Skip to content

feat(qwenpaw): adapt worker runtime to QwenPaw 2.0 - #1077

Draft
shiyiyue1102 wants to merge 35 commits into
mainfrom
codex/qwenpaw-2-startup
Draft

feat(qwenpaw): adapt worker runtime to QwenPaw 2.0#1077
shiyiyue1102 wants to merge 35 commits into
mainfrom
codex/qwenpaw-2-startup

Conversation

@shiyiyue1102

Copy link
Copy Markdown
Collaborator

Summary

  • pin the QwenPaw Worker runtime to qwenpaw==2.0.0.post3 and adopt its native startup and schema contracts
  • keep model, MCP, Agent Package skills, Matrix overlay, TeamHarness, and WorkerFlow compatible with QwenPaw 2.0
  • wait for runtime/runtime.yaml before starting local QwenPaw workers
  • add QwenPaw Worker dimensions to the existing integration-test workflow, including the TeamHarness plugin-mode end-to-end test

Why

QwenPaw 2.0 changes its Python/runtime contracts and no longer needs the QwenPaw 1.x source patch used for deferred MCP startup. The existing GitHub integration matrix also covered CoPaw and Hermes workers but did not build or exercise QwenPaw workers.

Validation

  • qwenpaw/.venv/bin/pytest -q qwenpaw/tests — 182 passed, 1 skipped
  • TeamHarness QwenPaw adapter tests — 11 passed
  • WorkerFlow QwenPaw adapter tests — 2 passed
  • focused Controller member-reconcile tests — passed
  • QwenPaw Worker image build, startup, health, and runtime hot-update smoke tests — passed locally
  • workflow YAML parsing and git diff --check — passed

Real model and full Matrix end-to-end behavior are intentionally left to the GitHub Actions integration run, which has the required LLM secret.

Change-Id: I9ad741de07f4b7bfbbe3721030df8749546a0def
@shiyiyue1102
shiyiyue1102 force-pushed the codex/qwenpaw-2-startup branch from 6e3cd41 to 912cfd3 Compare July 25, 2026 14:02
@github-actions

github-actions Bot commented Jul 25, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (controller-cr-2 / mgr=copaw / wk=copaw)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

@github-actions

github-actions Bot commented Jul 25, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (controller-cr / mgr=copaw / wk=copaw)

Commit: fbdf762
Workflow run: #1786

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

📦 Download full debug logs & test artifacts

@github-actions

github-actions Bot commented Jul 25, 2026

Copy link
Copy Markdown
Contributor

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

Commit: bcb6ed0
Workflow run: #1751

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

📦 Download full debug logs & test artifacts

@github-actions

github-actions Bot commented Jul 25, 2026

Copy link
Copy Markdown
Contributor

📊 CI Metrics Report

Summary

Metric Current Baseline Change
LLM Calls 117 97 +20 ↑ +20.6%
Input Tokens 3212392 2719498 +492894 ↑ +18.1%
Output Tokens 30112 16508 +13604 ↑ +82.4%
Total Tokens 3242504 2736006 +506498 ↑ +18.5%

By Role

Role Metric Current Baseline Change
🧠 Manager LLM Calls 64 72 -8 ↓ -11.1%
Input Tokens 1911018 2092724 -181706 ↓ -8.7%
Output Tokens 11212 10274 +938 ↑ +9.1%
Total Tokens 1922230 2102998 -180768 ↓ -8.6%
🔧 Workers LLM Calls 53 25 +28 ↑ +112.0%
Input Tokens 1301374 626774 +674600 ↑ +107.6%
Output Tokens 18900 6234 +12666 ↑ +203.2%
Total Tokens 1320274 633008 +687266 ↑ +108.6%

