Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 27 additions & 2 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,14 +9,39 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## Recent Releases

**v0.1.76 (April 13, 2026)** - Exa Search & Circuit Breaker Observability
New Exa AI-powered search tool for MCP. Circuit breaker Phase 3 with observability — probe ownership, lock release, per-attempt latency tracking. Copyable checkpoint agent instructions and Docker dependency fixes.

**v0.1.75 (April 10, 2026)** - Codex Hooks & Checkpoint WebUI
Hybrid hook system for Codex backend combining native and MCP capabilities. Checkpoint workflows now auto-launch the WebUI for visual monitoring. Standalone checkpoint MCP server documentation and safety policy integration.

**v0.1.74 (April 8, 2026)** - Checkpoint Improvements & Tool Call Fixes
Major improvements to standalone checkpoint MCP server. Fix for duplicate tool calls in ChatCompletions (including for MiniMax on OpenRouter) and Response API backends. Pre-collab evaluation criteria refinements.

**v0.1.73 (April 6, 2026)** - Eval Criteria Evolver & Checkpoint Objectives
New eval criteria evolver subagent that evolves criteria across rounds. Initial draft of checkpoint objective mode for safety planning of irreversible actions. Improved visibility of evaluation criteria.
---

## [0.1.76] - 2026-04-13

### Added
- **Exa AI Search Tool** ([#1057](https://github.com/massgen/MassGen/pull/1057)): New Exa AI-powered search tool added to MCP server registry with example config
- **Circuit Breaker Observability (Phase 3)** ([#1056](https://github.com/massgen/MassGen/pull/1056)): Observability module with probe ownership, lock release mechanisms, and per-attempt latency regression tracking
- **Checkpoint Agent Instructions** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Copyable custom instructions for agent memory files with checkpoint MCP information

### Fixed
- **Docker Dependencies** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Fixed Dockerfile installs for reliable container builds
- **Circuit Breaker Strengthening** ([#1056](https://github.com/massgen/MassGen/pull/1056)): Strengthened observability across all backends

### Documentation, Configurations and Resources
- **Updated MCP Server Registry**: Updated `docs/source/reference/mcp_server_registry.rst` with Exa search tool
- **Updated MCP Integration Guide**: Updated `docs/source/user_guide/tools/mcp_integration.rst`
- **Updated Standalone MCP README**: Updated `massgen/mcp_tools/standalone/README.md` with checkpoint instructions
- **New Checkpoint Instructions**: New `massgen/mcp_tools/standalone/checkpoint_instructions.md`
- **New Config**: New `massgen/configs/tools/web-search/exa_search_example.yaml`

### Technical Details
- **Major Focus**: Exa AI Search & Circuit Breaker Observability (Phase 3)
- **PRs Merged**: [#1056](https://github.com/massgen/MassGen/pull/1056), [#1057](https://github.com/massgen/MassGen/pull/1057), [#1058](https://github.com/massgen/MassGen/pull/1058)
- **Contributors**: @amabito, @HenryQi, @ncrispino, @teocollazo and the MassGen team

---

Expand Down
8 changes: 4 additions & 4 deletions CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -359,7 +359,7 @@ Create a `.env` file in the `massgen` directory as described in [README](README.

## 🔧 Development Workflow

> **Important**: Our next version is v0.1.76. If you want to contribute, please contribute to the `dev/v0.1.76` branch (or `main` if dev/v0.1.76 doesn't exist yet).
> **Important**: Our next version is v0.1.77. If you want to contribute, please contribute to the `dev/v0.1.77` branch (or `main` if dev/v0.1.77 doesn't exist yet).

