Evaluate baseline before LLM tuning

src/aituner/cli.py

@@ -113,7 +113,7 @@ def cmd_study_tune(args: argparse.Namespace) -> int:
     study_root = store.init_study(spec_path=spec_path, study=study)
     capability_profile = load_capability_profile(study, study_spec_path=spec_path)
     proposal_files = [Path(item).resolve() for item in (args.proposal_file or [])]
-    max_trials = args.max_trials or (len(proposal_files) if proposal_files else 1)
+    max_trials = args.max_trials or (len(proposal_files) if proposal_files else 2)
     if max_trials <= 0:
         raise SpecError("max_trials must be positive")
     if proposal_files and max_trials > len(proposal_files):
@@ -134,7 +134,29 @@ def cmd_study_tune(args: argparse.Namespace) -> int:
         prompt_name = f"prompt-{state.next_trial_index:04d}"
         store.write_prompt(study.study_id, prompt_name, prompt)
 
-        if proposal_files:
+        if (
+            not proposal_files
+            and not args.skip_baseline
+            and state.next_trial_index == 1
+            and not state.trials
+        ):
+            proposal_source = None
+            proposal_name = "baseline-0001"
+            proposal_text = json.dumps(
+                {
+                    "observation": "Evaluate the study's initial engine configuration before LLM-guided edits.",
+                    "diagnosis": "Baseline trial aligned with the AITuner evaluate-then-search loop.",
+                    "config_patch": {"env_patch": {}, "flag_patch": {}},
+                    "expected_effects": [
+                        "establish incumbent performance",
+                        "provide bottleneck evidence for harness-guided proposals",
+                    ],
+                    "why_not_previous_failures": "No config changes are applied.",
+                    "should_stop": False,
+                },
+                ensure_ascii=False,
+            )
+        elif proposal_files:
             proposal_source = proposal_files[idx]
             proposal_text = proposal_source.read_text(encoding="utf-8")
             proposal_name = proposal_source.stem
@@ -264,6 +286,11 @@ def build_parser() -> argparse.ArgumentParser:
     tune.add_argument("--store-root")
     tune.add_argument("--proposal-file", action="append")
     tune.add_argument("--max-trials", type=int)
+    tune.add_argument(
+        "--skip-baseline",
+        action="store_true",
+        help="Do not automatically evaluate the initial config before LLM proposals.",
+    )
     tune.set_defaults(func=cmd_study_tune)
 
     worker = subparsers.add_parser("worker")