Skip to content

fix(manager): stop repeated diagnostic loops#975

Open
RerankerGuo wants to merge 1 commit into
agentscope-ai:mainfrom
RerankerGuo:fix/issue-974-manager-diagnostic-loop
Open

fix(manager): stop repeated diagnostic loops#975
RerankerGuo wants to merge 1 commit into
agentscope-ai:mainfrom
RerankerGuo:fix/issue-974-manager-diagnostic-loop

Conversation

@RerankerGuo

Copy link
Copy Markdown

Summary

  • add Manager prompt safeguards against repeating the same no-op or malformed troubleshooting command
  • define Worker deletion completion as the target disappearing from hiclaw get workers
  • update worker lifecycle guidance to avoid looping on Matrix room probes such as copaw channels list after deletion

Fixes #974.

Tests

  • git diff --check
  • rg -n "Diagnostic loop safeguard|Worker deletion is complete|Delete Completion Boundary|Stop repeated diagnostics" manager/agent/AGENTS.md manager/agent/copaw-manager-agent/AGENTS.md manager/agent/skills/worker-management/references/lifecycle.md manager/agent/skills/worker-management/SKILL.md

@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

📊 CI Metrics Report

Summary

Metric Current Baseline Change
LLM Calls 153 81 +72 ↑ +88.9%
Input Tokens 5621347 2803871 +2817476 ↑ +100.5%
Output Tokens 28016 16791 +11225 ↑ +66.9%
Total Tokens 5649363 2820662 +2828701 ↑ +100.3%

By Role

Role Metric Current Baseline Change
🧠 Manager LLM Calls 130 68 +62 ↑ +91.2%
Input Tokens 4868918 2502214 +2366704 ↑ +94.6%
Output Tokens 23113 13725 +9388 ↑ +68.4%
Total Tokens 4892031 2515939 +2376092 ↑ +94.4%
🔧 Workers LLM Calls 23 13 +10 ↑ +76.9%
Input Tokens 752429 301657 +450772 ↑ +149.4%
Output Tokens 4903 3066 +1837 ↑ +59.9%
Total Tokens 757332 304723 +452609 ↑ +148.5%

Per-Test Breakdown

Test Mgr Calls Wkr Calls Δ Calls Mgr In Wkr In Mgr Out Wkr Out Δ Tokens Trend
02-create-worker 7 0 -5 ↓ -41.7% 103216 0 483 0 -254923 ↓ -71.1% ✅ improved
03-assign-task 22 5 +12 ↑ +80.0% 413044 99529 2140 583 +41640 ↑ +8.8% ⚠️ regressed
04-human-intervene 15 0 +2 ↑ +15.4% 395101 0 2074 0 -35823 ↓ -8.3% ⚠️ regressed
05-heartbeat 9 0 +2 ↑ +28.6% 283591 0 2443 0 +10782 ↑ +3.9% ⚠️ regressed
06-multi-worker 77 18 +61 ↑ +179.4% 3673966 652900 15973 4320 +3067025 ↑ +239.6% ⚠️ regressed

Trends

1 test(s) improved (fewer LLM calls)
⚠️ 4 test(s) regressed (more LLM calls)


Generated by HiClaw CI on 2026-07-08 07:01:52 UTC


📦 Download debug logs & test artifacts

@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction / mgr=copaw / wk=hermes)

Commit: 38e4c45
Workflow run: #1503

Test Results
No test output captured.
Debug Log (tail)
No debug logs available.

📦 Download full debug logs & test artifacts

@RerankerGuo RerankerGuo force-pushed the fix/issue-974-manager-diagnostic-loop branch from 25b153e to 38e4c45 Compare July 8, 2026 05:47
@github-actions

github-actions Bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction / mgr=copaw / wk=copaw)

Commit: 38e4c45
Workflow run: #1503

Test Results
No test output captured.
Debug Log (tail)
No debug logs available.

📦 Download full debug logs & test artifacts

@RerankerGuo

Copy link
Copy Markdown
Author

@shiyiyue1102 Hi! Both SHARD_A copaw/copaw and copaw/hermes failed. Same pattern as #984 — in the copaw/hermes case the hiclaw-worker-bob session directory does not exist at all and Manager never invoked hiclaw create worker --name bob — Manager only created alice. The copaw/copaw failure is similar (bob got created but a downstream assertion failed). The failure mode is a test-prompt interpretation flake, not anything in this PR's Manager prompt + worker-management guidance changes.

This PR is docs-only + prompt guidance; it doesn't touch runtime code paths. Could you re-run CI or merge if you agree the flake is unrelated?

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.

简单的使用就会陷入死循环,很慢 || Simple use will cause an infinite loop, which is very slow

1 participant