Provider gemini does not pass custom headers to gemini API

[siom79]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I'm not able to find a related conversation on GitHub discussions that reports the same bug
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: macOS
- Continue version: > 1.2.11
- IDE version: VSCode 1.114
- Model: gemini
- config:
  
name: Gemini
version: 1.0.0
models: 
  - name: Gemini Flash
    provider: gemini
    model: gemini-2.5-flash
    apiBase: https://example.com/v1/streaming-models/locations/europe-west4/publishers/google # region can be adjusted (all european regions are possible)
    apiKey: <api-key>
    requestOptions:
      headers:
        x-api-key: <api-key>
        Content-Type: application/json
      verifySsl: true
      caBundlePath: "ca-bundle.crt"
    roles:
      - apply
      - chat
      - edit
    defaultCompletionOptions: # optional
      contextLength: 1048576
      maxTokens: 65536

Description

The API we are using still uses the API-Header x-api-key instead of x-goog-api-key. But configuring the header as shown above does not send it to the gemini API.
It seems that the code in the gemini-Extension here sends two hard-coded headers but not custom ones.
Can you please extend the code such that it also sends custom header configured in config.yaml?
Thanks in advance.

To reproduce

1. Use the above configuration with a valide API key
2. Try to chat with gemini
   You will get the following error message:

{"error":{"message":"{\n  \"error\": {\n    \"code\": 400,\n    \"message\": \"API key not valid. Please pass a valid API key.\",\n    \"status\": \"INVALID_ARGUMENT\",\n    \"details\": [\n      {\n        \"@type\": \"type.googleapis.com/google.rpc.ErrorInfo\",\n        \"reason\": \"API_KEY_INVALID\",\n        \"domain\": \"googleapis.com\",\n        \"metadata\": {\n          \"service\": \"generativelanguage.googleapis.com\"\n        }\n      },\n      {\n        \"@type\": \"type.googleapis.com/google.rpc.LocalizedMessage\",\n        \"locale\": \"en-US\",\n        \"message\": \"API key not valid. Please pass a valid API key.\"\n      }\n    ]\n  }\n}\n","code":400,"status":"Bad Request"}}

Log output

{"error":{"message":"{\n  \"error\": {\n    \"code\": 400,\n    \"message\": \"API key not valid. Please pass a valid API key.\",\n    \"status\": \"INVALID_ARGUMENT\",\n    \"details\": [\n      {\n        \"@type\": \"type.googleapis.com/google.rpc.ErrorInfo\",\n        \"reason\": \"API_KEY_INVALID\",\n        \"domain\": \"googleapis.com\",\n        \"metadata\": {\n          \"service\": \"generativelanguage.googleapis.com\"\n        }\n      },\n      {\n        \"@type\": \"type.googleapis.com/google.rpc.LocalizedMessage\",\n        \"locale\": \"en-US\",\n        \"message\": \"API key not valid. Please pass a valid API key.\"\n      }\n    ]\n  }\n}\n","code":400,"status":"Bad Request"}}

[serhiizghama]

Working on a fix for this. The GeminiApi constructor initializes GoogleGenAI without forwarding requestOptions.headers — those headers are only applied when using raw customFetch (e.g. in embed()), not when using the @google/genai SDK for chat. The GoogleGenAI constructor supports httpOptions.headers which should receive the custom headers from config. Will open a PR shortly.

[siom79]

Thank you very much for the fast response. 😀