docs: Update phased plan with Phase 2/2b/2c completion status

- Mark Phase 2 (Devstral backend support) as COMPLETE
- Mark Phase 2b (Frontend dynamic layers) as COMPLETE
- Mark Phase 2c (API route conversion) as COMPLETE (partial)
- Note Spark toggle deferred until PyTorch GB10 support
- Update tag references

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

docs/devstral-spark-plan-phased.md

@@ -1817,10 +1817,25 @@ Before marking each phase complete, verify:
 - [x] **Phase 0**: Secure GPU HF Space + verify basic routing ✅ COMPLETE
 - [x] **Phase 0.5**: Fix critical API route routing (prove GPU routing works) ✅ COMPLETE
 - [ ] **Phase 1**: Deploy CodeGen to DGX Spark ⏸️ PAUSED (see blocker below)
-- [ ] **Phase 2**: Add Devstral backend support
-- [ ] **Phase 2b**: Frontend dynamic layer handling
-- [ ] **Phase 2c**: Wire Spark into frontend backend router + Deploy Devstral to GPU HF Space
-- [ ] **Phase 3**: Deploy Devstral to DGX Spark
+- [x] **Phase 2**: Add Devstral backend support ✅ COMPLETE
+  - MistralAdapter added for Mistral/Devstral architecture
+  - devstral-small config with 40 layers, GQA (32 Q heads, 8 KV heads)
+  - Model-specific dtype (recommended_dtype field: codegen→fp16, devstral→bf16)
+  - Percentage-based layer classification (works for any layer count)
+  - /models and /models/current endpoints added
+  - Environment variable support (DEFAULT_MODEL, TORCH_DTYPE, MAX_CONTEXT, BATCH_SIZE)
+- [x] **Phase 2b**: Frontend dynamic layer handling ✅ COMPLETE
+  - Percentage-based stage boundaries in VerticalPipeline
+  - Dynamic vocab size from modelInfo
+  - Dynamic head_dim derived from actual matrix data
+  - Removed hardcoded "64 dimensions" in tutorial
+- [x] **Phase 2c**: API route conversion ✅ COMPLETE (partial)
+  - All 8 API routes converted to use backendFetch helper
+  - Server-side auth with HF token for private Spaces
+  - Per-user backend routing working
+  - ⏸️ Spark toggle deferred (no benefit until PyTorch supports GB10)
+  - ⏸️ GPU HF Space Devstral deployment pending (requires VRAM upgrade)
+- [ ] **Phase 3**: Deploy Devstral to DGX Spark ⏸️ BLOCKED (PyTorch sm_121 support)
 - [ ] **Phase 4**: Future enhancements (optional)
 
 ---
@@ -1933,9 +1948,15 @@ When PyTorch officially supports sm_121 (expected in PyTorch 2.9.x patch or 2.10
 
 ### Pre-Devstral Tag
 
-Before making these changes, both repos were tagged: `pre-devstral-v1`
+Before making Phase 2 changes, both repos were tagged: `pre-devstral-phase2-v1`
 
 To restore to this state if needed:
 ```bash
-git checkout pre-devstral-v1
+git checkout pre-devstral-phase2-v1
 ```
+
+### Phase 2 Completion Tags
+
+After Phase 2/2b/2c completion (December 2024):
+- Backend: Contains MistralAdapter, devstral-small config, /models endpoints
+- Frontend: Contains dynamic layer handling, backendFetch conversion