Add Anthropic prompt caching, pluggable storage, and CORS proxy support

Storage Architecture:
- New pluggable storage system with backends (LocalStorage, ChromeStorage, IndexedDB)
- SettingsRepository for app settings (proxy config, etc.)
- ProviderKeysRepository for API key management
- AppStorage with global accessors (getAppStorage, setAppStorage, initAppStorage)

Transport Refactoring:
- Renamed DirectTransport → ProviderTransport (calls LLM providers with optional CORS proxy)
- Renamed ProxyTransport → AppTransport (uses app server with user auth)
- Updated TransportMode: "direct" → "provider", "proxy" → "app"

CORS Proxy Integration:
- ProviderTransport checks proxy.enabled/proxy.url from storage
- When enabled, modifies model baseUrl to route through proxy: {proxyUrl}/?url={originalBaseUrl}
- ProviderKeyInput test function also honors proxy settings
- Settings dialog with Proxy tab (Switch toggle, URL input, explanatory description)

Anthropic Prompt Caching:
- System prompt cached with cache_control markers (both OAuth and regular API keys)
- Last user message cached to cache conversation history
- Saves 90% on input tokens for cached content (10x cost reduction)

Settings Dialog Improvements:
- Configurable tab system with SettingsTab base class
- ApiKeysTab and ProxyTab as custom elements
- Switch toggle for proxy enable (instead of Checkbox)
- Explanatory paragraphs for each tab
- ApiKeyPromptDialog reuses ProviderKeyInput component

Removed:
- Deprecated ApiKeysDialog (replaced by ProviderKeyInput in SettingsDialog)
- Old storage-adapter and key-store (replaced by new storage architecture)
This commit is contained in:
Mario Zechner 2025-10-05 23:00:36 +02:00
parent 66f092c0c6
commit 0496651308
31 changed files with 1141 additions and 488 deletions

View file

@ -5,8 +5,10 @@ A collection of tools for managing LLM deployments and building AI agents.
## Packages
- **[@mariozechner/pi-ai](packages/ai)** - Unified multi-provider LLM API
- **[@mariozechner/pi-web-ui](packages/web-ui)** - Web components for building AI chat interfaces
- **[@mariozechner/pi-browser-extension](packages/browser-extension)** - Browser extension for AI assistance
- **[@mariozechner/pi-proxy](packages/proxy)** - CORS proxy for browser-based LLM API calls
- **[@mariozechner/pi-tui](packages/tui)** - Terminal UI library with differential rendering
- **[@mariozechner/pi](packages/browser-extension)** - CLI for managing vLLM deployments on GPU pods
- **[@mariozechner/pi-agent](packages/agent)** - General-purpose agent with tool calling and session persistence
- **[@mariozechner/pi](packages/pods)** - CLI for managing vLLM deployments on GPU pods