fix(deepseek): set default_aux_model on profile so aux warning stops firing

Closes #26924 (and supersedes #26926) in spirit.

DeepSeek was missing `default_aux_model` on its `ProviderProfile`, so
`_get_aux_model_for_provider("deepseek")` returned an empty string and
the compression / vision / session-search paths emitted

  "No auxiliary LLM provider configured -- context compression will
  drop middle turns without a summary."

on every DeepSeek session, even when the user had perfectly working
DeepSeek credentials.

Fix lands at the profile layer rather than the legacy
`_API_KEY_PROVIDER_AUX_MODELS_FALLBACK` dict the original PR targeted.
Every modern provider (gemini, zai, minimax, anthropic, kimi-coding,
stepfun, ollama-cloud, gmi, novita, kilocode, ai-gateway, opencode-zen)
sets `default_aux_model` on its `ProviderProfile`; the fallback dict
only exists for providers that predate the profiles system.

Tests added under `tests/plugins/model_providers/test_deepseek_profile.py`:
- `test_profile_advertises_deepseek_chat`  -- pins the profile attribute
- `test_consumer_api_returns_deepseek_chat` -- pins the consumer API behavior
- `test_consumer_api_returns_non_empty`     -- regression guard for the
  symptom in the issue

Original diagnosis and aux-model choice from @kriscolab in PR #26926;
moved one layer up.

Co-authored-by: kriscolab <71590782+kriscolab@users.noreply.github.com>
This commit is contained in:
teknium1 2026-05-16 22:52:28 -07:00 committed by Teknium
parent 9a9f8a6d99
commit 773a0faca0
2 changed files with 24 additions and 0 deletions

View file

@ -94,6 +94,7 @@ deepseek = DeepSeekProfile(
"deepseek-reasoner",
),
base_url="https://api.deepseek.com/v1",
default_aux_model="deepseek-chat",
)
register_provider(deepseek)

View file

@ -182,3 +182,26 @@ class TestDeepSeekFullKwargsIntegration:
)
assert "reasoning_effort" not in kwargs
assert "extra_body" not in kwargs or "thinking" not in kwargs.get("extra_body", {})
class TestDeepSeekAuxModel:
"""DeepSeek aux model is set on the profile so users stop seeing the
bogus 'No auxiliary LLM provider configured' warning (#26924).
Pinned at the profile layer rather than the legacy
`_API_KEY_PROVIDER_AUX_MODELS_FALLBACK` dict new providers are
expected to set `default_aux_model` on `ProviderProfile`, and the
fallback dict only exists for providers that predate the profiles
system.
"""
def test_profile_advertises_deepseek_chat(self, deepseek_profile):
assert deepseek_profile.default_aux_model == "deepseek-chat"
def test_consumer_api_returns_deepseek_chat(self):
from agent.auxiliary_client import _get_aux_model_for_provider
assert _get_aux_model_for_provider("deepseek") == "deepseek-chat"
def test_consumer_api_returns_non_empty(self):
from agent.auxiliary_client import _get_aux_model_for_provider
assert _get_aux_model_for_provider("deepseek") != ""