fix(openai): route compaction through Codex auth provider by funmerlin · Pull Request #86408 · openclaw/openclaw

funmerlin · 2026-05-25T09:06:26Z

Summary

Problem: when an openai/gpt-5.5 session reaches the embedded/context-engine compaction path after a stale or missing Codex thread binding, compaction can resolve auth against the direct openai provider and fail with missing OPENAI_API_KEY even though the selected runtime uses Codex OAuth.
Solution: resolve the selected OpenAI runtime provider before compaction model/auth lookup, so Codex-authenticated OpenAI sessions compact through openai-codex.
What changed: compaction now uses the selected runtime provider for model/auth resolution, preserves direct OpenAI API-key routing when no Codex auth profile is configured, uses the persisted/selected runtime for context-window lookup, and honors configured OpenAI Responses server compaction thresholds during preflight gating.
What did NOT change (scope boundary): this does not repair stale/missing Codex thread bindings, does not change startup provider auth prewarm defaults, does not touch hook scheduling/status/reset behavior, and does not address unrelated encrypted-reasoning retry/429 behavior.

AI-assisted: yes. This patch was prepared with Codex, with focused local test verification.

Motivation

Related prior work: Fix OpenAI compaction runtime routing #85413 identified the same core failure mode and was directionally correct: stale/missing Codex thread binding can push compaction into a fallback path that resolves openai/gpt-5.5 as direct OpenAI API-key auth instead of the selected Codex OAuth runtime.
Why this PR deviates from Fix OpenAI compaction runtime routing #85413: that draft mixed the compaction auth-route fix with broader startup/provider-auth-prewarm defaults, hook scheduling, runtime plugin loading, status/reset behavior, and other review surfaces. Those may be valid changes, but they are not required to fix this incident and make the auth-sensitive review harder.
This PR keeps the central compaction routing fix, preserves direct OpenAI API-key behavior, adds the missing production threshold logic behind the threshold tests, and leaves unrelated startup/default/runtime behavior unchanged.

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Closes #
Related Fix OpenAI compaction runtime routing #85413
This PR fixes a bug or regression

Real behavior proof (required for external PRs)

Behavior or issue addressed: Codex OAuth OpenAI compaction fallback should resolve against openai-codex, not direct openai API-key auth; OpenAI API-key-only compaction should remain on openai; preflight compaction should not run earlier than configured OpenAI Responses server compaction thresholds.
Real environment tested: local OpenClaw checkout on macOS, built with pnpm build, installed into the LaunchAgent-pinned OpenClaw path, restarted gateway, real Discord channel sessions using Merlin/main with openai/gpt-5.5 via Codex OAuth.
Exact steps or command run after this patch: pnpm build; npm install -g /Users/merlin/openclaw --prefix /Users/merlin/.nvm/versions/node/v24.13.0; openclaw gateway restart; continued a long-running Discord #claw-enhance session until timeout-recovery compaction triggered. Focused tests were also run with node scripts/run-vitest.mjs src/agents/openai-codex-routing.test.ts src/agents/pi-embedded-runner/compact.hooks.test.ts src/auto-reply/reply/agent-runner-memory.test.ts plus git diff --check.
Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output): PR comment with copied redacted live runtime logs: fix(openai): route compaction through Codex auth provider #86408 (comment). Key after-fix line: 2026-05-25T19:18:05.519+02:00 [timeout-compaction] compaction succeeded for openai-codex/gpt-5.5; retrying prompt. Session transcript also contains a type=compaction record at the same timestamp. Focused Vitest reported Test Files 4 passed (4) and Tests 135 passed (135); git diff --check exited cleanly.
Observed result after fix: a real oversized Codex OAuth Discord session compacted successfully through openai-codex/gpt-5.5, then retried the prompt and completed with session state status=done, modelProvider=openai-codex, compactionCount=6, and post-compaction memory sync. The prior direct provider=openai/gpt-5.5 / No_API_key_found_for_provider_openai failure did not recur for that channel after the patched build was installed. Unit coverage also confirms Codex-auth-configured OpenAI compaction resolves openai-codex before auth lookup, direct OpenAI API-key compaction remains openai, persisted Codex runtime context-window lookup uses openai-codex, and server-threshold gating defers/runs preflight at the configured threshold.
What was not tested: full pnpm check / full test suite were not run in this local proof pass; the live proof covered timeout-recovery compaction rather than a separate clean budget/preflight success.
Proof limitations or environment constraints: one timeout-recovery attempt in the same session timed out, but that failure also routed through provider=openai-codex/gpt-5.5, not direct openai/gpt-5.5, so the auth-provider regression stayed fixed even in the failure case.
Before evidence (optional but encouraged): the exact same Discord channel/session previously logged stale thread binding followed by context-engine fallback on provider=openai/gpt-5.5 and No_API_key_found_for_provider_openai on 2026-05-24 at 22:40:14 CEST.

Root Cause (if applicable)

Root cause: embedded compaction resolved the compaction target's raw model provider before applying the selected/persisted runtime provider. For OpenAI model refs using Codex OAuth, that let fallback compaction ask direct openai auth for an API key instead of using openai-codex.
Missing detection / guardrail: there was no regression test asserting that direct compaction resolves the selected Codex runtime provider before auth, no direct-OpenAI preservation test for the same path, and preflight threshold tests were not backed by production threshold logic.
Contributing context (if known): current main already avoids some Codex automatic compaction fallback behavior, but direct embedded/context-engine compaction still needed auth-route consistency.

Regression Test Plan (if applicable)

Coverage level that should have caught this:
- Unit test
- Seam / integration test
- End-to-end test
- Existing coverage already sufficient
Target test or file: src/agents/openai-codex-routing.test.ts, src/agents/pi-embedded-runner/compact.hooks.test.ts, src/auto-reply/reply/agent-runner-memory.test.ts.
Scenario the test should lock in: Codex-auth OpenAI compaction uses openai-codex; direct OpenAI compaction remains openai; persisted Codex runtime context sizing uses openai-codex; OpenAI Responses server thresholds are honored by production preflight gating.
Why this is the smallest reliable guardrail: it exercises the model/auth selection seam directly without requiring a live Codex account or a gateway restart.
Existing test that already covers this (if any): N/A
If no new test is added, why not: N/A

User-visible / Behavior Changes

Codex OAuth users should no longer see fallback compaction ask for a direct OpenAI API key when the selected runtime/auth route is Codex. Direct OpenAI API-key-only setups remain routed through openai.

Diagram (if applicable)

Before:
openai/gpt-5.5 + Codex runtime -> fallback compaction -> openai auth -> missing OPENAI_API_KEY

After:
openai/gpt-5.5 + configured Codex auth -> fallback compaction -> openai-codex auth -> Codex OAuth route
openai/gpt-5.5 + direct OpenAI only -> fallback compaction -> openai auth -> API-key route

Security Impact (required)

New permissions/capabilities? (Yes/No) No
Secrets/tokens handling changed? (Yes/No) Yes
New/changed network calls? (Yes/No) No
Command/tool execution surface changed? (Yes/No) No
Data access scope changed? (Yes/No) No
If any Yes, explain risk + mitigation: auth provider selection changes for compaction only. The routing predicate requires an explicit/configured Codex auth profile before mapping openai to openai-codex, and tests cover both Codex OAuth and direct OpenAI API-key preservation.

Repro + Verification

Environment

OS: macOS
Runtime/container: local checkout
Model/provider: openai/gpt-5.5, openai-codex/gpt-5.5
Integration/channel (if any): N/A for local tests
Relevant config (redacted): tests cover auth.order.openai-codex, auth.profiles with provider openai-codex, and direct OpenAI with no Codex auth profile.

Steps

Configure an OpenAI model selection using Codex auth.
Force the embedded compaction path to resolve the model before auth.
Observe provider passed to model/auth resolution.

Expected

Codex-auth OpenAI compaction resolves openai-codex.
Direct OpenAI API-key compaction resolves openai.

Actual

After this patch, focused tests observe the expected provider selection.

Evidence

Failing test/log before + passing after
Trace/log snippets
Screenshot/recording
Perf numbers (if relevant)

Focused verification:

Test Files  4 passed (4)
Tests  135 passed (135)

Human Verification (required)

What you personally verified (not just CI), and how:

Verified scenarios: focused Vitest for OpenAI/Codex routing, embedded compaction provider selection, context-window provider selection, and preflight threshold gating.
Edge cases checked: direct OpenAI API-key preservation when no Codex auth profile is configured; non-OpenAI providers are not rerouted.
What you did not verify: full pnpm check / full test suite in this proof pass; a separate clean budget/preflight success distinct from timeout-recovery compaction.

Review Conversations

I replied to or resolved every bot review conversation I addressed in this PR.
I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

Backward compatible? (Yes/No) Yes
Config/env changes? (Yes/No) No
Migration needed? (Yes/No) No
If yes, exact upgrade steps: N/A

Risks and Mitigations

Risk: auth-sensitive provider routing can break Codex OAuth or direct OpenAI setups.
- Mitigation: routing is narrowed to explicit/configured Codex auth and includes direct OpenAI preservation tests.
Risk: live proof covered timeout-recovery compaction, while maintainers may still want a separate clean budget/preflight success.
- Mitigation: the real session shows successful openai-codex/gpt-5.5 compaction and the same auth route on timeout failure; the exact proof log is linked in the PR comments.

clawsweeper · 2026-05-25T09:09:00Z

Codex review: needs maintainer review before merge. Reviewed May 25, 2026, 1:53 PM ET / 17:53 UTC.

Summary
The PR updates OpenAI/Codex compaction provider selection and preflight threshold gating, with focused regression tests for Codex OAuth, direct OpenAI, context-window lookup, and Responses server threshold behavior.

PR surface: Source +118, Tests +322. Total +440 across 8 files.

Reproducibility: yes. Source inspection shows current main resolves compaction model/auth against the raw OpenAI provider, and the PR discussion includes before-fix logs where fallback compaction used openai/gpt-5.5 and failed for missing direct OpenAI API-key auth.

Review metrics: 1 noteworthy metric.

Config behavior surfaces: 0 added, 1 existing model parameter honored in preflight. The PR does not add a new config key, but it makes existing responsesCompactThreshold behavior affect local preflight compaction timing.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

Run or wait for required changed checks covering the touched agents and auto-reply surfaces before merge.

Risk before merge

Auth-provider selection during compaction is compatibility-sensitive: a wrong predicate can make Codex OAuth ask for a direct OpenAI key or make direct OpenAI API-key setups use Codex auth.
The supplied proof and targeted tests are strong for the changed paths, but the PR body says full pnpm check or the full suite was not run in that local proof pass.

Maintainer options:

Merge after auth-route checks pass (recommended)
Accept the scoped compaction routing change once required CI or changed-gate proof passes for the touched agents and auto-reply surfaces.
Ask for broader live preflight proof
If maintainers want more runtime confidence, request a second live oversized preflight or timeout-compaction run that captures the provider route and session state after the latest head.
Pause for provider owner review
If the auth-routing predicate should be a product/API decision rather than a bugfix, pause merge for an owner to confirm the Codex-vs-direct OpenAI selection contract.

Next step before merge
No repair lane is needed; maintainer review should focus on CI/changed-gate proof and accepting the auth-provider merge risk.

Security
Cleared: The diff changes auth provider selection for compaction but does not add new permissions, storage, network calls, dependency sources, or secret exposure surfaces.

Review details

Best possible solution:

Land the scoped auth-route and threshold fix after required CI or changed-gate proof confirms the Codex OAuth and direct OpenAI preservation paths.

Do we have a high-confidence way to reproduce the issue?

Yes. Source inspection shows current main resolves compaction model/auth against the raw OpenAI provider, and the PR discussion includes before-fix logs where fallback compaction used openai/gpt-5.5 and failed for missing direct OpenAI API-key auth.

Is this the best way to solve the issue?

Yes. The PR uses the existing OpenAI/Codex routing helper in the compaction path, preserves direct OpenAI when Codex auth is not configured, and covers the previously noted server-threshold edge case.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 7cd15d249316.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR supplies redacted live runtime logs from a real Discord gateway session showing successful after-fix compaction through openai-codex/gpt-5.5 and preserved session state.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (logs): The PR supplies redacted live runtime logs from a real Discord gateway session showing successful after-fix compaction through openai-codex/gpt-5.5 and preserved session state.
remove rating: 🦐 gold shrimp: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove status: ⏳ waiting on author: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P2: This is a normal-priority auth-routing bugfix for long OpenAI/Codex sessions with focused blast radius.
merge-risk: 🚨 auth-provider: The diff changes which provider's credentials compaction uses for OpenAI model refs under Codex runtime conditions.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (logs): The PR supplies redacted live runtime logs from a real Discord gateway session showing successful after-fix compaction through openai-codex/gpt-5.5 and preserved session state.
proof: sufficient: Contributor real behavior proof is sufficient. The PR supplies redacted live runtime logs from a real Discord gateway session showing successful after-fix compaction through openai-codex/gpt-5.5 and preserved session state.

