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>

tests/test_thoughts.py

@@ -30,7 +30,8 @@ def lyra(tmp_path, monkeypatch):
 
     # Canned LLM: tests set `box["next"]` to the dict think() should "generate".
     box = {"next": {}}
-    monkeypatch.setattr(thoughts.llm, "complete", lambda messages, backend=None: json.dumps(box["next"]))
+    monkeypatch.setattr(thoughts.llm, "complete",
+                        lambda messages, backend=None, model=None: json.dumps(box["next"]))
     # Keep the loop offline + silent by default: no feed fetch, no push.
     monkeypatch.setattr(thoughts.feeds, "next_item", lambda **k: None)
     monkeypatch.setattr(thoughts.notify, "push", lambda **k: False)
@@ -274,6 +275,22 @@ def test_ping_salience_floor_is_optional(lyra, monkeypatch):
     assert th.maybe_ping(1, "hey", 0.8) is True
 
 
+def test_think_routes_to_introspection_backend(lyra, monkeypatch):
+    _, th, box = lyra
+    monkeypatch.setenv("INTROSPECTION_BACKEND", "local")
+    monkeypatch.setenv("INTROSPECTION_MODEL", "dolphin3:8b")
+    seen = {}
+
+    def cap(messages, backend="local", model=None):
+        seen["backend"], seen["model"] = backend, model
+        return json.dumps(box["next"])
+
+    monkeypatch.setattr(th.llm, "complete", cap)
+    _gen(box, content="a thought")
+    th.think(force_mode="new")
+    assert seen["backend"] == "local" and seen["model"] == "dolphin3:8b"
+
+
 def test_no_ping_without_ntfy(lyra, monkeypatch):
     _, th, _ = lyra
     sent = []