIPE instead of spinning · openclaw/openclaw@2aa5f17 fix(logging): preserve failure exit on EPIPE · openclaw/openclaw@623a60a fix(logging): keep string failure codes on EPIPE · openclaw/openclaw@78a1e7d fix(scripts): docs-spellcheck.sh fails on bash 3.2 with set -u · openclaw/openclaw@fef57f9 fix(docs): keep spellcheck bash 3.2-compatible · openclaw/openclaw@778fa87 fix(test): assert e2e agent reply payloads · openclaw/openclaw@74f3a1e test(gateway): pin live gateway models to pi runtime · openclaw/openclaw@c88f660 perf: speed up local TUI startup · openclaw/openclaw@a0023fb refactor: share realtime voice activation helpers (#86615) · openclaw/openclaw@d0ab0d9 fix(feishu): render native presentation buttons (#86588) · openclaw/openclaw@170e0aa fix(test): narrow plugin gauntlet prebuild · openclaw/openclaw@423f7d2 fix: route Discord gateway metadata through proxy (#86601) · openclaw/openclaw@5b6d409 fix: tighten Discord voice wake matching (#86595) · openclaw/openclaw@f00a912 refactor(logging): share diagnostic message lifecycle · openclaw/openclaw@baab4cf fix(cron): restore suspended lanes to default concurrency · openclaw/openclaw@e844d1d fix(auth): emit one-shot doctor-pointer warning for Keychain-only leg… · openclaw/openclaw@a61d530 fix(codex): recover stale preflight bindings (#86602) · openclaw/openclaw@9b9d897 fix(cron): preserve unsupported payload rows on writes · openclaw/openclaw@c916906 fix(cron): canonicalize preserved row ids · openclaw/openclaw@985bc93 test(cron): pin sequential duration regression · openclaw/openclaw@8351556 docs: update changelog for cron preservation (#86415) · openclaw/openclaw@bdc6b32 build: bump qs to patched release · openclaw/openclaw@9330b76 fix(status): prefer active OAuth for runtime aliases chore(acpx): bump bundled acpx to 0.10.0 · openclaw/openclaw@407cf8e docs: make changelog release-owned · openclaw/openclaw@c0f2d89 fix(google): stop appending preview to flash lite · openclaw/openclaw@915c820 docs: update changelog for bug sweep landings · openclaw/openclaw@cd7994f fix(crabbox): detect timed macos js commands · openclaw/openclaw@44bb0be fix(mantis): release telegram user leases on startup failure · openclaw/openclaw@cf27567 fix(agents): keep cron media completions run-scoped · openclaw/openclaw@f5d2db2 fix(agents): deliver stale cron media completions · openclaw/openclaw@f01b2a8 fix(agents): notify stale cron media failures · openclaw/openclaw@baf469f guide workspace-only scratch paths fix(cron): gate lifecycle diagnostic events behind isDiagnosticsEnabled · openclaw/openclaw@4853222 fix(cron): emit message.queued/processed for isolated-agent turns fix(cron): address review — drop unsupported taskLabel, pair with ses… · openclaw/openclaw@804a31e fix(cron): report rotated session in final diagnostics · openclaw/openclaw@207a5a2 fix: hydrate current turn image attachments · openclaw/openclaw@b5ada80 fix(gateway): ignore inherited launchd env