feat(providers): add Mistral AI, Nebius AI, and Scaleway as first-class providers - #4485
Closed
CrispStrobe wants to merge 1 commit into
Closed
CrispStrobe wants to merge 1 commit into
CrispStrobe wants to merge 1 commit into
Conversation
…ss providers Register all three in PROVIDER_REGISTRY with correct base URLs and env vars: - mistral: api.mistral.ai/v1, MISTRAL_API_KEY - nebius: api.tokenfactory.nebius.com/v1, NEBIUS_API_KEY (DSGVO-compliant EU) - scaleway: api.scaleway.ai/v1, SCALEWAY_API_KEY / SCW_SECRET_KEY Add curated model lists, display labels, canonical aliases, and provider order entries in models.py. Wire all three into the `hermes model` picker menu and route them through _model_flow_api_key_provider. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
19 tasks
9 tasks
alt-glitch
added
type/feature
|
Overlaps with #7856 (Mistral-only PR). This PR bundles Mistral + Nebius + Scaleway together — review which to accept. |
1 similar comment
|
Overlaps with #7856 (Mistral-only PR). This PR bundles Mistral + Nebius + Scaleway together — review which to accept. |
1 task
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
api.mistral.ai/v1,MISTRAL_API_KEY, 8 curated models (mistral-large/medium/small-latest, codestral, devstral, mistral-saba, ministral-8b/3b)api.tokenfactory.nebius.com/v1,NEBIUS_API_KEY, 7 chat models (DeepSeek-R1-0528, Nemotron-Ultra-253B, gpt-oss-120b, Kimi-K2-Instruct/Thinking, GLM-4.5, Llama-3.3-70B)api.scaleway.ai/v1,SCALEWAY_API_KEY/SCW_SECRET_KEY, 7 models (Llama-3.3-70B, Llama-3.1-8B, Mistral-Nemo, Qwen2.5-Coder-32B, DeepSeek-R1, Phi-4)Each provider is wired up consistently across all four integration points:
PROVIDER_REGISTRYinauth.py— base URL, env vars, auth type_PROVIDER_MODELS/_PROVIDER_LABELS/_PROVIDER_ALIASES/_PROVIDER_ORDERinmodels.pyhermes modelpicker menu inmain.py_model_flow_api_key_providerrouting inmain.pyAll three use the generic
api_keyauth flow — no new code paths needed.Test plan
test_models,test_model_validation,test_status_model_provider,test_setup_model_provider)ruff— no new issuesbandit— no new High/Medium issueshermes modelshows Mistral AI, Nebius AI, Scaleway in the picker~/.hermes/config.yaml🤖 Generated with Claude Code