feat: profile layer — semantic memory (consolidation step 2)

Derive a standing profile of the user from session gists and inject it into
every prompt, so identity/abstract questions ("what kind of player am I",
"what are my leaks") are answered from distilled knowledge instead of noisy
single-vector recall (which finds passages, not patterns).

- memory: profile table + get/set_profile, list_summaries
- lyra/profile.py: rebuild_profile map-reduces all gists (batch -> extract
  durable facts -> fold-merge) into one profile doc; `lyra-profile` CLI
- chat.build_messages injects "What you know about Brian" after the persona

Run after lyra-summarize (needs gists). Verified (stubbed): map-reduce, storage,
and prompt injection.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/chat.py

@@ -39,6 +39,14 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
     """Assemble the full, tiered message list for one turn."""
     messages: list[Message] = [{"role": "system", "content": persona.system_prompt()}]
 
+    # Semantic memory: the distilled profile (who Brian is) — answers identity
+    # questions that raw recall can't. Always in context when it exists.
+    profile = memory.get_profile()
+    if profile:
+        messages.append(
+            {"role": "system", "content": "What you know about Brian:\n" + profile}
+        )
+
     recent = memory.recent(session_id, n=RECENT_N)
     recent_ids = {ex.id for ex in recent}