fix(status): restore Codex synthetic usage line by brokemac79 · Pull Request #91709 · openclaw/openclaw

brokemac79 · 2026-06-09T13:29:03Z

Summary

Restores the /status provider-usage line for OpenAI/Codex sessions running on the Codex runtime, including the visible Usage: 5h ... Week ... windows that existed in the previous release.
Routes OpenAI/Codex synthetic usage reads through the Codex provider hook with the existing codex-app-server marker and the default Codex auth bridge, so live OAuth/CLI auth can be used without hard-coding any profile id.
Covers both OAuth-labeled Codex sessions and no-local-OpenAI-profile Codex sessions, and gives cold Codex app-server usage reads an 8s timeout.
Addresses the ClawSweeper SDK-boundary rank-up: the Codex app-server rate-limit parser is plugin-local in extensions/codex/src/app-server/rate-limits.ts, not exported from openclaw/plugin-sdk/provider-usage, so this PR does not add or baseline a new public SDK contract.
Keeps the change scoped to status/provider-usage paths; no changelog entry is included per CONTRIBUTING.md guidance for contributor PRs.

AI-assisted: prepared with Codex. The proof below was run on the reporter's live VPS OpenClaw host, which is where #91694 was found.

Linked context

Closes #91694.

Related: reporter requested live VPS proof instead of Crabbox/Testbox/Docker because the live VPS OpenClaw environment is where the regression was observed.

Real behavior proof (required for external PRs)

Behavior or issue addressed: /status for an OpenAI/Codex session on the Codex runtime should visibly show the restored 5h and weekly usage windows.
Real environment tested: Reporter live VPS OpenClaw host myvps (polymarket-mc), Linux 6.17.0-1011-oracle arm64, Node v22.22.0, pnpm 10.32.1, live OpenClaw config/Gateway from 2026.6.5-beta.6, patched source checkout /tmp/openclaw-91694-proof at PR head 5a0bdc4de39b7cde80b3eadb6c3647f64b8dc7a4. The proof used the reporter's live OpenAI/Codex auth profile with private details redacted; no profile id or account-specific value is committed in code.
Exact steps or command run after this patch: Checked out PR head 5a0bdc4de39b7cde80b3eadb6c3647f64b8dc7a4 on the live VPS, loaded the live OpenClaw config/session store, registered the PR source Codex provider in-process, and rendered the live chat /status text for session agent:main:beta531-smoke-codex-runtime-after-plugin.
Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output): Redacted terminal transcript from the reporter live VPS:

$ ssh myvps "cd /tmp/openclaw-91694-proof && node --import tsx ./proof-render-live-status-source-provider.mjs"
session: agent:main:beta531-smoke-codex-runtime-after-plugin
--- live VPS OpenClaw chat /status render with PR source provider start ---
🦞 OpenClaw 2026.6.2 (ad5614c)
⏱️ Uptime: gateway 13s · system 43d 19h
🧠 Model: openai/gpt-5.5
🔄 Fallbacks: google/gemini-3.1-pro-preview
🧮 Tokens: 11k in / 32 out
🗄️ Cache: 77% hit · 38k cached, 0 new
📚 Context: 50k/272k (18%) · 🧹 Compactions: 0
📊 Usage: 5h 84% left ⏱3h 1m · Week 44% left ⏱1d 9h
🧵 Session: agent:main:beta531-smoke-codex-runtime-after-plugin • updated 9d ago
⚙️ Execution: direct · Runtime: OpenAI Codex · Think: off · Fast: off · Text: low · elevated
🔊 Voice: inbound · provider=microsoft · voice=en-GB-RyanNeural · limit=1500 · summary=on
🪢 Queue: steer (depth 0)
--- live VPS OpenClaw chat /status render with PR source provider end ---
Your OpenClaw config was written by version 2026.6.5-beta.6, but this command is running 2026.6.2.
Check: `openclaw --version`, `which openclaw`, and `openclaw gateway status --deep`.
If unexpected, update PATH so `openclaw` points to the version you want, or reinstall the Gateway service from that same OpenClaw install.
Config warnings:
- plugins.entries.codex: plugin codex: plugin requires plugin API >=2026.6.5-beta.6, but this host is 2026.6.2; skipping discovery
- plugins.entries.tokenjuice: plugin tokenjuice: plugin requires plugin API >=2026.6.5-beta.6, but this host is 2026.6.2; skipping discovery
- plugins.entries.active-memory: plugin disabled (disabled in config) but config is present

Observed result after fix: The live VPS /status render now visibly includes 📊 Usage: 5h 84% left ... Week 44% left ... for Runtime: OpenAI Codex, matching the previous-release behavior shown in [Bug]: Codex/OpenAI usage line disappears from status after 2026.6.5-beta.6 #91694's before screenshot.
What was not tested: No Telegram/Desktop screenshot was captured; this proof renders the same chat status text path from the live VPS config/session/auth state. No production model quota was consumed beyond reading rate-limit/status state.
Proof limitations or environment constraints: The live VPS config/Gateway was from 2026.6.5-beta.6, while the source checkout reports 2026.6.2, so the proof command prints the version/config warnings shown above. The proof registers the PR source Codex provider in-process because the installed live plugin is pre-fix and skipped by the local source checkout; the status renderer, provider hook, live config/session store, and live auth bridge are still the patched code path and real VPS environment. Crabbox/Testbox/Docker were not used for the final proof because the reporter explicitly requested the live VPS as the bug source.
Before evidence (optional but encouraged): [Bug]: Codex/OpenAI usage line disappears from status after 2026.6.5-beta.6 #91694's before screenshot showed the prior expected line, for example Usage: 5h ... Week ...; the regression removed that visible line after upgrading.

Tests and validation

Focused commands run after the final patch:

Reporter live VPS (/tmp/openclaw-91694-proof, head 5a0bdc4de39b7cde80b3eadb6c3647f64b8dc7a4): ssh myvps "cd /tmp/openclaw-91694-proof && node --import tsx ./proof-render-live-status-source-provider.mjs" -> passed and copied above with visible Usage: output.
Reporter live VPS: env CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=4 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 node scripts/run-vitest.mjs src/infra/provider-usage.auth.plugin.test.ts src/infra/provider-usage.load.plugin.test.ts extensions/codex/provider.test.ts extensions/codex/src/app-server/rate-limits.test.ts src/auto-reply/reply/commands-status.test.ts -> passed, 3 Vitest shards, 67 tests.
Reporter live VPS: node scripts/run-tsgo.mjs -p tsconfig.core.json --noEmit --incremental false -> passed.
Reporter live VPS: node scripts/run-tsgo.mjs -p tsconfig.extensions.json --noEmit --incremental false -> passed.
Reporter live VPS: git diff --check -> passed.
Local Windows: node scripts/run-vitest.mjs extensions/codex/provider.test.ts -> passed, 18 tests.
Local Windows: node scripts/run-vitest.mjs extensions/codex/src/app-server/rate-limits.test.ts -> passed, 14 tests.
Local Windows: node scripts/run-vitest.mjs src/infra/provider-usage.auth.plugin.test.ts src/infra/provider-usage.load.plugin.test.ts -> passed, 10 tests.
Local Windows: node node_modules\vitest\vitest.mjs run src/auto-reply/reply/commands-status.test.ts -t "loads Codex synthetic usage" --config test\vitest\vitest.auto-reply.config.ts --reporter=verbose -> passed, 1 targeted status regression test.
Local Windows: node scripts/run-tsgo.mjs -p tsconfig.core.json --noEmit --incremental false -> passed.
Local Windows: node scripts/run-tsgo.mjs -p tsconfig.extensions.json --noEmit --incremental false -> passed.
Local Windows: git diff --check -> passed.

Regression coverage added or updated:

src/auto-reply/reply/commands-status.test.ts: covers Codex synthetic usage rendering for OpenAI/Codex sessions with OAuth labels and with no local OpenAI profile.
src/infra/provider-usage.auth.plugin.test.ts: covers synthetic Codex auth fallback for OpenAI usage.
src/infra/provider-usage.load.plugin.test.ts: covers routing an OpenAI usage request through the Codex provider hook while preserving OpenAI provider context.
extensions/codex/provider.test.ts: covers default Codex auth-bridge rate-limit reads, without forcing or committing any authProfileId.
extensions/codex/src/app-server/rate-limits.test.ts: covers plugin-local Codex app-server rate-limit payload parsing.

Risk checklist

Did user-visible behavior change? Yes.

Did config, environment, or migration behavior change? No.

Did security, auth, secrets, network, or tool execution behavior change? Yes, narrowly: status can read Codex app-server rate-limit data through the existing Codex provider hook when OpenAI/Codex synthetic auth is active.

Highest-risk area: provider-usage auth routing between OpenAI status context and Codex hook execution.