Evidence reviewed

PR surface:

Source +118, Tests +322. Total +440 across 8 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	5	142	24	+118
Tests	3	323	1	+322
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	8	465	25	+440

What I checked:

Current-main compaction source: Current main resolves the compaction target to provider directly from the raw compaction target, then passes that provider into model/auth resolution before applying the selected Codex runtime provider; that matches the reported direct-OpenAI auth failure path. (src/agents/pi-embedded-runner/compact.ts:499, 7cd15d249316)
Current-main preflight source: Current main computes preflight compaction threshold only as contextWindowTokens - reserveTokensFloor - softThresholdTokens, so it does not account for configured OpenAI Responses server compaction thresholds. (src/auto-reply/reply/agent-runner-memory.ts:730, 7cd15d249316)
OpenAI Responses contract evidence: The payload policy enables server compaction by default for direct openai Responses models unless explicitly disabled, and docs say responsesCompactThreshold overrides that server threshold. (src/agents/openai-responses-payload-policy.ts:282, 7cd15d249316)
PR patch evidence: The PR patch adds selected runtime provider resolution before compaction model/auth lookup, preserves direct OpenAI when no Codex auth is configured, and adds threshold tests including the implicit direct-OpenAI server-compaction default in commit ac388fb. (src/agents/pi-embedded-runner/compact.ts:499, ac388fb5a90b)
Real behavior proof: The PR body and comment fix(openai): route compaction through Codex auth provider #86408 (comment) include redacted live Discord gateway logs showing timeout compaction succeeded through openai-codex/gpt-5.5 and the prior direct openai/gpt-5.5 missing API-key failure did not recur. (ac388fb5a90b)
History/provenance sample: Local blame for the central current-main lines points to 2e3b59b, a recent ClawSweeper-generated maintenance commit, so the local checkout does not expose deeper original feature history; related PR Fix OpenAI compaction runtime routing #85413 covers the same OpenAI compaction runtime-routing surface. (src/agents/openai-codex-routing.ts:171, 2e3b59bc5804)

Likely related people:

clawsweeper[bot]: Local blame on current main attributes the central routing, compaction, and preflight threshold lines to recent generated maintenance commit 2e3b59b, though this is weak for original ownership. (role: recent area contributor; confidence: low; commits: 2e3b59bc5804; files: src/agents/openai-codex-routing.ts, src/agents/pi-embedded-runner/compact.ts, src/auto-reply/reply/agent-runner-memory.ts)
VACInc: Authored the related open PR Fix OpenAI compaction runtime routing #85413 on the same OpenAI compaction runtime-routing and threshold surface, and is co-author on this PR's commits. (role: adjacent prior contributor; confidence: medium; commits: 1f4a358fca3d, ac388fb5a90b; files: src/agents/openai-codex-routing.ts, src/agents/pi-embedded-runner/compact.ts, src/auto-reply/reply/agent-runner-memory.ts)
pfrederiksen: Reported the related stale Codex thread preflight compaction failure in Telegram inbound dispatch aborts when preflight compaction hits missing Codex thread #86211 and authored the companion stale-binding recovery PR fix: recover Codex binding after stale preflight compaction #86216. (role: adjacent reporter and repair contributor; confidence: medium; commits: a9ad8a918eba; files: src/auto-reply/reply/agent-runner-memory.ts, extensions/codex/src/conversation-binding.ts, extensions/codex/src/app-server/compact.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

clawsweeper · 2026-05-25T09:17:56Z

ClawSweeper PR egg

✨ Hatched: 💎 rare Tiny Merge Sprite

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

Merged PRs are hatchable.
Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 💎 rare.
Trait: purrs at green checks.
Image traits: location status garden; accessory tiny test log scroll; palette moonlit blue and soft silver; mood bright-eyed; pose peeking out from the egg shell; shell polished stone shell; lighting tiny status-light glow; background subtle branch markers.
Share on X: post this hatch
Copy: My PR egg hatched a 💎 rare Tiny Merge Sprite in ClawSweeper.

What is this egg doing here?

Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

funmerlin · 2026-05-25T10:20:26Z

Post-install real behavior proof from a live gateway/Discord run (partial, not yet a successful oversized compaction):

Setup:

Built this branch locally with pnpm build.
Installed it into the LaunchAgent-pinned global OpenClaw path with npm install -g /Users/merlin/openclaw --prefix /Users/merlin/.nvm/versions/node/v24.13.0.
Restarted the gateway with openclaw gateway restart.
Verified the live gateway was executing the patched checkout: post-restart log callsites point at /Users/merlin/openclaw/dist/..., not the previous package path.

Before-fix evidence from the same machine, same day:

2026-05-25T10:49:04.392+02:00 codex app-server compaction could not use thread binding recovery=missing_thread_binding
2026-05-25T10:49:04.395+02:00 native harness compaction could not use its session binding; falling back to context engine: no codex app-server thread binding
2026-05-25T10:49:06.661+02:00 [compaction-diag] ... provider=openai/gpt-5.5 ... outcome=failed ... detail=No_API_key_found_for_provider_openai_...

After-fix live run from Discord #merlins-tower on the patched gateway:

2026-05-25T12:17:34.504+02:00 codex app-server compaction could not use thread binding
sessionKey=agent:main:discord:channel:<redacted>
sessionId=e1580861-e3df-4680-a6f6-da33ebb822b1
threadId=019e5bc9-e4f6-7cb1-8fa9-c35e5086c91b
reason="thread not found: 019e5bc9-e4f6-7cb1-8fa9-c35e5086c91b"
recovery=stale_thread_binding
path=file:///Users/merlin/openclaw/dist/subsystem-BhMD7zU-.js:178:51

Follow-up checks for the post-fix 12:17-12:18 window found no native harness compaction could not use its session binding; falling back to context engine line and no [compaction-diag] ... provider=openai/gpt-5.5 ... No_API_key_found_for_provider_openai line. The next relevant line was:

2026-05-25T12:18:44.549+02:00 [session-resume] Injected continuity summary for agent:main:discord:channel:<redacted>

Persisted session state after the run was also on the Codex provider route:

{
  "status": "done",
  "abortedLastRun": false,
  "modelProvider": "openai-codex",
  "model": "gpt-5.5",
  "contextTokens": 272000,
  "totalTokensFresh": true,
  "compactionCount": 0,
  "authProfileOverride": "openai-codex:<redacted>"
}

Gateway health after the run:

{
  "ok": true,
  "durationMs": 2509,
  "eventLoop": { "degraded": false, "reasons": [] },
  "plugins": { "loaded": ["browser", "memory-core"], "errors": [] },
  "channelOrder": ["discord"]
}

Interpretation: this is useful real setup proof that the previously observed stale-binding path no longer continues into the old direct-OpenAI API-key failure on this patched gateway. It is still partial proof: this run hit a stale Codex app-server thread binding and then resumed via continuity summary; it does not prove a fully successful oversized Codex OAuth compaction through openai-codex. I am leaving the PR draft until we either capture that successful oversized compaction or maintainers decide this stale-binding negative proof is sufficient for the targeted regression.

funmerlin · 2026-05-25T17:27:55Z

Additional live proof from the long-running Discord #claw-enhance session:

Setup:

Same patched local gateway/install as above.
Real Discord channel session: agent:main:discord:channel:<redacted> (#claw-enhance).
Same session had before-fix failure on 2026-05-24.