### 1. Create Feature Branch

Expand All @@ -368,7 +368,7 @@ Create a `.env` file in the `massgen` directory as described in [README](README.
git fetch upstream

# Create feature branch from dev/v0.1.60 (or main if dev branch doesn't exist yet)
git checkout -b feature/your-feature-name upstream/dev/v0.1.76
git checkout -b feature/your-feature-name upstream/dev/v0.1.77
```

### 2. Make Your Changes
Expand Down Expand Up @@ -507,7 +507,7 @@ git push origin feature/your-feature-name
```

Then create a pull request on GitHub:
- Base branch: `dev/v0.1.76` (or `main` if dev branch doesn't exist yet)
- Base branch: `dev/v0.1.77` (or `main` if dev branch doesn't exist yet)
- Compare branch: `feature/your-feature-name`
- Add clear description of changes
- Link any related issues
Expand Down Expand Up @@ -617,7 +617,7 @@ Have a significant feature idea not covered by existing tracks?
- [ ] Tests pass locally
- [ ] Documentation is updated if needed
- [ ] Commit messages follow convention
- [ ] PR targets `dev/v0.1.76` branch (or `main` if dev branch doesn't exist yet)
- [ ] PR targets `dev/v0.1.77` branch (or `main` if dev branch doesn't exist yet)

### PR Description Should Include

Expand Down
47 changes: 25 additions & 22 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ This project started with the "threads of thought" and "iterative refinement" id
<details open>
<summary><h3>🆕 Latest Features</h3></summary>

- [v0.1.75 Features](#-latest-features-v0175)
- [v0.1.76 Features](#-latest-features-v0176)
</details>

<details open>
Expand Down Expand Up @@ -122,15 +122,15 @@ This project started with the "threads of thought" and "iterative refinement" id
<details open>
<summary><h3>🗺️ Roadmap</h3></summary>

- [Recent Achievements (v0.1.75)](#recent-achievements-v0175)
- [Previous Achievements (v0.0.3 - v0.1.74)](#previous-achievements-v003---v0174)
- [Recent Achievements (v0.1.76)](#recent-achievements-v0176)
- [Previous Achievements (v0.0.3 - v0.1.75)](#previous-achievements-v003---v0175)
- [Key Future Enhancements](#key-future-enhancements)
- Bug Fixes & Backend Improvements
- Advanced Agent Collaboration
- Expanded Model, Tool & Agent Integrations
- Improved Performance & Scalability
- Enhanced Developer Experience
- [v0.1.76 Roadmap](#v0176-roadmap)
- [v0.1.77 Roadmap](#v0177-roadmap)
</details>

<details open>
Expand All @@ -155,19 +155,19 @@ This project started with the "threads of thought" and "iterative refinement" id

---

## 🆕 Latest Features (v0.1.75)
## 🆕 Latest Features (v0.1.76)

**🎉 Released: April 10, 2026**
**🎉 Released: April 13, 2026**

**What's New in v0.1.75:**
- **🪝 Codex Native Hooks** - Hybrid hook system for Codex backend combining native and MCP capabilities.
- **🛡️ Checkpoint WebUI Auto-Launch** - Checkpoint workflows auto-launch the WebUI for visual monitoring.
- **📖 Standalone MCP Server Docs** - Guide for `massgen-checkpoint-mcp` with safety policy integration.
**What's New in v0.1.76:**
- **🔍 Exa AI Search Tool** - New Exa AI-powered search tool added to MCP server registry.
- **📊 Circuit Breaker Observability (Phase 3)** - Probe ownership, lock release, per-attempt latency tracking across all backends.
- **📋 Checkpoint Agent Instructions** - Copyable custom instructions for agent memory files with checkpoint MCP information.

**Try v0.1.75 Features:**
**Try v0.1.76 Features:**
```bash
pip install massgen==0.1.75
uv run massgen --config @examples/features/fast_iteration.yaml "Create an svg of an AI agent coding."
pip install massgen==0.1.76
uv run massgen --config @examples/tools/web-search/exa_search_example "Research the latest breakthroughs in multi-agent AI systems"
```

→ [See full release history and examples](massgen/configs/README.md#release-history--examples)
Expand Down Expand Up @@ -1239,16 +1239,19 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch

⚠️ **Early Stage Notice:** As MassGen is in active development, please expect upcoming breaking architecture changes as we continue to refine and improve the system.

