mirror of
https://github.com/tiennm99/ccs.git
synced 2026-07-16 16:16:52 +00:00
kaitranntt
d5f2acaa6e
Intercept Read tool calls for image/PDF files and route through CLIProxy with gemini-2.5-flash for vision analysis. Returns text descriptions instead of blocking, enabling Claude to "see" images via proxy. Key changes: - Add image-analyzer-transformer.cjs hook script - Add ImageAnalysisConfig type and loader - Add hook installer and profile injector - Add prompt templates for analysis customization - Add e2e test suite (excluded from normal CI runs) - Configure test:e2e script for manual testing Environment variables: - CCS_IMAGE_ANALYSIS_ENABLED: Enable/disable (default: 1) - CCS_IMAGE_ANALYSIS_MODEL: Vision model (default: gemini-2.5-flash) - CCS_IMAGE_ANALYSIS_TIMEOUT: Timeout in seconds (default: 60) - CCS_CLIPROXY_API_KEY: API key for CLIProxy auth - CCS_CLIPROXY_PORT: CLIProxy port (default: 8317) Closes #426
13 lines
525 B
Plaintext
13 lines
525 B
Plaintext
Analyze this image/document thoroughly and provide a detailed description.
|
|
|
|
Include:
|
|
1. Overall content and purpose
|
|
2. Text content (if any) - transcribe important text verbatim
|
|
3. Visual elements (diagrams, charts, UI components, icons)
|
|
4. Layout and structure (sections, hierarchy, flow)
|
|
5. Colors, styling, notable design elements
|
|
6. Any actionable information (buttons, links, code snippets)
|
|
|
|
Be comprehensive - this description replaces direct visual access.
|
|
The AI assistant reading this cannot see the original image.
|