openclaw/clawsweeper-state
openclaw/clawsweeper-state
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

chore: update sweep records

Browse Source 
[skip ci]
This commit is contained in:
clawsweeper 2026-05-08 23:27:42 +00:00
parent c7c6430dbd
commit 78699b104f
2 changed files with 141 additions and 123 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

242
records/openclaw-openclaw/items/78405.md
View File

@ -1,5 +1,4 @@
---
review_comment_synced_at: 2026-05-06T10:12:11.145Z
number: 78405
repository: openclaw/openclaw
type: issue
@ -7,15 +6,15 @@ title: "Silent text-reply drops with visibleReplies=\"message_tool\" — improve
url: https://github.com/openclaw/openclaw/issues/78405
state_at_review: open
item_created_at: 2026-05-06T10:04:10Z
item_updated_at: 2026-05-06T10:06:48Z
item_updated_at: 2026-05-08T23:13:33Z
author: cedricjanssens
author_association: NONE
labels: []
reviewed_at: 2026-05-06T10:11:37.664Z
main_sha: 1fe15f230617f2e6842bd4e6583c913186517672
reviewed_at: 2026-05-08T23:26:21.964Z
main_sha: 71816a3fb24660c1c6af09d77485cf52e52607f3
pull_head_sha: unknown
latest_release: v2026.5.5
latest_release_sha: b1abf9d8ae4410c6a6e08f7dfd2d617f4550281c
latest_release: v2026.5.7
latest_release_sha: eeef4864494f859838fec1586bedbab1f8fa5702
fixed_release: unknown
fixed_sha: unknown
fixed_at: unknown
@ -26,45 +25,45 @@ fixed_pr_merged_at: unknown
fixed_pr_sha: unknown
fixed_pr_confidence: unknown
fixed_pr_source: unknown
review_policy: 0c3089d8be55ac96
review_policy: 421d766edf9f773b
review_model: gpt-5.5
review_reasoning_effort: high
review_sandbox: danger-full-access
review_service_tier: default
review_prompt_chars: 47610
review_static_prompt_chars: 32829
review_context_chars: 13524
review_prompt_chars: 64720
review_static_prompt_chars: 33412
review_context_chars: 30042
review_schema_chars: 14081
review_additional_prompt_chars: 0
review_context_elapsed_ms: 1673
review_codex_elapsed_ms: 252699
review_context_elapsed_ms: 1515
review_codex_elapsed_ms: 208055
review_mode: propose
review_status: complete
local_checkout_access: verified
item_snapshot_hash: 392afad58f46ac199b79a0dab65060c3059b555952dbd7413c9638910eaf453c
close_comment_sha256: none
review_comment_sha256: ea050d3cc7c6cd26fd7fc1e2da936bc8f68dee9b72d384d9db305e0869ae739a
review_comment_id: 4386978352
review_comment_url: https://github.com/openclaw/openclaw/issues/78405#issuecomment-4386978352
decision: keep_open
close_reason: none
item_snapshot_hash: cd7f6073b2e925f8c527c3750db76aebb1121f216ba2534921e0ae2181b2d23d
close_comment_sha256: 0c9a46f58c684407479467501096890447d1595b1536fd7e08965a1c9df75015
review_comment_sha256: none
review_comment_id: unknown
review_comment_url: unknown
decision: close
close_reason: duplicate_or_superseded
confidence: high
action_taken: kept_open
work_candidate: queue_fix_pr
work_confidence: high
work_priority: high
work_status: candidate
work_reason_sha256: 7760aba76381038d999062e3e32ecf82746b0f8da757f740cebf98fb8b1c7478
work_prompt_sha256: 59f38586d4595b2f656101f91166febce10639bda0a848620ca8ed33e52467a1
work_cluster_refs: ["https://github.com/openclaw/openclaw/issues/78405"]
work_validation: ["pnpm test src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/source-reply-delivery-mode.test.ts extensions/discord/src/monitor/message-handler.process.test.ts","pnpm exec oxfmt --check --threads=1 src/auto-reply/reply/dispatch-from-config.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/source-reply-delivery-mode.test.ts extensions/discord/src/monitor/message-handler.process.test.ts","pnpm check:changed"]
work_likely_files: ["src/auto-reply/reply/dispatch-from-config.ts","src/auto-reply/reply/dispatch-from-config.test.ts","src/auto-reply/reply/source-reply-delivery-mode.ts","src/auto-reply/reply/source-reply-delivery-mode.test.ts","extensions/discord/src/monitor/message-handler.process.ts","extensions/discord/src/monitor/message-handler.process.test.ts","docs/channels/troubleshooting.md","CHANGELOG.md"]
action_taken: proposed_close
work_candidate: none
work_confidence: low
work_priority: low
work_status: none
work_reason_sha256: 726a66f43cfaa3abf58d320aa2a4f00c1124bbeda777fb12cf8e0d876ac46228
work_prompt_sha256: none
work_cluster_refs: []