Risk mitigation: focused tests cover auth fallback, hook routing, Codex payload parsing, provider hook integration, default auth-bridge behavior, and /status rendering; live VPS proof exercised the reporter's active OpenClaw config/session/auth state and visibly restored the 5h and weekly usage line.

Current review state

Next action: maintainer review after the current CI pass completes.

Still waiting on: maintainer acceptance for the OpenAI-to-Codex synthetic usage auth routing that ClawSweeper flagged as the remaining human review point.

CI note: d670f9c was an empty commit pushed only to retrigger the infra-failed OpenGrep check. The latest head $head adds test-only mock typing fixes after CI check-test-types found two test inference errors. Runtime code and live VPS behavior proof remain from 5a0bdc4; subsequent commits do not change runtime behavior.

Bot/reviewer comments addressed:

ClawSweeper re-review completed for 5a0bdc4: proof is sufficient, result is ready for maintainer review, and status: 👀 ready for maintainer look / proof: sufficient labels were applied.
ClawSweeper proof blocker addressed: this PR body includes redacted, unellipsized live VPS /status output with the restored Usage: line visibly present.
ClawSweeper SDK-boundary rank-up addressed: the Codex app-server parser is plugin-local in extensions/codex/src/app-server/rate-limits.ts; no new public Plugin SDK parser or SDK contract is introduced.
Real behavior proof format updated to match CONTRIBUTING.md and .github/pull_request_template.md, with live VPS proof from the environment where [Bug]: Codex/OpenAI usage line disappears from status after 2026.6.5-beta.6 #91694 was found.

clawsweeper · 2026-06-09T13:32:49Z

Codex review: needs maintainer review before merge. Reviewed June 9, 2026, 12:00 PM ET / 16:00 UTC.

Summary
The PR routes OpenAI/Codex status usage through the Codex provider hook, adds a plugin-local Codex app-server rate-limit usage parser, and expands status/provider-usage regression tests.

PR surface: Source +195, Tests +268. Total +463 across 10 files.

Reproducibility: yes. The linked report gives a concrete live VPS before/after path, and current main source shows OpenAI usage depends on an OAuth/token auth label that the no-local-profile Codex app-server case lacks.

Review metrics: 2 noteworthy metrics.

Provider-usage route: 1 cross-provider route added. OpenAI usage can now be fetched through the Codex hook, which is the core merge-risk decision.
Public Plugin SDK exports: 0 added. The Codex app-server parser stays plugin-local, so the previous SDK-boundary concern appears addressed.

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 a maintainer explicitly accept or reject the OpenAI-to-Codex synthetic usage routing before merge.
[P2] Optionally add a Telegram Desktop /status proof if maintainers want native transport evidence.

Mantis proof suggestion
A native Telegram /status recording would show the visible chat surface that originally regressed, beyond the shared terminal status text proof. A maintainer can ask Mantis to capture proof by posting a new PR comment that starts with the OpenClaw Mantis account mention, followed by:

telegram desktop proof: verify Telegram /status for an OpenAI/Codex session includes the 5h and Week Usage line.

Risk before merge

[P1] Merging intentionally lets an OpenAI usage summary execute the Codex provider hook with the synthetic codex-app-server marker; maintainers should explicitly accept that auth-provider boundary.
[P1] The proof covers the shared status text path on the reporter's live VPS, but it does not include a native Telegram Desktop transcript for the reporter-visible Telegram /status surface.

Maintainer options:

Accept Codex-owned OpenAI usage routing (recommended)
Maintainers can land after explicitly accepting that Codex-runtime OpenAI sessions report usage through the Codex plugin/app-server auth bridge instead of a local OpenAI profile.
Request native Telegram proof first
Maintainers can ask for a short Telegram Desktop /status proof if they want transport-visible evidence before accepting the shared status-text proof.
Pause for a different provider contract
If maintainers do not want OpenAI usage contexts to call Codex hooks, pause this PR and replace it with a more explicit provider-usage contract.

Next step before merge

[P2] The remaining action is maintainer acceptance of compatibility-sensitive auth-provider routing, not a narrow automatable code repair.

Security
Cleared: No concrete security or supply-chain issue was found; the diff adds a bounded Codex app-server rate-limit read and does not add dependencies, workflows, or new secret storage.

Review details

Best possible solution:

Land this only after maintainer acceptance of the OpenAI-to-Codex synthetic usage routing, keeping the rate-limit parser plugin-local and avoiding any new public SDK surface.

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

Yes. The linked report gives a concrete live VPS before/after path, and current main source shows OpenAI usage depends on an OAuth/token auth label that the no-local-profile Codex app-server case lacks.

Is this the best way to solve the issue?

Yes, with maintainer acceptance. Keeping the Codex rate-limit fetch and parser inside the Codex plugin is the right owner boundary; the only open question is whether maintainers accept the OpenAI usage context calling the Codex hook.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 86bab9699d0d.

Label changes

Label justifications:

P2: This fixes a real status/usage visibility regression with limited runtime blast radius, but the model still runs.
merge-risk: 🚨 compatibility: The PR changes provider-usage behavior for existing OpenAI/Codex setups during upgrade by restoring usage through a new cross-provider route.
merge-risk: 🚨 auth-provider: The diff deliberately routes OpenAI usage reads through the Codex provider hook and Codex app-server auth bridge.
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 (terminal): The PR body includes redacted live VPS terminal output from the reporter environment showing the restored after-fix Usage line in the shared chat status text path.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted live VPS terminal output from the reporter environment showing the restored after-fix Usage line in the shared chat status text path.
mantis: telegram-visible-proof: Mantis should capture Telegram visible proof. The restored /status Usage line is visible in Telegram, so a short Telegram Desktop proof would materially demonstrate the reporter-facing surface.

Evidence reviewed

PR surface:

Source +195, Tests +268. Total +463 across 10 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	5	201	6	+195
Tests	5	268	0	+268
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	10	469	6	+463

What I checked:

Repository policy applied: Root AGENTS.md and relevant scoped extension/plugin/provider guidance were read; this review applied the explicit Codex dependency-source gate and the compatibility-sensitive provider-routing policy. (AGENTS.md:8, 86bab9699d0d)
Current-main source of regression: Current main only loads OpenAI usage when the status auth label resolves as OAuth/token, so a Codex app-server synthetic route with no local OpenAI profile can suppress the Usage line. (src/status/status-text.ts:325, 86bab9699d0d)
Status fix path: The PR detects Codex runtime usage, treats it as token-backed for usage lookup, extends the timeout to 8s, passes config/workspace context, and supplies an explicit OpenAI auth object with hookProvider codex. (src/status/status-text.ts:342, 8b157997e863)
Provider-usage hook routing: The PR adds a synthetic OpenAI usage auth result with token codex-app-server and hookProvider codex, while the loader preserves OpenAI context but resolves the plugin hook through Codex. (src/infra/provider-usage.load.ts:57, 8b157997e863)
Codex plugin-local usage reader: The Codex plugin now accepts only the codex-app-server marker, calls account/rateLimits/read through an isolated app-server client, and converts the payload with a plugin-local parser rather than adding a public SDK parser. (extensions/codex/provider.ts:118, 8b157997e863)
Codex payload parser: The new parser selects the Codex bucket from rateLimitsByLimitId/rate_limits_by_limit_id payloads, formats 5h/Week-style windows, clamps percentages, and preserves plan/credit display metadata. (extensions/codex/src/app-server/rate-limits.ts:192, 8b157997e863)

Likely related people:

vincentkoc: Current-main blame in this checkout attributes the status/provider-usage/Codex integration files to Vincent Koc, and the PR timeline shows vincentkoc assigned for review. (role: recent area contributor and assigned reviewer signal; confidence: medium; commits: 5f13d0c81780, 2e08f0f4221f; files: src/status/status-text.ts, src/infra/provider-usage.auth.ts, extensions/codex/provider.ts)
Peter Steinberger: History shows Peter authored the provider usage runtime hooks and the original Codex app-server harness extension that this PR composes with. (role: introduced adjacent provider/Codex runtime surfaces; confidence: high; commits: e7555724af15, dd26e8c44d4e; files: src/plugins/provider-runtime.ts, src/plugins/types.ts, extensions/codex/provider.ts)
Eva H: History shows an adjacent Codex provider catalog/auth marker fix, relevant to the synthetic codex-app-server marker path. (role: adjacent Codex provider contributor; confidence: medium; commits: 49d99c750014; files: extensions/codex/provider.ts, extensions/codex/provider-discovery.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.

brokemac79 · 2026-06-09T14:07:47Z

@clawsweeper re-review

Addressed the review findings at head ad5614c5978d793bce04108e5a8049c928a1b874:

Moved buildCodexAppServerUsageSnapshot out of openclaw/plugin-sdk/provider-usage and into the Codex app-server rate-limit module, so the Codex app-server parser is no longer new public Plugin SDK API.
Refreshed the PR body with required Real behavior proof format and live reporter VPS proof from myvps / polymarket-mc, the environment where [Bug]: Codex/OpenAI usage line disappears from status after 2026.6.5-beta.6 #91694 was found.
Re-ran focused provider-usage, Codex provider/rate-limit, full auto-reply status, core tsgo, extensions tsgo, and git diff --check on that VPS at the exact head SHA.

clawsweeper · 2026-06-09T14:07:52Z

🦞🧹
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/27213498463
Updated: 2026-06-09T14:41:41.839Z

brokemac79 · 2026-06-09T14:12:04Z

@clawsweeper re-review

PR body is now updated directly with:

Real behavior proof in the template/CONTRIBUTING.md format.
Reporter live VPS OC proof from myvps / polymarket-mc, the environment where [Bug]: Codex/OpenAI usage line disappears from status after 2026.6.5-beta.6 #91694 was found.
Explicit ClawSweeper rank-up response: the Codex app-server parser is plugin-local in extensions/codex/src/app-server/rate-limits.ts and is no longer exported from openclaw/plugin-sdk/provider-usage, so there is no new public SDK contract to document or baseline.

Please re-review head ad5614c5978d793bce04108e5a8049c928a1b874 using the updated PR body.

clawsweeper · 2026-06-09T14:12:08Z

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

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/27212264450
Updated: 2026-06-09T14:23:03.429Z

brokemac79 · 2026-06-09T15:01:55Z

@clawsweeper re-review

Updated the PR body directly at head 5a0bdc4de39b7cde80b3eadb6c3647f64b8dc7a4 with the redacted live VPS OpenClaw /status transcript from the reporter host where #91694 was found. The body now visibly includes the restored line:

📊 Usage: 5h 84% left ⏱3h 1m · Week 44% left ⏱1d 9h

Also preserved the SDK-boundary response from the rank-up move: the Codex app-server parser is plugin-local in extensions/codex/src/app-server/rate-limits.ts, so this PR does not add or baseline a new public SDK contract. The repository real-behavior proof policy script passes against the updated body.

clawsweeper · 2026-06-09T15:01:58Z

🦞🧹
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/27215415691
Updated: 2026-06-09T15:11:00.986Z

vincentkoc · 2026-06-09T16:32:26Z

Maintainer verification before landing:

Pushed maintainer fixes to the PR branch at d71b028ec0bb50515b5b20139d61b2ea0333d0b9.
Autoreview: .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main -> clean, no accepted/actionable findings.
Focused verification: node scripts/run-vitest.mjs extensions/codex/provider.test.ts extensions/codex/src/app-server/rate-limits.test.ts src/auto-reply/reply/commands-status.test.ts src/infra/provider-usage.auth.plugin.test.ts src/infra/provider-usage.load.plugin.test.ts -> 3 shards passed, 71 tests.
Whitespace: git diff --check -> clean.
Codex contract checked against openai/codex: codex-rs/app-server-protocol/src/protocol/v2/account.rs, codex-rs/app-server/src/request_processors/account_processor.rs, codex-rs/app-server/tests/suite/v2/rate_limits.rs, codex-rs/tui/src/app_server_session.rs, and codex-rs/tui/src/status/rate_limits.rs.
GitHub reports mergeable=MERGEABLE, mergeStateStatus=CLEAN, and no required checks for the refreshed PR branch.

Known proof gap: pnpm check:changed / Testbox was not runnable from this shell because pnpm, corepack, blacksmith, and crabbox are not available on PATH here; the focused repo wrapper tests above covered the touched Codex/status/usage surfaces.

…26.6.6) (#1040) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.5` → `2026.6.6` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.6`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202666) [Compare Source](openclaw/openclaw@v2026.6.5...v2026.6.6) ##### Highlights - Security boundaries are substantially tighter across transcripts, sandbox binds, host environment inheritance, MCP stdio, Codex HTTP access, native search policy, elevated sender checks, deleted-agent ACP bypasses, loopback tools, Discord moderation, and Teams group actions; exec approvals now fail closed on timeout. ([#91529](openclaw/openclaw#91529), [#91618](openclaw/openclaw#91618), [#91615](openclaw/openclaw#91615), [#91619](openclaw/openclaw#91619), [#91741](openclaw/openclaw#91741), [#91745](openclaw/openclaw#91745), [#91746](openclaw/openclaw#91746), [#91748](openclaw/openclaw#91748), [#91749](openclaw/openclaw#91749), [#91750](openclaw/openclaw#91750), [#91751](openclaw/openclaw#91751), [#91752](openclaw/openclaw#91752), [#91763](openclaw/openclaw#91763), [#89938](openclaw/openclaw#89938)) Thanks [@joshavant](https://github.com/joshavant), [@pgondhi987](https://github.com/pgondhi987), [@mmaps](https://github.com/mmaps), [@eleqtrizit](https://github.com/eleqtrizit), [@shakkernerd](https://github.com/shakkernerd), and [@drobison00](https://github.com/drobison00). - Telegram delivery is safer and more coherent: account-scoped topics route to the right agent, streamed text survives tool calls, `/compact` works on generic ingress, callback handling uses concrete APIs, draft chunking is shared, durable dispatch dedupe moved into the SDK, and unauthorized DM text stays out of cache and prompt context. ([#91189](openclaw/openclaw#91189), [#88682](openclaw/openclaw#88682), [#89588](openclaw/openclaw#89588), [#90212](openclaw/openclaw#90212), [#91876](openclaw/openclaw#91876), [#91874](openclaw/openclaw#91874), [#91904](openclaw/openclaw#91904), [#91478](openclaw/openclaw#91478), [#91915](openclaw/openclaw#91915)) Thanks [@codysai001](https://github.com/codysai001), [@alexzhu0](https://github.com/alexzhu0), [@joelnishanth](https://github.com/joelnishanth), [@snowzlm](https://github.com/snowzlm), [@obviyus](https://github.com/obviyus), and [@sallyom](https://github.com/sallyom). - iMessage recovery and delivery now cover always-on inbound restart, durable echo markers, block streaming, idle approval discovery, hardened outbound transport, and actionable inbound startup diagnostics. ([#91335](openclaw/openclaw#91335), [#91449](openclaw/openclaw#91449), [#88969](openclaw/openclaw#88969), [#88530](openclaw/openclaw#88530), [#91783](openclaw/openclaw#91783), [#91785](openclaw/openclaw#91785)) Thanks [@omarshahine](https://github.com/omarshahine), [@jmissig](https://github.com/jmissig), and [@colmbrogan](https://github.com/colmbrogan). - Browser and MCP connectivity gained existing-session CDP support, discovered WebSocket validation, default-profile `cdpUrl` handling, safer browser-output boundaries, Streamable HTTP loopback transport, corrected OAuth/SSE authorization handling, and broader schema compatibility. ([#91422](openclaw/openclaw#91422), [#89851](openclaw/openclaw#89851), [#91736](openclaw/openclaw#91736), [#91747](openclaw/openclaw#91747), [#91451](openclaw/openclaw#91451), [#80143](openclaw/openclaw#80143)) Thanks [@pgondhi987](https://github.com/pgondhi987), [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@lifuyue](https://github.com/lifuyue), [@eleqtrizit](https://github.com/eleqtrizit), [@LiuwqGit](https://github.com/LiuwqGit), and [@HemantSudarshan](https://github.com/HemantSudarshan). - Control UI startup and first-reply latency are lower through cached model metadata, removal of the startup catalog wait, lazy slash-command loading, and first-event tracing with slow-reply diagnostics. ([#91531](openclaw/openclaw#91531), [#91538](openclaw/openclaw#91538), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583), [#91598](openclaw/openclaw#91598)) - Provider support expands with OpenRouter OAuth onboarding and Claude Fable 5 adaptive thinking, while Codex sessions keep correct compaction ownership, local models skip guardian review, dynamic tool progress normalizes cleanly, and Gemma 4 reasoning replay is preserved. ([#91830](openclaw/openclaw#91830), [#91882](openclaw/openclaw#91882), [#91590](openclaw/openclaw#91590), [#88630](openclaw/openclaw#88630), [#88768](openclaw/openclaw#88768), [#91696](openclaw/openclaw#91696)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@joshavant](https://github.com/joshavant), [@bdjben](https://github.com/bdjben), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). ##### Changes - CLI progress: emit Claude CLI commentary progress events and bridge inter-tool commentary into channel progress without exposing internal protocol scaffolding. ([#89834](openclaw/openclaw#89834), [#90883](openclaw/openclaw#90883)) Thanks [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia). - Observability: allow trusted diagnostics channels to capture tool input/output content, add first-assistant-event traces, and warn on slow initial replies. ([#91256](openclaw/openclaw#91256), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583)) Thanks [@amknight](https://github.com/amknight). - Plugins/ClawHub: dogfood reusable package publishing, let dry runs skip publish approval, allow declared installed trusted hooks, report managed plugin version drift, and warn instead of failing on retired Skill Workshop configuration. ([#91574](openclaw/openclaw#91574), [#91591](openclaw/openclaw#91591), [#90004](openclaw/openclaw#90004), [#90927](openclaw/openclaw#90927), [#90838](openclaw/openclaw#90838)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@brokemac79](https://github.com/brokemac79), and [@lonexreb](https://github.com/lonexreb). - Memory/providers: move the local llama.cpp runtime into its provider plugin, batch embeddings across files, persist the agent model catalog cache, and keep QMD JSON search one-shot while filtering stale REM recall previews. ([#91324](openclaw/openclaw#91324), [#89138](openclaw/openclaw#89138), [#90457](openclaw/openclaw#90457), [#91837](openclaw/openclaw#91837), [#91851](openclaw/openclaw#91851)) Thanks [@osolmaz](https://github.com/osolmaz), [@mushuiyu886](https://github.com/mushuiyu886), [@ai-hpc](https://github.com/ai-hpc), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Channels/mobile: add the QQBot group mention toggle, improve iPad and iPhone control surfaces, and expose the active connection host in the TUI footer. ([#91423](openclaw/openclaw#91423), [#91557](openclaw/openclaw#91557), [#89909](openclaw/openclaw#89909)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh), [@Solvely-Colin](https://github.com/Solvely-Colin), and [@baskduf](https://github.com/baskduf). - Performance: prewarm TUI runtime plugins, deduplicate plugin auto-enable fanout, trim dense text-delta snapshots, and reuse prepared startup model metadata. ([#90782](openclaw/openclaw#90782), [#89978](openclaw/openclaw#89978), [#91580](openclaw/openclaw#91580), [#91531](openclaw/openclaw#91531)) Thanks [@RomneyDa](https://github.com/RomneyDa) and [@ai-hpc](https://github.com/ai-hpc). ##### Fixes - Agent/session recovery: drop stale approval follow-ups after session rebind, remove drained reply-queue items by identity, recover stale main and visible replies, preserve Codex context-engine compaction ownership, lower the default compaction timeout to 180 seconds while respecting explicit configuration, and keep provider-failure terminal lifecycle state correct. ([#85679](openclaw/openclaw#85679), [#91450](openclaw/openclaw#91450), [#91566](openclaw/openclaw#91566), [#91840](openclaw/openclaw#91840), [#91590](openclaw/openclaw#91590), [#91361](openclaw/openclaw#91361), [#91895](openclaw/openclaw#91895)) Thanks [@openperf](https://github.com/openperf), [@yetval](https://github.com/yetval), [@joshavant](https://github.com/joshavant), [@wangmiao0668000666](https://github.com/wangmiao0668000666), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - User-visible content boundaries: suppress Codex/Harmony protocol artifacts, neutralize browser and LanceDB memory media directives, redact transcript images, and preserve native `/compact` replies through source suppression. ([#89151](openclaw/openclaw#89151), [#91422](openclaw/openclaw#91422), [#91425](openclaw/openclaw#91425), [#91529](openclaw/openclaw#91529), [#90212](openclaw/openclaw#90212)) Thanks [@joelnishanth](https://github.com/joelnishanth), [@pgondhi987](https://github.com/pgondhi987), [@joshavant](https://github.com/joshavant), and [@snowzlm](https://github.com/snowzlm). - Channel delivery: keep WhatsApp captured replies attached to the successor controller after restart, retry Feishu rate limits, preserve Mattermost thread replies, canonicalize LINE webhook paths, restore Discord reply hydration and runtime timeout exports, and show OpenAI Realtime WebRTC assistant transcripts. ([#85823](openclaw/openclaw#85823), [#89659](openclaw/openclaw#89659), [#91684](openclaw/openclaw#91684), [#91649](openclaw/openclaw#91649), [#90263](openclaw/openclaw#90263), [#91686](openclaw/openclaw#91686), [#90426](openclaw/openclaw#90426)) Thanks [@itsuzef](https://github.com/itsuzef), [@ladygege](https://github.com/ladygege), [@jacobtomlinson](https://github.com/jacobtomlinson), [@fuller-stack-dev](https://github.com/fuller-stack-dev), and [@shushushv](https://github.com/shushushv). - Cron: cancel active task runs cleanly, preserve terminal timeout/cancel state, and recover no-deliver tool warnings instead of silently losing the outcome. ([#90666](openclaw/openclaw#90666), [#90678](openclaw/openclaw#90678)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway/config/auth: share the approval runtime socket token, replace arrays explicitly in `config.patch`, skip the deleted-agent guard only for valid ACP harness sessions, surface headless LaunchAgent state, verify SQLite auth migration before cleanup, and arm QMD startup maintenance. ([#87105](openclaw/openclaw#87105), [#91551](openclaw/openclaw#91551), [#91219](openclaw/openclaw#91219), [#91614](openclaw/openclaw#91614), [#91740](openclaw/openclaw#91740), [#91978](openclaw/openclaw#91978)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev) and [@scotthuang](https://github.com/scotthuang). - Providers/Codex: clarify quota errors, restore the Codex synthetic usage line, canonicalize Codex protocol assets, require API-key auth for realtime voice, normalize ACP model refs, preserve Gemma 4 `reasoning_content`, and avoid guardian review for local models. ([#91390](openclaw/openclaw#91390), [#91709](openclaw/openclaw#91709), [#91507](openclaw/openclaw#91507), [#91567](openclaw/openclaw#91567), [#88630](openclaw/openclaw#88630), [#91696](openclaw/openclaw#91696)) Thanks [@hxy91819](https://github.com/hxy91819), [@brokemac79](https://github.com/brokemac79), [@RomneyDa](https://github.com/RomneyDa), [@joshavant](https://github.com/joshavant), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). - Updates/builds: recover package Gateway restarts after refresh failure, expose plugin convergence repair, fall back to Corepack in PATH-less pnpm environments, seed the correct Docker store packages, and keep ClawHub dry-run and publish paths reusable. ([#91581](openclaw/openclaw#91581), [#91599](openclaw/openclaw#91599), [#91547](openclaw/openclaw#91547), [#91591](openclaw/openclaw#91591)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@sallyom](https://github.com/sallyom), and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#91480](openclaw/openclaw#91480)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#80082](openclaw/openclaw#80082)) Thanks [@davelutztx](https://github.com/davelutztx). - Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#91550](openclaw/openclaw#91550)) Thanks [@joshavant](https://github.com/joshavant). </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/1040

