feat(api): config + role→model routing (qwen3.5 narrator default, think off)

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

api/app/config.py

@@ -0,0 +1,22 @@
+"""Server config, read from the environment at call time so tests can override
+without reimport. Charter §4 — all of this lives server-side; the client never
+sees it.
+"""
+
+import os
+
+
+def ollama_base_url() -> str:
+    return os.environ.get("OLLAMA_BASE_URL", "http://localhost:11434")
+
+
+def ollama_timeout_seconds() -> float:
+    return float(os.environ.get("OLLAMA_TIMEOUT_SECONDS", "30"))
+
+
+def narrator_model() -> str:
+    return os.environ.get("OLLAMA_NARRATOR_MODEL", "qwen3.5:latest")
+
+
+def call_log_path() -> str | None:
+    return os.environ.get("CALL_LOG_PATH") or None

api/app/routing.py

@@ -0,0 +1,25 @@
+"""Role → model routing (charter §4/§5). Model choice is config, not law — a
+deploy, not a client patch. Read at call time so an env override needs no reimport.
+The provider abstraction (Ollama → Replicate) slots in here later (YAGNI now).
+"""
+
+from dataclasses import dataclass
+
+from . import config
+
+
+@dataclass(frozen=True)
+class RoleConfig:
+    model: str
+    options: dict
+    think: bool | None = None  # Ollama top-level `think`; None omits it
+
+
+def for_role(role: str) -> RoleConfig:
+    if role == "narrator":
+        return RoleConfig(
+            model=config.narrator_model(),
+            options={"temperature": 0.8, "top_p": 0.9, "num_predict": 300},
+            think=False,  # qwen3.x thinking OFF; harmless on non-thinking models
+        )
+    raise KeyError(f"no routing for role: {role}")

api/tests/test_routing.py

@@ -0,0 +1,21 @@
+import pytest
+
+from app.routing import for_role
+
+
+def test_narrator_defaults():
+    cfg = for_role("narrator")
+    assert cfg.model == "qwen3.5:latest"
+    assert cfg.think is False
+    assert cfg.options["num_predict"] == 300
+    assert cfg.options["temperature"] == 0.8
+
+
+def test_env_overrides_model(monkeypatch):
+    monkeypatch.setenv("OLLAMA_NARRATOR_MODEL", "llama3.1:latest")
+    assert for_role("narrator").model == "llama3.1:latest"
+
+
+def test_unknown_role_raises():
+    with pytest.raises(KeyError):
+        for_role("wizard")