feat: add API provider selection UI and fix stuck features on agent crash

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>

.env.example

@@ -34,6 +34,22 @@
 # 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.