feat: in-app live log (SSE activity feed)

Turn the inert "Show Work" thinking panel into a real live activity log:
- lyra/logbus.py: thread-safe in-memory ring buffer other modules publish to
- chat.respond logs backend/model/embed per turn, recall counts, reply size;
  web layer logs chat errors
- server: replace the keep-alive /stream/thinking stub with /stream/logs, an
  SSE endpoint that replays the recent buffer then streams new events
- UI: repurpose the panel as a global "Live Log" — connects on load, renders
  level/time/msg/fields, drops the old per-session localStorage + dead popup

Every turn now shows its backend + model in-app, so local-vs-cloud (free vs
paid) is visible at a glance.

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

lyra/chat.py

@@ -6,7 +6,7 @@ session, then asks the model for a reply and persists both sides.
 """
 from __future__ import annotations
 
-from lyra import llm, memory, persona
+from lyra import config, llm, logbus, memory, persona
 from lyra.llm import Backend, Message
 
 RECALL_K = 5
@@ -34,6 +34,7 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
     recalled = [
         ex for ex in memory.recall(user_msg, k=RECALL_K) if ex.id not in recent_ids
     ]
+    logbus.log("debug", "context built", recent=len(recent), recalled=len(recalled))
     if recalled:
         messages.append(_memory_note(recalled))
 
@@ -46,8 +47,16 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
 
 def respond(session_id: str, user_msg: str, backend: Backend = "cloud") -> str:
     """Produce Lyra's reply to a single user message and persist the exchange."""
+    cfg = config.load()
+    model = cfg.local_model if backend == "local" else cfg.cloud_model
+    logbus.log(
+        "info", "chat request", session=session_id, backend=backend,
+        model=model, embed=cfg.embed_backend,
+    )
+
     messages = build_messages(session_id, user_msg)
     reply = llm.complete(messages, backend=backend)
+    logbus.log("info", "reply", session=session_id, chars=len(reply))
 
     memory.remember(session_id, "user", user_msg)
     memory.remember(session_id, "assistant", reply)