feat(memory): T03 complete — memory wired into orchestrator (consult + --explain-context surface + context to LLM + render); T01-T03 now done in workplan (ralph iters 1-3)

src/cya/orchestrator.py

@@ -23,6 +23,7 @@ from rich.console import Console
 from rich.panel import Panel
 
 from cya.context.collector import collect, render_explanation
+from cya.memory import recall_preferences
 from cya.safety.risk import classify, get_user_confirmation
 from cya.llm.adapter import AssistanceRequest, FakeLLMAdapter
 
@@ -62,7 +63,29 @@ def handle_request(
         except Exception as exc:
             console.print(f"[red]Context explanation error: {exc}[/red]")
 
-    # 2. Risk classification + mandatory confirmation (T03)
+    # T03 (memory wiring): consult after context (so safety can see it in future T04 0002),
+    # before risk/LLM. Real T02 prefs now available; graceful.
+    memory = {}
+    try:
+        memory = recall_preferences(".")
+    except Exception:
+        memory = {"error": "recall failed (graceful degradation)"}
+
+    if explain_context and memory.get("items"):
+        try:
+            prov = memory.get("provenance", [{}])[0]
+            console.print(
+                Panel(
+                    f"Phase: {memory.get('phase')} | {len(memory.get('items', []))} items | {prov.get('source', 'local')}",
+                    title="Memory Consulted (T03)",
+                    border_style="blue",
+                    padding=(0, 1),
+                )
+            )
+        except Exception:
+            pass
+
+    # 2. Risk classification + mandatory confirmation (T03 safety; T04 0002 will feed memory signals)
     assessment = classify(user_request, envelope)
 
     if assessment.requires_confirmation:
@@ -91,18 +114,23 @@ def handle_request(
 
     # 3. Call through the single LLMAdapter boundary (T04)
     adapter = FakeLLMAdapter()
+    ctx = (envelope.to_dict() if envelope else {}) or {}
+    ctx["memory"] = memory  # T03: memory now in context passed to LLM (for personalization + explain)
     llm_request = AssistanceRequest(
         user_request=user_request,
-        context=envelope.to_dict() if envelope else None,
+        context=ctx,
     )
     llm_response = adapter.complete(llm_request)
 
-    # 4. Render final user-facing artifact (T06 responsibility)
+    # 4. Render final user-facing artifact (T06 responsibility; T03 memory surface)
+    mem_line = ""
+    if memory.get("items"):
+        mem_line = f"\n[dim]Memory: {len(memory.get('items', []))} prefs (phase {memory.get('phase')}, {memory.get('provenance', [{}])[0].get('source', 'local')})[/dim]"
     console.print(
         Panel(
             f"[bold]Suggestion:[/bold]\n{llm_response.suggestion}\n\n"
             f"[dim]{llm_response.explanation}\n"
-            f"Rationale: {llm_response.rationale}[/dim]",
+            f"Rationale: {llm_response.rationale}{mem_line}[/dim]",
             title="LLM Response (via T04 seam)",
             border_style="magenta",
             padding=(1, 1),