Metadata-Version: 2.4
Name: sourcecode
Version: 0.34.0
Summary: Deterministic codebase context for AI coding agents
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other formats.
        
              "Work" shall mean the work of authorship made available under
              the License, as indicated by a copyright notice that is included in
              or attached to the work (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other transformations
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean, as submitted to the Licensor for inclusion
              in the Work by the copyright owner or by an individual or Legal Entity
              authorized to submit on behalf of the copyright owner. For the purposes
              of this definition, "submit" means any form of electronic, verbal, or
              written communication sent to the Licensor or its representatives,
              including but not limited to communication on electronic mailing lists,
              source code control systems, and issue tracking systems that are managed
              by, or on behalf of, the Licensor for the purpose of discussing and
              improving the Work, but excluding communication that is conspicuously
              marked or designated in writing by the copyright owner as "Not a
              Contribution."
        
              "Contributor" shall mean Licensor and any Legal Entity on behalf of
              whom a Contribution has been received by the Licensor and included
              within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by the combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a cross-claim
              or counterclaim in a lawsuit) alleging that the Work or any Contributor
              Contribution constitutes direct or contributory patent infringement,
              then any patent rights granted to You under this License for that Work
              shall terminate as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or Derivative
                  Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, You must include a readable copy of the
                  attribution notices contained within such NOTICE file, in
                  at least one of the following places: within a NOTICE text
                  file distributed as part of the Derivative Works; within
                  the Source form or documentation, if provided along with the
                  Derivative Works; or, within a display generated by the
                  Derivative Works, if and wherever such third-party notices
                  normally appear. The contents of the NOTICE file are for
                  informational purposes only and do not modify the License.
                  You may add Your own attribution notices within Derivative
                  Works that You distribute, alongside or in addition to the
                  NOTICE text from the Work, provided that such additional
                  attribution notices cannot be construed as modifying the License.
        
              You may add Your own license statement for Your modifications and
              may provide additional grant of rights to use, copy, modify, merge,
              publish, distribute, sublicense, and/or sell copies of the
              Derivative Works, as separate terms and conditions for their use,
              reproduction, and distribution, or alongside or as supplement to
              any license terms for such Derivative Works as a whole, provided
              Your use, reproduction, and distribution of the Work otherwise
              complies with the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or reproducing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or exemplary damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or all other
              commercial damages or losses), even if such Contributor has been
              advised of the possibility of such damages.
        
           9. Accepting Warranty or Liability. While redistributing the Work or
              Derivative Works thereof, You may choose to offer, and charge a fee
              for, acceptance of support, warranty, indemnity, or other liability
              obligations and/or rights consistent with this License. However, in
              accepting such obligations, You may offer such obligations only on
              Your own behalf and on Your sole responsibility, not on behalf of
              any other Contributor, and only if You agree to indemnify, defend,
              and hold each Contributor harmless for any liability incurred by,
              or claims asserted against, such Contributor by reason of your
              accepting any warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           Copyright 2024 sourcecode contributors
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
License-File: LICENSE
Keywords: agents,ai,codebase,context,developer-tools,llm
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Utilities
Requires-Python: >=3.9
Requires-Dist: pathspec>=1.0
Requires-Dist: ruamel-yaml>=0.18
Requires-Dist: tomli>=2.0; python_version < '3.11'
Requires-Dist: typer>=0.24
Provides-Extra: ast
Requires-Dist: tree-sitter-javascript>=0.21; extra == 'ast'
Requires-Dist: tree-sitter-typescript>=0.21; extra == 'ast'
Requires-Dist: tree-sitter>=0.21; extra == 'ast'
Provides-Extra: dev
Requires-Dist: mypy>=1.10; extra == 'dev'
Requires-Dist: pytest>=8; extra == 'dev'
Requires-Dist: ruff>=0.15; extra == 'dev'
Description-Content-Type: text/markdown

# sourcecode

**Deterministic codebase context for AI coding agents.**

[![PyPI](https://img.shields.io/pypi/v/sourcecode)](https://pypi.org/project/sourcecode/)
[![Python](https://img.shields.io/pypi/pyversions/sourcecode)](https://pypi.org/project/sourcecode/)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
[![CI](https://img.shields.io/github/actions/workflow/status/sourcecode-ai/sourcecode/ci.yml)](https://github.com/sourcecode-ai/sourcecode/actions)

Turn any repository into structured, reproducible context optimized for AI coding agents — in one command.

```bash
pip install sourcecode
sourcecode . --agent
```

```json
{
  "project": {
    "type": "api",
    "summary": "Python REST API built with FastAPI and SQLAlchemy. Layered architecture with domain, service, and infrastructure layers.",
    "primary_stack": "python",
    "frameworks": ["FastAPI", "SQLAlchemy"]
  },
  "entry_points": [
    { "path": "src/app/main.py", "kind": "server", "confidence": "high" }
  ],
  "architecture": "FastAPI application. Clean Architecture with domain, application, and infrastructure layers. Hub modules: schema.py, models.py.",
  "key_dependencies": [
    { "name": "fastapi", "declared_version": ">=0.100", "role": "runtime" },
    { "name": "sqlalchemy", "declared_version": "^2.0", "role": "runtime" },
    { "name": "pydantic", "declared_version": "^2.0", "role": "runtime" }
  ],
  "confidence_summary": { "overall": "high" }
}
```

---

## The problem

AI coding agents are only as good as the context they receive. In large, real-world repositories, that context is almost always wrong.

