spec(hunter-learning-loop): gap analysis and design

Feature engineering is the centre: a feature table with switchable columns
is the contract between producers (source.facts_for, semantic facts, entry
points, diff hunks; lizard and Semgrep only after their evaluations), the
ablation runner and the hunter program. DSPy runs the program (ReAct over a
HuntSignature; GEPA and MIPROv2 propose), our rule accepts on held-out
folds. The pilot stays held out; the hook, its client and the core install
are untouched. Requirements approved by the maintainer ('4 first').

Co-Authored-By: Claude Fable 5.1 <[email protected]>

.kiro/specs/hunter-learning-loop/spec.json

@@ -1,16 +1,17 @@
 {
   "feature_name": "hunter-learning-loop",
   "created_at": "2026-10-13T09:05:00+02:00",
-  "updated_at": "2026-10-13T09:20:00+02:00",
+  "updated_at": "2026-10-13T13:30:00+02:00",
   "language": "en",
-  "phase": "requirements-generated",
+  "phase": "design-generated",
   "approvals": {
     "requirements": {
       "generated": true,
-      "approved": false
+      "approved": true,
+      "note": "maintainer 2026-10-13: '4 first' (DSPy for the hunter program)"
     },
     "design": {
-      "generated": false,
+      "generated": true,
       "approved": false
     },
     "tasks": {
@@ -19,4 +20,4 @@
     }
   },
   "ready_for_implementation": false
-}
+}