getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 22:03:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
co-mono/todos/project-description.md
Mario Zechner 99ce76d66e feat(agent): Comprehensive reasoning token support across providers 
Added provider-specific reasoning/thinking token support for:
- OpenAI (o1, o3, gpt-5): Full reasoning events via Responses API, token counts via Chat Completions
- Groq: reasoning_format:"parsed" for Chat Completions, no summary support for Responses
- Gemini 2.5: extra_body.google.thinking_config with <thought> tag extraction
- OpenRouter: Unified reasoning parameter with message.reasoning field
- Anthropic: Limited support via OpenAI compatibility layer

Key improvements:
- Centralized provider detection based on baseURL
- parseReasoningFromMessage() extracts provider-specific reasoning content
- adjustRequestForProvider() handles provider-specific request modifications
- Smart reasoning support detection with caching per API type
- Comprehensive README documentation with provider support matrix

Fixes reasoning tokens not appearing for GPT-5 and other reasoning models.
2025-08-10 01:46:15 +02:00

1.7 KiB
Raw Blame History

Project: Pi Monorepo

A comprehensive toolkit for managing Large Language Model (LLM) deployments and building AI agents, specifically designed for deploying and managing LLMs on remote GPU pods with automatic vLLM configuration for agentic workloads.

Features

  • Terminal UI framework with differential rendering and interactive components
  • AI agent framework with tool calling, session persistence, and multiple renderers
  • GPU pod management CLI for automated vLLM deployment on various providers
  • Support for OpenAI, Anthropic, Groq, OpenRouter, Gemini, and compatible APIs
  • Built-in file system tools for agentic AI capabilities

Tech Stack

  • TypeScript/JavaScript with ES Modules
  • Node.js ≥20.0.0
  • OpenAI SDK for LLM integration
  • Custom TUI library with differential rendering
  • Biome for linting and formatting
  • npm workspaces for monorepo structure

Structure

  • packages/tui/ - Terminal UI library
  • packages/agent/ - AI agent with tool calling
  • packages/pods/ - CLI for GPU pod management
  • scripts/ - Utility scripts for version sync
  • todos/ - Task tracking

Architecture

  • Event-driven agent system with publish-subscribe pattern
  • Component-based TUI with differential rendering
  • SSH-based remote pod management
  • Tool calling system for file operations (read, bash, glob, ripgrep)
  • Session persistence in JSONL format
  • Multiple renderer strategies (Console, TUI, JSON)

Commands

  • Lint: npm run check
  • Dev/Run: npx tsx packages/agent/src/cli.ts (pi-agent), npx tsx packages/pods/src/cli.ts (pi)
  • Version: npm run version:patch/minor/major
  • Publish: npm run publish

Testing

Currently no formal testing framework is configured. Test infrastructure exists but no actual test files or framework dependencies are present.