Before-fix failure for this exact session/channel:

2026-05-24T22:40:10.320+02:00 codex app-server compaction could not use thread binding recovery=stale_thread_binding
2026-05-24T22:40:10.322+02:00 native harness compaction could not use its session binding; falling back to context engine: thread not found: <redacted-thread-id>
2026-05-24T22:40:14.163+02:00 [compaction-diag] ... sessionKey=agent:main:discord:channel:<redacted> trigger=budget provider=openai/gpt-5.5 attempt=1 maxAttempts=1 outcome=failed ... detail=No_API_key_found_for_provider_openai_...

After-fix live compaction evidence from today:

2026-05-25T19:17:48.271+02:00 [timeout-compaction] LLM timed out with high prompt token usage (76%); attempting compaction before retry (attempt 1/2) diagId=ovf-mplgz2i6-AQyaSQ
2026-05-25T19:18:02.136+02:00 [pre-compaction-session-snapshot] Wrote /Users/merlin/.openclaw/workspace-main/memory/sessions/agent_main_discord_channel_<redacted>.md
2026-05-25T19:18:05.519+02:00 [timeout-compaction] compaction succeeded for openai-codex/gpt-5.5; retrying prompt
2026-05-25T19:18:05.520+02:00 post-compaction guard armed for 3 attempts
2026-05-25T19:18:09.059+02:00 qmd sync completed for agent "main" reason=post-compaction durationMs=3583

Session transcript also contains a real compaction record at the same timestamp:

2026-05-25T17:18:05.457Z type=compaction id=95f31814 parentId=<redacted>

Persisted session state after the successful run:

{
  "status": "done",
  "abortedLastRun": false,
  "modelProvider": "openai-codex",
  "model": "gpt-5.5",
  "contextTokens": 272000,
  "totalTokens": 236692,
  "totalTokensFresh": true,
  "compactionCount": 6,
  "authProfileOverride": "openai-codex:<redacted>",
  "authProfileOverrideCompactionCount": 5,
  "memoryFlushCompactionCount": 5
}

Observed result:

The real oversized Codex OAuth Discord session compacted successfully through openai-codex/gpt-5.5.
The prior direct provider=openai/gpt-5.5 / No_API_key_found_for_provider_openai failure did not recur for this channel after the patched build was installed.
There was another timeout-recovery attempt in the same session that timed out, but it also used provider=openai-codex/gpt-5.5, not direct openai/gpt-5.5, so the auth-provider regression stayed fixed even in the failure case.

This satisfies the missing real behavior proof more directly than the earlier stale-binding-only evidence.

funmerlin · 2026-05-25T17:46:54Z

Addressed ClawSweeper P2 threshold feedback in ac388fb5a90:

resolveResponsesServerCompactionThreshold now matches the OpenAI Responses payload policy: direct openai treats server compaction as enabled by default unless responsesServerCompaction is explicitly false; non-OpenAI providers still require explicit true.
The existing defer-at-server-threshold test now covers responsesCompactThreshold without explicit responsesServerCompaction: true.
Added explicit-false coverage proving local preflight threshold behavior is used when direct OpenAI server compaction is disabled.

Validation after the fix:

node scripts/run-vitest.mjs src/auto-reply/reply/agent-runner-memory.test.ts src/agents/openai-codex-routing.test.ts src/agents/pi-embedded-runner/compact.hooks.test.ts
Test Files  4 passed (4)
Tests  136 passed (136)

git diff --check
# clean

@clawsweeper re-review

clawsweeper · 2026-05-25T17:46:57Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26413039139
Updated: 2026-05-25T17:57:49.293Z

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>

steipete · 2026-05-25T21:12:58Z

Maintainer rewrite/proof before landing:

Behavior addressed: selected runtime: "codex" OpenAI routing stays on openai-codex, while overflow compaction keeps the direct OpenAI API-key fallback only in the compaction-specific path.
Real environment tested: local checkout rebased on origin/main, plus GitHub CI on final head 097086e1ac0031b246d15bc766563599824f8e09.
Exact steps or command run after this patch:

node scripts/run-vitest.mjs src/agents/openai-codex-routing.test.ts src/agents/pi-embedded-runner/compact.hooks.test.ts src/auto-reply/reply/agent-runner-memory.test.ts src/agents/pi-embedded-runner/run.incomplete-turn.test.ts src/agents/pi-embedded-runner/run.overflow-compaction.test.ts
.agents/skills/autoreview/scripts/autoreview --mode local
git diff --check
GitHub CI run 26419812078
GitHub CodeQL run 26419812024
GitHub CodeQL Critical Quality run 26419812051
Evidence after fix: targeted Vitest passed 8 files / 418 tests; autoreview reported no accepted/actionable findings; final GitHub CI, CodeQL, and Critical Quality runs completed successfully.
Observed result after fix: PR is mergeable on final SHA 097086e1ac0031b246d15bc766563599824f8e09.
What was not tested: no live Codex app-server/OAuth session was run; coverage is routing/unit/CI proof for the changed compaction and provider-selection surface.

…6408) * fix(openai): route compaction through codex auth provider Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> * fix(openai): honor default responses compaction threshold Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> * fix(openai): preserve codex runtime routing * docs(changelog): note Codex routing fix --------- Co-authored-by: Merlin <258679497+funmerlin@users.noreply.github.com> Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> Co-authored-by: Peter Steinberger <steipete@gmail.com>

…026.5.26) (#682) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.22` → `2026.5.26` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/567) for more information. --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.26`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026526) [Compare Source](https://github.com/openclaw/openclaw/compare/v2026.5.22...v2026.5.26) ##### Highlights - Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load. - Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path. - More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals. - Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents. - Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies. - Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends. - More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened. - Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect. ##### Changes - Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence. - Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. ([#85667](https://github.com/openclaw/openclaw/issues/85667)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. ([#83019](https://github.com/openclaw/openclaw/issues/83019), [#80370](https://github.com/openclaw/openclaw/issues/80370), [#86191](https://github.com/openclaw/openclaw/issues/86191)) - Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. ([#85894](https://github.com/openclaw/openclaw/issues/85894), [#85952](https://github.com/openclaw/openclaw/issues/85952), [#85477](https://github.com/openclaw/openclaw/issues/85477)) - Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. ([#84094](https://github.com/openclaw/openclaw/issues/84094)) - TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. ([#86722](https://github.com/openclaw/openclaw/issues/86722), [#87115](https://github.com/openclaw/openclaw/issues/87115), [#86976](https://github.com/openclaw/openclaw/issues/86976)) - Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. ([#86270](https://github.com/openclaw/openclaw/issues/86270), [#86359](https://github.com/openclaw/openclaw/issues/86359)) - Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. ([#86735](https://github.com/openclaw/openclaw/issues/86735), [#87084](https://github.com/openclaw/openclaw/issues/87084)) - Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. ([#86798](https://github.com/openclaw/openclaw/issues/86798), [#86355](https://github.com/openclaw/openclaw/issues/86355)) Thanks [@ngutman](https://github.com/ngutman). - Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. ([#84649](https://github.com/openclaw/openclaw/issues/84649), [#85843](https://github.com/openclaw/openclaw/issues/85843), [#86517](https://github.com/openclaw/openclaw/issues/86517), [#86678](https://github.com/openclaw/openclaw/issues/86678)) - Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery. - Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection. - Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions. - Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths. - Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation. - Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration. - QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes. - Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter. - Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes [#12831](https://github.com/openclaw/openclaw/issues/12831). Thanks [@BunsDev](https://github.com/BunsDev). - Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. ([#85206](https://github.com/openclaw/openclaw/issues/85206)) - iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. ([#86355](https://github.com/openclaw/openclaw/issues/86355)) Thanks [@ngutman](https://github.com/ngutman). - Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. ([#86437](https://github.com/openclaw/openclaw/issues/86437)) - Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. ([#86772](https://github.com/openclaw/openclaw/issues/86772)) ##### Fixes - Memory/security: reject prompt-like text submitted through the explicit `memory_store` tool before embedding or storage, matching the existing auto-capture prompt-injection filter. ([#87142](https://github.com/openclaw/openclaw/issues/87142)) - Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when `gateway.auth.rateLimit` is unset, while preserving the loopback exemption. ([#87148](https://github.com/openclaw/openclaw/issues/87148)) - Prompt hardening: route untrusted group prompt metadata through sanitized untrusted structured context while preserving trusted operator-configured group system prompts and aligning the plugin SDK docs/test helpers. ([#87144](https://github.com/openclaw/openclaw/issues/87144)) - Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack `allowFrom` sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. ([#78526](https://github.com/openclaw/openclaw/issues/78526), [#87094](https://github.com/openclaw/openclaw/issues/87094), [#87062](https://github.com/openclaw/openclaw/issues/87062), [#83741](https://github.com/openclaw/openclaw/issues/83741), [#70707](https://github.com/openclaw/openclaw/issues/70707), [#86924](https://github.com/openclaw/openclaw/issues/86924)) Thanks [@zsxsoft](https://github.com/zsxsoft), [@ttzero25](https://github.com/ttzero25), and [@mmaps](https://github.com/mmaps). - Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart. - TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. ([#86722](https://github.com/openclaw/openclaw/issues/86722), [#87000](https://github.com/openclaw/openclaw/issues/87000), [#85786](https://github.com/openclaw/openclaw/issues/85786), [#87108](https://github.com/openclaw/openclaw/issues/87108), [#87001](https://github.com/openclaw/openclaw/issues/87001), [#86614](https://github.com/openclaw/openclaw/issues/86614), [#87115](https://github.com/openclaw/openclaw/issues/87115), [#86976](https://github.com/openclaw/openclaw/issues/86976)) - Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep `onDiagnosticEvent` exports discoverable through `Function.name`, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. ([#85936](https://github.com/openclaw/openclaw/issues/85936), [#87084](https://github.com/openclaw/openclaw/issues/87084), [#86977](https://github.com/openclaw/openclaw/issues/86977), [#87069](https://github.com/openclaw/openclaw/issues/87069), [#86771](https://github.com/openclaw/openclaw/issues/86771)) - Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama `top_p`, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. ([#87096](https://github.com/openclaw/openclaw/issues/87096), [#73950](https://github.com/openclaw/openclaw/issues/73950), [#87049](https://github.com/openclaw/openclaw/issues/87049), [#86689](https://github.com/openclaw/openclaw/issues/86689), [#86772](https://github.com/openclaw/openclaw/issues/86772)) - Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest `PATH`, and bootstrap raw AWS macOS Node/pnpm commands through `/usr/bin/env`. ([#86997](https://github.com/openclaw/openclaw/issues/86997)) - Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. ([#86989](https://github.com/openclaw/openclaw/issues/86989), [#86990](https://github.com/openclaw/openclaw/issues/86990), [#86991](https://github.com/openclaw/openclaw/issues/86991), [#86992](https://github.com/openclaw/openclaw/issues/86992), [#86993](https://github.com/openclaw/openclaw/issues/86993), [#86994](https://github.com/openclaw/openclaw/issues/86994)) Thanks [@keshavbotagent](https://github.com/keshavbotagent). - Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts. - Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. ([#82203](https://github.com/openclaw/openclaw/issues/82203), [#86934](https://github.com/openclaw/openclaw/issues/86934), [#87025](https://github.com/openclaw/openclaw/issues/87025)) Thanks [@martingarramon](https://github.com/martingarramon), [@vincentkoc](https://github.com/vincentkoc), and [@joshavant](https://github.com/joshavant). - Agents/sessions: handle active-fallback failures in `sessions_send` so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. ([#86638](https://github.com/openclaw/openclaw/issues/86638)) - Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. ([#86101](https://github.com/openclaw/openclaw/issues/86101)) - Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. ([#86677](https://github.com/openclaw/openclaw/issues/86677), [#86476](https://github.com/openclaw/openclaw/issues/86476)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle) and [@pashpashpash](https://github.com/pashpashpash). - Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. ([#87030](https://github.com/openclaw/openclaw/issues/87030), [#86818](https://github.com/openclaw/openclaw/issues/86818), [#86559](https://github.com/openclaw/openclaw/issues/86559)) Thanks [@joshavant](https://github.com/joshavant), [@luoyanglang](https://github.com/luoyanglang), and [@stevenepalmer](https://github.com/stevenepalmer). - Doctor/runtime: validate active bundled MCP tool schemas through the same runtime projection path so unsupported MCP input schemas are reported and quarantined instead of poisoning assistant startup. - CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. ([#87031](https://github.com/openclaw/openclaw/issues/87031), [#85387](https://github.com/openclaw/openclaw/issues/85387)) Thanks [@giodl73-repo](https://github.com/giodl73-repo) and [@vincentkoc](https://github.com/vincentkoc). - Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. ([#86814](https://github.com/openclaw/openclaw/issues/86814), [#86964](https://github.com/openclaw/openclaw/issues/86964)) Thanks [@Alix-007](https://github.com/Alix-007) and [@vincentkoc](https://github.com/vincentkoc). - Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates. - QA/Telegram: bound Telegram user credential tar and broker calls so live proof setup fails with a timeout instead of waiting for the outer Crabbox job deadline. - QA/Tool Search: bound gateway E2E HTTP probes, run only the fixture plugin, and clean up temporary fixture trees after the compact tool-catalog proof completes. - Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. ([#86762](https://github.com/openclaw/openclaw/issues/86762)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. ([#83873](https://github.com/openclaw/openclaw/issues/83873), [#85361](https://github.com/openclaw/openclaw/issues/85361), [#85555](https://github.com/openclaw/openclaw/issues/85555), [#85656](https://github.com/openclaw/openclaw/issues/85656), [#85709](https://github.com/openclaw/openclaw/issues/85709), [#86299](https://github.com/openclaw/openclaw/issues/86299), [#86553](https://github.com/openclaw/openclaw/issues/86553)) Thanks [@SebTardif](https://github.com/SebTardif), [@luoyanglang](https://github.com/luoyanglang), and [@neeravmakwana](https://github.com/neeravmakwana). - iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. ([#82642](https://github.com/openclaw/openclaw/issues/82642), [#85475](https://github.com/openclaw/openclaw/issues/85475), [#86569](https://github.com/openclaw/openclaw/issues/86569), [#86705](https://github.com/openclaw/openclaw/issues/86705), [#86706](https://github.com/openclaw/openclaw/issues/86706), [#86770](https://github.com/openclaw/openclaw/issues/86770)) Thanks [@homer-byte](https://github.com/homer-byte), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@swang430](https://github.com/swang430), and [@OmarShahine](https://github.com/OmarShahine). - WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. ([#83833](https://github.com/openclaw/openclaw/issues/83833), [#85309](https://github.com/openclaw/openclaw/issues/85309), [#85777](https://github.com/openclaw/openclaw/issues/85777), [#85794](https://github.com/openclaw/openclaw/issues/85794), [#85906](https://github.com/openclaw/openclaw/issues/85906), [#86318](https://github.com/openclaw/openclaw/issues/86318), [#86697](https://github.com/openclaw/openclaw/issues/86697)) Thanks [@sliverp](https://github.com/sliverp), [@neeravmakwana](https://github.com/neeravmakwana), and [@Kailigithub](https://github.com/Kailigithub). - Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. ([#80227](https://github.com/openclaw/openclaw/issues/80227), [#86238](https://github.com/openclaw/openclaw/issues/86238), [#86487](https://github.com/openclaw/openclaw/issues/86487), [#86571](https://github.com/openclaw/openclaw/issues/86571), [#86595](https://github.com/openclaw/openclaw/issues/86595), [#86601](https://github.com/openclaw/openclaw/issues/86601)) - Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. ([#85378](https://github.com/openclaw/openclaw/issues/85378), [#85542](https://github.com/openclaw/openclaw/issues/85542), [#85891](https://github.com/openclaw/openclaw/issues/85891), [#85909](https://github.com/openclaw/openclaw/issues/85909), [#86408](https://github.com/openclaw/openclaw/issues/86408)) - Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. ([#70473](https://github.com/openclaw/openclaw/issues/70473), [#85764](https://github.com/openclaw/openclaw/issues/85764), [#86014](https://github.com/openclaw/openclaw/issues/86014), [#86134](https://github.com/openclaw/openclaw/issues/86134), [#86427](https://github.com/openclaw/openclaw/issues/86427), [#86944](https://github.com/openclaw/openclaw/issues/86944)) Thanks [@openperf](https://github.com/openperf), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@zhangguiping-xydt](https://github.com/zhangguiping-xydt), and [@ferminquant](https://github.com/ferminquant). - Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. ([#85739](https://github.com/openclaw/openclaw/issues/85739), [#85787](https://github.com/openclaw/openclaw/issues/85787), [#86060](https://github.com/openclaw/openclaw/issues/86060), [#86260](https://github.com/openclaw/openclaw/issues/86260), [#86384](https://github.com/openclaw/openclaw/issues/86384), [#86533](https://github.com/openclaw/openclaw/issues/86533)) Thanks [@liaoyl830](https://github.com/liaoyl830). - Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. ([#85491](https://github.com/openclaw/openclaw/issues/85491)) - Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. ([#59299](https://github.com/openclaw/openclaw/issues/59299)) - Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. ([#85849](https://github.com/openclaw/openclaw/issues/85849), [#85934](https://github.com/openclaw/openclaw/issues/85934), [#86046](https://github.com/openclaw/openclaw/issues/86046), [#86557](https://github.com/openclaw/openclaw/issues/86557)) - Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. ([#85776](https://github.com/openclaw/openclaw/issues/85776), [#86037](https://github.com/openclaw/openclaw/issues/86037), [#86437](https://github.com/openclaw/openclaw/issues/86437), [#86857](https://github.com/openclaw/openclaw/issues/86857), [#86923](https://github.com/openclaw/openclaw/issues/86923)) - Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. ([#80613](https://github.com/openclaw/openclaw/issues/80613), [#82928](https://github.com/openclaw/openclaw/issues/82928), [#85060](https://github.com/openclaw/openclaw/issues/85060), [#85704](https://github.com/openclaw/openclaw/issues/85704), [#85967](https://github.com/openclaw/openclaw/issues/85967), [#86701](https://github.com/openclaw/openclaw/issues/86701)) Thanks [@brokemac79](https://github.com/brokemac79), [@openperf](https://github.com/openperf), and [@yaaboo-gif](https://github.com/yaaboo-gif). - Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. ([#86944](https://github.com/openclaw/openclaw/issues/86944)) Thanks [@ferminquant](https://github.com/ferminquant). - Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors. Thanks [@mmaps](https://github.com/mmaps). - Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. ([#86312](https://github.com/openclaw/openclaw/issues/86312)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes [#84462](https://github.com/openclaw/openclaw/issues/84462). ([#86553](https://github.com/openclaw/openclaw/issues/86553)) Thanks [@luoyanglang](https://github.com/luoyanglang). - CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install. - CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line. - CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker. - CI: bound Telegram user Crabbox proof Bot API calls so stalled Telegram responses fail instead of wedging credential and desktop proof cleanup. - CI: bound MCP channel stdio client initialization so Docker channel proof fails and closes the bridge transport instead of waiting for the outer job timeout. - CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command. - CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`. - CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke. - iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes [#30170](https://github.com/openclaw/openclaw/issues/30170). ([#86569](https://github.com/openclaw/openclaw/issues/86569)) - QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes [#83562](https://github.com/openclaw/openclaw/issues/83562). Thanks [@sliverp](https://github.com/sliverp). - Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. ([#86596](https://github.com/openclaw/openclaw/issues/86596)) Thanks [@ferminquant](https://github.com/ferminquant). - Control UI: keep host-local Markdown file paths inert while preserving app-relative links. ([#86620](https://github.com/openclaw/openclaw/issues/86620)) Thanks [@BryanTegomoh](https://github.com/BryanTegomoh). - Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. ([#86575](https://github.com/openclaw/openclaw/issues/86575)) Thanks [@ferminquant](https://github.com/ferminquant). - IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. ([#85906](https://github.com/openclaw/openclaw/issues/85906)) Thanks [@Kailigithub](https://github.com/Kailigithub). - Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. ([#85882](https://github.com/openclaw/openclaw/issues/85882)) Thanks [@MichaelZelbel](https://github.com/MichaelZelbel). - Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. ([#85909](https://github.com/openclaw/openclaw/issues/85909)) Thanks [@earlvanze](https://github.com/earlvanze). - Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. ([#82947](https://github.com/openclaw/openclaw/issues/82947)) Thanks [@SebTardif](https://github.com/SebTardif). - Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. ([#80059](https://github.com/openclaw/openclaw/issues/80059)) Thanks [@pavelzak](https://github.com/pavelzak). - Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. ([#85934](https://github.com/openclaw/openclaw/issues/85934)) Thanks [@SebTardif](https://github.com/SebTardif). - Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. ([#86046](https://github.com/openclaw/openclaw/issues/86046)) Thanks [@SebTardif](https://github.com/SebTardif). - Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes [#80227](https://github.com/openclaw/openclaw/issues/80227). Thanks [@Clivilwalker](https://github.com/Clivilwalker). - Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. ([#84812](https://github.com/openclaw/openclaw/issues/84812)) Thanks [@marchpure](https://github.com/marchpure). - Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. ([#86501](https://github.com/openclaw/openclaw/issues/86501)) Thanks [@tianxiaochannel-oss88](https://github.com/tianxiaochannel-oss88). - Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. ([#86529](https://github.com/openclaw/openclaw/issues/86529)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes [#83507](https://github.com/openclaw/openclaw/issues/83507). ([#85875](https://github.com/openclaw/openclaw/issues/85875)) Thanks [@brokemac79](https://github.com/brokemac79). - OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes [#72373](https://github.com/openclaw/openclaw/issues/72373). Thanks [@brokemac79](https://github.com/brokemac79). - Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes [#86151](https://github.com/openclaw/openclaw/issues/86151). ([#86240](https://github.com/openclaw/openclaw/issues/86240)) Thanks [@SebTardif](https://github.com/SebTardif). - Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages. - Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes [#80184](https://github.com/openclaw/openclaw/issues/80184). ([#86570](https://github.com/openclaw/openclaw/issues/86570)) Thanks [@brokemac79](https://github.com/brokemac79). - Agents/media: send direct fallback for generated media still missing after an active requester wake fails. ([#85489](https://github.com/openclaw/openclaw/issues/85489)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. ([#70473](https://github.com/openclaw/openclaw/issues/70473)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. ([#85542](https://github.com/openclaw/openclaw/issues/85542)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured. - Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. ([#86408](https://github.com/openclaw/openclaw/issues/86408)) Thanks [@funmerlin](https://github.com/funmerlin) and [@VACInc](https://github.com/VACInc). - Agent transcript: include OpenClaw agent session logs when finding local transcript candidates. - Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners. - Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage. - TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster. - Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes [#56827](https://github.com/openclaw/openclaw/issues/56827). Thanks [@openperf](https://github.com/openperf). - Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs. - Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn. - Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace. - Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes [#86518](https://github.com/openclaw/openclaw/issues/86518). ([#86533](https://github.com/openclaw/openclaw/issues/86533)) Thanks [@liaoyl830](https://github.com/liaoyl830). - Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume. - Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates. - Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes [#82928](https://github.com/openclaw/openclaw/issues/82928). Thanks [@galiniliev](https://github.com/galiniliev). - Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. ([#86487](https://github.com/openclaw/openclaw/issues/86487)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session. - Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated. - Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw. - Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. ([#86177](https://github.com/openclaw/openclaw/issues/86177)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work. - Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. ([#86461](https://github.com/openclaw/openclaw/issues/86461)) Thanks [@SebTardif](https://github.com/SebTardif). - Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated. - Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. ([#86037](https://github.com/openclaw/openclaw/issues/86037)) - Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes [#86014](https://github.com/openclaw/openclaw/issues/86014). Thanks [@openperf](https://github.com/openperf). - Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error. - Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. ([#86327](https://github.com/openclaw/openclaw/issues/86327)) Thanks [@abnershang](https://github.com/abnershang). - Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. ([#84409](https://github.com/openclaw/openclaw/issues/84409)) Thanks [@samzong](https://github.com/samzong). - Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. ([#85733](https://github.com/openclaw/openclaw/issues/85733)) - Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. ([#85348](https://github.com/openclaw/openclaw/issues/85348)) Thanks [@osolmaz](https://github.com/osolmaz). - Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. ([#86388](https://github.com/openclaw/openclaw/issues/86388)) Thanks [@XuZehan-iCenter](https://github.com/XuZehan-iCenter). - Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. ([#86378](https://github.com/openclaw/openclaw/issues/86378)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi). - Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. ([#86313](https://github.com/openclaw/openclaw/issues/86313)) Thanks [@ferminquant](https://github.com/ferminquant). - Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes [#84922](https://github.com/openclaw/openclaw/issues/84922). ([#86415](https://github.com/openclaw/openclaw/issues/86415)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. ([#86260](https://github.com/openclaw/openclaw/issues/86260)) Thanks [@stevenepalmer](https://github.com/stevenepalmer). - Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. ([#84338](https://github.com/openclaw/openclaw/issues/84338)) Thanks [@coygeek](https://github.com/coygeek). - QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes [#85267](https://github.com/openclaw/openclaw/issues/85267). ([#85271](https://github.com/openclaw/openclaw/issues/85271)) Thanks [@SymbolStar](https://github.com/SymbolStar). - Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. ([#86357](https://github.com/openclaw/openclaw/issues/86357)) Thanks [@udaymanish6](https://github.com/udaymanish6). - Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention. - Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. ([#86302](https://github.com/openclaw/openclaw/issues/86302)) Thanks [@SebTardif](https://github.com/SebTardif). - Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. ([#85704](https://github.com/openclaw/openclaw/issues/85704)) Thanks [@yaaboo-gif](https://github.com/yaaboo-gif). - Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. ([#86299](https://github.com/openclaw/openclaw/issues/86299)) Thanks [@SebTardif](https://github.com/SebTardif). - Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. ([#86318](https://github.com/openclaw/openclaw/issues/86318)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. ([#86341](https://github.com/openclaw/openclaw/issues/86341)) Thanks [@mushuiyu886](https://github.com/mushuiyu886). - Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. ([#85933](https://github.com/openclaw/openclaw/issues/85933)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily. - QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path. - Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff. - xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks. - Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes [#86102](https://github.com/openclaw/openclaw/issues/86102). ([#86384](https://github.com/openclaw/openclaw/issues/86384)) Thanks [@1052326311](https://github.com/1052326311). - Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. ([#86238](https://github.com/openclaw/openclaw/issues/86238)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. ([#86571](https://github.com/openclaw/openclaw/issues/86571)) Thanks [@joshavant](https://github.com/joshavant). - Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs. - Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`. - Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs. - Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget. - QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose. - Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts. - Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted. - Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`. - Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching. - Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof. - Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. ([#84749](https://github.com/openclaw/openclaw/issues/84749)) Thanks [@TeodoroRodrigo](https://github.com/TeodoroRodrigo). - Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes [#85639](https://github.com/openclaw/openclaw/issues/85639). Thanks [@openperf](https://github.com/openperf). - WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes [#86347](https://github.com/openclaw/openclaw/issues/86347). Thanks [@shakkernerd](https://github.com/shakkernerd). - Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes. - Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes. - Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import. - Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. ([#81153](https://github.com/openclaw/openclaw/issues/81153)) Thanks [@ai-hpc](https://github.com/ai-hpc). - xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. ([#86222](https://github.com/openclaw/openclaw/issues/86222)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - CLI: suppress benign self-update version-skew warnings during package post-update finalization. - Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results. - Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned. - Docker: restore writable `~/.config` in runtime images. Fixes [#85968](https://github.com/openclaw/openclaw/issues/85968). Thanks [@hkoessler](https://github.com/hkoessler) and [@Bartok9](https://github.com/Bartok9). - Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph. - Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings. - Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior. - Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. ([#86287](https://github.com/openclaw/openclaw/issues/86287)) Thanks [@ferminquant](https://github.com/ferminquant). - Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active. - Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs. - Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes [#80819](https://github.com/openclaw/openclaw/issues/80819). ([#86330](https://github.com/openclaw/openclaw/issues/86330), from [#81971](https://github.com/openclaw/openclaw/issues/81971)) Thanks [@guthirry](https://github.com/guthirry) and [@sallyom](https://github.com/sallyom). - Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. ([#86557](https://github.com/openclaw/openclaw/issues/86557)) Thanks [@sallyom](https://github.com/sallyom). - Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics. - Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy. - Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider. Thanks [@amknight](https://github.com/amknight). - Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. ([#83971](https://github.com/openclaw/openclaw/issues/83971)) Thanks [@damianFelixPago](https://github.com/damianFelixPago). - Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes [#82957](https://github.com/openclaw/openclaw/issues/82957). ([#82958](https://github.com/openclaw/openclaw/issues/82958)) Thanks [@galiniliev](https://github.com/galiniliev). - Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. ([#86286](https://github.com/openclaw/openclaw/issues/86286)) Thanks [@jason-allen-oneal](https://github.com/jason-allen-oneal). - Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. ([#85690](https://github.com/openclaw/openclaw/issues/85690)) Thanks [@ngutman](https://github.com/ngutman). - Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. ([#86134](https://github.com/openclaw/openclaw/issues/86134)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes [#65141](https://github.com/openclaw/openclaw/issues/65141). ([#86705](https://github.com/openclaw/openclaw/issues/86705)) Thanks [@swang430](https://github.com/swang430). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/682

