refactor(arms): run arms from a typed ArmsRunConfig instead of the parsed Namespace

dokimi/docs/architecture.md

@@ -152,7 +152,9 @@ where the model decides to call a doc-search or skill tool (`agent:`,
 The spec grammar — what an `--arms` entry means, where `+` splits a combined
 spec, and what each arm is *named* — is `treatments/specs.py`.
 `eval/arm_runner.py` generates and judges answers for every arm and reports
-per-arm deltas vs a baseline. `dokimi/plugins.py` adds runtime plugins that
+per-arm deltas vs a baseline. `eval/arms_run.py` runs it from an `ArmsRunConfig`,
+the one typed run configuration `arms run`, `arms matrix-run` (one per cell) and
+`subjects run` build from their flags. `dokimi/plugins.py` adds runtime plugins that
 modify every arm inside one run (`plugin:caveman`): a plugin changes the system
 prompt before the model runs or reshapes the answer after it. Entry point:
 `python cli.py arms run`. Details in

dokimi/docs/evaluating-treatments.md

@@ -2,6 +2,7 @@
 depends_on:
   - dokimi/dokimi/treatments/**
   - dokimi/dokimi/commands/arms.py
+  - dokimi/dokimi/eval/arms_run.py
   - dokimi/dokimi/schemas/arms.v1.json
   - dokimi/dokimi/skills/loader.py
   - dokimi/dokimi/agent_profiles/loader.py

dokimi/dokimi/commands/judge_reliability.py

@@ -118,7 +118,7 @@ def _check_judge_temperature(judges: list[tuple[str, str]], temperature) -> None
     """Exit 2 before any judgement when a (model, provider) judge rejects ``temperature``."""
     if temperature is None:
         return
-    from dokimi.commands.arms import _probe_sampling
+    from dokimi.eval.arms_run import probe_sampling
     from dokimi.llm import unsupported_sampling_params
     from dokimi.utils import bedrock_litellm_model
 
@@ -128,7 +128,7 @@ def _check_judge_temperature(judges: list[tuple[str, str]], temperature) -> None
         try:
             if unsupported_sampling_params(resolved, provider, temperature=temperature):
                 raise ValueError(f"provider '{provider}' does not support temperature for model '{model}'")
-            _probe_sampling(resolved, provider, temperature, None)
+            probe_sampling(resolved, provider, temperature, None)
         except ValueError as exc:
             print(f"Error: --judge-temperature {temperature} is rejected by judge {provider}/{model}: {exc}",
                   file=sys.stderr)

dokimi/dokimi/commands/subjects.py

@@ -88,11 +88,7 @@ def cmd_subjects_show(args: argparse.Namespace) -> None:
 def cmd_subjects_run(args: argparse.Namespace) -> None:
     """Run awareness matrix cells for one subject and write a scorecard."""
     from dokimi.artifacts import load_artifact, save_artifact
-    from dokimi.commands.arms import (
-        _safe_name,
-        cmd_arms_matrix_run,
-        forwarded_run_config,
-    )
+    from dokimi.commands.arms import _safe_name, run_config_from_args, run_matrix
     from dokimi.report.subject_report import render_subject_scorecard
     from dokimi.subjects import build_subject_scorecard, load_subject
     from dokimi.subjects.loader import awareness_arm_specs
@@ -137,19 +133,12 @@ def cmd_subjects_run(args: argparse.Namespace) -> None:
         run_dir = out_dir / _safe_name(product)
         rollup_json = run_dir / "matrix-rollup.json"
         rollup_md = run_dir / "matrix-rollup.md"
-        run_args = argparse.Namespace(
-            product=product,
-            questions=questions_path,
-            arms=",".join(awareness_arm_specs(descriptor)),
-            matrix_cells=str(matrix_path),
-            matrix_cell=None,
-            out_dir=str(run_dir),
-            out_json=str(rollup_json),
-            out_md=str(rollup_md),
+        run_matrix(
+            run_config_from_args(args, product=product, baseline_arm=baseline_arm),
+            arms=",".join(awareness_arm_specs(descriptor)), questions=questions_path,
+            matrix_cells=str(matrix_path), out_dir=run_dir, out_json=rollup_json, out_md=rollup_md,
             plugin_deltas=not args.no_plugin_deltas,
-            **forwarded_run_config(args, plugins="", baseline_arm=baseline_arm),
         )
-        cmd_arms_matrix_run(run_args)
         awareness_runs.append({
             "product": product,
             "questions": questions_path,