fix(irc): sanitize internal tool-trace lines from outbound text by masatohoshino · Pull Request #97214 · openclaw/openclaw

masatohoshino · 2026-06-27T07:59:33Z

Related: #90684

What Problem This Solves

Fixes an issue where IRC users would see OpenClaw's internal tool-execution traces leak into channel messages. When a tool run fails, the runtime injects a status banner such as ⚠️ 🛠️ `…(agent)` failed into the assistant's outbound text. On IRC — a plaintext-only transport — that banner was delivered verbatim instead of being stripped.

Why This Change Was Made

The IRC outbound adapter's sanitizeText ran only sanitizeForPlainText(text), which does not strip assistant-visible scaffolding. The Telegram (#95774) and Google Chat (#95084) outbound adapters already wrap the same call with sanitizeAssistantVisibleText — the canonical assistant-visible sanitizer that removes tool-trace banners and other internal scaffolding (reasoning tags, tool-call XML). This change applies that same wrap to IRC: one import plus sanitizeForPlainText(sanitizeAssistantVisibleText(text)), reusing the existing SDK sanitizer rather than adding a helper. The change is limited to the IRC adapter; other channels are tracked separately under #90684.

User Impact

IRC users no longer see internal tool-trace banners — or other assistant-internal scaffolding handled by the shared sanitizer — in delivered messages. Ordinary assistant prose is unaffected.

Evidence

Focused unit tests — extensions/irc/src/channel.test.ts adds 2 cases (tool-trace banner stripped; ordinary prose preserved):

$ node scripts/run-vitest.mjs extensions/irc/src/channel.test.ts
 Test Files  1 passed (1)
      Tests  3 passed (3)

Real-behavior proof — the patched IRC outbound adapter's ircOutboundBaseAdapter.sanitizeText, run directly against the real code path. No live IRC proof is included because the change is isolated to the outbound sanitizer; the command below exercises that adapter directly (the banner is runtime-injected, not model-produced, so a channel roundtrip adds no signal):

$ node --import tsx -e '
import { ircOutboundBaseAdapter } from "./extensions/irc/src/outbound-base.ts";
import { sanitizeForPlainText } from "openclaw/plugin-sdk/channel-outbound";
const trace = "Done.\n⚠️ 🛠️ `search repos (agent)` failed";
const prose = "The pipeline has 3 open deals.";
console.log("before (sanitizeForPlainText only):", JSON.stringify(sanitizeForPlainText(trace)));
console.log("after  (ircOutboundBaseAdapter):   ", JSON.stringify(ircOutboundBaseAdapter.sanitizeText({ text: trace })));
console.log("prose  (ircOutboundBaseAdapter):   ", JSON.stringify(ircOutboundBaseAdapter.sanitizeText({ text: prose })));
'
before (sanitizeForPlainText only): "Done.\n⚠️ 🛠️ `search repos (agent)` failed"
after  (ircOutboundBaseAdapter):    "Done."
prose  (ircOutboundBaseAdapter):    "The pipeline has 3 open deals."

Before the fix, sanitizeForPlainText(text) alone leaks the banner verbatim; after the fix it is stripped to Done., and ordinary prose passes through unchanged.

clawsweeper · 2026-06-27T08:01:00Z

Codex review: needs maintainer review before merge. Reviewed June 27, 2026, 11:29 AM ET / 15:29 UTC.

Summary
The PR adds sanitizeAssistantVisibleText() to the IRC outbound sanitizeText hook before plain-text formatting and adds IRC regression tests.

PR surface: Source +268, Tests +1134, Docs +11, Other +12. Total +1425 across 39 files.

Reproducibility: yes. Source inspection shows current main and v2026.6.10 only run IRC text through sanitizeForPlainText, while the canonical sanitizer tests and PR-head adapter tests cover the reported failure banner path.

Review metrics: none identified.

