feat(diagnostics-otel): capture tool input/output content via trusted channel by amknight · Pull Request #91256 · openclaw/openclaw

amknight · 2026-06-07T22:08:16Z

Summary

diagnostics.otel.captureContent.toolInputs / toolOutputs were documented and
config-wired but never produced any span content — the OTel exporter had a
consumer for tool content, but nothing on the runtime side emitted it.

This wires the missing producer, mirroring the model-content path (#86191):

Producer (agent-tools.before-tool-call.ts): on tool completion/error,
emit cloned tool args/results over the trusted private-data diagnostic
channel, gated behind the existing captureContent opt-in. Raw tool content
never rides the public diagnostic event bus.
Consumer (diagnostics-otel/service.ts): reads privateData.toolContent
and bounds/redacts/truncates (128KB) before setting openclaw.content.tool_input
and openclaw.content.tool_output span attributes.

Scope is the core embedded-runner tool path (the canonical producer). The Codex
harness (async-batched diagnostics) and the Claude CLI session remain follow-ups,
noted in docs/gateway/opentelemetry.md and tracked by #77391.

Verification

Tests: diagnostic-llm-content (4), attempt.model-diagnostic-events (13),
agent-tools.before-tool-call.e2e (54, incl. 4 new producer cases),
diagnostics-otel/service (87) — all pass via node scripts/run-vitest.mjs.
Types: tsgo:core, tsgo:extensions, tsgo:test:src, tsgo:test:extensions.
SDK contract: plugin-sdk:api:check passes (baseline regenerated for source
line shifts; no public declaration shape change).
oxfmt --check + oxlint clean; Codex autoreview clean (no findings).

Refs #77391

clawsweeper · 2026-06-07T22:10:28Z

Codex review: needs maintainer review before merge. Reviewed June 9, 2026, 3:25 PM ET / 19:25 UTC.

Summary
The branch wires embedded-runner tool input/output capture into trusted diagnostic private data, updates diagnostics-otel to export bounded/redacted span attributes, adds focused tests, and documents Codex/Claude exclusions.

PR surface: Source +53, Tests +206, Docs +7, Generated 0. Total +266 across 10 files.

Reproducibility: yes. Source inspection shows current main and v2026.6.5 expose the config/docs but emit embedded-runner tool terminal diagnostics without raw tool fields or privateData.toolContent.

Review metrics: 2 noteworthy metrics.

Config behavior activation: 2 existing subkeys activated, 0 new keys. toolInputs and toolOutputs already exist in config/docs, but this PR changes them from no-op to exporting sensitive content when enabled.
Trusted private data shape: 1 field added. Adding toolContent broadens the plugin-SDK-exposed internal diagnostics payload that trusted exporters can receive.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🌊 off-meta tidepool
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] Maintainers should explicitly accept the opt-in privacy and trusted diagnostic contract before merge.
Redacted real collector output would reduce the remaining runtime-proof uncertainty.

Risk before merge

[P1] Existing installations that already opted into diagnostics.otel.captureContent.toolInputs or toolOutputs will change from a documented no-op to exporting bounded/redacted tool args/results after upgrade.
[P1] DiagnosticEventPrivateData gains a toolContent field on a trusted internal diagnostics surface exported through the plugin SDK, so maintainers should explicitly accept the additive sensitive-data contract.
[P1] Codex and Claude harness parity remains out of scope and tracked by diagnostics.otel.captureContent.* is non-functional — runtime broadcast emits sanitized paramsSummary only #77391, so this PR intentionally fixes only the embedded-runner producer path.

Maintainer options:

Accept the opt-in content export
Maintainership can accept that already-enabled toolInputs/toolOutputs configs will begin exporting bounded/redacted tool content because the keys were documented for that purpose.
Require collector proof first
Before merge, ask for redacted OTLP collector output showing openclaw.content.tool_input and openclaw.content.tool_output on real embedded-runner tool spans.
Pause for private-data contract review
If the trusted diagnostic SDK surface is not yet accepted, pause the PR and decide whether toolContent belongs in this private contract or behind a narrower exporter-only seam.

Next step before merge

[P2] Protected maintainer handling plus privacy/SDK contract acceptance are the remaining actions; there is no narrow ClawSweeper repair to queue.

Security
Needs attention: No supply-chain issue was found, but the diff intentionally activates privacy-sensitive tool content export through trusted diagnostics.

Review details

Best possible solution:

Land only after maintainers explicitly accept the opt-in privacy behavior and trusted diagnostic private-data contract, while keeping Codex/Claude parity tracked in #77391.

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

Yes. Source inspection shows current main and v2026.6.5 expose the config/docs but emit embedded-runner tool terminal diagnostics without raw tool fields or privateData.toolContent.

Is this the best way to solve the issue?

Yes, this appears to be the best core fix for the embedded-runner path because it mirrors the model-content private-data design and keeps raw content off the public diagnostic bus. The open question is maintainer acceptance of the privacy/SDK contract, not a narrower code defect.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 5b9cb3bd3a36.

Label changes

Label justifications:

P2: This is a normal-priority diagnostics bug fix with limited blast radius but privacy-sensitive opt-in behavior.
merge-risk: 🚨 compatibility: Users with existing captureContent.toolInputs/toolOutputs settings will observe new exported span attributes after upgrade.
merge-risk: 🚨 security-boundary: The PR intentionally moves raw tool args/results onto a trusted private diagnostic channel before exporter redaction and truncation.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: The contributor real-behavior proof gate is not applied because this is a MEMBER-authored protected maintainer PR; the body lists focused tests, type checks, SDK checks, lint, and autoreview.

Evidence reviewed

PR surface:

Source +53, Tests +206, Docs +7, Generated 0. Total +266 across 10 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	5	94	41	+53
Tests	3	224	18	+206
Docs	1	7	0	+7
Config	0	0	0	0
Generated	1	2	2	0
Other	0	0	0	0
Total	10	327	61	+266

Security concerns:

[medium] Confirm opt-in tool content export is acceptable — src/agents/agent-tools.before-tool-call.ts:1268
The PR now emits cloned tool args/results over private diagnostics when captureContent.toolInputs/toolOutputs are enabled; even with trusted listeners and exporter redaction, this is a security-boundary decision for operators upgrading from a no-op setting.
Confidence: 0.86

What I checked:

Repository policy read and applied: Root AGENTS.md plus scoped docs/extensions/src/agents/embedded-runner guides were read; protected maintainer handling, plugin SDK/privacy risk, docs wording, and sibling Codex review requirements shaped the verdict. (AGENTS.md:1, 5b9cb3bd3a36)
Current main still lacks the producer: Current main emits embedded-runner tool completed/error diagnostics with emitTrustedDiagnosticEvent and no private content payload, so the PR remains necessary. (src/agents/agent-tools.before-tool-call.ts:1238, 5b9cb3bd3a36)
Latest release has the same gap: The latest release v2026.6.5 also emits tool terminal events without private tool content, confirming the fix has not shipped. (src/agents/agent-tools.before-tool-call.ts:1238, 5181e4f7c82b)
PR producer uses trusted private data: The PR emits completed/error tool diagnostics through emitTrustedDiagnosticEventWithPrivateData and builds cloned tool input/output content only when the capture policy opts in. (src/agents/agent-tools.before-tool-call.ts:1268, 1ccd84b86dfc)
PR consumer reads privateData.toolContent: diagnostics-otel assigns openclaw.content.tool_input/tool_output from privateData.toolContent, then uses the existing content normalization/redaction/truncation path. (extensions/diagnostics-otel/src/service.ts:3426, 1ccd84b86dfc)
Trusted diagnostics are narrowly granted: The internalDiagnostics capability is granted only to bundled or trusted-official diagnostics exporters, which limits but does not remove the privacy sensitivity of the new private payload shape. (src/plugins/services.ts:31, 5b9cb3bd3a36)

Likely related people:

amknight: Authored the current PR and the merged OpenTelemetry LLM content span work that established the private diagnostic-content pattern this PR extends. (role: feature owner and recent area contributor; confidence: high; commits: 1ccd84b86dfc, f824e1596ad5; files: src/agents/agent-tools.before-tool-call.ts, extensions/diagnostics-otel/src/service.ts, src/infra/diagnostic-events.ts)
vincentkoc: Co-authored the merged model-content OTel span PR and is connected to the shipped captureContent configuration/docs surface this branch extends to tool content. (role: adjacent contributor; confidence: medium; commits: f824e1596ad5; files: extensions/diagnostics-otel/src/service.ts, src/infra/diagnostic-events.ts, src/infra/diagnostic-llm-content.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.

… channel diagnostics.otel.captureContent.{toolInputs,toolOutputs} were documented and config-wired but never produced any span content. Emit tool args and results over the trusted private-data diagnostic channel (mirroring the model-content path), and have the OTel exporter bound/redact/truncate them before span export. Raw tool content never rides the public event bus. Scope: core embedded-runner tool path (canonical producer). Codex (async-batched) and Claude CLI remain follow-ups tracked by the issue. Refs #77391

… channel (openclaw#91256) diagnostics.otel.captureContent.{toolInputs,toolOutputs} were documented and config-wired but never produced any span content. Emit tool args and results over the trusted private-data diagnostic channel (mirroring the model-content path), and have the OTel exporter bound/redact/truncate them before span export. Raw tool content never rides the public event bus. Scope: core embedded-runner tool path (canonical producer). Codex (async-batched) and Claude CLI remain follow-ups tracked by the issue. Refs openclaw#77391

…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 docs Improvements or additions to documentation gateway Gateway runtime extensions: diagnostics-otel Extension: diagnostics-otel agents Agent runtime and tooling size: M maintainer Maintainer-authored PR labels Jun 7, 2026

amknight requested a review from vincentkoc June 8, 2026 02:39

amknight force-pushed the ak/otel-tool-content branch from f0207fd to 81ad9f3 Compare June 9, 2026 01:30

amknight force-pushed the ak/otel-tool-content branch from 81ad9f3 to 1ccd84b Compare June 9, 2026 19:15

amknight merged commit bf95883 into main Jun 9, 2026
159 checks passed

amknight deleted the ak/otel-tool-content branch June 9, 2026 19:52

github-actions Bot mentioned this pull request Jun 9, 2026

📡 Upstream Digest — 2026-06-09 19:57 UTC curtismercier/openclaw-mods#1047

Open

arniesaha mentioned this pull request Jun 9, 2026

feat(gateway): attribute runs via opt-in clientContext on the trusted diagnostic channel #91762

Closed

arniesaha mentioned this pull request Jun 10, 2026

feat(diagnostics-otel): native OTel run attribution via opt-in clientContext #91969

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(diagnostics-otel): capture tool input/output content via trusted channel#91256

feat(diagnostics-otel): capture tool input/output content via trusted channel#91256
amknight merged 1 commit into
mainfrom
ak/otel-tool-content

amknight commented Jun 7, 2026

Uh oh!

clawsweeper Bot commented Jun 7, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

amknight commented Jun 7, 2026

Summary

Verification

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!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

clawsweeper Bot commented Jun 7, 2026 •

edited

Loading