Per-Test Breakdown

Test Mgr Calls Wkr Calls Δ Calls Mgr In Wkr In Mgr Out Wkr Out Δ Tokens Trend
02-create-worker 4 0 -1 ↓ -20.0% 115162 0 518 0 -21308 ↓ -15.6% ✅ improved
03-assign-task 10 5 +2 ↑ +15.4% 293246 111681 1674 705 +97126 ↑ +31.3% ⚠️ regressed
04-human-intervene 22 13 +21 ↑ +150.0% 512234 282023 3222 1246 +462288 ↑ +137.4% ⚠️ regressed
05-heartbeat 5 4 +2 ↑ +28.6% 149354 98598 910 447 +51105 ↑ +25.8% ⚠️ regressed
06-multi-worker 23 31 -4 ↓ -6.9% 841022 809072 4888 16502 -82713 ↓ -4.7% ✅ improved

Trends

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


Generated by AgentTeams CI on 2026-07-27 18:47:58 UTC


📦 Download debug logs & test artifacts

Change-Id: I7d7930c2391217d2c1887eb4d7e20449b4b16ce8
@github-actions

github-actions Bot commented Jul 25, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (qwenpaw-teamharness / mgr=copaw / wk=qwenpaw)

Commit: 66f5c96
Workflow run: #1781

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

📦 Download full debug logs & test artifacts

Change-Id: I3073b27f43f0ecde4e6fa2164fd49d2659d50dcf
@shiyiyue1102

Copy link
Copy Markdown
Collaborator Author

@maplefeng-a CI 中发现的问题正在处理中。麻烦有空帮忙 review 一下这次整体改动逻辑是否有问题,重点可以看下 QwenPaw 2.0 的 runtime.yaml desired-state、Worker 启动和热更新链路。谢谢!

Change-Id: I31687da14f2d40bfb50dade36a8d7467e9aa8ddd
Change-Id: Ieeed7e69bf3b23e3f03aaa5168e4fe807040c1fe
@github-actions

Copy link
Copy Markdown
Contributor

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

Commit: 88f97c2
Workflow run: #1733

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

📦 Download full debug logs & test artifacts

@github-actions

github-actions Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (controller-cr / mgr=copaw / wk=qwenpaw)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

Change-Id: I9b2094e39e7dfc12437aedf347199ace79de1f5b
@github-actions

github-actions Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (controller-cr / mgr=copaw / wk=hermes)

Commit: 66b87bd
Workflow run: #1780

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

📦 Download full debug logs & test artifacts

Change-Id: I04a62daf94efad6d0445dce93a56cf897530c25e
@github-actions

github-actions Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (controller-cr / mgr=openclaw / wk=openclaw)

Commit: 66b87bd
Workflow run: #1780

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

📦 Download full debug logs & test artifacts

shiyiyue1102 and others added 11 commits July 26, 2026 12:37
Change-Id: I7af2aece15ab2c733754beee59e31d377ca1d810
Change-Id: I55ac99d6d22041bc7e0d229449fd0333f6ca8a29
Change-Id: I961ed24fb022cbe8ac01fab81dfe018a00c14a5d
Change-Id: Ic437642f20426d03f585442fb06867ede35e6151
Change-Id: I352dc6fa16715f0ce03ce00931e61a0abadc4efc
Change-Id: I03e49cd512911c176c9a8cb3d407877fdf8b2363
Change-Id: I50577926a078ed50232e3eb6af6583d1162be7df
Change-Id: I88060c8e6c49862205ec602de2ae3e72a4f2c879
Change-Id: I37fe3a251d02b74e1a8ef6b5c35b39c811b11914
@github-actions

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction-2 / mgr=copaw / wk=hermes)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

@github-actions

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction-2 / mgr=openclaw / wk=openclaw)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

@github-actions

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction-2 / mgr=copaw / wk=copaw)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

@github-actions

Copy link
Copy Markdown
Contributor

❌ Integration Tests Failed (llm-interaction-2 / mgr=copaw / wk=qwenpaw)

Commit: d44de0c
Workflow run: #1789

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

📦 Download full debug logs & test artifacts

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