feat: split introspection backend from consolidation (trial Dolphin for her voice)

reflect()/think() can now run on a different model than memory consolidation:
INTROSPECTION_BACKEND / INTROSPECTION_MODEL (default to SUMMARY_BACKEND, so unset =
unchanged). Consolidation (summaries/profile/narrative) keeps the capable model;
her *voice* (reflections, thoughts) can run a steerable tune. dream.py lets
reflect()/think() self-resolve to the introspection backend; both now thread a
`model` override into llm.complete.

Trial live: introspection -> dolphin3:8b on the 3090; consolidation -> Qwen-32B
on the MI50. Suite 73 green, ruff clean.

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

lyra/config.py

@@ -23,7 +23,9 @@ class Config:
     embed_model: str  # OpenAI embedding model
     local_embed_model: str  # Ollama embedding model
     embed_base_url: str  # Ollama endpoint for embeddings (own box, decoupled from local chat)
-    summary_backend: str  # "local" or "cloud" — backend used to compact memory
+    summary_backend: str  # backend for memory consolidation (summaries/profile/narrative)
+    introspection_backend: str  # backend for reflect()/think() — her *voice* (may differ)
+    introspection_model: str | None  # model override for introspection (e.g. a steerable tune)
     db_path: Path
     # Proactive reach-out (ntfy push). Empty ntfy_url disables pinging.
     ntfy_url: str          # base url, e.g. "http://10.0.0.41:8090"
@@ -44,6 +46,7 @@ def _csv(name: str, default: str) -> tuple[str, ...]:
 
 
 def load() -> Config:
+    _summary = os.getenv("SUMMARY_BACKEND", "local").lower()
     return Config(
         local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
         local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
@@ -58,7 +61,12 @@ def load() -> Config:
         # Embeddings can live on their own always-on box, separate from the local
         # chat backend. Defaults to LOCAL_BASE_URL so existing setups are unchanged.
         embed_base_url=os.getenv("EMBED_BASE_URL", os.getenv("LOCAL_BASE_URL", "http://localhost:11434")),
-        summary_backend=os.getenv("SUMMARY_BACKEND", "local").lower(),
+        summary_backend=_summary,
+        # Introspection (reflect/think) can run on a different model than consolidation —
+        # e.g. a steerable tune for her voice, while the capable model keeps her memory
+        # accurate. Defaults to the summary backend so unset = unchanged behavior.
+        introspection_backend=os.getenv("INTROSPECTION_BACKEND", _summary).lower(),
+        introspection_model=os.getenv("INTROSPECTION_MODEL") or None,
         db_path=Path(os.getenv("LYRA_DB_PATH", "data/lyra.db")),
         ntfy_url=os.getenv("NTFY_URL", "").rstrip("/"),
         ntfy_topic=os.getenv("NTFY_TOPIC", "lyra"),