feat: native OpenAI provider - #19
Merged
Merged
Conversation
Implements the OpenAI Chat Completions API in internal/provider/openai.go (previously a stub), mirroring the Anthropic provider: maps provider.Request → OpenAI body (system prompt as a leading system message), parses the response into provider.Response with token usage, honors ctx for cancellation, and reads OPENAI_API_KEY. The proxy already routes gpt-*/o1/o3 models here, so those calls now work end to end. Removes the OpenAI stub and refreshes the now-stale "OpenAI is a stub" comments. Tests: success (auth header + system-prepend + usage), API error, missing key, context cancel. Pricing entries for common OpenAI models already exist. Fixes #15
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implements the OpenAI Chat Completions API in
internal/provider/openai.go(previously a stub returningErrNotImplemented), mirroring the Anthropic provider:provider.Request→ OpenAI body (the system prompt becomes a leadingsystemmessage), parses the response intoprovider.Responsewith token usage, honorsctxfor cancellation (kill switch / time budget reach in-flight calls), readsOPENAI_API_KEY.gpt-*/o1/o3models here, so those calls now work end to end. Pricing entries for common OpenAI models already exist.Fixes #15
Tests: success (auth header + system-prepend + usage parsing), API error, missing key, context-cancel.
go test -race ./...green.