Skip to content

fix(copaw): harden Matrix channel routing#989

Merged
shiyiyue1102 merged 1 commit into
agentscope-ai:mainfrom
shiyiyue1102:codex/copaw-matrix-hardening-20260704
Jul 4, 2026
Merged

fix(copaw): harden Matrix channel routing#989
shiyiyue1102 merged 1 commit into
agentscope-ai:mainfrom
shiyiyue1102:codex/copaw-matrix-hardening-20260704

Conversation

@shiyiyue1102

Copy link
Copy Markdown
Collaborator

Summary

  • require Matrix group-room control commands to be explicitly mentioned and slash-prefixed
  • route reasoning/tool progress into task threads while keeping final replies visible in the main room
  • suppress NO_REPLY and cancellation noise in CoPaw Matrix output

Validation

  • python3 -m py_compile copaw/src/matrix/channel.py copaw/tests/test_channel_mention.py
  • git diff --check

uv run --python 3.11 --project copaw pytest tests/test_channel_mention.py was attempted locally but could not build python-olm==3.2.16 on this macOS environment because its native libolm build needs unavailable/incompatible local C++ build tooling (cmake/gmake, then clang const assignment failure). GitHub CI should run the normal Linux test environment.

Change-Id: Ib4e4d9b3ebf4eadb9a6d136b4e3c289067a66c52
@shiyiyue1102 shiyiyue1102 requested a review from maplefeng-a July 4, 2026 09:17
@github-actions

github-actions Bot commented Jul 4, 2026

Copy link
Copy Markdown
Contributor

📊 CI Metrics Report

Summary

Metric Current Baseline Change
LLM Calls 147 81 +66 ↑ +81.5%
Input Tokens 4336117 2803871 +1532246 ↑ +54.6%
Output Tokens 28055 16791 +11264 ↑ +67.1%
Total Tokens 4364172 2820662 +1543510 ↑ +54.7%

By Role

Role Metric Current Baseline Change
🧠 Manager LLM Calls 87 68 +19 ↑ +27.9%
Input Tokens 2779537 2502214 +277323 ↑ +11.1%
Output Tokens 15548 13725 +1823 ↑ +13.3%
Total Tokens 2795085 2515939 +279146 ↑ +11.1%
🔧 Workers LLM Calls 60 13 +47 ↑ +361.5%
Input Tokens 1556580 301657 +1254923 ↑ +416.0%
Output Tokens 12507 3066 +9441 ↑ +307.9%
Total Tokens 1569087 304723 +1264364 ↑ +414.9%

Per-Test Breakdown

Test Mgr Calls Wkr Calls Δ Calls Mgr In Wkr In Mgr Out Wkr Out Δ Tokens Trend
02-create-worker 6 0 -6 ↓ -50.0% 166449 0 810 0 -191363 ↓ -53.4% ✅ improved
03-assign-task 13 12 +10 ↑ +66.7% 362452 260845 2445 2134 +154220 ↑ +32.6% ⚠️ regressed
04-human-intervene 11 0 -2 ↓ -15.4% 273271 0 2063 0 -157664 ↓ -36.4% ✅ improved
05-heartbeat 6 0 -1 ↓ -14.3% 183063 0 1307 0 -90882 ↓ -33.0% ✅ improved
06-multi-worker 51 48 +65 ↑ +191.2% 1794302 1295735 8923 10373 +1829199 ↑ +142.9% ⚠️ regressed

Trends

3 test(s) improved (fewer LLM calls)
⚠️ 2 test(s) regressed (more LLM calls)


Generated by HiClaw CI on 2026-07-04 10:23:16 UTC


📦 Download debug logs & test artifacts

@shiyiyue1102

Copy link
Copy Markdown
Collaborator Author

@maplefeng-a CI is green now. Could you take a look when convenient?

@maplefeng-a maplefeng-a left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

CI is green and the CoPaw-scoped change looks good under the agreed review policy. Approving.

@shiyiyue1102 shiyiyue1102 merged commit 03c180f into agentscope-ai:main Jul 4, 2026
21 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants