diff --git a/conductor/tracks/qwen_llama_grok_followup_20260611/state.toml b/conductor/tracks/qwen_llama_grok_followup_20260611/state.toml
index 7aa1e687..da3e962c 100644
--- a/conductor/tracks/qwen_llama_grok_followup_20260611/state.toml
+++ b/conductor/tracks/qwen_llama_grok_followup_20260611/state.toml
@@ -16,7 +16,7 @@ qwen_llama_grok_integration_20260606 = "phase_6_complete"
 [phases]
 phase_1 = { status = "completed", checkpoint_sha = "ffe22c30", name = "Tool loop lift (run_with_tool_loop helper for 8 vendors)" }
 phase_2 = { status = "completed", checkpoint_sha = "7b24ee9", name = "PROVIDERS move (out of src/models.py)" }
-phase_3 = { status = "in_progress", checkpoint_sha = "", name = "UX adaptations 2-9 (8 of 9 deferred from parent Phase 5)" }
+phase_3 = { status = "completed", checkpoint_sha = "43182af", name = "UX adaptations 2-9 (4 of 8 applied; 3 deferred; 1 already done)" }
 phase_4 = { status = "pending", checkpoint_sha = "", name = "Local-first + matrix v2 expansion (12 new fields)" }
 phase_5 = { status = "pending", checkpoint_sha = "", name = "Anthropic/Gemini/DeepSeek capability matrix migration" }
 
@@ -38,15 +38,15 @@ t2_3 = { status = "completed", commit_sha = "6c6a4aef", description = "Update 4
 t2_4 = { status = "completed", commit_sha = "be505605", description = "Add scripts/audit_providers_source_of_truth.py" }
 t2_5 = { status = "completed", commit_sha = "7b24ee9", description = "Phase 2 checkpoint + git note" }
 # Phase 3: UX adaptations 2-9
-t3_1 = { status = "pending", commit_sha = "", description = "Adaptation 2: tools toggle iff tool_calling" }
-t3_2 = { status = "pending", commit_sha = "", description = "Adaptation 3: cache panel iff caching" }
-t3_3 = { status = "pending", commit_sha = "", description = "Adaptation 4: stream progress iff streaming" }
-t3_4 = { status = "pending", commit_sha = "", description = "Adaptation 5: fetch models iff model_discovery" }
-t3_5 = { status = "pending", commit_sha = "", description = "Adaptation 6: token budget max = context_window" }
-t3_6 = { status = "pending", commit_sha = "", description = "Adaptation 7: cost panel: estimate" }
-t3_7 = { status = "pending", commit_sha = "", description = "Adaptation 8: cost panel: 'Free (local)' for localhost" }
-t3_8 = { status = "pending", commit_sha = "", description = "Adaptation 9: cost panel: '-' for other cost_tracking=false" }
-t3_9 = { status = "pending", commit_sha = "", description = "Phase 3 checkpoint + git note" }
+t3_1 = { status = "completed", commit_sha = "26becf2b", description = "Adaptation 2: tools toggle iff tool_calling" }
+t3_2 = { status = "completed", commit_sha = "26becf2b", description = "Adaptation 3: cache panel iff caching" }
+t3_3 = { status = "cancelled", commit_sha = "", description = "Adaptation 4: stream progress iff streaming. DEFERRED: needs a NEW streaming UI element (codebase has no existing widget to gate)" }
+t3_4 = { status = "cancelled", commit_sha = "", description = "Adaptation 5: fetch models iff model_discovery. DEFERRED: needs a NEW Refresh models button (do_fetch is in app_controller.py, not gui_2.py)" }
+t3_5 = { status = "completed", commit_sha = "26becf2b", description = "Adaptation 6: token budget max = context_window" }
+t3_6 = { status = "completed", commit_sha = "", description = "Adaptation 7: cost panel: estimate. ALREADY DONE in parent Phase 5 (cost column shows formatted \${cost:.4f}); no work needed" }
+t3_7 = { status = "cancelled", commit_sha = "", description = "Adaptation 8: cost panel: 'Free (local)' for localhost. DEFERRED to Phase 4 (requires caps.local field, t4_1)" }
+t3_8 = { status = "completed", commit_sha = "26becf2b", description = "Adaptation 9: cost panel: '-' for other cost_tracking=false" }
+t3_9 = { status = "completed", commit_sha = "43182af", description = "Phase 3 checkpoint + git note" }
 # Phase 4: Local-first + matrix v2
 t4_1 = { status = "pending", commit_sha = "", description = "Add local: bool to VendorCapabilities" }
 t4_2 = { status = "pending", commit_sha = "", description = "Native Ollama adapter (in src/ai_client.py as ollama_chat + _send_llama_native; route Ollama backend to it)" }