Make harness verification portable

docs/harness-tuning-progress.md

@@ -48,12 +48,23 @@ Improve AITuner convergence for the `dash0` internal vLLM + Qwen3.5-27B 0-8k cha
 
 ## Remote Experiment Log
 
-Pending. Next steps:
+### 2026-04-25 16:30-16:45 CST
 
-1. Commit and push the harness implementation.
+- Pushed commit `2c5e9af` to `origin/main` and pulled it on `dash0`.
-2. Pull on `dash0` in `/home/admin/cpfs/wjh/aituner/aituner`.
+- Remote prompt check command:
-3. Start a real harness-guided Qwen3.5-27B 0-8k chat tuning run from `configs/examples/dash0_qwen27b_tight_slo_run4_0_8k.json`.
+  - `PYTHONPATH=src python3 -m aituner.cli study prompt --study-root /tmp/aituner-harness-prompt-check/dash0-qwen27b-tight-slo-10min-run4-chat-0-8k --store-root /tmp/aituner-harness-prompt-check --prompt-name harness-check`
-4. Compare the first few iterations against the prior 12-iteration behavior:
+- Harness profile for `chat_w20260311_1000`, after applying the 0-8k filter:
+  - L: p50 1992, p95 7628, p99 8102, tail ratio 3.83, regime `moderate_tail_prefill_sensitive`.
+  - C: repeated token ratio estimate 0.191, repeated block ratio 0.189, multi-turn ratio 0.160, regime `low_prefix_reuse`.
+  - A: request rate 29.52 req/s, p95 1s QPS 40, burst ratio 1.36, regime `smooth`.
+  - Active harnesses: `tensor-parallel-size` and `max-num-batched-tokens`, which matches a TTFT/prefill-sensitive 0-8k chat workload.
+- Remote `compileall` passed.
+- Remote `unittest discover` initially exposed two pre-existing path-sensitive tests that hardcoded `/home/gahow/phd/aituner`; fixed them to derive `REPO_ROOT` from the test file path.
+
+Remaining next steps:
+
+1. Start a real harness-guided Qwen3.5-27B 0-8k chat tuning run from `configs/examples/dash0_qwen27b_tight_slo_run4_0_8k.json`.
+2. Compare the first few iterations against the prior 12-iteration behavior:
    - best request rate per GPU should improve or reach the known good region in fewer trials;
    - proposals should follow the active bottleneck harness;
    - if the incumbent has converged, the LLM should emit `should_stop=true` instead of proposing a weak exploratory config.

tests/test_core_flow.py

@@ -36,6 +36,9 @@ from aituner.worker import (
 from aituner.trace import TraceRequest
 
 
+REPO_ROOT = Path(__file__).resolve().parents[1]
+
+
 def _write_study_assets(
     tmp_path: Path,
     *,
@@ -842,7 +845,7 @@ class CoreFlowTests(unittest.TestCase):
                     "--overwrite",
                 ],
                 check=True,
-                cwd="/home/gahow/phd/aituner",
+                cwd=str(REPO_ROOT),
             )
 
             windows_payload = json.loads((output_root / "windows.json").read_text(encoding="utf-8"))
@@ -907,7 +910,7 @@ class CoreFlowTests(unittest.TestCase):
                     "chat",
                     "--overwrite",
                 ],
-                cwd="/home/gahow/phd/aituner",
+                cwd=str(REPO_ROOT),
                 capture_output=True,
                 text=True,
             )