massgen · Henry-811 · Feb 9, 2026 · Feb 9, 2026 · Feb 9, 2026 · Feb 9, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,17 +9,73 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Recent Releases
 
+**v0.1.49 (February 9, 2026)** - Coordination Quality: Log Analysis TUI, Fairness Gate & Checklist Voting
+Log analysis mode built into TUI mode bar for in-app run analysis. Fairness gate prevents fast agents from dominating coordination. Checklist voting tool for structured quality evaluation. Automated testing infrastructure with CI/CD and SVG snapshot baselines.
+
 **v0.1.48 (February 6, 2026)** - Decomposition Mode & Worktree Isolation
 New decomposition coordination mode decomposes tasks into subtasks assigned to individual agents with a presenter role. Worktree isolation for file writes with review modal for approving changes. Quickstart wizard Docker setup with animated pull progress.
 
 **v0.1.47 (February 4, 2026)** - Codex Backend & TUI Theme Refactoring
 New Codex backend for OpenAI Codex CLI with local and Docker execution. TUI theme system refactored to palette-based architecture with unified base styles. Per-agent voting sensitivity configuration. Claude Code backend refactored with shared NativeToolMixin.
 
-**v0.1.46 (February 3, 2026)** - Subagent TUI Streaming & Event Architecture Refactor
-Subagents now stream in real-time with clickable preview cards that expand to full timeline views. Major TUI event architecture refactor with structured event emission pipeline. Improved final presentation display with workspace visualization and winning agent highlighting. Tutorial video GIF previews added to documentation.
-
 ---
 
+## [0.1.49] - 2026-02-09
+
+### Added
+- **Log Analysis Mode in TUI** ([#869](https://github.com/massgen/MassGen/pull/869)): New "Analyzing" state in the TUI mode bar for in-app run analysis
+  - Mode bar cycle: Normal → Planning → Executing → Analyzing
+  - Browse and select log directories and turns directly in the TUI
+  - Configurable analysis profiles for different analysis depths
+  - Empty submit in analysis mode runs default analysis on selected target
+
+- **Fairness Gate for Coordination** ([#869](https://github.com/massgen/MassGen/pull/869)): Prevents fast agents from dominating coordination rounds
+  - Configurable `fairness_lead_cap_answers` to limit how far ahead one agent can get
+  - `max_midstream_injections_per_round` to control injection frequency
+  - Ensures balanced participation across agents of different speeds
+
+- **Checklist Voting Tool** ([#869](https://github.com/massgen/MassGen/pull/869)): New `checklist_tools_server.py` MCP server for structured quality evaluation
+  - Binary pass/fail scoring for objective quality assessment
+  - Structured checklist-based evaluation replacing subjective voting
+
+- **Automated Testing Infrastructure** ([#869](https://github.com/massgen/MassGen/pull/869)): CI/CD workflow (`tests.yml`), SVG snapshot baselines, testing strategy spec, 16+ new test files
+  - GitHub Actions CI pipeline for automated test execution
+  - SVG snapshot baseline testing for TUI visual regression
+  - Comprehensive testing strategy specification
+
+- **Skills Modal in TUI** ([#869](https://github.com/massgen/MassGen/pull/869)): New modal for discovering and toggling skills in interactive mode
+  - `skills_modals.py` for skill discovery and management in TUI
+
+- **Docker Overlay Images** ([#869](https://github.com/massgen/MassGen/pull/869)): `Dockerfile.overlay` and build script for Agent Browser and OpenSkills integration
+
+### Changed
+- **Persona Easing in TUI Mode Bar** ([#869](https://github.com/massgen/MassGen/pull/869)): Persona easing toggle now accessible from the TUI mode bar
+- **Improved Decomposition Prompts** ([#869](https://github.com/massgen/MassGen/pull/869)): Better hook injection for non-hook backends
+- **Enhanced System Prompt Sections** ([#869](https://github.com/massgen/MassGen/pull/869)): Project instructions discovery and checklist evaluation blocks
+- **Expanded Skills Installer** ([#869](https://github.com/massgen/MassGen/pull/869)): Playwright, Agent Browser, and OpenSkills support
+- **Native Codex & Claude Code Skills** ([#869](https://github.com/massgen/MassGen/pull/869)): Direct skill integration for both backends
+
+### Fixed
+- **Shadow Agent Chunk Type Comparison** ([#861](https://github.com/massgen/MassGen/pull/861)): Fixed "[No response generated]" errors caused by incorrect chunk type comparison
+- **Round Banner Timing** ([#869](https://github.com/massgen/MassGen/pull/869)): Round banner no longer appears before final answer is locked
+- **Hook Injection for Non-Hook Backends** ([#869](https://github.com/massgen/MassGen/pull/869)): Corrected decomposition prompt injection for backends without native hook support
+- **Final Answer Lock Responsiveness** ([#869](https://github.com/massgen/MassGen/pull/869)): Improved lock timing and reduced hover lag
+- **Multiple Test Failures** ([#869](https://github.com/massgen/MassGen/pull/869)): Fixed hooks, persona easing, Docker mounts, and snapshot tests
+
+### Documentation, Configurations and Resources
+- **Testing Strategy**: New `docs/modules/testing.md` with testing architecture and CI gates
+- **SVG Snapshots**: Baseline snapshots in `massgen/tests/snapshot_tests/`
+- **CI/CD Pipeline**: `.github/workflows/tests.yml` for automated testing
+
+### Technical Details
+- **Major Focus**: Coordination quality improvements (log analysis TUI, fairness gate, checklist voting), automated testing infrastructure
+- **PRs Merged**: [#869](https://github.com/massgen/MassGen/pull/869) (Automate testing), [#861](https://github.com/massgen/MassGen/pull/861) (Shadow agent fix)
+- **Files Modified**:
+  - New: `massgen/mcp_tools/servers/checklist_tools_server.py`, `massgen/frontend/displays/textual/widgets/modals/skills_modals.py`
+  - Modified: `massgen/orchestrator.py` (fairness gate), `massgen/persona_generator.py` (easing), `massgen/frontend/displays/textual_widgets/mode_bar.py` (analysis mode)
+  - Infrastructure: `.github/workflows/tests.yml`, `Dockerfile.overlay`, `massgen/tests/` (16+ new test files)
+- **Contributors**: @ncrispino, @MuL1ian, and the MassGen team
+
 ## [0.1.48] - 2026-02-06
 
 ### Added

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -359,16 +359,16 @@ Create a `.env` file in the `massgen` directory as described in [README](README.
 
 ## 🔧 Development Workflow
 
-> **Important**: Our next version is v0.1.49. If you want to contribute, please contribute to the `dev/v0.1.49` branch (or `main` if dev/v0.1.49 doesn't exist yet).
+> **Important**: Our next version is v0.1.50. If you want to contribute, please contribute to the `dev/v0.1.50` branch (or `main` if dev/v0.1.50 doesn't exist yet).
 
 ### 1. Create Feature Branch
 
 ```bash
 # Fetch latest changes from upstream
 git fetch upstream
 
-# Create feature branch from dev/v0.1.49 (or main if dev branch doesn't exist yet)
-git checkout -b feature/your-feature-name upstream/dev/v0.1.49
+# Create feature branch from dev/v0.1.50 (or main if dev branch doesn't exist yet)
+git checkout -b feature/your-feature-name upstream/dev/v0.1.50
 ```
 
 ### 2. Make Your Changes
@@ -507,7 +507,7 @@ git push origin feature/your-feature-name
 ```
 
 Then create a pull request on GitHub:
-- Base branch: `dev/v0.1.49` (or `main` if dev branch doesn't exist yet)
+- Base branch: `dev/v0.1.50` (or `main` if dev branch doesn't exist yet)
 - Compare branch: `feature/your-feature-name`
 - Add clear description of changes
 - Link any related issues
@@ -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/v0.1.49` branch (or `main` if dev branch doesn't exist yet)
+- [ ] PR targets `dev/v0.1.50` branch (or `main` if dev branch doesn't exist yet)
 
 ### PR Description Should Include
 

diff --git a/README.md b/README.md
@@ -69,7 +69,7 @@ This project started with the "threads of thought" and "iterative refinement" id
 <details open>
 <summary><h3>🆕 Latest Features</h3></summary>
 
-- [v0.1.48 Features](#-latest-features-v0148)
+- [v0.1.49 Features](#-latest-features-v0149)
 </details>
 
 <details open>
@@ -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 (v0.1.48)](#recent-achievements-v0148)
-- [Previous Achievements (v0.0.3 - v0.1.47)](#previous-achievements-v003---v0147)
+- [Recent Achievements (v0.1.49)](#recent-achievements-v0149)
+- [Previous Achievements (v0.0.3 - v0.1.48)](#previous-achievements-v003---v0148)
 - [Key Future Enhancements](#key-future-enhancements)
   - Bug Fixes & Backend Improvements
   - Advanced Agent Collaboration
   - Expanded Model, Tool & Agent Integrations
   - Improved Performance & Scalability
   - Enhanced Developer Experience
-- [v0.1.49 Roadmap](#v0149-roadmap)
+- [v0.1.50 Roadmap](#v0150-roadmap)
 </details>
 
 <details open>
@@ -155,23 +155,24 @@ This project started with the "threads of thought" and "iterative refinement" id
 
 ---
 
-## 🆕 Latest Features (v0.1.48)
+## 🆕 Latest Features (v0.1.49)
 
-**🎉 Released: February 6, 2026**
+**🎉 Released: February 9, 2026**
 
-**What's New in v0.1.48:**
-- **🧩 Decomposition Mode** - New coordination mode that decomposes tasks into subtasks assigned to individual agents
-- **🔒 Worktree Isolation** - Git worktree-based isolation for agent file writes with review modal
-- **🐳 Quickstart Docker Setup** - Docker setup step in quickstart wizard with animated pull progress
-- **🛑 Stop Tool** - Agents can signal completion and exit workflows
-- **🐛 Bug Fixes** - Fixed subagent timeout, light theme visibility, post-evaluation restart crash
+**What's New in v0.1.49:**
+- **🔍 Log Analysis in TUI** - New "Analyzing" mode in the TUI mode bar for in-app run analysis with configurable profiles
+- **⚖️ Fairness Gate** - Prevents fast agents from dominating coordination with configurable lead caps
+- **✅ Checklist Voting** - Structured quality evaluation with binary pass/fail scoring via MCP server
+- **🧪 Testing Infrastructure** - CI/CD workflow, SVG snapshot baselines, 16+ new test files
+- **🎛️ Persona Easing in TUI** - Persona easing toggle now available in the TUI mode bar
+- **🐛 Bug Fixes** - Fixed shadow agent "[No response generated]" errors, round banner timing, hook injection
 
-**Try v0.1.48 Features:**
+**Try v0.1.49 Features:**
 ```bash
 # Install or upgrade
 pip install --upgrade massgen
 
-# Launch the quickstart wizard and select Decomposition mode
+# Launch with coordination quality improvements
 uv run massgen
 ```
 
@@ -1223,40 +1224,47 @@ 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 (v0.1.48)
+### Recent Achievements (v0.1.49)
 
-**🎉 Released: February 6, 2026**
+**🎉 Released: February 9, 2026**
 
-#### Decomposition Coordination Mode
-- **Task Decomposition**: New coordination mode that decomposes complex tasks into subtasks assigned to individual agents
-- **Presenter Agent**: Designated agent synthesizes subtask results into a final answer
-- **TUI Integration**: Mode bar toggle, subtask assignment display, and generation modals
+#### Log Analysis Mode in TUI
+- **TUI Mode Bar**: New "Analyzing" state in the mode bar cycle (Normal → Planning → Executing → Analyzing)
+- **In-App Analysis**: Browse and select log directories and turns directly in the TUI
+- **Configurable Profiles**: Different analysis depths for different needs
 
-#### Worktree Isolation
-- **Write Mode**: New `write_mode` config (`auto`/`worktree`/`isolated`/`legacy`) for git worktree-based isolation of agent file writes
-- **Review Modal**: Two-panel modal with file list toggles and syntax-highlighted diff for approving/rejecting changes
-- **Infrastructure**: `WorktreeManager`, `ShadowRepo`, `IsolationContextManager`, `ChangeApplier`
+#### Fairness Gate for Coordination
+- **Balanced Participation**: Prevents fast agents from dominating coordination rounds
+- **Configurable Controls**: `fairness_lead_cap_answers` and `max_midstream_injections_per_round`
+- **Use Case**: Ensures all agents contribute meaningfully regardless of speed
 
-#### Quickstart Wizard Docker Setup
-- **Docker Setup Step**: Integrated into quickstart wizard when Docker mode is selected
-- **Pull Progress**: Animated braille spinner with real-time `docker pull` stdout streaming
+#### Checklist Voting Tool
+- **MCP Server**: New `checklist_tools_server.py` for structured quality evaluation
+- **Binary Scoring**: Pass/fail scoring for objective quality assessment
+- **Consistency**: Repeatable evaluation across coordination rounds
+
+#### Automated Testing Infrastructure
+- **CI/CD Pipeline**: GitHub Actions workflow (`tests.yml`) for automated test execution
+- **SVG Snapshots**: Baseline testing for TUI visual regression
+- **Coverage**: 16+ new test files with comprehensive testing strategy
 
 #### Changed
-- **Codex Backend**: Default model updated from `gpt-5.2-codex` to `gpt-5.3-codex`
-- **Deprecation**: `use_two_tier_workspace` deprecated in favor of `write_mode`
+- **Persona Easing in TUI Mode Bar**: Persona easing toggle now accessible from the TUI mode bar
 
 #### Bug Fixes
-- **Subagent Timeout**: Timeout exemption for subagent-related MCP tools that manage their own timeouts
-- **Light Theme Visibility**: Fixed invisible mode bar underlines, separators, and toasts
-- **Post-evaluation Restarts**: Disabled by default in quickstart to prevent TUI crash
+- **Shadow Agent Responses**: Fixed "[No response generated]" errors from chunk type comparison (PR #861)
+- **Round Banner Timing**: No longer appears before final answer is locked
+- **Hook Injection**: Corrected decomposition prompt injection for non-hook backends
+- **Final Answer Lock**: Improved lock timing and reduced hover lag
 
 #### Documentation, Configurations and Resources
-- `docs/source/user_guide/agent_workspaces.rst` — new agent workspaces and code isolation guide
-- `docs/modules/worktrees.md` — new worktrees module documentation
-- `docs/source/reference/yaml_schema.rst` — decomposition mode configuration
-- `massgen/backend/capabilities.py` — updated with `gpt-5.3-codex`
+- `docs/modules/testing.md` — new testing strategy and architecture documentation
+- `.github/workflows/tests.yml` — CI/CD pipeline for automated testing
+- `massgen/tests/snapshot_tests/` — SVG snapshot baselines
+
+### Previous Achievements (v0.0.3 - v0.1.48)
 
-### Previous Achievements (v0.0.3 - v0.1.47)
+✅ **Decomposition Mode & Worktree Isolation (v0.1.48)**: New decomposition coordination mode that decomposes tasks into subtasks assigned to individual agents with a presenter role, git worktree-based isolation for agent file writes with review modal, quickstart wizard Docker setup with animated pull progress, stop tool for agent completion signaling
 
 ✅ **Codex Backend & TUI Theme Refactoring (v0.1.47)**: New Codex backend for OpenAI Codex CLI with local and Docker execution, NativeToolMixin for shared tool handling, TUI theme system refactored to palette-based architecture with dark and light variants, per-agent voting sensitivity configuration
 
@@ -1496,16 +1504,13 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch
 
 We welcome community contributions to achieve these goals.
 
-### v0.1.49 Roadmap
+### v0.1.50 Roadmap
 
-Version 0.1.49 focuses on enhanced log analysis capabilities:
+Version 0.1.50 focuses on log analysis improvements and worktree isolation:
 
 #### Planned Features
 - **Log Analysis Model Selector** ([#766](https://github.com/massgen/MassGen/issues/766)): Allow users to choose which model to use for `massgen logs analyze` self-analysis mode
-
-Key technical approach:
-- **Flexible Analysis**: Configurable model selection for cost/quality tradeoffs in log analysis
-- **Multi-Provider Support**: Works across OpenAI, Anthropic, Google backends
+- **Git Worktree Isolation** ([#853](https://github.com/massgen/MassGen/issues/853)): Worktree isolation improvements for agent file changes
 
 ---