bench(learn): harvest signals for the decision engine (decision-engine task 5)

`ousast plane harvest` (plane/harvest.py) writes two Runs over a label snapshot:
verify a/b + agree on the verify-family units (both sides of each labelled pair as
an opaque files-only Workspace, candidates outside the hunt's root, no declared
sites; v1 and dev-php pins with repo-facts first) and model roles on the candidate
files (pair excerpts grouped, one Task per population pin). Budgets sum under the
ceiling by construction. New roles task template; the generator re-pins it.

Spent by attribution: verify $2.54 (1961 calls, 150 units, 182 hunts per pass),
roles $1.40 (1034 calls, 799 files, 0 unclassified chunks); DeepSeek balance
19.63 -> 18.23. Engine on the pair corpus (benchmarks/learn/engine_pairs.py,
frozen e6ed785, one 3g container) is PARTIAL: 384 of 686 sides at commit, still
running; unfinished sides stay missing. benchmarks/learn/build_features.py built
1712 static+plane records into the memory store; counts-only record under
benchmarks/measurements/2026-10-01-decision-engine-harvest/.

source/roles parts are `none`, not `failed`, for a language without a declaration
pattern (C). ops/ax/README: Substrate golden-actor disk leak and the inline
Workspace limit (~20 KB).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

.kiro/specs/learned-decision-engine/tasks.md

@@ -28,10 +28,14 @@ the maintainer confirms its budget.
     commits (separate, never merged); a first label snapshot committed as counts only.
   - _Requirements: 2.1, 2.2, 2.3, 7.1_
 
-- [ ] 5. Harvest (needs budget go-ahead)
+- [x] 5. Harvest (needs budget go-ahead)
   - A plane Run of verify a/b on the verify-family pairs and development cases (~$6, ceiling $10), model roles on
     the candidate files (ceiling $10), engine features for the pair corpus on the host (frozen source, one
     container at a time, background).
+  - Done 2026-10-01 (`benchmarks/measurements/2026-10-01-decision-engine-harvest/record.json`): verify $2.54 and roles
+    $1.40 by attribution. The engine part was PARTIAL at commit (384 of 686 pair sides recorded, the job still
+    running): unfinished sides are `missing` in the feature records; rebuild them with
+    `benchmarks/learn/build_features.py` once `benchmarks/learn/engine_pairs.py` has finished.
   - _Requirements: 1.1_
 
 - [ ] 6. Train, calibrate, evaluate