work_validation: []
work_likely_files: []
item_category: feature
reproduction_status: source_reproducible
reproduction_confidence: high
requires_new_feature: true
requires_new_config_option: false
requires_product_decision: false
requires_product_decision: true
real_behavior_proof_status: not_applicable
real_behavior_proof_evidence_kind: not_applicable
real_behavior_proof_needs_contributor_action: false
@ -84,49 +83,49 @@ Labels: none
Created at: May 6, 2026, 10:04 UTC
Updated at: May 6, 2026, 10:06 UTC
Updated at: May 8, 2026, 23:13 UTC
Reviewed against: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
Reviewed against: [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3)
Codex review: model gpt-5.5, reasoning high
Latest release at review time: [v2026.5.5](https://github.com/openclaw/openclaw/releases/tag/v2026.5.5) ([b1abf9d8ae44](https://github.com/openclaw/openclaw/commit/b1abf9d8ae4410c6a6e08f7dfd2d617f4550281c))
Latest release at review time: [v2026.5.7](https://github.com/openclaw/openclaw/releases/tag/v2026.5.7) ([eeef4864494f](https://github.com/openclaw/openclaw/commit/eeef4864494f859838fec1586bedbab1f8fa5702))
Fixed in: not determined
## Decision
Keep open: kept open
Close: duplicate or superseded
Confidence: high
Action taken: kept_open
Action taken: proposed_close
## Summary
Keep open: current main documents the `message_tool` behavior and has a verbose pre-dispatch note, but the default runtime path can still finish successfully while suppressing normal final text without a default-visible warning or delivery signal.
Close as duplicate: the same remaining visible-reply observability/fallback problem is already tracked by the open canonical report at https://github.com/openclaw/openclaw/issues/77320, and current source/tests show this issue is the same `message_tool_only` suppression path rather than a distinct Discord-only transport bug.
## What This Changes
Request to make text replies suppressed by `messages.groupChat.visibleReplies = "message_tool"` observable and easier to diagnose.
The issue requests better observability when group/channel `message_tool` visible-reply mode suppresses normal text replies that did not use the message tool.
## Best Possible Solution
Add a deduped, default-visible suppression diagnostic for `message_tool_only` text finals, keep delivery semantics unchanged, and leave per-agent visible-reply overrides or deeper doctor history analysis for separate product work.
Track the shared product decision and implementation under https://github.com/openclaw/openclaw/issues/77320: either add a scoped default-visible diagnostic for suppressed non-empty finals or explicitly choose a fallback policy without weakening the private-by-default room contract.
## Reproduction Assessment
Yes, at source level: current code resolves group/channel turns to `message_tool_only`, sets `suppressDelivery`, and skips normal final replies while tests assert no final dispatcher call. I did not execute a live Discord repro in this read-only pass.
Yes, at source level: current main resolves group/channel turns to `message_tool_only`, suppresses automatic final delivery, and has tests proving no final reply is queued. I did not run a live Discord, WhatsApp, or Telegram scenario in this read-only review.
## Solution Assessment
Yes, the narrowest maintainable fix is an explicit diagnostic at the suppression decision rather than changing delivery behavior or adding per-agent config first. Current docs help, but they do not make the live silent-by-default runtime path observable.
Yes for cleanup: keeping one canonical issue open is the best maintainer path because https://github.com/openclaw/openclaw/issues/77320 tracks the same shared root cause and policy choices. The eventual fix should be made once there, not split across channel-specific duplicates.
## Review Findings
Overall correctness: not a patch
Overall confidence: 0.86
Overall confidence: 0.91
Full review comments:
@ -136,7 +135,7 @@ Full review comments:
Status: not_applicable
Summary: No patch is attached, and this ordinary observability issue is not security-sensitive.
Summary: Non-PR issue review; no patch security or supply-chain review applies.
