ask_gemini
Generates context from files and queries Gemini for a response.
Instructions
Generates context from files and sends it to Gemini for a response.
This tool combines context generation with a direct call to the Gemini API.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| user_instructions | No | The primary query or instructions for Gemini. | |
| file_selections | No | Optional list of files/line ranges to include in the context. | |
| project_path | No | Optional project root for relative paths. | |
| include_claude_memory | No | Include CLAUDE.md files in context. | |
| include_cursor_rules | No | Include Cursor rules files in context. | |
| auto_meta_prompt | No | If no user_instructions, generate a meta-prompt. | |
| temperature | No | AI temperature for generation. | |
| model | No | Specific Gemini model to use. | |
| thinking_budget | No | Optional token budget for thinking mode. | |
| text_output | No | If True, return the response as a string. If False, save it to a file. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |