fix(codex): normalize dynamic tool progress results by bdjben · Pull Request #88768 · openclaw/openclaw

bdjben · 2026-05-31T20:04:33Z

Summary

normalize Codex dynamic tool progress results into TUI-compatible content arrays
keep the existing tool start/result event path, but strip app-server protocol-only contentItems/success from verbose transcript payloads
add regression coverage for dynamic tool start/result events

Testing

pnpm exec vitest run extensions/codex/src/app-server/run-attempt.test.ts

Real behavior proof

Behavior or issue addressed: In the Codex TUI, verbose full mode could receive dynamic tool progress but did not get result details in the standard tool-result shape the transcript renderer expects. This made verbose output collapse toward bare tool labels instead of useful tool content.
Real environment tested: Local OpenClaw install on macOS with the Codex app-server runtime and TUI in verbose full mode.
Exact steps or command run after this patch: Started the local OpenClaw TUI, switched to verbose full, and sent a Codex job that invoked runtime tools including shell/Python-style work.
Evidence after fix:

Manual local TUI observation: verbose tool transcript updated live during the Codex job instead of staying at bare tool labels.
User-facing live validation from the same local setup: "verbose output now does appear and update (good)"

Observed result after fix: Tool progress now appears and updates during the active Codex run, and result payloads are emitted as content: [{ type: "text", text: ... }], which is the TUI-compatible shape.
What was not tested: This PR deliberately does not include or claim to fix /steer; steer behavior is still being investigated separately.
Proof: See below screenshot of "/verbose full" working again after implementing this fix (and below it an image of "/verbose full" not working before the fix; the "not working" image shows very basic verbose mode blocks (perhaps of the kind that should show in the more simplified "/verbose on" mode), and even then, those blocks would not show up until manually submitting repeated "/verbose" commands:
After:

- Before:

Note: this PR intentionally does not include any TUI /steer changes.

clawsweeper · 2026-05-31T20:11:32Z

Codex review: needs maintainer review before merge. Reviewed June 8, 2026, 10:54 AM ET / 14:54 UTC.

Summary
The PR changes Codex app-server dynamic tool progress result events to emit sanitized TUI-compatible content arrays, strip protocol-only contentItems and success from that event payload, and add regression coverage.

PR surface: Source +38, Tests +102. Total +140 across 3 files.

Reproducibility: yes. Current main sends dynamic tool progress results with contentItems and success, while the TUI and ACP paths extract visible output from result.content; the supplied screenshot shows the fixed TUI path rendering tool output.

Review metrics: none identified.

Merge readiness
Overall: 🦞 diamond lobster
Proof: 🦞 diamond lobster ✨ media proof bonus
Patch quality: 🦞 diamond lobster
Result: ready for maintainer review.

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

Risk before merge

[P1] The author noted a separate verbose-mode refresh case where new user messages can still require toggling verbose modes; this PR should be treated as the dynamic-tool-result normalization, not a full verbose-mode follow-up.

Maintainer options:

Decide the mitigation before merge
Merge the normalized app-server event shape after normal maintainer and CI handling, and track the remaining verbose refresh behavior separately if it still reproduces.
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 the reviewed diff has no discrete automated blocker; the next action is ordinary maintainer and CI handling.

Security
Cleared: The diff only changes Codex runtime event normalization and tests, keeps protocol output sanitized before transcript emission, and does not touch dependencies, workflows, scripts, credentials, or package metadata.

Review details

Best possible solution:

Merge the normalized app-server event shape after normal maintainer and CI handling, and track the remaining verbose refresh behavior separately if it still reproduces.

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

Yes. Current main sends dynamic tool progress results with contentItems and success, while the TUI and ACP paths extract visible output from result.content; the supplied screenshot shows the fixed TUI path rendering tool output.

Is this the best way to solve the issue?

Yes. Normalizing once at the Codex app-server event boundary after sanitization is the narrowest maintainable fix; teaching generic TUI/ACP consumers about Codex contentItems would leak a Codex protocol shape into broader event consumers.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against e3ef136bca85.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body provides a real macOS OpenClaw TUI verbose-full run, and the inspected screenshot directly shows rendered tool output after the fix.
add rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
remove rating: 🐚 platinum hermit: Current PR rating is rating: 🦞 diamond lobster, so this older rating label is no longer current.