for respawn · openclaw/openclaw@177ebdc fix(test): preserve undici exports in discord proxy tests · openclaw/openclaw@b0c8a4d fix: raise default cron concurrency · openclaw/openclaw@bc12e04 fix(doctor): skip restart prompt when gateway is healthy after recent… · openclaw/openclaw@6e8d2db fix: emit agent.send lifecycle hooks on rotation (#85875) · openclaw/openclaw@8129dba fix(crabbox): bootstrap macos shell js commands · openclaw/openclaw@7cd15d2 fix: preflight malformed openshell exec commands fix: tighten openshell exec preflight · openclaw/openclaw@822ee62 docs: clarify unshipped compat policy · openclaw/openclaw@f87aa0f fix(update): allow package-manager hardlinks in swaps · openclaw/openclaw@8061d66 docs: ban repo-hosted proof artifacts · openclaw/openclaw@17954a4 fix(discord): restore bare numeric channel sends (#86571) · openclaw/openclaw@c5b9872 fix(installer): handle alpine apk runtime floors · openclaw/openclaw@b83dfcb fix(security): audit Claude permission overrides under YOLO (#86557) · openclaw/openclaw@bd65b42 fix: speed up Discord voice wake consults · openclaw/openclaw@5ae91f0 fix(qa): harden restart inflight Windows scenario · openclaw/openclaw@3eb06e3 Recover Codex context overflow prompt errors (#85542) · openclaw/openclaw@5cfa577 docs: update changelog for #70473 · openclaw/openclaw@d967760 fix(agents): derive overflow budgets from provider errors · openclaw/openclaw@d5b0174 fix(plugins): only memoize complete metadata snapshots · openclaw/openclaw@3137622 docs: update changelog for media wake fallback (#85489) · openclaw/openclaw@a11d4e6 fix: fallback after active media wake failure (#85489) · openclaw/openclaw@1b64ccb perf(plugins): reuse derived metadata snapshots · openclaw/openclaw@159e440 docs: require maintainer-editable PR branches · openclaw/openclaw@f271f00 fix: scan OpenClaw sessions in agent transcript finder · openclaw/openclaw@4012ae4 docs: note agent transcript OpenClaw session scan · openclaw/openclaw@dd375f9 docs: require generic local fixes · openclaw/openclaw@fc93af5 fix: broaden leading voice wake fuzzing · openclaw/openclaw@a9c91ca test(agents): preserve provider hook mock exports (#86523) · openclaw/openclaw@657b246 Policy: add agent-scoped policy overlays (#85817) · openclaw/openclaw@fbb6340 fix(kilocode): normalize string stop param to array in stream wrapper… · openclaw/openclaw@abe9923 Doctor: expose shell completion health findings (#85566) · openclaw/openclaw@dc17412 fix(agents): honor effective exec policy for Claude live Bash (#86330) fix(test): stabilize e2e runtime imports fix(test): clean plugin gauntlet temp roots · openclaw/openclaw@633e4b8 perf: cache plugin package realpaths (#86517) · openclaw/openclaw@69d728a fix(crabbox): sync full sparse lease runs · openclaw/openclaw@e97e831
fix(openai): route compaction through Codex auth provider (#86408) · openclaw/openclaw@f4cfa01
funmerlin · 2026-05-26 · via Recent Commits to openclaw:main

@@ -12,7 +12,9 @@ import {

1212

listRegisteredPluginAgentPromptGuidanceMock,

1313

loadCompactHooksHarness,

1414

maybeCompactAgentHarnessSessionMock,

15+

resolveAgentHarnessPolicyMock,

1516

registerProviderStreamForModelMock,

17+

resolveContextWindowInfoMock,

1618

resolveContextEngineMock,

1719

resolveEmbeddedAgentStreamFnMock,

1820

resolveMemorySearchConfigMock,

@@ -441,6 +443,115 @@ describe("compactEmbeddedPiSessionDirect hooks", () => {

441443

}

442444

});

443445446+

it("routes OpenAI compaction through the selected Codex runtime provider before auth", async () => {

447+

resolveAgentHarnessPolicyMock.mockReturnValue({ runtime: "codex" });

448+

resolveModelMock.mockImplementation((provider = "openai", modelId = "fake") => ({

449+

model: { provider, api: "responses", id: modelId, input: [] },

450+

error: null,

451+

authStorage: { setRuntimeApiKey: vi.fn() },

452+

modelRegistry: {},

453+

}));

454+455+

const result = await compactEmbeddedPiSessionDirect({

456+

sessionId: "session-1",

457+

sessionKey: TEST_SESSION_KEY,

458+

sessionFile: "/tmp/session.jsonl",

459+

workspaceDir: "/tmp/workspace",

460+

provider: "openai",

461+

model: "gpt-5.5",

462+

config: {

463+

models: {

464+

providers: {

465+

openai: { models: [{ id: "gpt-5.5", contextWindow: 1_000_000 }] },

466+

"openai-codex": { models: [{ id: "gpt-5.5", contextWindow: 350_000 }] },

467+

},

468+

},

469+

auth: {

470+

order: {

471+

"openai-codex": ["openai-codex:work"],

472+

},

473+

},

474+

agents: { defaults: { embeddedHarness: { runtime: "codex" } } },

475+

} as never,

476+

});

477+478+

expect(result.ok).toBe(true);

479+

expect(mockCallArg(resolveModelMock)).toBe("openai-codex");

480+

expect(mockCallArg(resolveModelMock, 0, 1)).toBe("gpt-5.5");

481+

});

482+483+

it("preserves direct OpenAI API-key compaction when no Codex auth is configured", async () => {

484+

resolveAgentHarnessPolicyMock.mockReturnValue({ runtime: "codex" });

485+

resolveModelMock.mockImplementation((provider = "openai", modelId = "fake") => ({

486+

model: { provider, api: "responses", id: modelId, input: [] },

487+

error: null,

488+

authStorage: { setRuntimeApiKey: vi.fn() },

489+

modelRegistry: {},

490+

}));

491+492+

const result = await compactEmbeddedPiSessionDirect({

493+

sessionId: "session-1",

494+

sessionKey: TEST_SESSION_KEY,

495+

sessionFile: "/tmp/session.jsonl",

496+

workspaceDir: "/tmp/workspace",

497+

provider: "openai",

498+

model: "gpt-5.5",

499+

config: {

500+

models: {

501+

providers: {

502+

openai: { models: [{ id: "gpt-5.5", contextWindow: 1_000_000 }] },

503+

},

504+

},

505+

agents: { defaults: { embeddedHarness: { runtime: "codex" } } },

506+

} as never,

507+

});

508+509+

expect(result.ok).toBe(true);

510+

expect(mockCallArg(resolveModelMock)).toBe("openai");

511+

expect(mockCallArg(resolveModelMock, 0, 1)).toBe("gpt-5.5");

512+

});

513+514+

it("uses the persisted Codex runtime for compaction context windows", async () => {

515+

resolveAgentHarnessPolicyMock.mockReturnValue({ runtime: "pi" });

516+

resolveModelMock.mockImplementation((provider = "openai", modelId = "fake") => ({

517+

model: { provider, api: "responses", id: modelId, input: [], contextWindow: 1_000_000 },

518+

error: null,

519+

authStorage: { setRuntimeApiKey: vi.fn() },

520+

modelRegistry: {},

521+

}));

522+523+

const result = await compactEmbeddedPiSessionDirect({

524+

sessionId: "session-1",

525+

sessionKey: TEST_SESSION_KEY,

526+

sessionFile: "/tmp/session.jsonl",

527+

workspaceDir: "/tmp/workspace",

528+

provider: "openai",

529+

model: "gpt-5.5",

530+

agentHarnessId: "codex",

531+

config: {

532+

models: {

533+

providers: {

534+

openai: { models: [{ id: "gpt-5.5", contextWindow: 1_000_000 }] },

535+

"openai-codex": { models: [{ id: "gpt-5.5", contextWindow: 350_000 }] },

536+

},

537+

},

538+

auth: {

539+

order: {

540+

"openai-codex": ["openai-codex:work"],

541+

},

542+

},

543+

agents: { defaults: { embeddedHarness: { runtime: "pi" } } },

544+

} as never,

545+

});

546+547+

expect(result.ok).toBe(true);

548+

expect(mockCallArg(resolveModelMock)).toBe("openai-codex");

549+

expectRecordFields(mockCallArg(resolveContextWindowInfoMock), {

550+

provider: "openai-codex",

551+

modelId: "gpt-5.5",

552+

});

553+

});

554+444555

it("keeps compaction fallback selection ephemeral", async () => {

445556

resolveModelMock.mockImplementation((provider = "openai", modelId = "fake") => ({

446557

model: { provider, api: "responses", id: modelId, input: [] },