### Recent Achievements (v0.1.75)
### Recent Achievements (v0.1.76)

**🎉 Released: April 10, 2026**
**🎉 Released: April 13, 2026**

#### Codex Hooks & Checkpoint WebUI
- **Codex Native Hooks** ([#1053](https://github.com/massgen/MassGen/pull/1053)): Hybrid hook system for Codex backend combining native hooks and MCP capabilities
- **Checkpoint WebUI Auto-Launch** ([#1053](https://github.com/massgen/MassGen/pull/1053)): Checkpoint workflows auto-launch WebUI with configurable host/port for visual monitoring
- **Standalone MCP Server Docs**: Guide for `massgen-checkpoint-mcp` with safety policy integration
#### Exa Search & Circuit Breaker Observability
- **Exa AI Search Tool** ([#1057](https://github.com/massgen/MassGen/pull/1057)): New Exa AI-powered search tool added to MCP server registry
- **Circuit Breaker Observability (Phase 3)** ([#1056](https://github.com/massgen/MassGen/pull/1056)): Probe ownership, lock release, per-attempt latency tracking across all backends
- **Checkpoint Agent Instructions** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Copyable custom instructions for agent memory files with checkpoint MCP information
- **Docker Dependency Fixes** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Fixed Dockerfile installs for reliable container builds

### Previous Achievements (v0.0.3 - v0.1.74)
### Previous Achievements (v0.0.3 - v0.1.75)

✅ **Codex Hooks & Checkpoint WebUI (v0.1.75)**: Hybrid hook system for Codex backend. Checkpoint workflows auto-launch WebUI for visual monitoring. Standalone checkpoint MCP server docs with safety policy integration.

✅ **Checkpoint Improvements & Tool Call Fixes (v0.1.74)**: Major improvements to standalone checkpoint MCP server. Fix for duplicate tool calls in ChatCompletions and Response API backends.

Expand Down Expand Up @@ -1543,9 +1546,9 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch

We welcome community contributions to achieve these goals.

### v0.1.76 Roadmap
### v0.1.77 Roadmap

Version 0.1.76 focuses on cloud execution:
Version 0.1.77 focuses on cloud execution:

#### Planned Features
- **Cloud Modal MVP** ([#982](https://github.com/massgen/MassGen/issues/982)): Run MassGen as a cloud job on Modal — progress streams to terminal, results saved locally under `.massgen/cloud_jobs/`
Expand Down
47 changes: 25 additions & 22 deletions README_PYPI.md
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ This project started with the "threads of thought" and "iterative refinement" id
<details open>
<summary><h3>🆕 Latest Features</h3></summary>

- [v0.1.75 Features](#-latest-features-v0175)
- [v0.1.76 Features](#-latest-features-v0176)
</details>

<details open>
Expand Down Expand Up @@ -121,15 +121,15 @@ This project started with the "threads of thought" and "iterative refinement" id
<details open>
<summary><h3>🗺️ Roadmap</h3></summary>

- [Recent Achievements (v0.1.75)](#recent-achievements-v0175)
- [Previous Achievements (v0.0.3 - v0.1.74)](#previous-achievements-v003---v0174)
- [Recent Achievements (v0.1.76)](#recent-achievements-v0176)
- [Previous Achievements (v0.0.3 - v0.1.75)](#previous-achievements-v003---v0175)
- [Key Future Enhancements](#key-future-enhancements)
- Bug Fixes & Backend Improvements
- Advanced Agent Collaboration
- Expanded Model, Tool & Agent Integrations
- Improved Performance & Scalability
- Enhanced Developer Experience
- [v0.1.76 Roadmap](#v0176-roadmap)
- [v0.1.77 Roadmap](#v0177-roadmap)
</details>

<details open>
Expand All @@ -154,19 +154,19 @@ This project started with the "threads of thought" and "iterative refinement" id

---

## 🆕 Latest Features (v0.1.75)
## 🆕 Latest Features (v0.1.76)

**🎉 Released: April 10, 2026**
**🎉 Released: April 13, 2026**

**What's New in v0.1.75:**
- **🪝 Codex Native Hooks** - Hybrid hook system for Codex backend combining native and MCP capabilities.
- **🛡️ Checkpoint WebUI Auto-Launch** - Checkpoint workflows auto-launch the WebUI for visual monitoring.
- **📖 Standalone MCP Server Docs** - Guide for `massgen-checkpoint-mcp` with safety policy integration.
**What's New in v0.1.76:**
- **🔍 Exa AI Search Tool** - New Exa AI-powered search tool added to MCP server registry.
- **📊 Circuit Breaker Observability (Phase 3)** - Probe ownership, lock release, per-attempt latency tracking across all backends.
- **📋 Checkpoint Agent Instructions** - Copyable custom instructions for agent memory files with checkpoint MCP information.

**Try v0.1.75 Features:**
**Try v0.1.76 Features:**
```bash
pip install massgen==0.1.75
uv run massgen --config @examples/features/fast_iteration.yaml "Create an svg of an AI agent coding."
pip install massgen==0.1.76
uv run massgen --config @examples/tools/web-search/exa_search_example "Research the latest breakthroughs in multi-agent AI systems"
```

→ [See full release history and examples](massgen/configs/README.md#release-history--examples)
Expand Down Expand Up @@ -1238,16 +1238,19 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch

⚠️ **Early Stage Notice:** As MassGen is in active development, please expect upcoming breaking architecture changes as we continue to refine and improve the system.

### Recent Achievements (v0.1.75)
### Recent Achievements (v0.1.76)

**🎉 Released: April 10, 2026**
**🎉 Released: April 13, 2026**

#### Codex Hooks & Checkpoint WebUI
- **Codex Native Hooks** ([#1053](https://github.com/massgen/MassGen/pull/1053)): Hybrid hook system for Codex backend combining native hooks and MCP capabilities
- **Checkpoint WebUI Auto-Launch** ([#1053](https://github.com/massgen/MassGen/pull/1053)): Checkpoint workflows auto-launch WebUI with configurable host/port for visual monitoring
- **Standalone MCP Server Docs**: Guide for `massgen-checkpoint-mcp` with safety policy integration
#### Exa Search & Circuit Breaker Observability
- **Exa AI Search Tool** ([#1057](https://github.com/massgen/MassGen/pull/1057)): New Exa AI-powered search tool added to MCP server registry
- **Circuit Breaker Observability (Phase 3)** ([#1056](https://github.com/massgen/MassGen/pull/1056)): Probe ownership, lock release, per-attempt latency tracking across all backends
- **Checkpoint Agent Instructions** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Copyable custom instructions for agent memory files with checkpoint MCP information
- **Docker Dependency Fixes** ([#1058](https://github.com/massgen/MassGen/pull/1058)): Fixed Dockerfile installs for reliable container builds

### Previous Achievements (v0.0.3 - v0.1.74)
### Previous Achievements (v0.0.3 - v0.1.75)

✅ **Codex Hooks & Checkpoint WebUI (v0.1.75)**: Hybrid hook system for Codex backend. Checkpoint workflows auto-launch WebUI for visual monitoring. Standalone checkpoint MCP server docs with safety policy integration.

✅ **Checkpoint Improvements & Tool Call Fixes (v0.1.74)**: Major improvements to standalone checkpoint MCP server. Fix for duplicate tool calls in ChatCompletions and Response API backends.

Expand Down Expand Up @@ -1542,9 +1545,9 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch

We welcome community contributions to achieve these goals.

### v0.1.76 Roadmap
### v0.1.77 Roadmap

Version 0.1.76 focuses on cloud execution:
Version 0.1.77 focuses on cloud execution:

#### Planned Features
- **Cloud Modal MVP** ([#982](https://github.com/massgen/MassGen/issues/982)): Run MassGen as a cloud job on Modal — progress streams to terminal, results saved locally under `.massgen/cloud_jobs/`
Expand Down
28 changes: 20 additions & 8 deletions ROADMAP.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
# MassGen Roadmap

**Current Version:** v0.1.75
**Current Version:** v0.1.76

**Release Schedule:** Mondays, Wednesdays, Fridays @ 9am PT

**Last Updated:** April 10, 2026
**Last Updated:** April 13, 2026

This roadmap outlines MassGen's development priorities for upcoming releases. Each release focuses on specific capabilities with real-world use cases.

Expand Down Expand Up @@ -42,14 +42,26 @@ Want to contribute or collaborate on a specific track? Reach out to the track ow

| Release | Target | Feature | Owner | Use Case |
|---------|--------|---------|-------|----------|
| **v0.1.76** | 04/13/26 | Cloud Modal MVP | @ncrispino | Run MassGen as a cloud job on Modal ([#982](https://github.com/massgen/MassGen/issues/982)) |
| **v0.1.77** | 04/15/26 | OpenAI Audio API | @ncrispino | Support OpenAI audio API for audio understanding ([#960](https://github.com/massgen/MassGen/issues/960)) |
| **v0.1.78** | 04/17/26 | Image/Video Edit Capabilities | @ncrispino | Check and support img/video editing capabilities ([#959](https://github.com/massgen/MassGen/issues/959)) |
| **v0.1.77** | 04/15/26 | Cloud Modal MVP | @ncrispino | Run MassGen as a cloud job on Modal ([#982](https://github.com/massgen/MassGen/issues/982)) |
| **v0.1.78** | 04/17/26 | OpenAI Audio API | @ncrispino | Support OpenAI audio API for audio understanding ([#960](https://github.com/massgen/MassGen/issues/960)) |
| **v0.1.79** | 04/20/26 | Image/Video Edit Capabilities | @ncrispino | Check and support img/video editing capabilities ([#959](https://github.com/massgen/MassGen/issues/959)) |

*All releases ship on MWF @ 9am PT when ready*

---

## ✅ v0.1.76 - Exa Search & Circuit Breaker Observability (Completed)

**Released:** April 13, 2026 | PRs: [#1056](https://github.com/massgen/MassGen/pull/1056), [#1057](https://github.com/massgen/MassGen/pull/1057), [#1058](https://github.com/massgen/MassGen/pull/1058)

### Features
- **Exa AI Search Tool**: New Exa AI-powered search tool for MCP with example config
- **Circuit Breaker Observability (Phase 3)**: Probe ownership, lock release, per-attempt latency tracking across all backends
- **Checkpoint Agent Instructions**: Copyable custom instructions for agent memory files with checkpoint MCP information
- **Docker Dependency Fixes**: Fixed Dockerfile installs for reliable container builds

---

## ✅ v0.1.75 - Codex Hooks & Checkpoint WebUI (Completed)

**Released:** April 10, 2026 | PRs: [#1053](https://github.com/massgen/MassGen/pull/1053)
Expand All @@ -62,7 +74,7 @@ Want to contribute or collaborate on a specific track? Reach out to the track ow

---

## 📋 v0.1.76 - Cloud Modal MVP
## 📋 v0.1.77 - Cloud Modal MVP

### Features

Expand All @@ -78,7 +90,7 @@ Want to contribute or collaborate on a specific track? Reach out to the track ow

---

## 📋 v0.1.77 - OpenAI Audio API
## 📋 v0.1.78 - OpenAI Audio API

### Features

Expand All @@ -94,7 +106,7 @@ Want to contribute or collaborate on a specific track? Reach out to the track ow

---

## 📋 v0.1.78 - Image/Video Edit Capabilities
## 📋 v0.1.79 - Image/Video Edit Capabilities

### Features

Expand Down
10 changes: 5 additions & 5 deletions ROADMAP_v0.1.77.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
# MassGen v0.1.76 Roadmap
# MassGen v0.1.77 Roadmap

**Target Release:** April 13, 2026
**Target Release:** April 15, 2026

## Overview

Version 0.1.76 focuses on running MassGen as a cloud job on Modal.
Version 0.1.77 focuses on running MassGen as a cloud job on Modal.

---

Expand All @@ -27,5 +27,5 @@ Version 0.1.76 focuses on running MassGen as a cloud job on Modal.

## Related Tracks

- **v0.1.75**: Codex Hooks & Checkpoint WebUI — hybrid Codex hooks, checkpoint WebUI auto-launch, standalone MCP server docs ([#1053](https://github.com/massgen/MassGen/pull/1053))
- **v0.1.77**: OpenAI Audio API ([#960](https://github.com/massgen/MassGen/issues/960))
- **v0.1.76**: Exa Search & Circuit Breaker Observability — Phase 3 observability, Exa AI search, checkpoint instructions ([#1056](https://github.com/massgen/MassGen/pull/1056), [#1057](https://github.com/massgen/MassGen/pull/1057), [#1058](https://github.com/massgen/MassGen/pull/1058))
- **v0.1.78**: OpenAI Audio API ([#960](https://github.com/massgen/MassGen/issues/960))
Loading
Loading