Label justifications:

P2: This is a focused fix for a Codex verbose TUI regression with limited blast radius and no emergency data-loss, security, or availability signal.
rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (screenshot): The PR body provides a real macOS OpenClaw TUI verbose-full run, and the inspected screenshot directly shows rendered tool output after the fix.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body provides a real macOS OpenClaw TUI verbose-full run, and the inspected screenshot directly shows rendered tool output after the fix.
proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. The PR body provides a real macOS OpenClaw TUI verbose-full run, and the inspected screenshot directly shows rendered tool output after the fix.

Evidence reviewed

PR surface:

Source +38, Tests +102. Total +140 across 3 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	39	1	+38
Tests	2	104	2	+102
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	3	143	3	+140

What I checked:

Repository policy applied: Read the full root AGENTS.md and the scoped extensions/AGENTS.md; the Codex upstream-source gate and bundled extension boundary shaped this review. (AGENTS.md:10, e3ef136bca85)
Current main still has the mismatch: Current main emits result: sanitizeCodexToolResponse(progressResponse) for dynamic tool progress, which preserves Codex protocol fields instead of producing the TUI result-content shape. (extensions/codex/src/app-server/run-attempt.ts:1720, e3ef136bca85)
TUI expects result.content: The TUI forwards data.result to the tool renderer, and the renderer only extracts visible output from result.content; a protocol-only contentItems payload renders as empty output. (src/tui/components/tool-execution.ts:42, e3ef136bca85)
PR normalizes at the Codex event boundary: The PR sanitizes the dynamic tool response, maps sanitized contentItems into content, deletes contentItems and success, and emits that normalized result for progress events. (extensions/codex/src/app-server/run-attempt.ts:312, 0f291319fd96)
Regression coverage checks the event contract: The added tests verify dynamic tool result events contain content, omit contentItems and success, and keep sanitized secret text out of emitted events. (extensions/codex/src/app-server/run-attempt.test.ts:1165, 0f291319fd96)
Upstream Codex contract checked: The sibling Codex source defines dynamic tool responses as contentItems plus success, and inputText/inputImage are the supported output item variants. (../codex/codex-rs/app-server-protocol/schema/typescript/v2/DynamicToolCallResponse.ts:6, 0526cb56ac35)

Likely related people:

steipete: Git history shows Peter Steinberger introduced and repeatedly hardened the Codex app-server control/lifecycle path that now emits these dynamic tool events. (role: introduced Codex app-server area; confidence: high; commits: 31a0b7bd42a5, 3b65e2302a55, 659bcc5e5b59; files: extensions/codex/src/app-server/run-attempt.ts)
vincentkoc: Recent history on the same Codex app-server file includes auth/runtime refactors by Vincent Koc shortly before this change. (role: recent Codex app-server contributor; confidence: medium; commits: f1cc8f0cfc7c, 859eb0666282; files: extensions/codex/src/app-server/run-attempt.ts)
Vignesh Natarajan: Recent TUI history includes multiple fixes around active-run routing, final output handling, and session-key aliases, which are adjacent to the verbose tool-event consumer path. (role: TUI event routing contributor; confidence: medium; commits: 61a0b0293104, 726ef48c2ac8, 9f2cb3b58212; files: src/tui/tui-event-handlers.ts)
Jason (Json): Current-main blame on the dynamic tool progress emission and TUI tool-event lines points to a broad recent commit by Jason, so they are a useful routing candidate even though the commit covered many areas. (role: recent area contributor; confidence: medium; commits: 57e0bdaabe0a; files: extensions/codex/src/app-server/run-attempt.ts, src/tui/tui-event-handlers.ts, src/tui/components/tool-execution.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.

bdjben · 2026-05-31T21:12:34Z

Note: this largely fixes the verbose mode issue, but not fully. At times, a new user message sent in the TUI does not show its verbose mode content until the user toggles verbose modes once or twice.

byungskers · 2026-05-31T23:03:00Z

This normalization looks like the right fix for the TUI contract mismatch. One thing I'm unsure about: toTranscriptToolResultContentItem() currently falls back to { type: "text", text: "" } for any non-inputText / non-imageUrl item. That keeps the shape TUI-friendly, but it also silently drops any future Codex output variant. Would it be worth either preserving an explicit placeholder / metadata marker, or constraining this helper to the known output union so new upstream item types fail loudly in tests instead of degrading to an empty text block?

bdjben · 2026-06-01T01:08:59Z

Hmm. I'm not sure that any non-text codex output would be tui compliant anyway. The fail loudly vs quietly is worth noting, but I think getting verbose mode back up and running as is is critical; the rest can wait for another day. But something to think about!

bdjben · 2026-06-05T00:10:22Z

@clawsweeper re-run

clawsweeper · 2026-06-05T00:10:24Z

🦞🧹
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/26987288739
Updated: 2026-06-05T00:18:40.937Z

bdjben · 2026-06-07T17:40:36Z

@clawsweeper re-review

Updated in f33d0f1.

What changed:

toTranscriptToolResult now maps transcript content from the sanitizeCodexToolResponse output, not raw contentItems.
Tool progress result payloads stay TUI-compatible as content[] while omitting protocol-only success/contentItems.
Added regression coverage for redacted dynamic tool output text and the full app-server progress event contract.

Local verification:

node scripts/run-vitest.mjs run extensions/codex/src/app-server/run-attempt.dynamic-tools.test.ts
node scripts/run-vitest.mjs run extensions/codex/src/app-server/run-attempt.test.ts
node scripts/run-vitest.mjs run src/tui/tui-event-handlers.test.ts
node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.extensions.json extensions/codex/src/app-server/run-attempt.ts extensions/codex/src/app-server/run-attempt.dynamic-tools.test.ts extensions/codex/src/app-server/run-attempt.test.ts
pnpm tsgo:extensions:test

clawsweeper · 2026-06-07T17:40:38Z

🦞🧹
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/27099964120
Updated: 2026-06-07T17:51:34.911Z

shakkernerd · 2026-06-08T15:16:23Z

Thanks @bdjben, merged this via squash.

This lands the Codex app-server normalization for dynamic tool progress results: emitted progress events now expose sanitized TUI-compatible result.content and omit protocol-only contentItems / success.

The remaining verbose-mode refresh/toggle behavior noted above looks separate from this event-shape fix and should be tracked separately if it still reproduces.

…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

openclaw-barnacle Bot added extensions: codex size: S triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 31, 2026

bdjben force-pushed the codex-harness-tool-events branch from 98519a7 to c002448 Compare May 31, 2026 20:16

bdjben changed the title ~~fix(codex): emit dynamic tool progress events~~ fix(codex): normalize dynamic tool progress results May 31, 2026

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 May 31, 2026

bdjben force-pushed the codex-harness-tool-events branch from c002448 to 1aa4ae3 Compare May 31, 2026 20:23

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 7, 2026

shakkernerd self-assigned this Jun 8, 2026

shakkernerd force-pushed the codex-harness-tool-events branch from f33d0f1 to 9309526 Compare June 8, 2026 14:00

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 8, 2026

shakkernerd force-pushed the codex-harness-tool-events branch from 9309526 to e8e65b1 Compare June 8, 2026 14:04

bdjben and others added 3 commits June 8, 2026 15:41

fix(codex): normalize dynamic tool progress results

627a3b4

fix(codex): redact normalized tool progress results

c9b732a

fix: handle unsupported Codex dynamic tool output

0f29131

shakkernerd force-pushed the codex-harness-tool-events branch from 61f7b15 to 0f29131 Compare June 8, 2026 14:42

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 8, 2026

shakkernerd merged commit 60d716e into openclaw:main Jun 8, 2026
291 of 294 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(codex): normalize dynamic tool progress results#88768

fix(codex): normalize dynamic tool progress results#88768
shakkernerd merged 3 commits into
openclaw:mainfrom
bdjben:codex-harness-tool-events

bdjben commented May 31, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 31, 2026 •

edited

Loading

Uh oh!

bdjben commented May 31, 2026

Uh oh!

byungskers commented May 31, 2026

Uh oh!

bdjben commented Jun 1, 2026

Uh oh!

bdjben commented Jun 5, 2026

Uh oh!

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading

Uh oh!

bdjben commented Jun 7, 2026

Uh oh!

clawsweeper Bot commented Jun 7, 2026 •

edited

Loading

Uh oh!

Uh oh!

shakkernerd commented Jun 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

bdjben commented May 31, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Testing

Real behavior proof

Uh oh!

clawsweeper Bot commented May 31, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

bdjben commented May 31, 2026

Uh oh!

byungskers commented May 31, 2026

Uh oh!

bdjben commented Jun 1, 2026

Uh oh!

bdjben commented Jun 5, 2026

Uh oh!

clawsweeper Bot commented Jun 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

bdjben commented Jun 7, 2026

Uh oh!

clawsweeper Bot commented Jun 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

shakkernerd commented Jun 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

bdjben commented May 31, 2026 •

edited

Loading

clawsweeper Bot commented May 31, 2026 •

edited

Loading

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading

clawsweeper Bot commented Jun 7, 2026 •

edited

Loading