Add Codex multi-agent config migration coverage by ooiuuii · Pull Request #90317 · openclaw/openclaw

ooiuuii · 2026-06-04T12:10:03Z

Summary

add regression coverage for a live 6.1 upgrade shape where agents.defaults.model and multiple agents.list[].model entries still use openai-codex/gpt-5.5
assert doctor repair rewrites those routes to openai/gpt-5.5, preserves Codex intent via per-agent agentRuntime.id = "codex", and enables/allows the codex plugin when an allowlist is present

Context

This is PR1 from the Codex/OpenAI migration follow-up. It focuses only on config migration coverage and does not touch session-store repair or route re-persistence.

Refs #90047. Related to #90036 because stale config defaults/list entries can keep Telegram/direct sessions resolving through the legacy openai-codex/* route after upgrade.

Verification

pnpm tsx .tmp-check-codex-pr1.mts behavior check: PR1_BEHAVIOR_OK
git diff --check

Note: targeted Vitest (pnpm vitest run src/commands/doctor/shared/codex-route-warnings.test.ts -t "repairs live multi-agent Codex upgrade configs" --pool=forks --maxWorkers=1) was attempted locally, but the first-run build stayed in repeated Rolldown PLUGIN_TIMINGS output without reaching test execution in a reasonable time. The added test mirrors the behavior check above.

Real behavior proof (redacted, Windows official 6.1)

Behavior or issue addressed: openclaw doctor --fix must repair a live 6.1 upgrade shape where agents.defaults.model and multiple agents.list[].model entries still point at openai-codex/gpt-5.5, while preserving Codex runtime intent and repairing restrictive plugin allowlists.
Real environment tested: Windows official OpenClaw 2026.6.1 (2e08f0f) package, using an isolated temporary config instead of the live .openclaw config/token state.
Exact steps or command run after this patch: Ran openclaw doctor --fix --yes --non-interactive against the redacted upgrade config shown below.
Evidence after fix: Terminal output / copied live output from the real run:

OpenClaw 2026.6.1 (2e08f0f)
openclaw doctor --fix --yes --non-interactive
DOCTOR_EXIT=0

Input config used a restrictive allowlist and multiple legacy Codex routes:

{
  "agents": {
    "defaults": {
      "model": "openai-codex/gpt-5.5",
      "models": {
        "openai-codex/gpt-5.5": { "agentRuntime": { "id": "codex" } }
      }
    },
    "list": [
      { "id": "main", "model": "openai-codex/gpt-5.5" },
      { "id": "telegram", "model": "openai-codex/gpt-5.5" }
    ]
  },
  "plugins": { "allow": ["openai"], "entries": {} }
}

After doctor repair:

{
  "agents": {
    "defaults": {
      "model": "openai/gpt-5.5",
      "models": {
        "openai/gpt-5.5": { "agentRuntime": { "id": "codex" } }
      }
    },
    "list": [
      {
        "id": "main",
        "model": "openai/gpt-5.5",
        "models": { "openai/gpt-5.5": { "agentRuntime": { "id": "codex" } } }
      },
      {
        "id": "telegram",
        "model": "openai/gpt-5.5",
        "models": { "openai/gpt-5.5": { "agentRuntime": { "id": "codex" } } }
      }
    ]
  },
  "plugins": {
    "allow": ["openai", "codex", "memory-core", "telegram"],
    "entries": { "codex": { "enabled": true } },
    "bundledDiscovery": "compat"
  }
}

Observed result after fix: The real doctor run exited 0, canonicalized legacy openai-codex/* config refs to openai/*, preserved Codex runtime metadata, enabled plugins.entries.codex, and extended the restrictive allowlist to include codex.
What was not tested: No additional gaps for this regression; unrelated session-store repair is intentionally covered by a separate PR.

clawsweeper · 2026-06-04T12:12:18Z

Codex review: needs maintainer review before merge. Reviewed June 4, 2026, 9:09 PM ET / 01:09 UTC.

Summary
Adds a Vitest regression case for maybeRepairCodexRoutes covering multiple legacy openai-codex agent refs plus restrictive plugins.allow repair.

PR surface: Tests +48. Total +48 across 1 file.

Reproducibility: not applicable. as a test-only PR. The behavior under coverage is source-auditable through maybeRepairCodexRoutes, and the PR body supplies redacted Windows 2026.6.1 doctor --fix output for the upgrade-shaped config.

Review metrics: none identified.

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:

[P2] Have CI or Testbox run the codex-route-warnings.test.ts shard containing the new regression before merge.

Risk before merge

[P1] The PR body's targeted Vitest attempt stalled before test execution, so CI or Testbox still needs to prove the added regression case actually runs before merge.

Maintainer options:

Decide the mitigation before merge
Land the focused regression test after CI/Testbox executes the relevant doctor test shard; keep the session-store and forward write-boundary work in the related PRs.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

No ClawSweeper repair lane is needed because I found no discrete patch defect; maintainers should rely on CI/Testbox for the added test execution gate.

Security
Cleared: The diff only adds a regression test and does not change runtime code, dependency resolution, CI, scripts, credentials, or supply-chain surfaces.

Review details

Best possible solution:

Land the focused regression test after CI/Testbox executes the relevant doctor test shard; keep the session-store and forward write-boundary work in the related PRs.

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

Not applicable as a test-only PR. The behavior under coverage is source-auditable through maybeRepairCodexRoutes, and the PR body supplies redacted Windows 2026.6.1 doctor --fix output for the upgrade-shaped config.

Is this the best way to solve the issue?

Yes. A focused regression in the existing doctor shared test suite is the narrowest maintainable layer for this config-repair invariant, while the related session-store and write-boundary behaviors remain split into separate PRs.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 4fa5092cdc39.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted copied live output from a Windows official 2026.6.1 openclaw doctor --fix run showing exit 0 and the repaired config shape for the behavior under test.

Label justifications:

P2: This is normal-priority regression coverage for Codex/OpenAI migration repair with a limited test-only surface.
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 (live_output): The PR body includes redacted copied live output from a Windows official 2026.6.1 openclaw doctor --fix run showing exit 0 and the repaired config shape for the behavior under test.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted copied live output from a Windows official 2026.6.1 openclaw doctor --fix run showing exit 0 and the repaired config shape for the behavior under test.

Evidence reviewed

PR surface:

Tests +48. Total +48 across 1 file.

View PR surface stats

Area	Files	Added	Net
Source	0	0	0
Tests	1	48	+48
Docs	0	0	0
Config	0	0	0
Generated	0	0	0
Other	0	0	0
Total	1	48	+48

What I checked:

PR diff: The PR adds one regression test asserting default and listed-agent legacy Codex refs migrate to openai/gpt-5.5, per-agent/default Codex runtime policy is preserved, plugins.entries.codex is enabled, and codex is appended to an existing allowlist. (src/commands/doctor/shared/codex-route-warnings.test.ts:2929, 906e342e7d2c)
Current repair entry point: maybeRepairCodexRoutes rewrites config model refs, then re-collects disabled Codex-plugin hits and applies plugin repair before returning warnings and changes. (src/commands/doctor/shared/codex-route-warnings.ts:2821, 4fa5092cdc39)
Allowlist repair source: enableCodexPluginForRequiredRoutes enables plugins.entries.codex and appends codex to a non-empty restrictive plugins.allow that does not already include it. (src/commands/doctor/shared/codex-route-warnings.ts:1209, 4fa5092cdc39)
Runtime policy preservation source: ensureCodexRuntimePolicy writes agentRuntime.id: "codex" onto repaired canonical model refs when no explicit non-default runtime pin should be preserved. (src/commands/doctor/shared/codex-route-warnings.ts:2242, 4fa5092cdc39)
Product contract docs: The OpenAI provider docs define openai/* as the canonical OpenAI route and say legacy Codex model refs are repaired by openclaw doctor --fix to openai/* plus the Codex runtime. Public docs: docs/providers/openai.md. (docs/providers/openai.md:14, 4fa5092cdc39)
Codex dependency contract: The sibling Codex app-server protocol has explicit model and model_provider thread fields, and session setup persists config.model_provider_id, supporting OpenClaw's separation of canonical model provider from runtime/auth handling. (../codex/codex-rs/app-server-protocol/src/protocol/v2/thread.rs:95, ecae41274091)

Likely related people:

steipete: Current-line blame for collectDisabledCodexPluginRouteHits and maybeRepairCodexRoutes points at Peter Steinberger's recent commit covering the doctor Codex route repair module and its tests. (role: recent area contributor; confidence: medium; commits: f5b6a977d743; files: src/commands/doctor/shared/codex-route-warnings.ts, src/commands/doctor/shared/codex-route-warnings.test.ts)
vincentkoc: The latest shipped v2026.6.1 release baseline commit touched the same Codex route repair source and test files, making this a useful routing candidate for shipped-migration context. (role: release baseline contributor; confidence: low; commits: 2e08f0f4221f; files: src/commands/doctor/shared/codex-route-warnings.ts, src/commands/doctor/shared/codex-route-warnings.test.ts, src/agents/openai-routing.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.

ooiuuii · 2026-06-04T13:29:40Z

@clawsweeper re-review after adding redacted Windows 6.1 doctor --fix proof to the PR body.

clawsweeper · 2026-06-04T13:29:43Z

🦞🧹
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/26954912598
Updated: 2026-06-04T13:39:15.745Z

…26.6.5) (#963) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.1` → `2026.6.5` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.5`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202665) [Compare Source](openclaw/openclaw@v2026.6.1...v2026.6.5) ##### Highlights - QQBot now strips model reasoning/thinking scaffolding before native delivery, preventing raw `<thinking>` content from leaking into channel replies. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - MCP tool results now coerce `resource_link`, `resource`, `audio`, malformed image, and future non-text/image blocks at the materialize boundary, preventing Anthropic 400s and poisoned session history after a tool returns richer MCP content. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic extended-thinking sessions recover after prompt-cache expiry or Gateway restart because stream start events wait for `message_start`, letting pre-generation signature errors trigger the existing recovery retry. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697)) Thanks [@openperf](https://github.com/openperf). - Parallel is now a bundled `web_search` provider with `PARALLEL_API_KEY` discovery, guarded endpoint handling, cache-safe session ids, onboarding picker support, and docs. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Google Vertex ADC users get static catalog rows and runtime model resolution again, while single-provider cooldown recovery and memory adapter status checks are more reliable. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90816](openclaw/openclaw#90816)) Thanks [@849261680](https://github.com/849261680). - Matrix can preflight voice notes before mention gating, preserve thread reads/replies through Matrix relations pagination, and carry QA coverage for voice and thread flows. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Auth and plugin install state is more durable: auth profiles now live in SQLite, official npm plugin install records keep their trusted pins, and prerelease fallback integrity checks avoid carrying stale integrity forward. ([#89102](openclaw/openclaw#89102), [#88585](openclaw/openclaw#88585)) - macOS node mode no longer silently self-reconnects away from a healthy direct Gateway session, reducing unexpected companion app session churn. ([#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@vrurg](https://github.com/vrurg). - Upgrade and service paths are safer: cron legacy JSON stores migrate during doctor preflight, service env placeholders no longer mask state-dir secrets, WhatsApp startup waits are bounded, and disabled WhatsApp accounts tear down on config reload. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488), [#90486](openclaw/openclaw#90486), [#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT), [@sallyom](https://github.com/sallyom), [@mcaxtr](https://github.com/mcaxtr), and [@MukundaKatta](https://github.com/MukundaKatta). ##### Changes - Search/providers: add the Parallel bundled web-search plugin, live provider tests, registration contracts, onboarding/docs wiring, and guarded `api.parallel.ai/v1/search` support. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Matrix/channels: add voice-message preflight and thread-aware read/reply behavior, including Matrix QA scenario wiring and docs for voice-message behavior. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Skills/ClawHub: install ClawHub skills backed by GitHub repositories through the resolved install API, download the pinned GitHub commit, keep install-policy checks, and report install telemetry after success. ([#90478](openclaw/openclaw#90478)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - Google Chat/channels: add native approval card actions and click handling so Google Chat approvals use platform-native cards instead of generic message flow. - Mobile: Android provider/model screens now surface expiring, unavailable, unresolved, and attention states more clearly, while iOS settings and Talk tabs keep diagnostics, gateway rows, attachment labels, and unavailable Talk controls reachable. - Memory: QMD search can use the new rerank toggle, and memory adapter status uses the resolved default model identity when checking plain status. ([#61834](openclaw/openclaw#61834)) - Docs/tooling: add Parallel search docs, refresh weather-skill guidance toward `web_fetch`, clarify legacy `openai-codex` auth, document release/test helper scripts, and tighten changed-test routing docs for CI/debugging work. ([#90028](openclaw/openclaw#90028), [#90250](openclaw/openclaw#90250)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Release/process: switch release trains to `YYYY.M.PATCH` monthly patch numbering, keep pre-transition tags compatible, and pin the June 2026 floor at `2026.6.5` after the published beta. - Platform maintenance: refresh Android, Swift/macOS, Docker, CodeQL, Buildx, Docker build/push, and Codex Action dependencies for this release train. ([#74980](openclaw/openclaw#74980), [#81757](openclaw/openclaw#81757), [#86481](openclaw/openclaw#86481), [#86483](openclaw/openclaw#86483), [#90601](openclaw/openclaw#90601)) - QQBot: add `/bot-group-allways on|off` slash command (with named-account and default-account support) to toggle whether group messages require an `@mention` before the bot replies, and clear the runtime config snapshot after the write so the new account-level `defaultRequireMention` takes effect immediately without restart. ([#91423](openclaw/openclaw#91423)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh). ##### Fixes - Channel content boundaries: QQBot now strips reasoning/thinking tags before sending, preserving final answers while hiding internal model narration from users. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - Agents/MCP/providers: coerce non-text/image MCP tool-result blocks before they reach provider converters, preserving valid images and turning richer MCP content into text instead of malformed image blocks. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic/Codex/ACP/agent recovery: defer Anthropic stream start events until `message_start`, strip stale compaction thinking signatures before Anthropic replay, detect unsigned thinking-only stalls, refresh prompt fences after compaction writes, reject empty completion handoffs, preserve parent streaming-off overrides/shared progress commentary, forward heartbeat metadata to context-engine hooks, and cover Codex session/thread migration edge cases. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697), [#90163](openclaw/openclaw#90163), [#90108](openclaw/openclaw#90108), [#89874](openclaw/openclaw#89874), [#89505](openclaw/openclaw#89505), [#90632](openclaw/openclaw#90632), [#89302](openclaw/openclaw#89302), [#90729](openclaw/openclaw#90729), [#90317](openclaw/openclaw#90317), [#90319](openclaw/openclaw#90319)) Thanks [@openperf](https://github.com/openperf), [@100yenadmin](https://github.com/100yenadmin), and [@ooiuuii](https://github.com/ooiuuii). - Provider/model resolution: preserve Google Vertex ADC auth markers in generated catalogs, re-probe a single-provider primary after cooldown, share Codex model visibility, fail closed for unknown model auth, preserve Codex alias availability, keep unresolved profile refs unknown, and avoid resolving auth while listing models. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90702](openclaw/openclaw#90702)) Thanks [@849261680](https://github.com/849261680). - Gateway/macOS/mobile: avoid duplicate Gateway probe warnings by identity, rate-limit node pairing requests while preserving paired-node reconnects, keep macOS node mode on a healthy direct Gateway session, keep iOS diagnostics and gateway rows reachable, and avoid Linux ARM Gradle resource tasks during Android builds. ([#85791](openclaw/openclaw#85791), [#90147](openclaw/openclaw#90147), [#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@giodl73-repo](https://github.com/giodl73-repo) and [@vrurg](https://github.com/vrurg). - TUI/chat/Workboard/auto-reply: optimistic user messages stay stable across stale history reloads, runId reassignment, and abort windows instead of disappearing, jumping, or lingering as ghost rows; Workboard stale lifecycle bulk updates no longer overwrite newer status/provenance; message-tool sends now count as delivery. ([#86205](openclaw/openclaw#86205), [#89600](openclaw/openclaw#89600), [#88592](openclaw/openclaw#88592), [#90123](openclaw/openclaw#90123)) Thanks [@RomneyDa](https://github.com/RomneyDa). - Cron/update/service env: doctor config preflight now migrates legacy cron JSON stores into SQLite before runtime reads, service env planning skips unresolved placeholders that would mask state-dir `.env` values, and session transcript rewrites keep registry markers/discriminants consistent. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT) and [@sallyom](https://github.com/sallyom). - Security/config/tooling: guard MCP HTTP redirects, protect global agent config defaults, and keep release/test/tooling proof failures bounded and explicit. ([#89732](openclaw/openclaw#89732), [#90145](openclaw/openclaw#90145)) - Channels: WhatsApp restarts when per-account config changes, bounds background startup waits, closes failed sockets, and preserves reconnect behavior; Mattermost slash commands keep their state on `globalThis`; Feishu streaming cards preserve full merged content; voice-call tracks Twilio streams after connect; ClickClack reply tools respect `toolsAllow`. ([#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965), [#90486](openclaw/openclaw#90486), [#68113](openclaw/openclaw#68113), [#90534](openclaw/openclaw#90534), [#90181](openclaw/openclaw#90181), [#90607](openclaw/openclaw#90607), [#89500](openclaw/openclaw#89500)) Thanks [@MukundaKatta](https://github.com/MukundaKatta), [@mcaxtr](https://github.com/mcaxtr), [@infoanton](https://github.com/infoanton), [@mushuiyu886](https://github.com/mushuiyu886), and [@sahibzada-allahyar](https://github.com/sahibzada-allahyar). - Feishu: retry transient send rate-limit errors (HTTP 429, per-chat code 230020, tenant-level code 11232) with linear backoff, including SDK responses that fulfill with rate-limit bodies instead of throwing, and route streaming-card sends through the retry wrapper. ([#89659](openclaw/openclaw#89659)) Thanks [@ladygege](https://github.com/ladygege). - Release/CI/E2E: main CI guard drift, PR merge diff scoping, live Docker credential staging, base-image qualification, installer Docker classification, Playwright dependency install recovery, API-key auth for Codex live Docker lanes, Parallels option terminators, and JSON-mode progress handling are tighter so release proof fails cleaner. ([#90532](openclaw/openclaw#90532), [#90287](openclaw/openclaw#90287), [#90058](openclaw/openclaw#90058)) Thanks [@RomneyDa](https://github.com/RomneyDa), [@hxy91819](https://github.com/hxy91819), and [@mrunalp](https://github.com/mrunalp). - Release/CI/E2E: Docker E2E and live Docker harness runs now apply default memory, CPU, and process ceilings while preserving explicit per-lane overrides. - Release/CI/E2E: plugin lifecycle matrix resource sampling now fails phases that exceed RSS, wall-clock, or CPU ceilings instead of only logging the measurements. - Release/CI/E2E: Codex npm plugin live assertions now cap transcript discovery and diagnostic log reads so failure proof stays bounded. - Tests/state isolation: QA Lab valid-tool-call metrics now require runtime tool-call evidence when runtime parity data is available instead of counting tool-backed scenario pass status alone. - Tests/state isolation: QA Lab runtime parity now fails planned-only tool-call rows without matching tool results instead of treating matching mock plans as real tool evidence. - Tests/state isolation: provider, media, auth, cron, task, session, sandbox, Gateway, and Codex timeout fixtures now scope more home/state/env data per test, reducing cross-test leakage and making release validation failures less noisy. ([#90027](openclaw/openclaw#90027), [#89974](openclaw/openclaw#89974)) </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/963

openclaw-barnacle Bot added commands Command implementations size: XS labels Jun 4, 2026

This was referenced Jun 4, 2026

Codex migration (2026.6.1) drops the gpt-5.5 model when a canonical openai provider exists for embeddings — agents go silent #90047

Closed

Session model route drifts from openai/gpt-5.5 to openai-codex/gpt-5.5 with native Codex runtime #90036

Open

openclaw-barnacle Bot added the triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. label Jun 4, 2026

ooiuuii mentioned this pull request Jun 4, 2026

Add Codex session route migration coverage #90319

Merged

ooiuuii mentioned this pull request Jun 4, 2026

Normalize legacy Codex session runtime state #90321

Closed

openclaw-barnacle Bot removed the triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. label Jun 4, 2026

Add Codex multi-agent migration coverage

906e342

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed proof: sufficient ClawSweeper judged the real behavior proof convincing. labels Jun 5, 2026

ooiuuii force-pushed the agent/xiaozhua/codex-config-migration branch from 74b4bc4 to 906e342 Compare June 5, 2026 01:02

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 5, 2026

RomneyDa merged commit cfd5f1a into openclaw:main Jun 5, 2026
169 checks passed

github-actions Bot mentioned this pull request Jun 5, 2026

📡 Upstream Digest — 2026-06-05 08:00 UTC curtismercier/openclaw-mods#1018

Open

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request Jun 6, 2026

Add Codex multi-agent migration coverage (openclaw#90317)

90246af

849261680 pushed a commit to 849261680/openclaw that referenced this pull request Jun 7, 2026

Add Codex multi-agent migration coverage (openclaw#90317)

37c6da4

wangmiao0668000666 pushed a commit to wangmiao0668000666/openclaw that referenced this pull request Jun 9, 2026

Add Codex multi-agent migration coverage (openclaw#90317)

f84b464

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add Codex multi-agent config migration coverage#90317

Add Codex multi-agent config migration coverage#90317
RomneyDa merged 1 commit into
openclaw:mainfrom
ooiuuii:agent/xiaozhua/codex-config-migration

ooiuuii commented Jun 4, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

Uh oh!

ooiuuii commented Jun 4, 2026

Uh oh!

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

ooiuuii commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Context

Verification

Real behavior proof (redacted, Windows official 6.1)

Uh oh!

clawsweeper Bot commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ooiuuii commented Jun 4, 2026

Uh oh!

clawsweeper Bot commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

ooiuuii commented Jun 4, 2026 •

edited

Loading

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading