perf: 18s/turn -> 2.5s/turn (SQLite busy_timeout, parallel state pairs, OpenRouter Cerebras-pinned classifier)

Four changes that compound:

1) **SQLite busy_timeout 5.0s -> 0.1s** in chat/db/connection.py. Root
   cause of the bulk of the slowness. The embedding worker contends
   for the WAL write lock while the request handler holds an open
   transaction; conn.execute's busy-wait does NOT release the GIL, so
   every state_update LLM call after the narrative was silently
   freezing the asyncio event loop for ~5s. With 0.1s the worker
   fails fast and logs (already handled), the chat keeps moving, and
   any missed embedding can be backfilled out of band. Also takes the
   test suite from ~290s -> 13s as a bonus.

2) **Parallel state-update pairs** in multi_state_update.py. Each
   directed (src, tgt) pair becomes a coroutine in asyncio.gather
   instead of a sequential for-loop. Returned order is preserved.

3) **Classifier on OpenRouter, provider-pinned to Cerebras**. New
   prefix-based router: model id with mlx-community/ -> local MLX,
   model == narrative_model -> narrative remote, else -> classifier
   remote. Settings.classifier_provider_order populates extra_body for
   the classifier client only (FeatherlessClient now accepts
   default_extra_body to merge into every chat.completions.create).
   Llama-3.1-8B on Cerebras runs at ~423 tok/s, ~10x the default
   provider. narrative still routes to mistral-nemo:nitro (Friendli).

4) **Cap classify max_tokens at 512**. A misbehaving classifier
   (response_format=json_object ignored) could otherwise generate
   thousands of tokens of prose before classify's JSON validation
   trips the retry. 512 is generous; usual completions are 50-150.

CHAT_LLM_TIMING=1 env var enables per-call timing logs on stderr;
zero overhead when unset. Useful for finding the slow link.

Suite: 464 passed in 13s (was 290s).

tests/test_router_client.py

@@ -36,58 +36,72 @@ class _StubClient:
 
 
 @pytest.mark.asyncio
-async def test_router_generate_dispatches_narrative_to_narrative_backend():
+async def test_router_generate_routes_remote_model_to_remote_backend():
+    """Any model id NOT starting with a local prefix goes to the remote
+    backend — narrative model, remote classifiers, anything else."""
     narrative = _StubClient("narrative")
     local = _StubClient("local")
     router = RoutedLLMClient(
         narrative=narrative,
         local=local,
-        narrative_model="big-model",
+        narrative_model="provider/big-model",
+        local_prefixes=("mlx-community/",),
     )
 
-    out = await router.generate([Message(role="user", content="hi")], model="big-model")
+    out = await router.generate(
+        [Message(role="user", content="hi")], model="provider/big-model"
+    )
 
-    assert out == "narrative:big-model"
-    assert narrative.generate_calls == ["big-model"]
+    assert out == "narrative:provider/big-model"
+    assert narrative.generate_calls == ["provider/big-model"]
     assert local.generate_calls == []
 
 
 @pytest.mark.asyncio
-async def test_router_generate_dispatches_classifier_to_local_backend():
+async def test_router_generate_routes_local_prefix_to_local_backend():
+    """Models prefixed with a local prefix (e.g. ``mlx-community/``)
+    go to the local MLX backend regardless of whether the rest of the
+    path looks like a remote provider id."""
     narrative = _StubClient("narrative")
     local = _StubClient("local")
     router = RoutedLLMClient(
         narrative=narrative,
         local=local,
-        narrative_model="big-model",
+        narrative_model="provider/big-model",
+        local_prefixes=("mlx-community/",),
     )
 
     out = await router.generate(
-        [Message(role="user", content="hi")], model="small-model"
+        [Message(role="user", content="hi")],
+        model="mlx-community/Hermes-3-Llama-3.1-8B-8bit",
     )
 
-    assert out == "local:small-model"
-    assert local.generate_calls == ["small-model"]
+    assert out == "local:mlx-community/Hermes-3-Llama-3.1-8B-8bit"
+    assert local.generate_calls == ["mlx-community/Hermes-3-Llama-3.1-8B-8bit"]
     assert narrative.generate_calls == []
 
 
 @pytest.mark.asyncio
-async def test_router_stream_dispatches_by_model():
+async def test_router_stream_dispatches_by_prefix():
     narrative = _StubClient("narrative")
     local = _StubClient("local")
     router = RoutedLLMClient(
-        narrative=narrative, local=local, narrative_model="big-model"
+        narrative=narrative,
+        local=local,
+        narrative_model="provider/big-model",
+        local_prefixes=("mlx-community/",),
     )
 
-    chunks_big = [c async for c in router.stream(
-        [Message(role="user", content="hi")], model="big-model"
+    chunks_remote = [c async for c in router.stream(
+        [Message(role="user", content="hi")], model="provider/big-model"
     )]
-    chunks_small = [c async for c in router.stream(
-        [Message(role="user", content="hi")], model="other-model"
+    chunks_local = [c async for c in router.stream(
+        [Message(role="user", content="hi")],
+        model="mlx-community/Hermes-3-Llama-3.1-8B-8bit",
     )]
 
-    assert chunks_big == ["narrative:big-model"]
-    assert chunks_small == ["local:other-model"]
+    assert chunks_remote == ["narrative:provider/big-model"]
+    assert chunks_local == ["local:mlx-community/Hermes-3-Llama-3.1-8B-8bit"]
 
 
 @pytest.mark.asyncio