fix(providers): add deepseek to _API_KEY_PROVIDER_AUX_MODELS_FALLBACK (#26924)#26926
Closed
kriscolab wants to merge 1 commit into
Closed
fix(providers): add deepseek to _API_KEY_PROVIDER_AUX_MODELS_FALLBACK (#26924)#26926kriscolab wants to merge 1 commit into
kriscolab wants to merge 1 commit into
Conversation
…NousResearch#26924) DeepSeek is a direct API-key provider without a ProviderProfile plugin, so _get_aux_model_for_provider() falls through to the legacy hardcoded dict. Without an entry there, it returns "" which triggers the misleading "No auxiliary LLM provider configured" warning. Add "deepseek": "deepseek-chat" to the fallback dict, consistent with how minimax, stepfun, and kimi-coding are handled. Add two regression tests verifying DeepSeek resolves to deepseek-chat and never returns empty string.
2 tasks
This comment was marked as spam.
This comment was marked as spam.
teknium1
added a commit
that referenced
this pull request
May 17, 2026
…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>
teknium1
added a commit
that referenced
this pull request
May 17, 2026
…tors Adds release-note attribution mappings for 10 contributors from the low-hanging-fruit salvage group 2 batch: - @shellybotmoyer (PR #26661, #25576) - @ether-btc (PR #26632) - @LifeJiggy (PR #26516) - @nekwo (PR #26481) - @flooryyyy (PR #26374) - @dgians (PR #26034, incl. zealy-tzco bot-committer alias) - @flanny7 (PR #27030) - @hermesagent26 (PR #26438) - @kriscolab (PR #26926, co-author on salvage commit)
Contributor
|
Merged via PR #27292 — the bug you diagnosed (deepseek users seeing the bogus 'No auxiliary LLM provider configured' warning) is fixed, but the salvage shape diverged from your patch. The legacy Your diagnosis and aux-model choice were correct — credited via |
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…firing Closes NousResearch#26924 (and supersedes NousResearch#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 NousResearch#26926; moved one layer up. Co-authored-by: kriscolab <71590782+kriscolab@users.noreply.github.com>
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…tors Adds release-note attribution mappings for 10 contributors from the low-hanging-fruit salvage group 2 batch: - @shellybotmoyer (PR NousResearch#26661, NousResearch#25576) - @ether-btc (PR NousResearch#26632) - @LifeJiggy (PR NousResearch#26516) - @nekwo (PR NousResearch#26481) - @flooryyyy (PR NousResearch#26374) - @dgians (PR NousResearch#26034, incl. zealy-tzco bot-committer alias) - @flanny7 (PR NousResearch#27030) - @hermesagent26 (PR NousResearch#26438) - @kriscolab (PR NousResearch#26926, co-author on salvage commit)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #26924 — adds
deepseekto_API_KEY_PROVIDER_AUX_MODELS_FALLBACKso DeepSeek users no longer get the misleading "No auxiliary LLM provider configured" warning.Problem
When
provider = "deepseek", every Hermes startup and cron job emits:Root cause: DeepSeek is a direct API-key provider (no
ProviderProfileplugin withdefault_aux_model), so_get_aux_model_for_provider()falls through to the legacy_API_KEY_PROVIDER_AUX_MODELS_FALLBACKdict — which didn't includedeepseek.Fix
One-line addition to the fallback dict:
Consistent with how
minimax,stepfun,kimi-coding, and other direct API-key providers are handled.Tests
Two new regression tests in
test_minimax_provider.py(TestDeepseekAuxModel):test_deepseek_aux_is_chat— asserts_get_aux_model_for_provider("deepseek") == "deepseek-chat"test_deepseek_aux_not_empty— asserts the return value is non-emptyVerification
venv/bin/python -m pytest tests/agent/test_minimax_provider.py::TestDeepseekAuxModel -v # 2 passed in 2.00sType
🐛 Bug fix (non-breaking)