feat: add Fireworks AI as a native provider - #18664
Closed
nateGeorge wants to merge 1 commit into
Closed
Conversation
Fireworks AI (fireworks.ai) is a popular API provider for models like
Kimi K2.6, DeepSeek V3, Llama 4, Qwen 3, etc. Previously users had to
configure it via custom_providers / custom endpoint. This commit adds
first-class support.
Changes:
- hermes_cli/auth.py: Add 'fireworks' to PROVIDER_REGISTRY with
FIREWORKS_API_KEY / FIREWORKS_BASE_URL env vars
- hermes_cli/models.py: Add 'fireworks' to CANONICAL_PROVIDERS list
with aliases (fireworks-ai, fw)
- hermes_cli/auth.py: Add provider aliases for fireworks-ai and fw
- tests/hermes_cli/test_fireworks_provider.py: 20 tests covering
registry, aliases, auto-detection, credentials, model catalog,
canonical provider list, and API mode routing
Usage after this commit:
model:
provider: fireworks
model: accounts/fireworks/models/kimi-k2p6
Closes NousResearch#3510 (Firework Pass Support)
alt-glitch
added
type/feature
Collaborator
1 similar comment
Collaborator
Contributor
Author
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds first-class support for Fireworks AI as a native Hermes provider, eliminating the need for custom endpoint configuration.
Background
Fireworks AI (fireworks.ai) hosts popular models including Kimi K2.6, DeepSeek V3, Llama 4, and Qwen 3. Users previously had to configure it via
customprovider with manualbase_urlandapi_key.Changes
fireworksto PROVIDER_REGISTRY with:fireworksto CANONICAL_PROVIDERS for model picker UIUsage
Related