…6408) * fix(openai): route compaction through codex auth provider Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> * fix(openai): honor default responses compaction threshold Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> * fix(openai): preserve codex runtime routing * docs(changelog): note Codex routing fix --------- Co-authored-by: Merlin <258679497+funmerlin@users.noreply.github.com> Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com> Co-authored-by: Peter Steinberger <steipete@gmail.com>

openclaw-barnacle Bot added agents Agent runtime and tooling size: M triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 25, 2026

clawsweeper Bot mentioned this pull request May 25, 2026

fix: recover Codex binding after stale preflight compaction #86216

Closed

brokemac79 mentioned this pull request May 25, 2026

Telegram inbound dispatch aborts when preflight compaction hits missing Codex thread #86211

Closed

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 25, 2026

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 25, 2026

funmerlin marked this pull request as ready for review May 25, 2026 17:47

steipete self-assigned this May 25, 2026

funmerlin and others added 3 commits May 25, 2026 21:55

fix(openai): route compaction through codex auth provider

d6b8a44

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>

fix(openai): honor default responses compaction threshold

9568bde

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>

fix(openai): preserve codex runtime routing

385d470

steipete force-pushed the fix/openai-codex-compaction-routing branch from ac388fb to 385d470 Compare May 25, 2026 21:02

openclaw-barnacle Bot added size: L and removed size: M labels May 25, 2026

docs(changelog): note Codex routing fix

097086e

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 25, 2026

steipete merged commit f4cfa01 into openclaw:main May 25, 2026
100 of 101 checks passed

jalehman mentioned this pull request May 25, 2026

fix: preserve plugin LLM command auth #85936

Merged

This was referenced May 25, 2026

📡 Upstream Digest — 2026-05-25 22:53 UTC curtismercier/openclaw-mods#947

Open

Track OpenClaw native Codex auth mismatch claytono/infra#2061

Open

TameTheGame mentioned this pull request May 26, 2026

docs(discord): use canonical Codex model ref #86998

Closed

clawsweeper Bot mentioned this pull request May 26, 2026

fix(issue): resolve #86820 [Bug]: Codex OAuth compaction falls back to direct OpenAI AP #87011

Closed

3 tasks

Applied-AI-Solutions-hub mentioned this pull request May 30, 2026

[Bug]: Codex OAuth compaction falls back to direct OpenAI API and fails without OPENAI_API_KEY #86820

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(openai): route compaction through Codex auth provider#86408

fix(openai): route compaction through Codex auth provider#86408
steipete merged 4 commits into
openclaw:mainfrom
funmerlin:fix/openai-codex-compaction-routing

funmerlin commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

steipete commented May 25, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

funmerlin commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Motivation

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Real behavior proof (required for external PRs)

Root Cause (if applicable)

Regression Test Plan (if applicable)

User-visible / Behavior Changes

Diagram (if applicable)

Security Impact (required)

Repro + Verification

Environment

Steps

Expected

Actual

Evidence

Human Verification (required)

Review Conversations

Compatibility / Migration

Risks and Mitigations

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Hatch command

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

funmerlin commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

steipete commented May 25, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

funmerlin commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading