arbiter-dev 0.2.0__tar.gz

arbiter_dev-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Reuben Bowlby, Daniel Matha / HUMMBL LLC
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

arbiter_dev-0.2.0/PKG-INFO

@@ -0,0 +1,216 @@
+Metadata-Version: 2.4
+Name: arbiter-dev
+Version: 0.2.0
+Summary: Agent-aware code quality system for multi-agent codebases
+Author: Reuben Bowlby, Daniel Matha
+License-Expression: MIT
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: analyzers
+Requires-Dist: ruff>=0.4.0; extra == "analyzers"
+Requires-Dist: radon>=6.0; extra == "analyzers"
+Requires-Dist: vulture>=2.10; extra == "analyzers"
+Requires-Dist: bandit>=1.7.0; extra == "analyzers"
+Provides-Extra: test
+Requires-Dist: pytest>=7.0; extra == "test"
+Provides-Extra: all
+Requires-Dist: arbiter[analyzers,test]; extra == "all"
+Dynamic: license-file
+
+# Arbiter
+
+**Agent-aware code quality system for multi-agent codebases.**
+
+In 2026, code is written by fleets of AI agents. Arbiter knows *who* wrote each line — human or AI — and scores quality accordingly.
+
+## What Makes Arbiter Different
+
+| Feature | Traditional Tools | Arbiter |
+|---------|------------------|---------|
+| Agent attribution | None | First-class: tracks Claude, Codex, Gemini, Copilot, humans |
+| Per-commit scoring | Repo-wide only | Scores each commit's changed files individually |
+| Diff analysis | N/A | Score only what changed in a PR/branch |
+| Transparency | Opaque score | Every score decomposes into lint + security + complexity |
+| Agent-specific gates | N/A | Different quality thresholds per agent trust tier |
+| Tool integration | Proprietary | Wraps tools you already trust: ruff, Bandit, radon, vulture |
+| Dashboard | SaaS login | Single HTML file with per-agent timelines, commit feed, fleet view |
+| Dependencies | Heavy | Analysis tools only; core is stdlib Python |
+
+## Quick Start
+
+```bash
+git clone https://github.com/hummbl-dev/arbiter.git
+cd arbiter
+
+# Install (makes `arbiter` command available)
+pip install ".[analyzers]"
+
+# Quick score (no persistence)
+arbiter score /path/to/your/repo
+
+# Full analysis with per-commit agent attribution
+arbiter analyze /path/to/your/repo
+
+# Score only files changed since main
+arbiter diff /path/to/your/repo --base main
+
+# Agent leaderboard
+arbiter agents
+
+# Start dashboard
+arbiter serve --port 8080
+# Open http://localhost:8080
+```
+
+### Without install (PYTHONPATH)
+
+```bash
+PYTHONPATH=src python -m arbiter score /path/to/your/repo
+```
+
+### With Docker
+
+```bash
+docker build -t arbiter .
+docker run -p 8080:8080 -v /path/to/repo:/repo:ro arbiter
+```
+
+## Architecture
+
+```
+Git Repo ──→ [Git Historian] ──→ [Analyzer Runner] ──→ [Scoring Engine] ──→ [SQLite Store]
+                  │                      │                     │                    │
+           agent attribution      tool invocation        weighted rubric       trend data
+           (Co-Authored-By,       (ruff, radon,          (lint 35%,             │
+            email matching)        vulture, bandit)        security 30%,        ├──→ REST API
+                                                           complexity 35%)     └──→ Dashboard
+             ┌────────────┐
+             │Diff Analyzer│ ←── v0.2: scores only changed files per commit/branch
+             └────────────┘
+```
+
+### Per-Commit Scoring (v0.2)
+
+Every commit is scored against only the files it changed, not the entire repo. This makes the agent leaderboard meaningful — a commit that touches 1 clean file scores differently than one that touches 10 messy files.
+
+### Diff Mode (v0.2)
+
+`arbiter diff` scores only files changed since a base branch. Ideal for CI/PR quality gates — fast, scoped, actionable.
+
+### Agent Attribution
+
+Arbiter identifies which agent authored each commit:
+
+1. **Co-Authored-By trailer** — `Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>`
+2. **Author email** — maps `noreply@anthropic.com` → claude, `codex@openai.com` → codex
+3. **Default** — "human" if no agent pattern matches
+
+Configure in `agents.yml`:
+```yaml
+agents:
+  - name: claude
+    emails: [noreply@anthropic.com]
+    co_author_patterns: ["Claude\\s+(Opus|Sonnet|Haiku)"]
+    trust_tier: verified
+    quality_threshold: 70.0
+  - name: gemini
+    trust_tier: probation
+    quality_threshold: 80.0  # Higher bar for probationary agents
+```
+
+### Analyzers (pluggable)
+
+| Analyzer | Tool | What It Finds |
+|----------|------|--------------|
+| Lint | ruff | Style violations, import errors, bugbear patterns |
+| Complexity | radon | Cyclomatic complexity (grade A-F per function) |
+| Security | bandit | Hardcoded secrets, shell injection, dangerous patterns |
+| Dead Code | vulture | Unused functions, imports, variables |
+| Duplication | AST hash | Near-duplicate function bodies |
+
+### Scoring
+
+Deterministic. Same code → same score. Always.
+
+```
+Overall = Lint (35%) + Security (30%) + Complexity (35%)
+
+Penalty points by severity:
+  CRITICAL: 50 | HIGH: 20 | MEDIUM: 5 | LOW: 1
+
+Score = 100 - (total_penalty / LOC) * normalization_factor
+```
+
+Grades: A (90+) | B (80+) | C (70+) | D (60+) | F (<60)
+
+### Dashboard (v2)
+
+Single HTML file with Chart.js. No build step, no React, no npm.
+
+- **Score Card** — Big number + breakdown bars
+- **Agent Leaderboard** — Who writes the best code? Color-coded by agent
+- **Per-Agent Quality Timeline** — Score over time per agent (not just repo-wide)
+- **Commit Feed** — Recent commits with agent, score, changes, timestamp
+- **Hotspot Files** — Ranked by finding count
+- **Fleet View** — Multi-repo quality grid with color-coded scores
+- **Tabbed UI** — Overview, Commits, Fleet tabs
+
+### API
+
+```
+GET /api/score                  Current repo score
+GET /api/agents                 Agent leaderboard
+GET /api/agents/{name}/trend    Per-agent quality over time
+GET /api/trend?days=30          Quality over time
+GET /api/worst?limit=20         Worst files
+GET /api/commits                Recent commits with scores
+GET /api/commits/{hash}         Detail for one commit
+GET /api/fleet                  Fleet report (multi-repo)
+GET /api/health                 System health
+```
+
+## CLI Commands
+
+```bash
+arbiter analyze <repo>                     # Full analysis + per-commit scoring + persist
+arbiter score <repo> [--json] [--exclude]  # Quick score (no persist)
+arbiter diff <repo> [--base main] [--json] # Score only changed files vs base branch
+arbiter agents                             # Agent leaderboard
+arbiter trend [--days 30]                  # Quality trend
+arbiter worst [--limit 20]                 # Worst files
+arbiter commits [--agent claude]           # Recent commits
+arbiter audit-fleet <directory>            # Audit all repos in a directory
+arbiter fleet-report                       # Fleet quality summary
+arbiter triage                             # Auto-classify repos: green/yellow/red/archive
+arbiter fix <repo> [--dry-run]             # Auto-fix ruff findings + before/after score
+arbiter serve [--port 8080]                # API + dashboard
+```
+
+## Tests
+
+```bash
+pip install ".[test]"
+PYTHONPATH=src python -m pytest tests/ -v
+# 78 tests, <7 seconds
+```
+
+## Requirements
+
+- Python 3.11+
+- git (for historian)
+- Optional: ruff, radon, vulture, bandit (for full analysis)
+- Docker (for containerized deployment)
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+
+---
+
+Built by [HUMMBL LLC](https://hummbl.io) from production experience coordinating Claude, Codex, Gemini, and human engineers on a 6,000+ test codebase.

arbiter_dev-0.2.0/README.md

@@ -0,0 +1,191 @@
+# Arbiter
+
+**Agent-aware code quality system for multi-agent codebases.**
+
+In 2026, code is written by fleets of AI agents. Arbiter knows *who* wrote each line — human or AI — and scores quality accordingly.
+
+## What Makes Arbiter Different
+
+| Feature | Traditional Tools | Arbiter |
+|---------|------------------|---------|
+| Agent attribution | None | First-class: tracks Claude, Codex, Gemini, Copilot, humans |
+| Per-commit scoring | Repo-wide only | Scores each commit's changed files individually |
+| Diff analysis | N/A | Score only what changed in a PR/branch |
+| Transparency | Opaque score | Every score decomposes into lint + security + complexity |
+| Agent-specific gates | N/A | Different quality thresholds per agent trust tier |
+| Tool integration | Proprietary | Wraps tools you already trust: ruff, Bandit, radon, vulture |
+| Dashboard | SaaS login | Single HTML file with per-agent timelines, commit feed, fleet view |
+| Dependencies | Heavy | Analysis tools only; core is stdlib Python |
+
+## Quick Start
+
+```bash
+git clone https://github.com/hummbl-dev/arbiter.git
+cd arbiter
+
+# Install (makes `arbiter` command available)
+pip install ".[analyzers]"
+
+# Quick score (no persistence)
+arbiter score /path/to/your/repo
+
+# Full analysis with per-commit agent attribution
+arbiter analyze /path/to/your/repo
+
+# Score only files changed since main
+arbiter diff /path/to/your/repo --base main
+
+# Agent leaderboard
+arbiter agents
+
+# Start dashboard
+arbiter serve --port 8080
+# Open http://localhost:8080
+```
+
+### Without install (PYTHONPATH)
+
+```bash
+PYTHONPATH=src python -m arbiter score /path/to/your/repo
+```
+
+### With Docker
+
+```bash
+docker build -t arbiter .
+docker run -p 8080:8080 -v /path/to/repo:/repo:ro arbiter
+```
+
+## Architecture
+
+```
+Git Repo ──→ [Git Historian] ──→ [Analyzer Runner] ──→ [Scoring Engine] ──→ [SQLite Store]
+                  │                      │                     │                    │
+           agent attribution      tool invocation        weighted rubric       trend data
+           (Co-Authored-By,       (ruff, radon,          (lint 35%,             │
+            email matching)        vulture, bandit)        security 30%,        ├──→ REST API
+                                                           complexity 35%)     └──→ Dashboard
+             ┌────────────┐
+             │Diff Analyzer│ ←── v0.2: scores only changed files per commit/branch
+             └────────────┘
+```
+
+### Per-Commit Scoring (v0.2)
+
+Every commit is scored against only the files it changed, not the entire repo. This makes the agent leaderboard meaningful — a commit that touches 1 clean file scores differently than one that touches 10 messy files.
+
+### Diff Mode (v0.2)
+
+`arbiter diff` scores only files changed since a base branch. Ideal for CI/PR quality gates — fast, scoped, actionable.
+
+### Agent Attribution
+
+Arbiter identifies which agent authored each commit:
+
+1. **Co-Authored-By trailer** — `Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>`
+2. **Author email** — maps `noreply@anthropic.com` → claude, `codex@openai.com` → codex
+3. **Default** — "human" if no agent pattern matches
+
+Configure in `agents.yml`:
+```yaml
+agents:
+  - name: claude
+    emails: [noreply@anthropic.com]
+    co_author_patterns: ["Claude\\s+(Opus|Sonnet|Haiku)"]
+    trust_tier: verified
+    quality_threshold: 70.0
+  - name: gemini
+    trust_tier: probation
+    quality_threshold: 80.0  # Higher bar for probationary agents
+```
+
+### Analyzers (pluggable)
+
+| Analyzer | Tool | What It Finds |
+|----------|------|--------------|
+| Lint | ruff | Style violations, import errors, bugbear patterns |
+| Complexity | radon | Cyclomatic complexity (grade A-F per function) |
+| Security | bandit | Hardcoded secrets, shell injection, dangerous patterns |
+| Dead Code | vulture | Unused functions, imports, variables |
+| Duplication | AST hash | Near-duplicate function bodies |
+
+### Scoring
+
+Deterministic. Same code → same score. Always.
+
+```
+Overall = Lint (35%) + Security (30%) + Complexity (35%)
+
+Penalty points by severity:
+  CRITICAL: 50 | HIGH: 20 | MEDIUM: 5 | LOW: 1
+
+Score = 100 - (total_penalty / LOC) * normalization_factor
+```
+
+Grades: A (90+) | B (80+) | C (70+) | D (60+) | F (<60)
+
+### Dashboard (v2)
+
+Single HTML file with Chart.js. No build step, no React, no npm.
+
+- **Score Card** — Big number + breakdown bars
+- **Agent Leaderboard** — Who writes the best code? Color-coded by agent
+- **Per-Agent Quality Timeline** — Score over time per agent (not just repo-wide)
+- **Commit Feed** — Recent commits with agent, score, changes, timestamp
+- **Hotspot Files** — Ranked by finding count
+- **Fleet View** — Multi-repo quality grid with color-coded scores
+- **Tabbed UI** — Overview, Commits, Fleet tabs
+
+### API
+
+```
+GET /api/score                  Current repo score
+GET /api/agents                 Agent leaderboard
+GET /api/agents/{name}/trend    Per-agent quality over time
+GET /api/trend?days=30          Quality over time
+GET /api/worst?limit=20         Worst files
+GET /api/commits                Recent commits with scores
+GET /api/commits/{hash}         Detail for one commit
+GET /api/fleet                  Fleet report (multi-repo)
+GET /api/health                 System health
+```
+
+## CLI Commands
+
+```bash
+arbiter analyze <repo>                     # Full analysis + per-commit scoring + persist
+arbiter score <repo> [--json] [--exclude]  # Quick score (no persist)
+arbiter diff <repo> [--base main] [--json] # Score only changed files vs base branch
+arbiter agents                             # Agent leaderboard
+arbiter trend [--days 30]                  # Quality trend
+arbiter worst [--limit 20]                 # Worst files
+arbiter commits [--agent claude]           # Recent commits
+arbiter audit-fleet <directory>            # Audit all repos in a directory
+arbiter fleet-report                       # Fleet quality summary
+arbiter triage                             # Auto-classify repos: green/yellow/red/archive
+arbiter fix <repo> [--dry-run]             # Auto-fix ruff findings + before/after score
+arbiter serve [--port 8080]                # API + dashboard
+```
+
+## Tests
+
+```bash
+pip install ".[test]"
+PYTHONPATH=src python -m pytest tests/ -v
+# 78 tests, <7 seconds
+```
+
+## Requirements
+
+- Python 3.11+
+- git (for historian)
+- Optional: ruff, radon, vulture, bandit (for full analysis)
+- Docker (for containerized deployment)
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+
+---
+
+Built by [HUMMBL LLC](https://hummbl.io) from production experience coordinating Claude, Codex, Gemini, and human engineers on a 6,000+ test codebase.

arbiter_dev-0.2.0/pyproject.toml

@@ -0,0 +1,36 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "arbiter-dev"
+version = "0.2.0"
+description = "Agent-aware code quality system for multi-agent codebases"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.11"
+authors = [
+    {name = "Reuben Bowlby"},
+    {name = "Daniel Matha"},
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
+[project.optional-dependencies]
+analyzers = ["ruff>=0.4.0", "radon>=6.0", "vulture>=2.10", "bandit>=1.7.0"]
+test = ["pytest>=7.0"]
+all = ["arbiter[analyzers,test]"]
+
+[project.scripts]
+arbiter = "arbiter.__main__:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

arbiter_dev-0.2.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

arbiter_dev-0.2.0/src/arbiter/__init__.py

@@ -0,0 +1,3 @@
+"""Arbiter — Agent-aware code quality system."""
+
+__version__ = "0.1.0"