Concerns:
@ -150,104 +149,123 @@ Evidence kind: not_applicable
Needs contributor action: false
Summary: Not applicable for issue triage because there is no PR patch under review.
Summary: Non-PR issue review; the external PR real-behavior proof gate does not apply.
## Work Candidate
Candidate: queue_fix_pr
Candidate: none
Confidence: high
Confidence: low
Priority: high
Priority: low
Status: candidate
Status: none
Reason: Safe repair candidate: the implicated suppression path is narrow, already covered by focused tests, and can gain diagnostics without changing reply delivery semantics.
Cluster refs:
- https://github.com/openclaw/openclaw/issues/78405
Likely files:
- src/auto-reply/reply/dispatch-from-config.ts
- src/auto-reply/reply/dispatch-from-config.test.ts
- src/auto-reply/reply/source-reply-delivery-mode.ts
- src/auto-reply/reply/source-reply-delivery-mode.test.ts
- extensions/discord/src/monitor/message-handler.process.ts
- extensions/discord/src/monitor/message-handler.process.test.ts
- docs/channels/troubleshooting.md
- CHANGELOG.md
Validation:
- pnpm test src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/source-reply-delivery-mode.test.ts extensions/discord/src/monitor/message-handler.process.test.ts
- pnpm exec oxfmt --check --threads=1 src/auto-reply/reply/dispatch-from-config.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/source-reply-delivery-mode.test.ts extensions/discord/src/monitor/message-handler.process.test.ts
- pnpm check:changed
## Repair Work Prompt
Fix https://github.com/openclaw/openclaw/issues/78405 by adding a focused observability signal for group/channel source replies suppressed by `sourceReplyDeliveryMode: "message_tool_only"`. In `src/auto-reply/reply/dispatch-from-config.ts`, emit a deduped default-visible warning or structured log when a non-reasoning final/text reply is suppressed because automatic source delivery is disabled and no visible message-tool output was queued. Keep delivery semantics unchanged, do not add per-agent config overrides, and stop for maintainer input if the fix grows into a doctor session-history scanner or broader product policy. Add or update regression coverage around the suppressed final path; update docs or `CHANGELOG.md` if the user-visible diagnostic text changes.
Reason: Closing as a duplicate; any repair should be queued from the canonical open issue instead of this satellite report.
## Evidence
- **Group/channel policy defaults to tool-only visible replies:** Group or channel chats resolve to `message_tool_only` unless `messages.groupChat.visibleReplies` or the global visible-replies setting is `automatic`.
- file: [src/auto-reply/reply/source-reply-delivery-mode.ts:28](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/src/auto-reply/reply/source-reply-delivery-mode.ts#L28)
- command: `nl -ba src/auto-reply/reply/source-reply-delivery-mode.ts | sed -n '1,130p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Suppression is modeled as delivery suppression:** `message_tool_only` sets `suppressAutomaticSourceDelivery` and `suppressDelivery`, with the reason `sourceReplyDeliveryMode: message_tool_only`.
- file: [src/auto-reply/reply/source-reply-delivery-mode.ts:72](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/src/auto-reply/reply/source-reply-delivery-mode.ts#L72)
- command: `nl -ba src/auto-reply/reply/source-reply-delivery-mode.ts | sed -n '1,130p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Final replies are skipped under suppression:** The final-reply loop continues without delivery when `suppressDelivery` is true and the payload lacks the explicit bypass metadata, then returns a completed dispatch result with no queued final.
- file: [src/auto-reply/reply/dispatch-from-config.ts:1534](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/src/auto-reply/reply/dispatch-from-config.ts#L1534)
- command: `nl -ba src/auto-reply/reply/dispatch-from-config.ts | sed -n '1518,1645p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Existing runtime note is verbose/debug gated:** The only generic suppression log in this path is `logVerbose`, and `logVerbose` returns unless verbose mode or debug file logging is enabled.
- file: [src/auto-reply/reply/dispatch-from-config.ts:1081](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/src/auto-reply/reply/dispatch-from-config.ts#L1081)
- command: `nl -ba src/auto-reply/reply/dispatch-from-config.ts | sed -n '1065,1100p'; nl -ba src/globals.ts | sed -n '1,28p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Discord status reactions do not cover this default case:** Discord disables status reactions by default for tool-only source replies unless explicitly enabled, and its error reaction only follows dispatch errors or final delivery failures, not configured suppression with zero queued finals.