fix(status): restore Codex synthetic usage line

80adac0

openclaw-barnacle Bot added extensions: codex size: L triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 9, 2026

clawsweeper Bot had a problem deploying to qa-live-shared June 9, 2026 13:41 Failure

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 9, 2026

clawsweeper Bot added the merge-risk: 🚨 auth-provider 🚨 May break OAuth, tokens, provider routing, model choice, or credentials. label Jun 9, 2026

fix(codex): keep usage parser plugin-local

ad5614c

openclaw-barnacle Bot added size: M and removed size: L labels Jun 9, 2026

fix(codex): restore status usage windows

5a0bdc4

brokemac79 marked this pull request as ready for review June 9, 2026 15:12

chore: retrigger CI

d670f9c

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 9, 2026

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 9, 2026

test: type synthetic auth mocks

8b15799

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 9, 2026

vincentkoc self-assigned this Jun 9, 2026

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 9, 2026

vincentkoc added 9 commits June 10, 2026 00:51

fix(codex): use configured app-server for usage

c38b079

fix(status): keep Codex usage auth scoped

ec7ca0e

fix(status): preserve Codex usage profile

ded4b0b

fix(codex): preserve weekly usage cadence

7c0ccf7

fix(codex): label app-server credits

875feca

fix(status): guard Codex usage profile

679ae0e

fix(status): validate Codex usage profile

399cfe8

fix(status): skip Codex API-key usage probes

8bf9771

fix(status): preserve legacy Codex usage profiles

d71b028

openclaw-barnacle Bot added size: L and removed size: M labels Jun 9, 2026

vincentkoc merged commit 1893a07 into openclaw:main Jun 9, 2026
43 of 45 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(status): restore Codex synthetic usage line#91709

fix(status): restore Codex synthetic usage line#91709
vincentkoc merged 14 commits into
openclaw:mainfrom
brokemac79:fix/issue-91694-codex-usage-status

brokemac79 commented Jun 9, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

Uh oh!

vincentkoc commented Jun 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

brokemac79 commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Linked context

Real behavior proof (required for external PRs)

Tests and validation

Risk checklist

Current review state

Uh oh!

clawsweeper Bot commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

brokemac79 commented Jun 9, 2026

Uh oh!

clawsweeper Bot commented Jun 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

vincentkoc commented Jun 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

brokemac79 commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading

clawsweeper Bot commented Jun 9, 2026 •

edited

Loading