mirror of
https://github.com/leonvanzyl/autocoder.git
synced 2026-03-17 19:03:09 +00:00
13785325d7
API Provider Selection: - Add provider switcher in Settings modal (Claude, Kimi, GLM, Ollama, Custom) - Auth tokens stored locally only (registry.db), never returned by API - get_effective_sdk_env() builds provider-specific env vars for agent subprocess - All chat sessions (spec, expand, assistant) use provider settings - Backward compatible: defaults to Claude, env vars still work as override Fix Stuck Features: - Add _cleanup_stale_features() to process_manager.py - Reset in_progress features when agent stops, crashes, or fails healthcheck - Prevents features from being permanently stuck after rate limit crashes - Uses separate SQLAlchemy engine to avoid session conflicts with subprocess Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
81 lines
3.3 KiB
Plaintext
81 lines
3.3 KiB
Plaintext
# Optional: N8N webhook for progress notifications
|
|
# PROGRESS_N8N_WEBHOOK_URL=https://your-n8n-instance.com/webhook/...
|
|
|
|
# Playwright Browser Configuration
|
|
#
|
|
# PLAYWRIGHT_BROWSER: Which browser to use for testing
|
|
# - firefox: Lower CPU usage, recommended (default)
|
|
# - chrome: Google Chrome
|
|
# - webkit: Safari engine
|
|
# - msedge: Microsoft Edge
|
|
# PLAYWRIGHT_BROWSER=firefox
|
|
#
|
|
# PLAYWRIGHT_HEADLESS: Run browser without visible window
|
|
# - true: Browser runs in background, saves CPU (default)
|
|
# - false: Browser opens a visible window (useful for debugging)
|
|
# PLAYWRIGHT_HEADLESS=true
|
|
|
|
# Extra Read Paths (Optional)
|
|
# Comma-separated list of absolute paths for read-only access to external directories.
|
|
# The agent can read files from these paths but cannot write to them.
|
|
# Useful for referencing documentation, shared libraries, or other projects.
|
|
# Example: EXTRA_READ_PATHS=/Volumes/Data/dev,/Users/shared/libs
|
|
# EXTRA_READ_PATHS=
|
|
|
|
# Google Cloud Vertex AI Configuration (Optional)
|
|
# To use Claude via Vertex AI on Google Cloud Platform, uncomment and set these variables.
|
|
# Requires: gcloud CLI installed and authenticated (run: gcloud auth application-default login)
|
|
# Note: Use @ instead of - in model names (e.g., claude-opus-4-5@20251101)
|
|
#
|
|
# CLAUDE_CODE_USE_VERTEX=1
|
|
# CLOUD_ML_REGION=us-east5
|
|
# ANTHROPIC_VERTEX_PROJECT_ID=your-gcp-project-id
|
|
# ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-5@20251101
|
|
# ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-4-5@20250929
|
|
# ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-3-5-haiku@20241022
|
|
|
|
# ===================
|
|
# Alternative API Providers
|
|
# ===================
|
|
# NOTE: These env vars are the legacy way to configure providers.
|
|
# The recommended way is to use the Settings UI (API Provider section).
|
|
# UI settings take precedence when api_provider != "claude".
|
|
|
|
# Kimi K2.5 (Moonshot) Configuration (Optional)
|
|
# Get an API key at: https://kimi.com
|
|
#
|
|
# ANTHROPIC_BASE_URL=https://api.kimi.com/coding/
|
|
# ANTHROPIC_API_KEY=your-kimi-api-key
|
|
# ANTHROPIC_DEFAULT_SONNET_MODEL=kimi-k2.5
|
|
# ANTHROPIC_DEFAULT_OPUS_MODEL=kimi-k2.5
|
|
# ANTHROPIC_DEFAULT_HAIKU_MODEL=kimi-k2.5
|
|
|
|
# GLM/Alternative API Configuration (Optional)
|
|
# To use Zhipu AI's GLM models instead of Claude, uncomment and set these variables.
|
|
# This only affects AutoForge - your global Claude Code settings remain unchanged.
|
|
# Get an API key at: https://z.ai/subscribe
|
|
#
|
|
# ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic
|
|
# ANTHROPIC_AUTH_TOKEN=your-zhipu-api-key
|
|
# API_TIMEOUT_MS=3000000
|
|
# ANTHROPIC_DEFAULT_SONNET_MODEL=glm-4.7
|
|
# ANTHROPIC_DEFAULT_OPUS_MODEL=glm-4.7
|
|
# ANTHROPIC_DEFAULT_HAIKU_MODEL=glm-4.5-air
|
|
|
|
# Ollama Local Model Configuration (Optional)
|
|
# To use local models via Ollama instead of Claude, uncomment and set these variables.
|
|
# Requires Ollama v0.14.0+ with Anthropic API compatibility.
|
|
# See: https://ollama.com/blog/claude
|
|
#
|
|
# ANTHROPIC_BASE_URL=http://localhost:11434
|
|
# ANTHROPIC_AUTH_TOKEN=ollama
|
|
# API_TIMEOUT_MS=3000000
|
|
# ANTHROPIC_DEFAULT_SONNET_MODEL=qwen3-coder
|
|
# ANTHROPIC_DEFAULT_OPUS_MODEL=qwen3-coder
|
|
# ANTHROPIC_DEFAULT_HAIKU_MODEL=qwen3-coder
|
|
#
|
|
# Model recommendations:
|
|
# - For best results, use a capable coding model like qwen3-coder or deepseek-coder-v2
|
|
# - You can use the same model for all tiers, or different models per tier
|
|
# - Larger models (70B+) work best for Opus tier, smaller (7B-20B) for Haiku
|