Skip to content

perf(tui): prewarm runtime plugins before first send#90782

Merged
RomneyDa merged 5 commits into
mainfrom
fix/tui-prewarm-runtime-plugins
Jun 9, 2026
Merged

perf(tui): prewarm runtime plugins before first send#90782
RomneyDa merged 5 commits into
mainfrom
fix/tui-prewarm-runtime-plugins

Conversation

@RomneyDa

@RomneyDa RomneyDa commented Jun 5, 2026 •
edited
Loading

Copy link
Copy Markdown
Member

Profile Evidence

Run CPU profile Startup ready Submit -> first model request startup.runtime-plugins on first submit First-turn embedded duration Request -> visible response
Before .artifacts/tui-local-cpu/full-surface-1780700761191/openclaw-tui-99042-2026-06-05T23-06-02-328Z.cpuprofile 4,494ms 12,683ms 5,164ms 10,824ms 17ms
After .artifacts/tui-local-cpu/full-surface-runtime-prewarm-1780701756700/openclaw-tui-98266-2026-06-05T23-22-43-120Z.cpuprofile 10,929ms 7,412ms 1ms 3,859ms 20ms

The local mocked Responses server still returned in ~20ms, so the user-visible freeze is before provider I/O. This patch moves the measured ensureRuntimePluginsLoaded cold activation out of the first submit path and into the embedded TUI history readiness path.

Summary

  • Warm embedded local runtime plugins inside EmbeddedTuiBackend.loadHistory() using the same resolved agent workspace as the local send path.
  • Keep the TUI backend contract unchanged: no prewarmAgentRuntime hook, no public harness prewarm API, and no separate warming runtime submit state.
  • Return best-effort warmup status as part of the existing history response so TUI can show a system message if runtime warmup fails while still rendering history.
  • Leave gateway TUI behavior unchanged; this targets only local embedded TUI startup before first send.

Relationship to #86981

#86981 prewarms the selected plugin harness runtime and was stacked on the closed #86930 base hook. In this repro the selected harness is the built-in OpenClaw runtime, so that approach does not remove the measured ensureRuntimePluginsLoaded spike. This PR targets the measured local embedded TUI stage directly without adding another hook seam.

Verification

  • node scripts/run-vitest.mjs src/tui/embedded-backend.test.ts src/tui/tui-session-actions.test.ts src/tui/tui.test.ts src/tui/tui-command-handlers.test.ts
  • git diff --check origin/main...HEAD
  • .agents/skills/autoreview/scripts/autoreview --mode local
  • Profiled pnpm openclaw tui --local with an isolated config and mocked local Responses endpoint before and after the patch.

Notes

The previous check-lint failure on the pre-rebase head was unrelated to this PR; the reported files were src/agents/sandbox/registry.ts and src/agents/sandbox/registry.test.ts, while this PR only touches TUI files.

@openclaw-barnacle openclaw-barnacle Bot added size: S maintainer Maintainer-authored PR labels Jun 5, 2026
@clawsweeper

clawsweeper Bot commented Jun 5, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Codex review: needs maintainer review before merge. Reviewed June 9, 2026, 4:19 AM ET / 08:19 UTC.

Summary
The PR prewarms embedded local TUI runtime plugins during history loading, returns best-effort warmup status in the history payload, and shows a system message if prewarm fails.

PR surface: Source +32, Tests +49. Total +81 across 3 files.

Reproducibility: yes. for the code path, but not as a freshly rerun performance profile: current main lacks embedded history prewarm and the PR body provides before/after profile data. This read-only review did not rerun the local TUI profiling, and the current head changed after the profile evidence.

Review metrics: 1 noteworthy metric.

  • Profiled latency tradeoff: startup ready +6,435ms; first-turn embedded duration -6,965ms. The PR moves measured cold plugin work from first send into local TUI startup/history readiness, so maintainers should review the availability tradeoff before merge.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
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] Refresh the local TUI profile on the current head after the workspace-parity fix.
  • [P2] Have maintainers explicitly accept the slower history/startup readiness tradeoff before merge.

Risk before merge

  • [P1] The PR intentionally moves cold runtime-plugin activation into embedded history loading; the PR body reports startup ready increasing from 4,494ms to 10,929ms while first-turn embedded duration drops from 10,824ms to 3,859ms.
  • [P1] The final head includes a workspace-parity correction after the profile evidence, so maintainers should confirm the final startup-versus-first-send numbers before accepting the tradeoff.

Maintainer options:

  1. Refresh final-head profile before merge (recommended)
    Reprofile the current head after the workspace-parity fix so the measured startup and first-send latency tradeoff matches the code being merged.
  2. Accept the startup tradeoff
    Maintainers can intentionally accept slower local TUI history readiness if the first-send freeze reduction is the more important user-visible behavior.
  3. Pause for a sidecar warmup
    If startup readiness must remain fast, pause this branch and move the warmup into a cancellable post-ready sidecar instead of blocking history load.

Next step before merge

  • [P2] Protected maintainer ownership plus the startup-versus-first-send latency tradeoff make this a human review decision rather than an automated repair lane.

Security
Cleared: The diff only changes TUI runtime prewarm timing and focused tests; it does not add dependencies, workflows, package metadata, permissions, or new secret handling.

Review details

Best possible solution:

Land only after final-head local TUI proof confirms the moved cold load is worth the slower history/startup path; otherwise use a cancellable post-ready warmup that preserves fast readiness.

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

Yes for the code path, but not as a freshly rerun performance profile: current main lacks embedded history prewarm and the PR body provides before/after profile data. This read-only review did not rerun the local TUI profiling, and the current head changed after the profile evidence.

Is this the best way to solve the issue?

Acceptable but still a maintainer tradeoff: warming during embedded history is a narrow implementation that preserves the public backend contract, but it deliberately shifts latency into startup/history readiness. A cancellable post-ready warmup is the safer alternative if fast startup is the priority.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 257b251e2690.

Label changes

Label changes:

  • add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
  • add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The external-contributor proof gate does not apply to this MEMBER-authored maintainer PR, though the PR body includes local before/after profiling evidence.
  • remove rating: 🦐 gold shrimp: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
  • remove status: ⏳ waiting on author: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

  • P2: This is a bounded embedded TUI performance improvement with limited blast radius, but it affects a real first-send latency path.
  • merge-risk: 🚨 availability: Merging can make local embedded TUI startup/history readiness noticeably slower even while improving first-send latency.
  • rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
  • status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The external-contributor proof gate does not apply to this MEMBER-authored maintainer PR, though the PR body includes local before/after profiling evidence.
Evidence reviewed

PR surface:

Source +32, Tests +49. Total +81 across 3 files.

View PR surface stats
Area Files Added Removed Net
Source 2 33 1 +32
Tests 1 49 0 +49
Docs 0 0 0 0
Config 0 0 0 0
Generated 0 0 0 0
Other 0 0 0 0
Total 3 82 1 +81

What I checked:

  • Protected maintainer item: The live PR metadata reports authorAssociation MEMBER and the maintainer label, so ClawSweeper cleanup should not close it automatically even if the patch looks useful. (001be10a85e9)
  • Current main history path: Current main EmbeddedTuiBackend.loadHistory builds session/history/model data and returns without any runtime plugin prewarm result, so the PR is not already implemented on main. (src/tui/embedded-backend.ts:405, 257b251e2690)
  • Current send workspace contract: The local send path calls agentCommandFromIngress, whose execution falls back to resolveAgentWorkspaceDir(cfg, sessionAgentId) when no spawned workspace is explicitly passed. (src/agents/agent-command.ts:704, 257b251e2690)
  • PR prewarm implementation: The PR helper uses resolveAgentWorkspaceDir and ensureRuntimePluginsLoaded during embedded history loading, then returns runtimePluginsPrewarm in the existing history response. (src/tui/embedded-backend.ts:133, 001be10a85e9)
  • PR failure surfacing: The TUI session action layer reads runtimePluginsPrewarm and adds a system message only when best-effort prewarm fails, while still completing history load. (src/tui/tui-session-actions.ts:426, 001be10a85e9)
  • CI status at current head: GitHub check runs for the current head showed 166 checks total with no failure, timed_out, cancelled, or action_required conclusions across the paginated check-run data inspected. (001be10a85e9)

Likely related people:

  • vincentkoc: Recent git history touches the TUI embedded/session-action surface, and the related closed prewarm PRs in the provided context were authored by this handle. (role: recent TUI prewarm contributor; confidence: high; commits: 2e08f0f4221f, 45fff13b1d60; files: src/tui/embedded-backend.ts, src/tui/tui-session-actions.ts)
  • Peter Steinberger: History shows repeated TUI/session-action work plus the runtime-plugin bootstrap commit that underpins the cold-load path this PR moves earlier. (role: adjacent TUI and runtime-plugin contributor; confidence: high; commits: 661af2acd394, 768e606f96c5, 32ebaa37574e; files: src/agents/runtime-plugins.ts, src/tui/tui-session-actions.ts)
  • Gustavo Madeira Santana: Runtime plugin history includes shared registry resolution and compatibility helper commits that are directly exercised by ensureRuntimePluginsLoaded. (role: runtime registry contributor; confidence: medium; commits: ee7f5825c85e, fd0aac297c96; files: src/agents/runtime-plugins.ts, src/plugins/runtime/standalone-runtime-registry-loader.ts)
What the crustacean ranks mean
  • 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
  • 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
  • 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
  • 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
  • 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
  • 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
  • 🌊 off-meta tidepool: rating does not apply to this item.

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

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

@clawsweeper clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. P2 Normal backlog priority with limited blast radius. merge-risk: 🚨 availability 🚨 May cause crashes, hangs, restart loops, stalls, or process outages. labels Jun 5, 2026
@RomneyDa RomneyDa force-pushed the fix/tui-prewarm-runtime-plugins branch from b9ab416 to f191785 Compare June 7, 2026 01:41
@blacksmith-sh

This comment has been minimized.

Sign in to view
@RomneyDa RomneyDa force-pushed the fix/tui-prewarm-runtime-plugins branch from f191785 to 0ee14da Compare June 7, 2026 06:16
@RomneyDa RomneyDa mentioned this pull request Jun 7, 2026
Merged
@RomneyDa RomneyDa force-pushed the fix/tui-prewarm-runtime-plugins branch from 0ee14da to 1de8e4c Compare June 7, 2026 06:41
@clawsweeper clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. and removed proof: sufficient ClawSweeper judged the real behavior proof convincing. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. labels Jun 7, 2026
@RomneyDa RomneyDa force-pushed the fix/tui-prewarm-runtime-plugins branch from d46dc69 to 7e3ca01 Compare June 9, 2026 02:50
@clawsweeper clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. and removed rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. labels Jun 9, 2026
@RomneyDa RomneyDa mentioned this pull request Jun 9, 2026
Closed
@clawsweeper clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. and removed rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. labels Jun 9, 2026
@RomneyDa RomneyDa merged commit 8b84e95 into main Jun 9, 2026
184 of 188 checks passed
@RomneyDa RomneyDa deleted the fix/tui-prewarm-runtime-plugins branch June 9, 2026 18:30
@github-actions github-actions Bot mentioned this pull request Jun 9, 2026
Open
github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request Jun 10, 2026
@RomneyDa
perf(tui): prewarm runtime plugins before first send (openclaw#90782)
6bf0d5f 
* perf: prewarm TUI runtime plugins before first send

* fix: satisfy TUI prewarm lint

* fix(tui): clarify runtime warmup submit block

* refactor(tui): warm embedded runtime during history load

* fix(tui): align runtime prewarm workspace
eleboucher pushed a commit to eleboucher/homelab that referenced this pull request Jun 12, 2026
@eleboucher
fix(container): update image ghcr.io/openclaw/openclaw (2026.6.5 ➔ 20…
bb872cc 
…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. ([#&#8203;91529](openclaw/openclaw#91529), [#&#8203;91618](openclaw/openclaw#91618), [#&#8203;91615](openclaw/openclaw#91615), [#&#8203;91619](openclaw/openclaw#91619), [#&#8203;91741](openclaw/openclaw#91741), [#&#8203;91745](openclaw/openclaw#91745), [#&#8203;91746](openclaw/openclaw#91746), [#&#8203;91748](openclaw/openclaw#91748), [#&#8203;91749](openclaw/openclaw#91749), [#&#8203;91750](openclaw/openclaw#91750), [#&#8203;91751](openclaw/openclaw#91751), [#&#8203;91752](openclaw/openclaw#91752), [#&#8203;91763](openclaw/openclaw#91763), [#&#8203;89938](openclaw/openclaw#89938)) Thanks [@&#8203;joshavant](https://github.com/joshavant), [@&#8203;pgondhi987](https://github.com/pgondhi987), [@&#8203;mmaps](https://github.com/mmaps), [@&#8203;eleqtrizit](https://github.com/eleqtrizit), [@&#8203;shakkernerd](https://github.com/shakkernerd), and [@&#8203;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. ([#&#8203;91189](openclaw/openclaw#91189), [#&#8203;88682](openclaw/openclaw#88682), [#&#8203;89588](openclaw/openclaw#89588), [#&#8203;90212](openclaw/openclaw#90212), [#&#8203;91876](openclaw/openclaw#91876), [#&#8203;91874](openclaw/openclaw#91874), [#&#8203;91904](openclaw/openclaw#91904), [#&#8203;91478](openclaw/openclaw#91478), [#&#8203;91915](openclaw/openclaw#91915)) Thanks [@&#8203;codysai001](https://github.com/codysai001), [@&#8203;alexzhu0](https://github.com/alexzhu0), [@&#8203;joelnishanth](https://github.com/joelnishanth), [@&#8203;snowzlm](https://github.com/snowzlm), [@&#8203;obviyus](https://github.com/obviyus), and [@&#8203;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. ([#&#8203;91335](openclaw/openclaw#91335), [#&#8203;91449](openclaw/openclaw#91449), [#&#8203;88969](openclaw/openclaw#88969), [#&#8203;88530](openclaw/openclaw#88530), [#&#8203;91783](openclaw/openclaw#91783), [#&#8203;91785](openclaw/openclaw#91785)) Thanks [@&#8203;omarshahine](https://github.com/omarshahine), [@&#8203;jmissig](https://github.com/jmissig), and [@&#8203;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. ([#&#8203;91422](openclaw/openclaw#91422), [#&#8203;89851](openclaw/openclaw#89851), [#&#8203;91736](openclaw/openclaw#91736), [#&#8203;91747](openclaw/openclaw#91747), [#&#8203;91451](openclaw/openclaw#91451), [#&#8203;80143](openclaw/openclaw#80143)) Thanks [@&#8203;pgondhi987](https://github.com/pgondhi987), [@&#8203;anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@&#8203;lifuyue](https://github.com/lifuyue), [@&#8203;eleqtrizit](https://github.com/eleqtrizit), [@&#8203;LiuwqGit](https://github.com/LiuwqGit), and [@&#8203;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. ([#&#8203;91531](openclaw/openclaw#91531), [#&#8203;91538](openclaw/openclaw#91538), [#&#8203;91568](openclaw/openclaw#91568), [#&#8203;91583](openclaw/openclaw#91583), [#&#8203;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. ([#&#8203;91830](openclaw/openclaw#91830), [#&#8203;91882](openclaw/openclaw#91882), [#&#8203;91590](openclaw/openclaw#91590), [#&#8203;88630](openclaw/openclaw#88630), [#&#8203;88768](openclaw/openclaw#88768), [#&#8203;91696](openclaw/openclaw#91696)) Thanks [@&#8203;Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@&#8203;joshavant](https://github.com/joshavant), [@&#8203;bdjben](https://github.com/bdjben), and [@&#8203;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. ([#&#8203;89834](openclaw/openclaw#89834), [#&#8203;90883](openclaw/openclaw#90883)) Thanks [@&#8203;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. ([#&#8203;91256](openclaw/openclaw#91256), [#&#8203;91568](openclaw/openclaw#91568), [#&#8203;91583](openclaw/openclaw#91583)) Thanks [@&#8203;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. ([#&#8203;91574](openclaw/openclaw#91574), [#&#8203;91591](openclaw/openclaw#91591), [#&#8203;90004](openclaw/openclaw#90004), [#&#8203;90927](openclaw/openclaw#90927), [#&#8203;90838](openclaw/openclaw#90838)) Thanks [@&#8203;Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@&#8203;brokemac79](https://github.com/brokemac79), and [@&#8203;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. ([#&#8203;91324](openclaw/openclaw#91324), [#&#8203;89138](openclaw/openclaw#89138), [#&#8203;90457](openclaw/openclaw#90457), [#&#8203;91837](openclaw/openclaw#91837), [#&#8203;91851](openclaw/openclaw#91851)) Thanks [@&#8203;osolmaz](https://github.com/osolmaz), [@&#8203;mushuiyu886](https://github.com/mushuiyu886), [@&#8203;ai-hpc](https://github.com/ai-hpc), and [@&#8203;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. ([#&#8203;91423](openclaw/openclaw#91423), [#&#8203;91557](openclaw/openclaw#91557), [#&#8203;89909](openclaw/openclaw#89909)) Thanks [@&#8203;cxyhhhhh](https://github.com/cxyhhhhh), [@&#8203;Solvely-Colin](https://github.com/Solvely-Colin), and [@&#8203;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. ([#&#8203;90782](openclaw/openclaw#90782), [#&#8203;89978](openclaw/openclaw#89978), [#&#8203;91580](openclaw/openclaw#91580), [#&#8203;91531](openclaw/openclaw#91531)) Thanks [@&#8203;RomneyDa](https://github.com/RomneyDa) and [@&#8203;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. ([#&#8203;85679](openclaw/openclaw#85679), [#&#8203;91450](openclaw/openclaw#91450), [#&#8203;91566](openclaw/openclaw#91566), [#&#8203;91840](openclaw/openclaw#91840), [#&#8203;91590](openclaw/openclaw#91590), [#&#8203;91361](openclaw/openclaw#91361), [#&#8203;91895](openclaw/openclaw#91895)) Thanks [@&#8203;openperf](https://github.com/openperf), [@&#8203;yetval](https://github.com/yetval), [@&#8203;joshavant](https://github.com/joshavant), [@&#8203;wangmiao0668000666](https://github.com/wangmiao0668000666), and [@&#8203;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. ([#&#8203;89151](openclaw/openclaw#89151), [#&#8203;91422](openclaw/openclaw#91422), [#&#8203;91425](openclaw/openclaw#91425), [#&#8203;91529](openclaw/openclaw#91529), [#&#8203;90212](openclaw/openclaw#90212)) Thanks [@&#8203;joelnishanth](https://github.com/joelnishanth), [@&#8203;pgondhi987](https://github.com/pgondhi987), [@&#8203;joshavant](https://github.com/joshavant), and [@&#8203;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. ([#&#8203;85823](openclaw/openclaw#85823), [#&#8203;89659](openclaw/openclaw#89659), [#&#8203;91684](openclaw/openclaw#91684), [#&#8203;91649](openclaw/openclaw#91649), [#&#8203;90263](openclaw/openclaw#90263), [#&#8203;91686](openclaw/openclaw#91686), [#&#8203;90426](openclaw/openclaw#90426)) Thanks [@&#8203;itsuzef](https://github.com/itsuzef), [@&#8203;ladygege](https://github.com/ladygege), [@&#8203;jacobtomlinson](https://github.com/jacobtomlinson), [@&#8203;fuller-stack-dev](https://github.com/fuller-stack-dev), and [@&#8203;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. ([#&#8203;90666](openclaw/openclaw#90666), [#&#8203;90678](openclaw/openclaw#90678)) Thanks [@&#8203;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. ([#&#8203;87105](openclaw/openclaw#87105), [#&#8203;91551](openclaw/openclaw#91551), [#&#8203;91219](openclaw/openclaw#91219), [#&#8203;91614](openclaw/openclaw#91614), [#&#8203;91740](openclaw/openclaw#91740), [#&#8203;91978](openclaw/openclaw#91978)) Thanks [@&#8203;fuller-stack-dev](https://github.com/fuller-stack-dev) and [@&#8203;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. ([#&#8203;91390](openclaw/openclaw#91390), [#&#8203;91709](openclaw/openclaw#91709), [#&#8203;91507](openclaw/openclaw#91507), [#&#8203;91567](openclaw/openclaw#91567), [#&#8203;88630](openclaw/openclaw#88630), [#&#8203;91696](openclaw/openclaw#91696)) Thanks [@&#8203;hxy91819](https://github.com/hxy91819), [@&#8203;brokemac79](https://github.com/brokemac79), [@&#8203;RomneyDa](https://github.com/RomneyDa), [@&#8203;joshavant](https://github.com/joshavant), and [@&#8203;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. ([#&#8203;91581](openclaw/openclaw#91581), [#&#8203;91599](openclaw/openclaw#91599), [#&#8203;91547](openclaw/openclaw#91547), [#&#8203;91591](openclaw/openclaw#91591)) Thanks [@&#8203;fuller-stack-dev](https://github.com/fuller-stack-dev), [@&#8203;sallyom](https://github.com/sallyom), and [@&#8203;Patrick-Erichsen](https://github.com/Patrick-Erichsen).
- UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#&#8203;91480](openclaw/openclaw#91480)) Thanks [@&#8203;TurboTheTurtle](https://github.com/TurboTheTurtle).
- Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#&#8203;80082](openclaw/openclaw#80082)) Thanks [@&#8203;davelutztx](https://github.com/davelutztx).
- Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#&#8203;91550](openclaw/openclaw#91550)) Thanks [@&#8203;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.

---

 - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box

---

This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4xMDEuMSIsInVwZGF0ZWRJblZlciI6IjQzLjEwMS4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6WyJyZW5vdmF0ZS9jb250YWluZXIiLCJ0eXBlL3BhdGNoIl19-->

Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1040
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

maintainer Maintainer-authored PR merge-risk: 🚨 availability 🚨 May cause crashes, hangs, restart loops, stalls, or process outages. P2 Normal backlog priority with limited blast radius. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. size: S status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@RomneyDa