fix: Neuralwatt provider#3608
Merged
Merged
Conversation
Add Neuralwatt as a built-in OpenAI-compatible provider. - Register NEURALWATT ProviderId (constant, from_str, built_in list, display name) - Add neuralwatt entry to provider.json (base URL https://api.neuralwatt.com/v1) - Add unit tests for provider id and provider config - Document NEURALWATT_API_KEY in README Docs: https://portal.neuralwatt.com/docs/api/overview
github-actions
Bot
added
type: feature
amitksingh1490
marked this pull request as draft
July 1, 2026 13:26
amitksingh1490
added
type: fix
Neuralwatt's /v1/models endpoint returns a non-standard schema (model metadata nested under a 'metadata' object), which does not map cleanly to the OpenAI-compatible model list parser. Hardcode all 11 models with their full metadata (context length, tool support, reasoning, modalities) instead of fetching from the URL. Models were generated programmatically from the live API response to avoid missing any model or metadata.
amitksingh1490
marked this pull request as ready for review
July 1, 2026 13:33
M1lan
pushed a commit
to M1lan/forgecode
that referenced
this pull request
Jul 9, 2026
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 Neuralwatt as a built-in OpenAI-compatible LLM provider.
Neuralwatt Cloud exposes OpenAI-compatible endpoints at
https://api.neuralwatt.com/v1, so it plugs in as a standardOpenAIresponse-type provider.Changes
crates/forge_domain/src/provider.rs: registerProviderId::NEURALWATT(constant,FromStr,built_in_providers(), and display nameNeuralwatt).crates/forge_repo/src/provider/provider.json: add theneuralwattprovider entryhttps://api.neuralwatt.com/v1/chat/completionshttps://api.neuralwatt.com/v1/modelsNEURALWATT_API_KEYcrates/forge_repo/src/provider/provider_repo.rs: addtest_neuralwatt_configunit test.README.md: documentNEURALWATT_API_KEY.Testing
cargo build✅cargo test -p forge_domain neuralwatt✅ (3 passing)cargo test -p forge_repo neuralwatt✅ (1 passing)forge list providershows Neuralwatt (host api.neuralwatt.com)neuralwatt/glm-5.2-fastwith a test key — model correctly repliedPONG.