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>

pyproject.toml

@@ -18,6 +18,7 @@ lyra = "lyra.__main__:main"
 lyra-web = "lyra.web.server:serve"
 lyra-import = "lyra.ingest:main"
 lyra-summarize = "lyra.summary:main"
+lyra-profile = "lyra.profile:main"
 
 [dependency-groups]
 dev = [