- file: [extensions/discord/src/monitor/message-handler.process.ts:203](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/extensions/discord/src/monitor/message-handler.process.ts#L203)
- command: `nl -ba extensions/discord/src/monitor/message-handler.process.ts | sed -n '150,235p'; nl -ba extensions/discord/src/monitor/message-handler.process.ts | sed -n '700,830p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Docs already describe the workaround:** The group-channel docs now say normal final answers stay private under `message_tool`, point to `didSendViaMessagingTool: false`, and recommend `messages.groupChat.visibleReplies: "automatic"` or a reliable tool-calling model.
- file: [docs/channels/groups.md:43](https://github.com/openclaw/openclaw/blob/1fe15f230617f2e6842bd4e6583c913186517672/docs/channels/groups.md#L43)
- command: `nl -ba docs/channels/groups.md | sed -n '35,96p'`
- sha: [1fe15f230617](https://github.com/openclaw/openclaw/commit/1fe15f230617f2e6842bd4e6583c913186517672)
- **Canonical related report:** https://github.com/openclaw/openclaw/issues/77320 is open and tracks the same root behavior: group/channel `visibleReplies="message_tool"` turns can finish with assistant text but no visible channel delivery, and the requested fix is a hard diagnostic or fallback policy.
- command: `gh issue view 77320 --repo openclaw/openclaw --json number,title,state,comments,url`
- **Current delivery-mode policy:** Group/channel chats resolve to `message_tool_only` unless configured `automatic`, and that mode sets `suppressAutomaticSourceDelivery` and `suppressDelivery`.
- file: [src/auto-reply/reply/source-reply-delivery-mode.ts:37](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/source-reply-delivery-mode.ts#L37)
- command: `nl -ba src/auto-reply/reply/source-reply-delivery-mode.ts | sed -n '1,140p'`
- sha: [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3)
- **Current suppression implementation:** The final-reply loop continues without delivery when `suppressDelivery` is true and the payload is not explicitly marked to bypass source-reply suppression.
- file: [src/auto-reply/reply/dispatch-from-config.ts:1567](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/dispatch-from-config.ts#L1567)
- command: `nl -ba src/auto-reply/reply/dispatch-from-config.ts | sed -n '1500,1575p'`
- sha: [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3)
- **Regression coverage for this path:** Focused tests assert default group/channel turns use `message_tool_only`, return `queuedFinal: false`, and do not call `sendFinalReply`.
- file: [src/auto-reply/reply/dispatch-from-config.test.ts:4748](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/dispatch-from-config.test.ts#L4748)
- command: `nl -ba src/auto-reply/reply/dispatch-from-config.test.ts | sed -n '4748,4810p'`
- sha: [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3)
- **Docs describe the current workaround:** The group docs now say normal final answers stay private in `message_tool` mode, point to `didSendViaMessagingTool: false`, and recommend `messages.groupChat.visibleReplies: "automatic"` to restore automatic visible final replies.
- file: [docs/channels/groups.md:43](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/docs/channels/groups.md#L43)
- command: `nl -ba docs/channels/groups.md | sed -n '1,105p'`
- sha: [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3)
- **Feature history:** Merged https://github.com/openclaw/openclaw/pull/73046 introduced the safer Discord/group visible-reply behavior and touched the central docs, dispatch, config, and tests.
- command: `gh pr view 73046 --repo openclaw/openclaw --json number,title,state,author,mergedAt,mergeCommit,files,url,body`
- sha: [3c636208b0a0](https://github.com/openclaw/openclaw/commit/3c636208b0a00ff325e4f48d048d1fd9820f3ea0)
- **Additional context on this issue:** The follow-up comments report the same failure signature on WhatsApp groups and Telegram forum topics, which supports a shared core visible-reply suppression issue rather than a channel-specific Discord root cause.
- command: `gh issue view 78405 --repo openclaw/openclaw --json number,title,state,comments,url`
## Likely Related People
- **vincentkoc:** introduced behavior and recent maintainer
- reason: Available blame/history for the visible-reply resolver, Discord handling, and current docs points to Vincent Koc on the shallow-boundary commit that contains the current `message_tool_only` policy and diagnostics text.
- **scoootscooob:** introduced behavior
- reason: Authored merged https://github.com/openclaw/openclaw/pull/73046, which made group/channel visible output depend on explicit message-tool sends and touched the central resolver, dispatch tests, docs, and Discord handling.
