fix(talk): show OpenAI Realtime WebRTC assistant transcripts by shushushv · Pull Request #90426 · openclaw/openclaw

shushushv · 2026-06-04T17:20:06Z

Summary

handle current OpenAI Realtime WebRTC assistant transcript events (response.output_audio_transcript.delta/done)
keep compatibility with legacy response.audio_transcript.* and text output events
avoid duplicate assistant bubbles when a final transcript arrives shortly after streamed deltas — fixed in the shared conversation aggregation, so the gateway-relay path benefits too

Background

In browser OpenAI Realtime WebRTC sessions, user ASR was visible, but assistant text was missing while assistant audio still played. The direct WebRTC data channel receives current OpenAI transcript events such as response.output_audio_transcript.delta and response.output_audio_transcript.done, but the WebRTC transport only handled the legacy response.audio_transcript.done event.

The gateway relay path already handles both old and current event names, so this aligns the direct WebRTC path with gateway relay behavior.

The duplicate-bubble dedup lives in the shared conversation aggregation (ui/src/ui/app.ts onTranscript -> updateRealtimeTalkConversation), which both transports feed. The gateway-relay path already streamed delta+done, so it shared the same latent duplicate-bubble issue; fixing it at the shared layer addresses both transports rather than patching only WebRTC.

Verification

pnpm test ui/src/ui/chat/realtime-talk-conversation.test.ts ui/src/ui/realtime-talk-webrtc.test.ts — conversation 13 + webrtc 7 tests pass
pnpm tsgo:test:ui — passes
pnpm ui:build — passes
oxlint / oxfmt on touched files — clean

Real behavior proof

Behavior addressed: OpenAI Realtime direct WebRTC Talk in the Control UI now renders assistant transcript text (streamed deltas + final), and a final transcript arriving shortly after deltas no longer produces a duplicate assistant bubble.

Real environment tested: macOS, Google Chrome, Control UI Chat Talk over the OpenAI Realtime direct webrtc transport, model gpt-realtime-2.

Exact steps or command run after this patch:

Build this branch and start the gateway (pnpm ui:build, then run the gateway), open Control UI Chat in Chrome on macOS.
Start a Talk live session using OpenAI Realtime over the direct webrtc transport.
Speak short prompts, e.g. Hallo. then Which model are you used to converse with me?.

Evidence after fix: before/after screenshots below. Before: only the user ("You") bubbles appear; the assistant speaks but no assistant text is rendered. After: assistant ("C3-PO") transcript bubbles appear — Hey there! How's it going? and I'm ChatGPT, a voice-capable AI model made by OpenAI..

Observed result after fix: assistant transcript text renders alongside the audio for each turn, with no duplicate assistant bubbles observed across multiple turns.

What was not tested: gateway-relay transport was not re-verified live in this PR (the shared dedup change is covered by unit tests and reasoned from app.ts:1242 feeding both transports); Gemini Live path is unaffected and untested.

clawsweeper · 2026-06-04T17:26:45Z

Codex review: needs maintainer review before merge. Reviewed June 7, 2026, 9:11 AM ET / 13:11 UTC.

Summary
The PR updates Control UI direct OpenAI Realtime WebRTC event parsing for assistant transcript delta/done events and adds shared conversation dedup coverage for late final assistant transcripts.

PR surface: Source +74, Tests +135. Total +209 across 4 files.

Reproducibility: yes. Current main's direct WebRTC handler only handles the legacy assistant transcript completion event, while OpenAI's current event contract and the supplied before/after screenshots show the missing assistant transcript path for direct WebRTC.

Review metrics: 1 noteworthy metric.

Transport Proof Coverage: 1 live direct WebRTC path, 1 source/unit-only gateway-relay path. The diff fixes direct WebRTC parsing and shared aggregation, so maintainers should notice that only one of the affected visible transport paths has live proof.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster ✨ media proof bonus
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:

Let the latest head complete normal CI and merge checks.
Optionally run or request one live gateway-relay Talk smoke if maintainers want transport-specific proof for the shared dedup path.

Risk before merge

[P1] The shared conversation aggregation change is unit/source-covered but not live-smoked through gateway relay, so a relay-specific duplicate or suppressed visible assistant bubble would be caught by maintainer proof rather than the supplied direct WebRTC screenshot.

Maintainer options:

Accept The Shared-Updater Proof
Maintainers can land with the direct WebRTC screenshot proof and focused unit/source coverage because both transports feed the same onTranscript updater.
Ask For A Relay Smoke
Request one live gateway-relay Talk run that streams assistant deltas plus a final transcript to prove the shared dedup does not suppress or duplicate relay bubbles.

Next step before merge

[P2] Maintainer review should decide whether the current direct WebRTC proof plus shared unit/source coverage is enough, or whether to require one live gateway-relay smoke before merge.

Security
Cleared: No concrete security or supply-chain concern found; the diff only changes browser data-channel event parsing, shared UI aggregation, and focused tests.

Review details

Best possible solution:

Merge after normal CI and maintainer review if maintainers accept direct WebRTC screenshot proof plus shared/unit evidence, or request one live gateway-relay Talk smoke before landing.

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

Yes. Current main's direct WebRTC handler only handles the legacy assistant transcript completion event, while OpenAI's current event contract and the supplied before/after screenshots show the missing assistant transcript path for direct WebRTC.

Is this the best way to solve the issue?

Yes. The branch handles the current event names at the direct WebRTC boundary and keeps late-final dedup in the shared conversation updater, which is cleaner than adding a transport-specific duplicate-bubble workaround.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 66b91d78feb3.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix real behavior proof with before/after Chrome Control UI screenshots showing assistant text absent before and present after the direct OpenAI Realtime WebRTC patch.

Label justifications:

P2: This is a normal-priority Control UI Talk bugfix for missing assistant transcript text in direct OpenAI Realtime WebRTC sessions.
merge-risk: 🚨 message-delivery: The PR changes shared transcript aggregation used by multiple Talk transports, so a merge regression could duplicate or suppress visible assistant transcript bubbles.
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 (screenshot): The PR body includes after-fix real behavior proof with before/after Chrome Control UI screenshots showing assistant text absent before and present after the direct OpenAI Realtime WebRTC patch.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix real behavior proof with before/after Chrome Control UI screenshots showing assistant text absent before and present after the direct OpenAI Realtime WebRTC patch.
proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. The PR body includes after-fix real behavior proof with before/after Chrome Control UI screenshots showing assistant text absent before and present after the direct OpenAI Realtime WebRTC patch.

Evidence reviewed

PR surface:

Source +74, Tests +135. Total +209 across 4 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	90	16	+74
Tests	2	135	0	+135
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	4	225	16	+209

What I checked:

Repository policy read: Read the root and scoped UI policy; the root review policy affected this review by requiring caller/sibling/dependency-contract proof, while ui/AGENTS.md had no conflicting guidance for these files. (AGENTS.md:1, 66b91d78feb3)
Current main misses the direct WebRTC event names: Current main's direct WebRTC handler emits assistant text only for legacy response.audio_transcript.done, so response.output_audio_transcript.delta/done does not reach the Control UI transcript path. (ui/src/ui/chat/realtime-talk-webrtc.ts:174, 66b91d78feb3)
OpenAI Realtime contract checked: OpenAI's current Realtime reference documents response.output_audio_transcript.delta with a delta field, response.output_audio_transcript.done with a transcript field, and response.output_text.done with a text field, matching the fields read by the PR. (platform.openai.com)
Branch maps current and legacy assistant transcript events: The PR branch handles current audio/text transcript delta and done events plus the legacy response.audio_transcript.* names, then normalizes them into onTranscript and Talk output.text.* events. (ui/src/ui/chat/realtime-talk-webrtc.ts:172, 05bb2b3a51ac)
Shared aggregation is the right boundary: Control UI feeds every Talk transport callback through updateRealtimeTalkConversation, so deduping late assistant finals in the shared helper covers direct WebRTC and gateway relay without transport-specific display logic. (ui/src/ui/app.ts:1243, 66b91d78feb3)
Gateway relay sibling shares the updater path: Gateway relay emits transcript events through the same onTranscript callback shape, so the shared dedup change can affect relay-visible bubbles even though the contributor only live-smoked direct WebRTC. (ui/src/ui/chat/realtime-talk-gateway-relay.ts:183, 66b91d78feb3)

Likely related people:

steipete: Recent GitHub path history for the Control UI WebRTC/conversation files and OpenAI realtime provider shows repeated Talk and OpenAI realtime work by this author. (role: recent area contributor and likely follow-up owner; confidence: high; commits: 12a56d4d46dd, 13c0b1952e8f, 96e581242605; files: ui/src/ui/chat/realtime-talk-webrtc.ts, ui/src/ui/chat/realtime-talk-conversation.ts, extensions/openai/realtime-voice-provider.ts)
VACInc: The conversation helper history includes prior stabilization work for realtime Talk playback, transcript ordering, and gateway relay behavior. (role: adjacent feature contributor; confidence: medium; commits: 683ad75b3191; files: ui/src/ui/chat/realtime-talk-conversation.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.

