fix(llm): apply DeepSeek capabilities to OpenRouter-namespaced models

- OpenRouter exposes DeepSeek as deepseek/<id>, which matched neither the exact
  IDs nor the patterns, so a thinking model like deepseek/deepseek-v4-flash fell
  through to _DEFAULT and had object-form tool_choice forced on it
- strip the official deepseek/ namespace before lookup so it reuses the native
  quirks; deepseek/deepseek-chat still keeps tool_choice, and third-party
  finetunes on other publishers stay on _DEFAULT #1199
This commit is contained in:
Yijia-Xiao
2026-08-31 02:15:32 +00:00
parent 63be7fe7f1
commit 45c1744b86
2 changed files with 40 additions and 0 deletions

View File

@@ -116,6 +116,37 @@ class TestDefault:
assert caps.supports_tool_choice is True
@pytest.mark.unit
class TestOpenRouterDeepSeekNamespace:
"""OpenRouter namespaces DeepSeek as ``deepseek/<id>``; strip it so the
same quirks apply as the native provider (#1199)."""
def test_prefixed_v4_flash_suppresses_tool_choice(self):
# Was falling through to _DEFAULT (tool_choice on) -> slow object-form call.
assert get_capabilities("deepseek/deepseek-v4-flash").supports_tool_choice is False
def test_prefixed_reasoner_suppresses_tool_choice(self):
assert get_capabilities("deepseek/deepseek-reasoner").supports_tool_choice is False
def test_prefixed_chat_selects_deepseek_chat_not_default(self):
# Must resolve to _DEEPSEEK_CHAT, not _DEFAULT: supports_json_schema=False
# is what distinguishes them (both keep tool_choice).
caps = get_capabilities("deepseek/deepseek-chat")
assert caps.supports_tool_choice is True
assert caps.supports_json_schema is False # _DEEPSEEK_CHAT, not _DEFAULT
def test_only_official_namespace_is_stripped(self):
# A third-party publisher whose model name WOULD match a deepseek pattern
# must stay _DEFAULT: proves we strip only "deepseek/", not any "*/".
caps = get_capabilities("tngtech/deepseek-v4-flash")
assert caps.supports_tool_choice is True # not thinking
assert caps.supports_json_schema is True # _DEFAULT
def test_native_ids_unchanged(self):
assert get_capabilities("deepseek-v4-flash").supports_tool_choice is False
assert get_capabilities("deepseek-chat").supports_tool_choice is True
@pytest.mark.unit
def test_capabilities_dataclass_is_frozen():
"""Capability rows are immutable so they can be safely shared."""

View File

@@ -118,6 +118,15 @@ _BY_PATTERN: list[tuple[re.Pattern[str], ModelCapabilities]] = [
def get_capabilities(model_name: str) -> ModelCapabilities:
"""Resolve capabilities by exact ID, then pattern, then default."""
# OpenRouter namespaces official DeepSeek models as ``deepseek/<id>``, so
# strip that prefix to reuse the same quirks as the native provider — e.g.
# ``deepseek/deepseek-v4-flash`` must suppress tool_choice like
# ``deepseek-v4-flash`` does, not fall through to _DEFAULT (#1199). Only the
# official namespace is stripped; third-party finetunes on other publishers
# (e.g. ``tngtech/deepseek-...``) keep _DEFAULT, since their quirks are unknown.
if model_name.startswith("deepseek/"):
model_name = model_name.removeprefix("deepseek/")
if model_name in _BY_ID:
return _BY_ID[model_name]
for pattern, caps in _BY_PATTERN: