docs: update decoupling report with deletion commit details

docs/reports/ai_decoupling_revert_report.md

@@ -58,13 +58,38 @@ Timeline of discovery:
 - `sloppy.py` - Added AI_SERVER_ENABLED routing
 - `src/app_controller.py` - Lazy rag_engine import, async RAG init
 
-## Files That Should Be Removed/Restored
+## Files That Were Deleted
 
-The following changes represent incomplete decoupling that should be cleaned up:
+The following files were created during the attempt and subsequently deleted:
 
-1. `src/ai_client_stub.py` - Should be evaluated for deletion if AI server is not implemented
+| File | Size | Purpose | Deleted |
-2. `src/ai_client_proxy.py` - Same as above
+|------|------|---------|---------|
-3. Environment variable `AI_SERVER_ENABLED` in `sloppy.py` - No longer needed if decoupling is removed
+| `src/ai_client_stub.py` | 14KB | Lightweight stub module for routing AI calls | ✅ (commit b2fdca0c) |
+| `src/ai_client_proxy.py` | 3.6KB | Proxy client for spawning AI server subprocess | ✅ (commit b2fdca0c) |
+
+## Cleanup Commits
+
+### Commit b2fdca0c (2026-05-13)
+```
+remove(ai_client): delete unused stub and proxy files
+
+Deleted:
+- src/ai_client_stub.py
+- src/ai_client_proxy.py
+
+Fixed test imports to use ai_client instead of ai_client_stub.
+```
+
+### Commit 4025a713 (2026-05-13)
+```
+revert(ai_client): remove incomplete decoupling, restore clean startup
+
+The AI client decoupling was never properly implemented and added
+unnecessary complexity. The actual startup bottleneck was RAG initialization
+which is now handled via async initialization.
+
+Report written to docs/reports/ai_decoupling_revert_report.md
+```
 
 ## Current State
 
@@ -78,11 +103,11 @@ After reverting the decoupling attempt:
 
 The application now starts quickly with RAG loading in the background.
 
-## Recommendations
+## Recommendations (Completed)
 
-1. **If AI server is not implemented:** Remove `ai_client_stub.py`, `ai_client_proxy.py`, and clean up `sloppy.py`
+1. ✅ **Cleanup done:** `ai_client_stub.py`, `ai_client_proxy.py` deleted, `sloppy.py` restored
 
-2. **If AI server is needed:** Implement it properly as a separate concern, not as a module replacement hack
+2. **If AI server is needed in future:** Implement properly as a separate concern, not as a module replacement hack
 
 3. **Keep async RAG init:** The background thread for RAG is a good pattern and should remain