test: make multi-worker bob setup deterministic

[RerankerGuo]

Summary

• make test-06-multi-worker create Bob via hiclaw apply worker instead of a Manager DM request
• keep the rest of the test focused on multi-worker collaboration after Alice and Bob exist
• avoid CI flakes where the Manager is still processing heartbeat/task follow-ups or hits tool-guard approval before creating Bob

Why

Recent failures on #972, #983, #984, and older PRs all failed in test-06-multi-worker with the same pattern: the Manager did not produce a matching Bob creation reply, wait_worker_provisioned bob timed out, hiclaw get workers bob returned 404, and hiclaw-worker-bob did not exist. The logs also show the Manager processing unrelated heartbeat/task work or denied shell commands during the Bob creation window.

This makes Bob creation an unreliable LLM interaction inside a test whose stated purpose is multi-worker collaboration. test-02-create-worker already covers Manager-mediated worker creation for Alice; test-06 can use deterministic setup for Bob.

Verification

• bash -n tests/test-06-multi-worker.sh
• git diff --check

I could not run the embedded integration test locally because this environment cannot access /var/run/docker.sock (permission denied).

[github-actions]

📊 CI Metrics Report

Summary

Metric	Current	Baseline	Change
LLM Calls	147	81	+66 ↑ +81.5%
Input Tokens	5209931	2803871	+2406060 ↑ +85.8%
Output Tokens	38619	16791	+21828 ↑ +130.0%
Total Tokens	5248550	2820662	+2427888 ↑ +86.1%

By Role

Role	Metric	Current	Baseline	Change
🧠 Manager	LLM Calls	92	68	+24 ↑ +35.3%
	Input Tokens	3319336	2502214	+817122 ↑ +32.7%
	Output Tokens	16853	13725	+3128 ↑ +22.8%
	Total Tokens	3336189	2515939	+820250 ↑ +32.6%
🔧 Workers	LLM Calls	55	13	+42 ↑ +323.1%
	Input Tokens	1890595	301657	+1588938 ↑ +526.7%
	Output Tokens	21766	3066	+18700 ↑ +609.9%
	Total Tokens	1912361	304723	+1607638 ↑ +527.6%

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	-8 ↓ -66.7%	107727	0	694	0	-250201 ↓ -69.8%	✅ improved
03-assign-task	12	6	+3 ↑ +20.0%	329985	135237	1744	907	-5783 ↓ -1.2%	⚠️ regressed
04-human-intervene	18	10	+15 ↑ +115.4%	464566	247203	2495	1113	+282379 ↑ +65.2%	⚠️ regressed
05-heartbeat	9	7	+9 ↑ +128.6%	289127	152095	2126	751	+168847 ↑ +61.3%	⚠️ regressed
06-multi-worker	49	32	+47 ↑ +138.2%	2127931	1356060	9794	18995	+2232646 ↑ +174.4%	⚠️ regressed

Trends

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

---

Generated by HiClaw CI on 2026-07-03 09:09:38 UTC

---

📦 Download debug logs & test artifacts