- confidence: medium
- commits: 53809e52e91644722252cf7b2ebeea41c63041fd
- files: src/auto-reply/reply/source-reply-delivery-mode.ts, src/auto-reply/reply/dispatch-from-config.ts, extensions/discord/src/monitor/message-handler.process.ts, docs/channels/groups.md, docs/channels/troubleshooting.md
- commits: 3c636208b0a00ff325e4f48d048d1fd9820f3ea0, 85e4ec1fb1ac78262c1bd7048638ae000e89dc55
- files: src/auto-reply/reply/source-reply-delivery-mode.ts, src/auto-reply/reply/dispatch-from-config.ts, src/auto-reply/reply/dispatch-from-config.test.ts, docs/channels/groups.md, docs/channels/discord.md, extensions/discord/src/monitor/message-handler.process.ts
- **steipete:** recent maintainer
- reason: Recent commits on the visible-reply policy, doctor/docs warning placement, and private group reply behavior changed the same resolver/docs surface after the original group/channel policy landed.
- confidence: medium
- commits: 8989ceee50abd77c33352e36468b341f40591a5e, fc1e2c505ad0ba173b80e0193064798856caf5f4, 82ca6ecdde801a4a858cf63f6400d25bec004308, 2493ab197852ae2f117563582fe948c1bbfa57f9
- files: src/auto-reply/reply/source-reply-delivery-mode.ts, src/auto-reply/reply/dispatch-from-config.ts, docs/channels/groups.md, docs/channels/discord.md
## Risks / Open Questions
- I did not run a live Discord gateway scenario in this read-only review; the reproduction is source- and test-backed.
- A default-visible warning needs care to avoid noisy logs for intentional tool-only rooms.
- none
## Close Comment
_No close comment posted._
Thanks for the context here. I swept through the related work, and this is now duplicate or superseded.
Close as duplicate: the same remaining visible-reply observability/fallback problem is already tracked by the open canonical report at https://github.com/openclaw/openclaw/issues/77320, and current source/tests show this issue is the same `message_tool_only` suppression path rather than a distinct Discord-only transport bug.
So I’m closing this here and keeping the remaining discussion on the canonical linked item.
<details>
<summary>Review details</summary>
Best possible solution:
Track the shared product decision and implementation under https://github.com/openclaw/openclaw/issues/77320: either add a scoped default-visible diagnostic for suppressed non-empty finals or explicitly choose a fallback policy without weakening the private-by-default room contract.
Do we have a high-confidence way to reproduce the issue?
Yes, at source level: current main resolves group/channel turns to `message_tool_only`, suppresses automatic final delivery, and has tests proving no final reply is queued. I did not run a live Discord, WhatsApp, or Telegram scenario in this read-only review.
Is this the best way to solve the issue?
Yes for cleanup: keeping one canonical issue open is the best maintainer path because https://github.com/openclaw/openclaw/issues/77320 tracks the same shared root cause and policy choices. The eventual fix should be made once there, not split across channel-specific duplicates.
Security review:
Security review: Non-PR issue review; no patch security or supply-chain review applies.
What I checked:
- **Canonical related report:** https://github.com/openclaw/openclaw/issues/77320 is open and tracks the same root behavior: group/channel `visibleReplies="message_tool"` turns can finish with assistant text but no visible channel delivery, and the requested fix is a hard diagnostic or fallback policy.
- **Current delivery-mode policy:** Group/channel chats resolve to `message_tool_only` unless configured `automatic`, and that mode sets `suppressAutomaticSourceDelivery` and `suppressDelivery`. ([`src/auto-reply/reply/source-reply-delivery-mode.ts:37`](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/source-reply-delivery-mode.ts#L37), [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3))
- **Current suppression implementation:** The final-reply loop continues without delivery when `suppressDelivery` is true and the payload is not explicitly marked to bypass source-reply suppression. ([`src/auto-reply/reply/dispatch-from-config.ts:1567`](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/dispatch-from-config.ts#L1567), [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3))
- **Regression coverage for this path:** Focused tests assert default group/channel turns use `message_tool_only`, return `queuedFinal: false`, and do not call `sendFinalReply`. ([`src/auto-reply/reply/dispatch-from-config.test.ts:4748`](https://github.com/openclaw/openclaw/blob/71816a3fb24660c1c6af09d77485cf52e52607f3/src/auto-reply/reply/dispatch-from-config.test.ts#L4748), [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3))
- **Docs describe the current workaround:** The group docs now say normal final answers stay private in `message_tool` mode, point to `didSendViaMessagingTool: false`, and recommend `messages.groupChat.visibleReplies: "automatic"` to restore automatic visible final replies. Public docs: [`docs/channels/groups.md`](https://docs.openclaw.ai/channels/groups). ([`docs/channels/groups.md:43`](https://docs.openclaw.ai/channels/groups), [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3))
- **Feature history:** Merged https://github.com/openclaw/openclaw/pull/73046 introduced the safer Discord/group visible-reply behavior and touched the central docs, dispatch, config, and tests. ([3c636208b0a0](https://github.com/openclaw/openclaw/commit/3c636208b0a00ff325e4f48d048d1fd9820f3ea0))
Likely related people:
- **scoootscooob:** Authored merged https://github.com/openclaw/openclaw/pull/73046, which made group/channel visible output depend on explicit message-tool sends and touched the central resolver, dispatch tests, docs, and Discord handling. (role: introduced behavior; confidence: medium; commits: [3c636208b0a0](https://github.com/openclaw/openclaw/commit/3c636208b0a00ff325e4f48d048d1fd9820f3ea0), [85e4ec1fb1ac](https://github.com/openclaw/openclaw/commit/85e4ec1fb1ac78262c1bd7048638ae000e89dc55); files: `src/auto-reply/reply/source-reply-delivery-mode.ts`, `src/auto-reply/reply/dispatch-from-config.ts`, `src/auto-reply/reply/dispatch-from-config.test.ts`)
- **steipete:** Recent commits on the visible-reply policy, doctor/docs warning placement, and private group reply behavior changed the same resolver/docs surface after the original group/channel policy landed. (role: recent maintainer; confidence: medium; commits: [8989ceee50ab](https://github.com/openclaw/openclaw/commit/8989ceee50abd77c33352e36468b341f40591a5e), [fc1e2c505ad0](https://github.com/openclaw/openclaw/commit/fc1e2c505ad0ba173b80e0193064798856caf5f4), [82ca6ecdde80](https://github.com/openclaw/openclaw/commit/82ca6ecdde801a4a858cf63f6400d25bec004308); files: `src/auto-reply/reply/source-reply-delivery-mode.ts`, `src/auto-reply/reply/dispatch-from-config.ts`, `docs/channels/groups.md`)
Codex review notes: model gpt-5.5, reasoning high; reviewed against [71816a3fb246](https://github.com/openclaw/openclaw/commit/71816a3fb24660c1c6af09d77485cf52e52607f3).
</details>
## GitHub Snapshot
- comments: 1
- timeline events: 1
- related items: 0
- comments: 3
- timeline events: 5
- related items: 1
- PR files: 0
- PR commits: 0
## Review Telemetry
- prompt chars: 47610
- static prompt chars: 32829
- context chars: 13524
- prompt chars: 64720
- static prompt chars: 33412
- context chars: 30042
- schema chars: 14081
- additional prompt chars: 0
- context collection ms: 1673
- Codex review ms: 252699
- context collection ms: 1515
- Codex review ms: 208055

22
results/sweep-status/openclaw-openclaw.json
View File

@ -3,15 +3,15 @@
"slug": "openclaw-openclaw",
"display_name": "OpenClaw",
"target_repo": "openclaw/openclaw",
"state": "Apply finished",
"detail": "Apply/comment-sync run finished with 0 fresh closes out of requested limit 0. See apply-report.json for per-item results.",
"run_url": "https://github.com/openclaw/clawsweeper/actions/runs/25584366338",
"planned_count": null,
"planned_capacity": null,
"planned_shards": null,
"active_codex": null,
"due_backlog": null,
"oldest_unreviewed_at": null,
"capacity_reason": null,
"updated_at": "2026-05-08T23:25:19.477Z"
"state": "Hot intake publish complete",
"detail": "Merged 1 hot intake artifacts for run 25584307417 without full folder reconciliation. Captured 1 shard metrics; 0 shards reported non-success review status.",
"run_url": "https://github.com/openclaw/clawsweeper/actions/runs/25584307417",
"planned_count": 1,
"planned_capacity": 1,
"planned_shards": 1,
"active_codex": 0,
"due_backlog": 1111,
"oldest_unreviewed_at": "2026-05-05T13:38:28Z",
"capacity_reason": "saturated: due backlog filled planned capacity",
"updated_at": "2026-05-08T23:27:38.711Z"
}