Irina Levit
3546c04348
Some checks failed
CI / backend-test (push) Successful in 4m9s
CI / frontend-test (push) Failing after 3m48s
CI / lint-python (push) Successful in 1m41s
CI / secret-scanning (push) Successful in 1m20s
CI / dependency-scan (push) Successful in 10m50s
CI / workflow-summary (push) Successful in 1m11s
## Features Added
### Document Reference System
- Implemented numbered document references (@1, @2, etc.) with autocomplete dropdown
- Added fuzzy filename matching for @filename references
- Document filtering now prioritizes numeric refs > filename refs > all documents
- Autocomplete dropdown appears when typing @ with keyboard navigation (Up/Down, Enter/Tab, Escape)
- Document numbers displayed in UI for easy reference
### Conversation Management
- Added conversation rename functionality with inline editing
- Implemented conversation search (by title and content)
- Search box always visible, even when no conversations exist
- Export reports now replace @N references with actual filenames
### UI/UX Improvements
- Removed debug toggle button
- Improved text contrast in dark mode (better visibility)
- Made input textarea expand to full available width
- Fixed file text color for better readability
- Enhanced document display with numbered badges
### Configuration & Timeouts
- Made HTTP client timeouts configurable (connect, write, pool)
- Added .env.example with all configuration options
- Updated timeout documentation
### Developer Experience
- Added `make test-setup` target for automated test conversation creation
- Test setup script supports TEST_MESSAGE and TEST_DOCS env vars
- Improved Makefile with dev and test-setup targets
### Documentation
- Updated ARCHITECTURE.md with all new features
- Created comprehensive deployment documentation
- Added GPU VM setup guides
- Removed unnecessary markdown files (CLAUDE.md, CONTRIBUTING.md, header.jpg)
- Organized documentation in docs/ directory
### GPU VM / Ollama (Stability + GPU Offload)
- Updated GPU VM docs to reflect the working systemd environment for remote Ollama
- Standardized remote Ollama port to 11434 (and added /v1/models verification)
- Documented required env for GPU offload on this VM:
- `OLLAMA_MODELS=/mnt/data/ollama`, `HOME=/mnt/data/ollama/home`
- `OLLAMA_LLM_LIBRARY=cuda_v12` (not `cuda`)
- `LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12`
## Technical Changes
### Backend
- Enhanced `docs_context.py` with reference parsing (numeric and filename)
- Added `update_conversation_title` to storage.py
- New endpoints: PATCH /api/conversations/{id}/title, GET /api/conversations/search
- Improved report generation with filename substitution
### Frontend
- Removed debugMode state and related code
- Added autocomplete dropdown component
- Implemented search functionality in Sidebar
- Enhanced ChatInterface with autocomplete and improved textarea sizing
- Updated CSS for better contrast and responsive design
## Files Changed
- Backend: config.py, council.py, docs_context.py, main.py, storage.py
- Frontend: App.jsx, ChatInterface.jsx, Sidebar.jsx, and related CSS files
- Documentation: README.md, ARCHITECTURE.md, new docs/ directory
- Configuration: .env.example, Makefile
- Scripts: scripts/test_setup.py
## Breaking Changes
None - all changes are backward compatible
## Testing
- All existing tests pass
- New test-setup script validates conversation creation workflow
- Manual testing of autocomplete, search, and rename features
81 lines
3.1 KiB
Plaintext
81 lines
3.1 KiB
Plaintext
# ============================================================================
|
|
# LLM Council Configuration
|
|
# ============================================================================
|
|
# Copy this file to .env and customize as needed
|
|
# ============================================================================
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Provider & Server Configuration
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Use local Ollama (automatically sets base URL to http://localhost:11434)
|
|
USE_LOCAL_OLLAMA=true
|
|
|
|
# For remote Ollama or other OpenAI-compatible servers, comment USE_LOCAL_OLLAMA
|
|
# and set the base URL instead:
|
|
# OPENAI_COMPAT_BASE_URL=http://your-server:11434
|
|
# OPENAI_COMPAT_BASE_URL=http://10.0.30.63:8000
|
|
|
|
# Optional API key if your server requires authentication
|
|
# OPENAI_COMPAT_API_KEY=your_api_key_here
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Model Configuration
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Models for the council (comma or newline separated)
|
|
# Tip: Check available models with: curl -s 'http://localhost:8001/api/llm/status?probe=true'
|
|
COUNCIL_MODELS=llama3.2:3b,qwen2.5:3b,gemma2:2b
|
|
|
|
# Chairman model (synthesizes final response from council)
|
|
CHAIRMAN_MODEL=llama3.2:3b
|
|
|
|
# Maximum tokens per request
|
|
MAX_TOKENS=1024
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Timeout Configuration
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Default timeout for general LLM queries (Stage 1: council responses)
|
|
LLM_TIMEOUT_SECONDS=300.0
|
|
|
|
# Timeout for chairman synthesis (may need longer for complex responses)
|
|
CHAIRMAN_TIMEOUT_SECONDS=180.0
|
|
|
|
# Timeout for title generation (short responses)
|
|
TITLE_GENERATION_TIMEOUT_SECONDS=120.0
|
|
|
|
# HTTP client timeout for OpenAI-compatible server (fallback, rarely used)
|
|
OPENAI_COMPAT_TIMEOUT_SECONDS=300
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Retry Configuration
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Number of retries for failed requests (retryable HTTP errors)
|
|
OPENAI_COMPAT_RETRIES=2
|
|
|
|
# Exponential backoff base delay between retries (seconds)
|
|
OPENAI_COMPAT_RETRY_BACKOFF_SECONDS=0.5
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Concurrency Configuration
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Maximum concurrent model requests (0 = unlimited, 1 = sequential)
|
|
LLM_MAX_CONCURRENCY=1
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Document Upload Configuration (Optional)
|
|
# ----------------------------------------------------------------------------
|
|
|
|
# Directory for uploaded markdown documents (per-conversation)
|
|
# DOCS_DIR=data/docs
|
|
|
|
# Maximum document size in bytes (default: 1MB)
|
|
# MAX_DOC_BYTES=1000000
|
|
|
|
# Maximum characters to preview when fetching documents (default: 20000)
|
|
# MAX_DOC_PREVIEW_CHARS=20000
|