mirror of
https://github.com/tiennm99/ccs.git
synced 2026-07-16 20:17:45 +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
14 lines
446 B
Plaintext
14 lines
446 B
Plaintext
Analyze this document/PDF thoroughly for a developer.
|
|
|
|
Extract and provide:
|
|
1. Document title, type, and structure
|
|
2. All text content - transcribe in reading order
|
|
3. Tables - format as markdown tables
|
|
4. Lists and bullet points - preserve structure
|
|
5. Code blocks or technical content
|
|
6. Diagrams or flowcharts - describe in detail
|
|
7. Headers and section organization
|
|
8. Any important metadata visible
|
|
|
|
Accuracy in text extraction is critical.
|