spec(learned-decision-engine): Req 3 -- an AI classifier with local memory, DSPy-style

Maintainer: data will not scale; the decision engine is an AI classifier, not ML,
with local memory, DSPy style. In-house on the metered client; retrieval by signal
profile re-ranked by code embeddings; compiled (bootstrap few-shot, instruction
search) per training fold; retrieval never crosses the evaluation boundary;
confidence calibrated on held-out repositories. Design and tasks 6+ to revise.

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

.kiro/specs/learned-decision-engine/spec.json

@@ -1,9 +1,9 @@
 {
   "feature_name": "learned-decision-engine",
   "created_at": "2026-09-30T14:00:00Z",
-  "updated_at": "2026-09-30T16:30:00Z",
+  "updated_at": "2026-10-01T09:00:00Z",
   "language": "en",
-  "phase": "implementation",
+  "phase": "requirements-amended",
   "approvals": {
     "requirements": {
       "generated": true,
@@ -11,12 +11,13 @@
     },
     "design": {
       "generated": true,
-      "approved": true
+      "approved": false
     },
     "tasks": {
       "generated": true,
-      "approved": true
+      "approved": false
     }
   },
-  "ready_for_implementation": true
+  "ready_for_implementation": true,
+  "note": "2026-10-01: Req 3 changed to an AI classifier with local memory (DSPy-style, in-house); design and tasks 6+ to be revised; tasks 1-5 remain valid."
 }