feat: tiered, compacting memory (phase 1.5)

Older sessions fade to a general idea; details stay retrievable.

- memory: summaries table (one compacted gist per session, embedded), plus
  store_summary/get_summary/recall_summaries and unsummarized_count (tracks
  exchanges newer than the current summary)
- lyra/summary.py: summarize_session compacts a session's raw turns into a
  third-person gist (default SUMMARY_BACKEND=local, so compaction is free);
  maybe_summarize re-summarizes once SUMMARIZE_AFTER new turns accumulate
- chat.build_messages now layers context in tiers: persona -> gists of other
  sessions -> a few sharp raw cross-session details -> current session raw
  turns -> new message; respond() compacts the session after each turn
- web: POST /sessions/{id}/summarize to compact on demand
- summarization activity surfaces in the live log

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

lyra/web/server.py

@@ -18,7 +18,7 @@ from fastapi import FastAPI, Request
 from fastapi.responses import StreamingResponse
 from fastapi.staticfiles import StaticFiles
 
-from lyra import chat, logbus, memory
+from lyra import chat, logbus, memory, summary
 from lyra.llm import Backend
 
 
@@ -77,6 +77,11 @@ def create_app() -> FastAPI:
         memory.delete_session(session_id)
         return {"ok": True}
 
+    @app.post("/sessions/{session_id}/summarize")
+    async def summarize(session_id: str) -> dict:
+        gist = await asyncio.to_thread(summary.summarize_session, session_id)
+        return {"ok": gist is not None, "summary": gist}
+
     @app.post("/v1/chat/completions")
     async def chat_completions(request: Request) -> dict:
         body = await request.json()