chisel-test-impact 0.9.2

Test impact analysis and code intelligence for LLM agents

Chisel

Test impact analysis and code intelligence built for AI coding agents. Zero external dependencies, open source, MIT licensed.

Chisel maps tests to code, code to git history, and answers: what to run, what’s risky, and who touched it. It runs as an MCP server alongside your agent — Claude Code, Cursor, Windsurf, Cline, or any MCP-compatible client.

What it does

Chisel builds a graph connecting your code, tests, and git history, then answers three questions:

1. What to run

You change engine.py:store_document(). Instead of running all 287 tests or guessing with -k “test_store”, Chisel tells the agent exactly which tests are impacted — through direct edges and transitive import-chain coupling.

2. What’s risky

Risk scores per file based on churn rate, coupling breadth, test coverage gaps, author concentration, and test instability. A file that changes often, has one author, and no tests? That’s your highest risk.

3. Who touched it

Blame-based ownership (who wrote it) and commit-activity-based reviewer suggestions (who maintains it). Useful when multiple agents or developers work on the same codebase and you need to understand lineage.

Why it exists

When multiple LLM agents (or agents + humans) work on the same codebase, changes in one area can silently break another.

Chisel gives AI coding assistants the intelligence to understand the blast radius of their changes before they commit. One agent’s refactor doesn’t silently regress another agent’s work — automated code quality checks that work at the speed of your agent.

Install

Available on PyPI:

pip install chisel-test-impact

Or from source:

git clone https://github.com/IronAdamant/Chisel.git
cd Chisel
pip install -e .

Use with Claude Code (MCP)

Add to your Claude Code MCP config (~/.claude/settings.json or project .mcp.json):

{
  “mcpServers”: {
    “chisel”: {
      “command”: “chisel-mcp”,
      “env”: {
        “CHISEL_PROJECT_DIR”: “/path/to/your/project”
      }
    }
  }
}

Run analyze first to build the project graph, then diff_impact after edits to see which tests to run. For large repos, analyze with force=True automatically falls back to a background job so you don't hit MCP timeouts. Working-tree analysis (--working-tree) reuses a cached static import index and falls back to fast stem-matching for untracked files to stay within timeout budgets.

Monorepo sharding: Split large codebases across multiple SQLite databases with the CHISEL_SHARDS environment variable or .chisel/shards.toml. Query tools automatically aggregate across shards; writes route to the correct shard by file path.

After running tests, call record_result so Chisel can track failure rates and test instability over time. Or use chisel run -- pytest tests/ to run tests and record results automatically.

Use with Cursor, Windsurf, Cline, or other MCP clients

Chisel exposes a standard MCP interface. For stdio-based clients:

pip install chisel-test-impact[mcp]
chisel-mcp

For HTTP-based clients:

chisel serve --port 8377

Quickstart (CLI)

# Analyze a project (builds the graph)
chisel analyze .

# What tests are impacted by my current changes?
chisel diff-impact

# What tests should I run for this file?
chisel suggest-tests engine.py

# Risk heatmap across the project
chisel risk-map

# Find code with no test coverage, sorted by risk
chisel test-gaps

# Who owns this code?
chisel ownership engine.py

# Incremental update (only re-process changed files)
chisel update

Try it on this repo

git clone https://github.com/IronAdamant/Chisel.git
cd Chisel
pip install -e .

chisel analyze .
chisel risk-map
chisel diff-impact
chisel test-gaps

MCP Tools

20 functional tools plus 6 advisory file-lock helpers for multi-agent coordination.

Tool	What it does
analyze	Full project scan — builds the code/test/git graph. Optional shard param for sharded monorepos
update	Incremental re-analysis of changed files only. Optional shard param for sharded monorepos
diff_impact	Detects your changes from git diff and returns impacted tests. working_tree=true enables full static import scanning for untracked files. auto_update=true refreshes stale DB inline
suggest_tests	Ranks tests by relevance for a given file. Prefers same-directory tests via stem matching. auto_update=true refreshes stale DB inline
impact	Which tests cover these files or functions?
risk_map	Risk scores for all files (churn + coupling + coverage gaps). working_tree=true includes untracked files. exclude_new_file_boost=true suppresses the temporary boost. auto_update=true refreshes stale DB inline
test_gaps	Code with zero test coverage, sorted by risk. working_tree=true elevates uncommitted files to the top. auto_update=true refreshes stale DB inline
triage	Top risks + gaps + stale tests in one call. Supports exclude_new_file_boost and auto_update
churn	How often does this file or function change?
coupling	Files that change together or import each other
ownership	Blame-based — who wrote this code?
who_reviews	Commit-activity-based — who maintains this code?
stale_tests	Tests pointing at code that no longer exists
history	Commit history for a file
record_result	Log test pass/fail outcomes for future prioritization
run	CLI-only: run tests and auto-record results (pytest, Jest)
stats	Database summary and diagnostic counts
start_job	Run analyze/update in background (avoids MCP timeouts)
job_status	Poll a background job until complete

Features

• Zero dependencies — stdlib only, Python 3.11+, works anywhere
• Multi-language — Python, JavaScript/TypeScript, Go, Rust, C#, Java, Kotlin, C/C++, Swift, PHP, Ruby, Dart
• Framework-aware — pytest, Jest, Go test, Rust #[test], Playwright, xUnit/NUnit/MSTest, JUnit, XCTest, PHPUnit, RSpec, Minitest, gtest, Dart test
• Incremental — only re-processes changed files, not the whole repo
• Branch-aware — diff_impact auto-detects feature branch vs main
• Multi-agent safe — cross-process locks so parallel agents don’t corrupt the graph
• MCP + CLI — stdio and HTTP MCP servers, plus a full CLI with 28 subcommands
• Monorepo sharding — split analysis across per-directory SQLite databases (CHISEL_SHARDS)
• Custom extractors — plug in tree-sitter or LSP via register_extractor() if you need it

Ecosystem

Chisel sits in the agent loop: impact -> tests -> record results -> refresh analysis. It works standalone or alongside Stele for semantic code context.

Docs: Agent playbook | Zero-dependency policy | Custom extractors

License

MIT