refactor(cookbook): move endpoint registration out of the routes closure (#7031)

* refactor(cookbook): move endpoint registration out of the routes closure

_auto_register_llm_endpoint and _auto_register_image_endpoint use no
closure state and model_serve is their only caller, so they can live in a
plain module and be imported and tested directly. Bodies are unchanged
apart from indentation.

Tests now import the helpers instead of reading them from the route's
closure. That lookup also failed if the route stopped referencing a
helper, so add a test that pins which helper model_serve calls.

Part of #4071

* fix(cookbook): bound the OLLAMA_HOST port scan

The pattern rescanned the rest of the token from every OLLAMA_HOST=
occurrence, so a long serve command with repeated assignments took
quadratic time. model_serve runs this on the event loop, and a 192 KB
command stalled the whole app for about 9s.

Cap the host at 253 characters, the longest DNS name, so every valid host
still matches.

Part of #4071

tests/test_cookbook_endpoint_registration.py

@@ -50,17 +50,10 @@ def _launch_llm(
     port: int,
     serve_session_id: str | None = None,
 ) -> str:
-    import routes.cookbook_routes as cookbook_routes
+    from routes.cookbook.endpoint_registration import _auto_register_llm_endpoint
     from routes.cookbook_helpers import ServeRequest
 
-    router = cookbook_routes.setup_cookbook_routes()
-    serve = next(
-        route.endpoint for route in router.routes
-        if route.path == "/api/model/serve" and "POST" in route.methods
-    )
-    cells = dict(zip(serve.__code__.co_freevars, serve.__closure__ or ()))
-    register = cells["_auto_register_llm_endpoint"].cell_contents
-    endpoint_id = register(
+    endpoint_id = _auto_register_llm_endpoint(
         ServeRequest(repo_id=repo_id, cmd=f"vllm serve {repo_id} --port {port}"),
         None,
         serve_session_id=serve_session_id,
@@ -76,6 +69,83 @@ def _endpoint(factory, endpoint_id: str):
         return db.get(database.ModelEndpoint, endpoint_id)
 
 
+@pytest.mark.parametrize(
+    ("cmd", "registers", "skips"),
+    [
+        (
+            "python scripts/diffusion_server.py --port 8100",
+            "_auto_register_image_endpoint",
+            "_auto_register_llm_endpoint",
+        ),
+        (
+            "llama-server -m /models/model.gguf --port 8085",
+            "_auto_register_llm_endpoint",
+            "_auto_register_image_endpoint",
+        ),
+    ],
+)
+@pytest.mark.asyncio
+async def test_serve_registers_endpoint_for_its_model_type(monkeypatch, tmp_path, cmd, registers, skips):
+    from unittest.mock import AsyncMock, MagicMock
+
+    from starlette.requests import Request
+
+    from routes import cookbook_routes
+    from routes.cookbook_helpers import ServeRequest
+
+    launch =MagicMock(returncode=0, wait=AsyncMock(return_value=0))
+    monkeypatch.setattr(cookbook_routes, "TMUX_LOG_DIR", tmp_path)
+    monkeypatch.setattr(cookbook_routes, "require_admin", lambda request: None)
+    monkeypatch.setattr(cookbook_routes, "_binary_available", AsyncMock(return_value=True))
+    monkeypatch.setattr(cookbook_routes, "load_stored_hf_token", lambda **kwargs: "")
+    monkeypatch.setattr(cookbook_routes.asyncio, "create_subprocess_shell", AsyncMock(return_value=launch))
+    # Returning no endpoint id keeps the crash watchdog from being scheduled.
+    register = MagicMock(return_value=None)
+    skip = MagicMock(return_value=None)
+    monkeypatch.setattr(cookbook_routes, registers, register)
+    monkeypatch.setattr(cookbook_routes, skips, skip)
+
+    router = cookbook_routes.setup_cookbook_routes()
+    serve = next(
+        route.endpoint for route in router.routes
+        if route.path == "/api/model/serve" and "POST" in route.methods
+    )
+    req = ServeRequest(repo_id="organization-a/Model-A", cmd=cmd, remote_host="gpu-box")
+
+    response = await serve(Request({"type": "http", "headers": []}), req)
+
+    register.assert_called_once_with(req, "gpu-box", serve_session_id=response["session_id"])
+    skip.assert_not_called()
+
+
+def _register_ollama(cmd: str) -> str:
+    from routes.cookbook.endpoint_registration import _auto_register_llm_endpoint
+    from routes.cookbook_helpers import ServeRequest
+
+    endpoint_id = _auto_register_llm_endpoint(ServeRequest(repo_id="library/model", cmd=cmd), None)
+    assert endpoint_id
+    return endpoint_id
+
+
+@pytest.mark.parametrize("host", ["0.0.0.0", "h" * 253])
+def test_registers_port_from_ollama_host(endpoint_db, host):
+    endpoint_id = _register_ollama(f"OLLAMA_HOST={host}:11435 ollama serve")
+
+    assert _endpoint(endpoint_db, endpoint_id).base_url == "http://localhost:11435/v1"
+
+
+def test_repeated_ollama_host_assignments_register_quickly(endpoint_db):
+    import time
+
+    start = time.perf_counter()
+    endpoint_id = _register_ollama("OLLAMA_HOST=" * 32000 + " ollama serve")
+    elapsed = time.perf_counter() - start
+
+    # The unbounded pattern took about 30s on this input and blocked the event loop.
+    assert elapsed < 4.0, f"registration took {elapsed:.2f}s"
+    assert _endpoint(endpoint_db, endpoint_id).base_url == "http://localhost:11434/v1"
+
+
 @pytest.mark.parametrize("reuse", [False, True])
 def test_launch_keeps_endpoint_of_other_model_with_same_short_name(endpoint_db, reuse):
     if reuse:
@@ -448,20 +518,13 @@ async def test_ordinary_admin_delete_does_not_require_serve_owner(
 
 
 def _launch_image(repo_id: str, port: int, monkeypatch) -> str:
-    import routes.cookbook_routes as cookbook_routes
     import src.settings as settings
+    from routes.cookbook.endpoint_registration import _auto_register_image_endpoint
     from routes.cookbook_helpers import ServeRequest
 
     monkeypatch.setattr(settings, "load_settings", lambda: {"image_gen_enabled": True, "image_model": repo_id})
     monkeypatch.setattr(settings, "save_settings", lambda _settings: None)
-    router = cookbook_routes.setup_cookbook_routes()
-    serve = next(
-        route.endpoint for route in router.routes
-        if route.path == "/api/model/serve" and "POST" in route.methods
-    )
-    cells = dict(zip(serve.__code__.co_freevars, serve.__closure__ or ()))
-    register = cells["_auto_register_image_endpoint"].cell_contents
-    endpoint_id = register(
+    endpoint_id = _auto_register_image_endpoint(
         ServeRequest(repo_id=repo_id, cmd=f"python diffusion_server.py --model {repo_id} --port {port}"), None
     )
     assert endpoint_id