fix(provider): meta muse spark 1.1 provider#3688
Draft
gonzoga wants to merge 3 commits into
Draft
Conversation
Co-Authored-By: ForgeCode <noreply@forgecode.dev>
Co-authored-by: Amit Singh <amitksingh1490@gmail.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add Meta as a new built-in provider to ForgeCode, using the Meta Model API at
https://api.meta.ai/v1. Meta's API is OpenAI Responses-compatible with Bearer token authentication viaMODEL_API_KEY.Context
Meta recently launched their Model API with Muse Spark 1.1, a multimodal model supporting agentic tool calling, coding, structured output, image/video understanding, and long-context reasoning with a 1M-token context window. The API is drop-in compatible with the OpenAI Responses API, making this a pure configuration-driven integration with no new behavioral code needed.
Changes
crates/forge_repo/src/provider/provider.json: Addmetaprovider entry withOpenAIResponsesresponse type,MODEL_API_KEYenv var, and hardcodedmuse-spark-1.1model (1,048,576 context, tools + parallel tools + reasoning, text + image input)crates/forge_domain/src/provider.rs: RegisterMETAconstant, add tobuilt_in_providers(), addfrom_str()anddisplay_name()match arms, add 3 new tests + update 2 existing testscrates/forge_repo/src/provider/provider_repo.rs: Addtest_meta_configtest verifying provider config, response type, URL, and hardcoded model specsREADME.md: Add Meta env var documentation entryTesting
cargo checkpasses with no errorscargo test -p forge_domain -- provider::tests— 42 passed, 0 failed (including 3 new Meta tests)cargo test -p forge_repo -- provider_repo::tests— 14 passed, 0 failed (includingtest_meta_config)cargo insta test --accept— no snapshot changes neededNotes
OpenAIResponsesresponse type per Meta's recommendation for "the full feature set for agentic workflows" including reasoning replay across turnsInputModalityenum only supportsTextandImage— the Meta API also accepts video and PDF inputs, but these cannot be represented in the current domain modelOpenAIResponses+ hardcoded models) and the Neuralwatt precedent (hardcoded model content verification)Co-Authored-By: ForgeCode noreply@forgecode.dev