Releases: ceilf6/FrontAgent
Releases · ceilf6/FrontAgent
FrontAgent v1.0.1
FrontAgent v1.0.1
FrontAgent v1.0.1 aligns the npm CLI package, VS Code extension, and GitHub Release messaging around the new two-mode workflow: use fa from the terminal, or use the FrontAgent sidebar directly inside VS Code.
Highlights
- Added the first FrontAgent VS Code desktop extension.
- Added an Activity Bar task console for running FrontAgent tasks from VS Code.
- Added current-file, selected-text, and browser URL context entry points.
- Added VS Code approval cards for sensitive tool actions.
- Added phase/step progress, final result rendering, and run log access.
- Added SDD initialization and validation commands in VS Code.
- Added shared
@frontagent/runtime-nodeAPIs reused by the CLI and VS Code extension. - Added cooperative cancellation support via
AbortSignal.
Usage
Use FrontAgent from the terminal:
npm install -g frontagent@1.0.1
fa init
fa run "Create a user login page"Use FrontAgent from VS Code:
- Install the Marketplace extension
ceilf6.frontagent. - Open a workspace folder.
- Run
FrontAgent: Configureand set your API key. - Open the FrontAgent Activity Bar view and run a task from the sidebar.
Release Artifacts
- npm package:
frontagent@1.0.1 - VS Code extension:
ceilf6.frontagent@1.0.1 - VSIX artifact:
frontagent-1.0.1.vsix
Notes
- VS Code support is desktop-only in this release because FrontAgent depends on Node.js, local file-system access, shell execution, browser automation, and MCP packages.
- Only one active VS Code run is allowed per workspace in this first extension version.
- Cancel is cooperative and stops at phase/step boundaries.
v0.1.9
Fixed
- Removed hard-coded CLI version reporting.
fa -v,fa --version,fa version, andfa infonow read the rootfrontagentpackage version.- Added regression coverage so nested workspace package versions do not override the published package version.
Changed
- Synced GitHub
mainandv0.1.9with the npmfrontagent@0.1.9release. - Includes the latest security architecture updates from
develop.
v0.1.8
v0.1.7
Added
- Added progressive exploration so file-system changes are planned as observe-first workflows before writes.
- Added built-in FrontAgent identity context for query answers.
Changed
- Shortened the published CLI command from
frontagenttofa. - Simplified default
fa runoutput to status, tool-call summary, and final answer, with verbose internals behind--debug.
Fixed
- Fixed the ESM bundle bootstrap for packages that expect
__filename. - Normalized OpenAI-compatible base URLs that already include
/chat/completions. - Made query tasks report a clear failure when no final answer is generated.
v0.1.6
Added
- Added Weaviate-backed semantic vector storage for RAG while keeping BM25 local.
- Added RAG cache bundle export/import workflow for distributing prebuilt knowledge-base indexes.
- Added a retrieval-only LLM query rewrite step that rewrites user input into frontend-oriented search queries before RAG.
Changed
- Clarified all RAG-facing terminology so remote RAG evidence is referred to as "knowledge base" instead of the current workspace repository.
- Updated English and Chinese documentation with Weaviate, query rewrite, and cache bundle usage examples.
Fixed
- Prevented the planner from treating remote RAG hits as local workspace files during query tasks.
- Improved semantic index resilience for Weaviate-backed retrieval and related RAG execution flow.
v0.1.5
Full Changelog: v0.1.4...v0.1.5
v0.1.4
v0.1.3
v0.1.2 - npm Package Fix
🐛 Bug Fixes
This release fixes the npm installation issues from v0.1.0 and v0.1.1.
What's Fixed
- ✅ Bundled all dependencies into a single executable using esbuild
- ✅ Reduced package size from 709KB to 6MB (bundled)
- ✅ Fixed module resolution errors when installing from npm
- ✅ Simplified installation - now only requires
playwrightas external dependency
📦 Installation
# Install globally
npm install -g frontagent
# Or using pnpm
pnpm add -g frontagent
# Or using npx (no installation needed)
npx frontagent --help🚀 Quick Start
# 1. Configure your LLM provider
export PROVIDER="openai"
export API_KEY="sk-..."
export MODEL="gpt-4"
# 2. Navigate to your project and initialize
cd your-project
frontagent init
# 3. Run tasks
frontagent run "Create a user login page"📋 Package Info
- npm: https://www.npmjs.com/package/frontagent
- Size: 6.0 MB (compressed), 35.7 MB (unpacked)
- Files: 5 (bundled)
📝 Changes Since v0.1.0
- Added esbuild bundling for CLI
- Removed workspace dependency issues
- Updated installation documentation
- Added npm badges to README
Full Changelog: v0.1.0...v0.1.2
v0.1.0 - Initial Release
🎉 Initial Release
FrontAgent is an enterprise AI agent platform for frontend engineering with planning/execution architecture, SDD constraints, and MCP-controlled code generation.
✨ Features
- Planning/Execution Architecture: Dual-stage architecture for reliable code generation
- SDD-Based Constraints: Software Design Document driven development workflow
- MCP Protocol Integration: Model Context Protocol for controlled actions
- Project Automation: Full project-level automation support
- Browser Validation: Built-in browser port validation
- File Structure Scanning: Pre-planning project structure analysis
📦 Installation
npm install -g frontagent@0.1.2
# or
pnpm add -g frontagent@0.1.2Note: Please use v0.1.2 instead, which includes bug fixes for npm installation.
📋 Requirements
- Node.js >= 20.0.0
- pnpm >= 9.0.0
Full Changelog: https://github.com/ceilf6/FrontAgent/commits/v0.1.0