Skip to content

Release v0.2.0

Choose a tag to compare

@github-actions github-actions released this 13 Feb 07:29
· 97 commits to main since this release

Shannon v0.2.0

🖥️ Desktop Apps

Download the desktop application for your platform:

macOS (Universal Binary - Intel & Apple Silicon)

  • .dmg installer (recommended)
  • .app.tar.gz for manual installation

Windows

  • .msi installer (recommended)
  • .exe NSIS installer (alternative)

Linux

  • .AppImage (portable, no installation required)
  • .deb package (Debian/Ubuntu)

🐳 Docker Images

docker pull waylandzhang/gateway:v0.2.0
docker pull waylandzhang/orchestrator:v0.2.0
docker pull waylandzhang/agent-core:v0.2.0
docker pull waylandzhang/llm-service:v0.2.0

🚀 Quick Start

Recommended: One-command install

curl -fsSL https://raw.githubusercontent.com/Kocoro-lab/Shannon/v0.2.0/scripts/install.sh | bash

This downloads all required files (config, migrations, WASM interpreter) and starts services.

Manual setup: Clone the repo and use deploy/compose/docker-compose.release.yml with the full directory structure.

📚 Documentation

📝 What's Changed

See CHANGELOG.md for detailed changes.

What's Changed

  • fix(citations): add three-tier LLM signal detection to prevent snippet pollution by @Awakehsh in #111
  • fix(gateway): improve SSE streaming reliability for long-running tasks by @waylandzhang in #115
  • feat(browser): migrate browser_use from Enterprise to OSS by @waylandzhang in #113
  • feat(web-search): multi-engine support, localization, Finance API & Search-First strategy by @Awakehsh in #112
  • feat(research): multi-tool loop hardening + citation pipeline fixes by @Awakehsh in #117
  • feat(research): Citation V2 + Verify V2 + P1 Efficiency Improvements by @Awakehsh in #118
  • fix(security): remove WASI /tmp symlink bypass and unify ModelTier enum by @waylandzhang in #120
  • fix(security): SSRF hardening, BM25 guard, URL sanitization, alias scoring by @waylandzhang in #121
  • feat: add DAG cycle detection, tool filtering, and idempotency TTL cleanup by @waylandzhang in #122
  • feat: Deep Research output quality improvements by @Awakehsh in #124
  • fix(research): comprehensive Deep Research output quality improvements by @Awakehsh in #125
  • feat(trading): add trading agent roles and template workflows by @waylandzhang in #126
  • fix: add template_results truncation and warning-level import logging by @waylandzhang in #127
  • Deep Research: Domain Discovery & Prefetch Optimization + Multilingual Enhancement by @Awakehsh in #129
  • fix: use general output format for non-research roles by @Awakehsh in #130
  • Feat/makefile by @weedge in #128
  • feat(templates): add parallel_by expansion and cron scheduling support by @waylandzhang in #131
  • Revert "Feat/makefile" by @waylandzhang in #132
  • feat: Research Workflow Upgrade - Domain Analysis, OODA Loop, and Quality Improvements by @Awakehsh in #133
  • feat(citation): implement placement-based citation with fallback by @Awakehsh in #135
  • feat: add skills system, filesystem tools, and WASI sandbox integration by @waylandzhang in #137
  • feat(research): optimize research strategy cost and performance by @Awakehsh in #138
  • fix(citations): filter fallback-only snippets and block table row placements by @Awakehsh in #140
  • feat: WASI session workspace mounting + hybrid Python sandbox scaffolding by @waylandzhang in #139
  • feat(hitl): Human-in-the-Loop research plan review system by @Awakehsh in #141
  • feat(swarm): add swarm multi-agent workflow with P2P messaging by @waylandzhang in #144

New Contributors

Full Changelog: v0.1.0...v0.2.0