Handle current OpenAI Realtime assistant transcript events on the direct WebRTC transport (response.output_audio_transcript.delta/done, response.output_text.*), keep legacy response.audio_transcript.* compatibility, and dedup duplicate assistant bubbles in the shared conversation aggregation so both webrtc and gateway-relay benefit. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

vincentkoc · 2026-06-10T16:16:17Z

Maintainer review and proof are complete.

Autoreview found that the original shared late-final similarity heuristic could rewrite an earlier assistant turn when a similar next-turn final arrived inside the grace window. I removed that heuristic and retained the scoped transport fix: current OpenAI Realtime text/audio transcript delta and done events now map into the existing transcript callback and talk-event surfaces.

Verification on head 4dc4bffd8e23b6951d02ba04104ee087c770bcda:

node scripts/run-vitest.mjs ui/src/ui/realtime-talk-webrtc.test.ts ui/src/ui/chat/realtime-talk-conversation.test.ts — 20 tests passed after rebase
.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main ... — clean; no accepted/actionable findings
current OpenAI Realtime event field contracts were checked against the event families represented by the transport (delta, text, and transcript)

Known gap: no fresh live WebRTC call was run on this host; the PR's supplied screenshot proof and focused transport tests cover the changed event mapping.

…w#90426) * fix(talk): show OpenAI Realtime WebRTC assistant transcripts Handle current OpenAI Realtime assistant transcript events on the direct WebRTC transport (response.output_audio_transcript.delta/done, response.output_text.*), keep legacy response.audio_transcript.* compatibility, and dedup duplicate assistant bubbles in the shared conversation aggregation so both webrtc and gateway-relay benefit. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(talk): drop unsafe transcript rewrite heuristic --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org>

…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

shushushv force-pushed the codex/fix-openai-realtime-webrtc-transcripts branch from ecc8097 to 9123c35 Compare June 5, 2026 02:56

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 5, 2026

clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. merge-risk: 🚨 message-delivery 🚨 May drop, duplicate, misroute, suppress, or wrongly target messages. labels Jun 5, 2026

shushushv force-pushed the codex/fix-openai-realtime-webrtc-transcripts branch from 9123c35 to 89c931d Compare June 5, 2026 06:49

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 5, 2026

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

shushushv force-pushed the codex/fix-openai-realtime-webrtc-transcripts branch from 89c931d to 05bb2b3 Compare June 7, 2026 13:04

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

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 7, 2026

vincentkoc self-assigned this Jun 10, 2026

shushushv and others added 2 commits June 11, 2026 01:16

fix(talk): drop unsafe transcript rewrite heuristic

4dc4bff

vincentkoc force-pushed the codex/fix-openai-realtime-webrtc-transcripts branch from 05bb2b3 to 4dc4bff Compare June 10, 2026 16:16

vincentkoc merged commit 7926ace into openclaw:main Jun 10, 2026
10 of 12 checks passed

openclaw-barnacle Bot added size: S and removed size: M proof: sufficient ClawSweeper judged the real behavior proof convincing. labels Jun 10, 2026

github-actions Bot mentioned this pull request Jun 10, 2026

📡 Upstream Digest — 2026-06-10 16:54 UTC curtismercier/openclaw-mods#1053

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(talk): show OpenAI Realtime WebRTC assistant transcripts#90426

fix(talk): show OpenAI Realtime WebRTC assistant transcripts#90426
vincentkoc merged 2 commits into
openclaw:mainfrom
shushushv:codex/fix-openai-realtime-webrtc-transcripts

shushushv commented Jun 4, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading

Uh oh!

vincentkoc commented Jun 10, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

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

Uh oh!

Summary

Background

Verification

Real behavior proof

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!

vincentkoc commented Jun 10, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

shushushv commented Jun 4, 2026 •

edited

Loading

clawsweeper Bot commented Jun 4, 2026 •

edited

Loading