-
Notifications
You must be signed in to change notification settings - Fork 0
17073 gpt 5 support #9
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
|
@coderabbitai full review, summary |
|
@destitutus: I'll perform a full review of all the changes in this PR and regenerate the summary for the GPT-5 support implementation. ✅ Actions performedSummary regeneration triggered. |
WalkthroughUpdates Go/Docker base versions and dependencies, adds OpenAI Responses API support. Introduces request/response types, cost estimation for responses and tools, middleware validations, new routes, logging, and a proxy handler with non‑streaming and SSE streaming support. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant C as Client
participant P as Proxy (Gin)
participant H as Responses Handler
participant O as OpenAI Responses API
participant E as Estimator
Note over P,H: Non-streaming flow
C->>P: POST /api/providers/openai/v1/responses
P->>H: getResponsesHandler(...)
H->>O: POST /v1/responses (proxied)
O-->>H: 200 + JSON body
H->>E: EstimateResponseApiTotalCost(model, usage)
H->>E: EstimateResponseApiToolCallsCost(tools, model)
E-->>H: Costs
H-->>P: Status + body + headers
P-->>C: Forwarded response
sequenceDiagram
autonumber
participant C as Client
participant P as Proxy (Gin)
participant H as Responses Handler
participant O as OpenAI Responses API (SSE)
participant E as Estimator
Note over P,H: Streaming (SSE) flow
C->>P: POST /api/providers/openai/v1/responses (stream=true)
P->>H: getResponsesHandler(...)
H->>O: POST /v1/responses (Accept: text/event-stream)
loop SSE events
O-->>H: data: {delta/...}
H-->>C: Stream line
Note right of H: Accumulate content and usage
end
H->>E: EstimateResponseApiTotalCost(model, usage)
H->>E: EstimateResponseApiToolCallsCost(tools, model)
E-->>H: Costs
H-->>P: Finalize metrics/context
P-->>C: Stream end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~75 minutes ✨ Finishing touches
🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (9)
Comment |
https://bugtracker.codiodev.com/issue/codio-17073/Update-Bricks-LLM-to-Support-GPT-5-API-Calls
Summary by CodeRabbit
New Features
Chores