perf: reuse serializer wrapper models instead of rebuilding them on every call

marshal_json and unmarshal call pydantic.create_model on every call, so each
chat request built about 19 model classes. An SDK init hook now caches one
wrapper model per type. Fixes #1056.

Author: devin-ai-integration[bot]

src/openrouter/_hooks/registration.py

@@ -1,4 +1,5 @@
 from .types import Hooks
+from . import serializer_cache
 
 
 # This file is only ever generated once on the first generation and then is free to be modified.
@@ -11,3 +12,4 @@ def init_hooks(hooks: Hooks):
     """Add hooks by calling hooks.register{sdk_init/before_request/after_success/after_error}Hook
     with an instance of a hook that implements that specific Hook interface
     Hooks are registered per SDK instance, and are valid for the lifetime of the SDK instance"""
+    serializer_cache.install()

src/openrouter/_hooks/serializer_cache.py

@@ -0,0 +1,46 @@
+"""Reuse the wrapper models that ``utils.serializers`` builds for each type.
+
+``marshal_json`` and ``unmarshal`` call ``pydantic.create_model`` on every
+call, so each request builds and compiles new model classes. This module
+replaces ``serializers.create_model`` with a version that builds one model per
+(name, type, config) and returns it on later calls. Calls in any other shape,
+or with unhashable arguments, fall through to ``pydantic.create_model``.
+"""
+
+import functools
+from typing import Any, Callable, Tuple, Type
+
+from pydantic import BaseModel, ConfigDict
+
+from ..utils import serializers
+
+_uncached_create_model: Callable[..., Type[BaseModel]] = serializers.create_model
+
+
+@functools.lru_cache(maxsize=None)
+def _cached_wrapper_model(
+    name: str, typ: Any, config_items: Tuple[Tuple[str, Any], ...]
+) -> Type[BaseModel]:
+    return _uncached_create_model(
+        name, body=(typ, ...), __config__=ConfigDict(**dict(config_items))  # type: ignore[typeddict-item]
+    )
+
+
+def _create_model(name: str, **kwargs: Any) -> Type[BaseModel]:
+    body, config = kwargs.get("body"), kwargs.get("__config__")
+    if (
+        set(kwargs) != {"body", "__config__"}
+        or not isinstance(body, tuple)
+        or len(body) != 2
+        or body[1] is not ...
+        or not isinstance(config, dict)
+    ):
+        return _uncached_create_model(name, **kwargs)
+    try:
+        return _cached_wrapper_model(name, body[0], tuple(sorted(config.items())))
+    except TypeError:
+        return _uncached_create_model(name, **kwargs)
+
+
+def install() -> None:
+    setattr(serializers, "create_model", _create_model)

tests/test_serializer_cache.py

@@ -0,0 +1,76 @@
+import json
+
+import httpx
+
+from openrouter import OpenRouter
+from openrouter._hooks import serializer_cache
+from openrouter.utils import serializers
+
+COMPLETION = {
+    "id": "gen-test",
+    "object": "chat.completion",
+    "created": 1760000000,
+    "model": "openai/gpt-4o-mini",
+    "system_fingerprint": None,
+    "choices": [
+        {
+            "index": 0,
+            "finish_reason": "stop",
+            "message": {"role": "assistant", "content": "ok"},
+        }
+    ],
+    "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+}
+
+
+def _client() -> OpenRouter:
+    transport = httpx.MockTransport(
+        lambda request: httpx.Response(200, json=COMPLETION)
+    )
+    return OpenRouter(api_key="test-key", client=httpx.Client(transport=transport))
+
+
+def _send(client: OpenRouter):
+    return client.chat.send(
+        model="openai/gpt-4o-mini",
+        messages=[{"role": "user", "content": "hi"}],
+    )
+
+
+def test_sdk_init_installs_serializer_cache():
+    _client()
+
+    assert serializers.create_model is serializer_cache._create_model
+
+
+def test_repeated_requests_reuse_serializer_models(monkeypatch):
+    built = []
+    uncached_create_model = serializer_cache._uncached_create_model
+
+    def counting_create_model(*args, **kwargs):
+        built.append(args[0] if args else kwargs.get("__model_name"))
+        return uncached_create_model(*args, **kwargs)
+
+    client = _client()
+    serializer_cache._cached_wrapper_model.cache_clear()
+    monkeypatch.setattr(serializer_cache, "_uncached_create_model", counting_create_model)
+
+    first = _send(client)
+    built_by_first_request = len(built)
+    second = _send(client)
+
+    assert built_by_first_request > 0
+    assert len(built) == built_by_first_request
+    assert first.choices[0].message.content == "ok"
+    assert second.model_dump() == first.model_dump()
+
+
+def test_cached_models_serialize_like_uncached_ones():
+    _client()
+
+    value = {"a": [1, 2]}
+    typ = dict[str, list[int]]
+
+    assert json.loads(serializers.marshal_json(value, typ)) == value
+    assert serializers.unmarshal(value, typ) == value
+    assert serializers.unmarshal(value, typ) == value