feat(opencode): add llmgateway-providers provider - #40310
Open
smakosh wants to merge 6 commits into
Open
Conversation
Contributor
|
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
No issue — per CONTRIBUTING, new providers start with a models.dev PR: anomalyco/models.dev#4011.
Type of change
What does this PR do?
LLM Gateway is splitting its models.dev catalog in two (anomalyco/models.dev#4011): the existing
llmgatewayprovider is renamed to "DevPass (LLM Gateway)" (same id, same aggregated model ids, existing configs unaffected), and a newllmgateway-providers("LLM Gateway") provider lists provider-pinned ids likeanthropic/claude-sonnet-5— one entry per upstream deployment, same endpoint and API key.This PR wires the new provider id where opencode keys on
llmgatewaytoday:provider.ts: custom loader forllmgateway-providerswithautoload: falseand the referer/source headers, copied from thellmgatewayentry. Both providers shareLLMGATEWAY_API_KEY, so autoload stays off to avoid enabling both when the env var is set.transform.tssmallOptions: the openrouter/llmgateway branch that disables reasoning for Google small-model tasks now includesllmgateway-providers. Mapped ids likegoogle-vertex/gemini-…contain "google", so the existingapi.id.includes("google")check works unchanged.providers.mdx: documents the two providers in the LLM Gateway section.No other code is needed: the core
LLMGatewayPluginmatches providers by API URL (not id) so it already covers the new one, and provider icons are fetched from models.dev logos at build time.How did you verify your code works?
bun run typecheckinpackages/opencodepasses.bun test test/providerinpackages/opencode(532 tests) andpackages/coretest/plugin/provider-llmgateway.test.ts(3 tests) pass.bun validateon the models.dev PR.Screenshots / recordings
Not a UI change.
Checklist