Stored data model
Persistent data-model change detected: database schema: scripts/lib/official-external-plugin-catalog.json, database schema: src/plugins/official-external-plugin-catalog.test.ts, database schema: src/plugins/official-external-plugin-catalog.ts, migration/backfill/repair: extensions/codex/src/migration/plan.ts, migration/backfill/repair: extensions/codex/src/migration/provider.test.ts, persistent cache schema: extensions/nostr/src/nostr-bus.integration.test.ts, and 4 more. Confirm migration or upgrade compatibility proof before merge.

Root-cause cluster
Relationship: fixed_by_candidate
Canonical: #90684
Summary: This PR is a focused IRC candidate for the broader non-Discord outbound assistant-visible sanitizer umbrella; merged sibling PRs already fixed Google Chat and Telegram slices.

Members:

canonical: Feishu (and non-Discord channels) should apply sanitizeAssistantVisibleText() on outbound text #90684 - The open umbrella issue tracks non-Discord channels applying sanitizeAssistantVisibleText() on outbound text, and this PR covers the IRC slice.
same_root_cause: fix(googlechat): sanitize internal tool-trace lines from outbound text (#90684) #95084 - The merged Google Chat PR fixed the same missing sanitizer composition for a sibling channel.
same_root_cause: fix(telegram): sanitize outbound tool traces #95774 - The merged Telegram PR fixed the same outbound adapter sanitizer gap for another sibling channel.

Proposal only: this assessment does not dispatch repair, suppress jobs, mutate sibling items, close, or merge anything.

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:

none.

Risk before merge

[P1] Merging intentionally changes IRC outbound delivery by suppressing lines that the canonical assistant-visible sanitizer classifies as internal scaffolding, so maintainers should accept that IRC should match the sibling channel behavior.

Maintainer options:

Accept the canonical IRC sanitizer (recommended)
Merge the adapter-level sanitizer after accepting that IRC should suppress canonical assistant-scaffolding lines instead of exposing internal tool traces.
Request live IRC smoke proof
Ask for a redacted IRC send proof only if maintainers want transport-level confirmation beyond the direct adapter proof already in the PR body.
Hold for the umbrella policy
Pause this PR if maintainers want all remaining non-Discord sanitizer coverage to land under one canonical boundary decision instead of channel-by-channel fixes.

Next step before merge

No automated repair is needed; maintainers should review the IRC filtering tradeoff and land the narrow fix or request live IRC proof.

Security
Cleared: No security or supply-chain concern was found in the current-main merge delta; the unique change narrows IRC outbound text visibility and adds tests.

Review details

Best possible solution:

Land the narrow IRC adapter sanitizer hook and tests after maintainer acceptance, while keeping broader uncovered-channel coverage tracked in #90684.

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

Yes. Source inspection shows current main and v2026.6.10 only run IRC text through sanitizeForPlainText, while the canonical sanitizer tests and PR-head adapter tests cover the reported failure banner path.

Is this the best way to solve the issue?

Yes. The PR fixes the channel-owned adapter hook that shared delivery already calls, reuses the existing SDK sanitizer, and matches merged Google Chat and Telegram sibling fixes instead of adding a new regex or config surface.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 4010b81a77f4.

Label changes

Label justifications:

P1: The PR addresses internal tool/runtime trace leakage into a user-facing messaging channel, matching the urgent channel-workflow impact of the linked sanitizer umbrella.
merge-risk: 🚨 message-delivery: The patch changes IRC outbound filtering and can suppress lines before users see them when they match canonical assistant-scaffolding patterns.
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. Sufficient (terminal): The PR body includes after-fix terminal output importing the patched IRC outbound adapter and showing the trace stripped while ordinary prose is preserved.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix terminal output importing the patched IRC outbound adapter and showing the trace stripped while ordinary prose is preserved.

Evidence reviewed

PR surface:

Source +268, Tests +1134, Docs +11, Other +12. Total +1425 across 39 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	20	314	46	+268
Tests	15	1136	2	+1134
Docs	2	19	8	+11
Config	0	0	0	0
Generated	0	0	0	0
Other	2	23	11	+12
Total	39	1492	67	+1425

What I checked:

Repository policy read: Root AGENTS.md and scoped guides for extensions, docs, scripts, plugin SDK, plugins, outbound tests, and Telegram notes were read; plugin-boundary and PR-review depth guidance apply to this review. (AGENTS.md:1, 4010b81a77f4)
Current main IRC gap: Current main IRC outbound sanitization only calls sanitizeForPlainText(text), so it does not run the assistant-visible sanitizer before delivery. (extensions/irc/src/outbound-base.ts:10, 4010b81a77f4)
Latest release IRC gap: The latest release tag v2026.6.10 has the same IRC adapter behavior, so the IRC fix is not already shipped. (extensions/irc/src/outbound-base.ts:10, aa69b12d0086)
PR head IRC fix: The PR head composes sanitizeForPlainText(sanitizeAssistantVisibleText(text)) in the IRC outbound adapter. (extensions/irc/src/outbound-base.ts:14, dd3a00abf036)
PR regression coverage: The PR adds focused IRC tests for stripping the compact tool-trace failure line and preserving ordinary prose. (extensions/irc/src/channel.test.ts:24, dd3a00abf036)
Shared delivery owner boundary: Shared outbound delivery calls a plugin sanitizeText hook when present, making the IRC adapter hook the narrow owner boundary for this fix. (src/infra/outbound/deliver.ts:390, 4010b81a77f4)

Likely related people:

steipete: GitHub history shows repeated work on the IRC outbound seam and the shared assistant-visible sanitizer that this PR reuses. (role: feature owner / adjacent owner; confidence: high; commits: 76bc0ae32fe0, 712479eea1a1, 96e581242605; files: extensions/irc/src/outbound-base.ts, extensions/irc/src/channel.test.ts, src/shared/text/assistant-visible-text.ts)
vincentkoc: Recent history includes IRC runtime import narrowing and shared sanitizer maintenance near the affected surfaces. (role: recent area contributor; confidence: medium; commits: 6349e6aa3e6a, 4a4a5968e88a; files: extensions/irc/src/channel-api.ts, extensions/irc/src/channel.ts, src/shared/text/assistant-visible-text.ts)
obviyus: Recent sanitizer commits added and covered compact failure trace suppression that the IRC adapter now reuses. (role: sanitizer hardening contributor; confidence: medium; commits: 8f1ae5967ef2, d82bfcecb1d8; files: src/shared/text/assistant-visible-text.ts, src/shared/text/assistant-visible-text.test.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.

vincentkoc · 2026-06-27T15:34:44Z

Merged via squash.

Prepared head SHA: dd3a00abf036fdbdb4fb1b28f88a68e31048a10a
Landed commit: ddedf13190c105374be3cb7347a809ca384d5cd4

…claw#97214) * fix(irc): sanitize internal tool-trace lines from outbound text * fix(irc): sanitize internal tool-trace lines from outbound text --------- Co-authored-by: Vincent Koc <[email protected]>

…97372) Wrap the matrix outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under #90684 (Telegram #95774, Google Chat #95084, IRC #97214).

…7367) Wrap the slack outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under #90684 (Telegram #95774, Google Chat #95084, IRC #97214).

…penclaw#97360) Wrap the signal outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214).

…penclaw#97372) Wrap the matrix outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit 25490d4)

…claw#97214) * fix(irc): sanitize internal tool-trace lines from outbound text * fix(irc): sanitize internal tool-trace lines from outbound text --------- Co-authored-by: Vincent Koc <[email protected]>

…penclaw#97372) Wrap the matrix outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214).

…enclaw#97367) Wrap the slack outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214).

…penclaw#97360) Wrap the signal outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214).

…enclaw#97367) Wrap the slack outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit cd6d0f9)

…penclaw#97360) Wrap the signal outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit c026546)

…enclaw#97367) Wrap the slack outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit cd6d0f9)

…penclaw#97360) Wrap the signal outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit c026546)

…text The Nextcloud Talk outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered chat messages. The same one-line sanitizeText hook was already shipped to 13 sibling channels (mattermost openclaw#98693, feishu openclaw#98705, twitch openclaw#103109, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText: ({ text }) => sanitizeAssistantVisibleText(text) to the outbound base adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Nostr outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Nostr DMs. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText to the NostrOutboundAdapter type and adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Zalo outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Zalo messages. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText: ({ text }) => sanitizeAssistantVisibleText(text) to the outbound adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Nostr outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Nostr DMs. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText to the NostrOutboundAdapter type and adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Zalo outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Zalo messages. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText: ({ text }) => sanitizeAssistantVisibleText(text) to the outbound adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Nostr outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Nostr DMs. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText to the NostrOutboundAdapter type and adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

The Zalo outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Zalo messages. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText: ({ text }) => sanitizeAssistantVisibleText(text) to the outbound adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

…claw#97214) * fix(irc): sanitize internal tool-trace lines from outbound text * fix(irc): sanitize internal tool-trace lines from outbound text --------- Co-authored-by: Vincent Koc <[email protected]> (cherry picked from commit ddedf13)

…penclaw#97372) Wrap the matrix outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit 25490d4)

…enclaw#97367) Wrap the slack outbound sanitizeText hook with sanitizeAssistantVisibleText so assistant internal tool-trace scaffolding is stripped before delivery, matching the sibling channel fixes under openclaw#90684 (Telegram openclaw#95774, Google Chat openclaw#95084, IRC openclaw#97214). (cherry picked from commit cd6d0f9)

The Nostr outbound adapter had no sanitizeText hook, so internal assistant tool-trace scaffolding (e.g. "⚠️ 🛠️ `exec (agent)` failed", raw <tool_call>/<function_response> XML) leaked verbatim into delivered Nostr DMs. The same one-line sanitizeText hook was already shipped to 13 sibling channels (twitch openclaw#103109, mattermost openclaw#98693, feishu openclaw#98705, signal openclaw#97360, slack openclaw#97367, matrix openclaw#97372, irc openclaw#97214, telegram, googlechat openclaw#90684, qqbot openclaw#90132, discord, whatsapp openclaw#71830, sms). Add sanitizeText to the NostrOutboundAdapter type and adapter, matching those precedents. Co-Authored-By: Claude <[email protected]>

fix(irc): sanitize internal tool-trace lines from outbound text

1fd8820

openclaw-barnacle Bot added channel: irc size: XS labels Jun 27, 2026

fix(irc): sanitize internal tool-trace lines from outbound text

dd3a00a

vincentkoc merged commit ddedf13 into openclaw:main Jun 27, 2026
156 of 160 checks passed

github-actions Bot mentioned this pull request Jun 27, 2026

📡 Upstream Digest — 2026-06-27 16:59 UTC curtismercier/openclaw-mods#1160

Open

This was referenced Jun 28, 2026

fix(signal): sanitize internal tool-trace lines from outbound text #97360

Merged

fix(slack): sanitize internal tool-trace lines from outbound text #97367

Merged

fix(matrix): sanitize internal tool-trace lines from outbound text #97372

Merged

clawsweeper Bot mentioned this pull request Jun 28, 2026

fix(llm): preserve structured tool result text across providers #97450

Closed

clawsweeper Bot mentioned this pull request Jul 3, 2026

feat(irc): support markdown messages via draft/multiline #55901

Open

This was referenced Jul 10, 2026

fix(nextcloud-talk): strip internal tool-trace banners from outbound text #103355

Closed

fix(nostr): strip internal tool-trace banners from outbound text #103361

Open

fix(zalo): strip internal tool-trace banners from outbound text #103377

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(irc): sanitize internal tool-trace lines from outbound text#97214

fix(irc): sanitize internal tool-trace lines from outbound text#97214
vincentkoc merged 2 commits into
openclaw:mainfrom
masatohoshino:fix/irc-outbound-tool-trace-sanitize

masatohoshino commented Jun 27, 2026

Uh oh!

clawsweeper Bot commented Jun 27, 2026 •

edited

Loading

Uh oh!

Uh oh!

vincentkoc commented Jun 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

masatohoshino commented Jun 27, 2026

What Problem This Solves

Why This Change Was Made

User Impact

Evidence

Uh oh!

clawsweeper Bot commented Jun 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

vincentkoc commented Jun 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

clawsweeper Bot commented Jun 27, 2026 •

edited

Loading