- **Agents start blind.** Without repo structure, they hallucinate imports, file paths, and architecture decisions.
- **Context is noisy.** Raw file trees contain benchmark dirs, generated files, tooling configs, and docs that consume tokens without helping.
- **Architecture is invisible.** LLMs see files, not systems. They miss layers, plugin systems, entry points, and runtime topology.
- **Context decays.** What you paste today is stale tomorrow. There's no reproducible baseline.
- **Manual context doesn't scale.** Handcrafting prompts per project is engineering debt that grows with every new agent, team, and task.

---

## The solution

`sourcecode` analyzes your repository and produces a structured, reproducible context package — ready to inject into any AI coding agent.

**What it does:**
- Detects stacks, frameworks, entry points, and project type across 10+ languages
- Infers runtime topology: which packages are core, which are plugins, which are noise
- Ranks files by operational relevance for agents: git churn + runtime proximity + bootstrap signal
- Suppresses non-runtime noise: benchmarks, docs, tooling, generated files
- Produces structured JSON/YAML that agents can reason over, not raw file trees
- Runs deterministically — same repo, same output, every time

**What it outputs:**
- `project_summary` — one-sentence natural language description
- `architecture_summary` — runtime topology: layers, plugin systems, entry flows
- `entry_points` — where execution actually starts (production, not benchmarks)
- `key_dependencies` — runtime dependencies with role classification
- `relevant_files` — ranked by usefulness for coding tasks, not folder position
- `confidence_summary` — detection quality and analysis gaps

All fields are stable, machine-readable, and designed for LLM consumption.

---

## Install

```bash
pip install sourcecode
```

Requires Python 3.9+. No API keys. No network calls. Runs locally.

---

## Quickstart

**Basic analysis:**
```bash
sourcecode .
```

**Agent-optimized output** (structured, noise-free, gap-aware):
```bash
sourcecode . --agent
```

**Task-specific context for coding agents:**
```bash
# Explain the project architecture
sourcecode . prepare-context explain

# Find likely bug locations
sourcecode . prepare-context fix-bug

# Onboard a new agent to the codebase
sourcecode . prepare-context onboard

# Ranked context for a specific task
sourcecode . prepare-context refactor
```

**Pipe directly into Claude Code or any agent:**
```bash
sourcecode . --agent | claude -p "Review the architecture and suggest improvements"
```

**Write to file for session injection:**
```bash
sourcecode . --agent --output context.json
```

**Include git activity signals:**
```bash
sourcecode . --agent --git-context
```

---

## Use cases

### Claude Code
```bash
# Start every session with full context
sourcecode . --agent > .claude/context.json

# Use with CLAUDE.md for persistent context
echo "$(sourcecode . --agent --compact)" >> CLAUDE.md
```

### Cursor / Windsurf / Copilot
```bash
# Generate context snapshot before starting a feature
sourcecode . --agent --git-context --output .cursor/context.json
```

### OpenAI / Anthropic API
```python
import json, subprocess

context = json.loads(
    subprocess.check_output(["sourcecode", ".", "--agent"])
)

system_prompt = f"""
You are working on: {context['project']['summary']}
Architecture: {context['architecture']}
Entry points: {[ep['path'] for ep in context['entry_points']]}
"""
```

### CI / CD pipelines
```yaml
# .github/workflows/context.yml
- name: Generate codebase context
  run: sourcecode . --agent --output context.json

- name: AI-assisted code review
  run: |
    CONTEXT=$(cat context.json)
    # Inject into your preferred AI review step
```

### Onboarding new engineers
```bash
# Generate human-readable architecture summary
sourcecode . prepare-context onboard --llm-prompt
```

### Architecture audits
```bash
sourcecode . --agent --architecture --graph-modules --dependencies
```

---

## How it works

`sourcecode` runs a local, static analysis pipeline on your repository:

```
Repository
    │
    ├── Scanner          # File tree, manifests, workspace detection
    ├── Stack Detectors  # Language, framework, package manager detection
    ├── Entry Points     # Production entry points (not benchmarks/docs)
    ├── Git Analyzer     # Churn hotspots, uncommitted changes
    ├── Relevance Scorer # Runtime proximity × git churn × bootstrap signal
    └── Serializer       # Structured JSON/YAML output
```

No LLM calls. No network requests. No sampling. Fully deterministic.

The same repository produces the same output on every run — which means agents can cache it, diff it, and rely on it.

---

## Output modes

| Mode | Use case | Size |
|------|----------|------|
| `sourcecode .` | Full analysis | Full |
| `sourcecode . --agent` | AI agent injection | ~600–1000 tokens |
| `sourcecode . --compact` | Prompts, handoffs | ~500–700 tokens |
| `sourcecode . prepare-context <task>` | Task-specific context | ~800–1200 tokens |

### Available flags

| Flag | Description |
|------|-------------|
| `--agent` | Structured, noise-free output for AI agents. Auto-enables `--dependencies`, `--env-map`, `--code-notes`. |
| `--dependencies` | Direct dependencies with versions and role classification. |
| `--git-context` | Recent commits, change hotspots, uncommitted files. |
| `--architecture` | Layer inference: MVC, layered, hexagonal, domain-based. |
| `--graph-modules` | Module import graph and call relationships. |
| `--semantics` | Cross-file symbol resolution and call graph. |
| `--env-map` | All environment variables referenced in source. |
| `--code-notes` | TODOs, FIXMEs, HACKs, and Architecture Decision Records. |
| `--compact` | Minimal output for token-constrained prompts. |
| `--format yaml` | YAML instead of JSON. |
| `--output PATH` | Write to file instead of stdout. |

Full reference: `sourcecode --help`

### Prepare-context tasks

| Task | What it produces |
|------|-----------------|
| `explain` | Architecture + entry points + key dependencies |
| `fix-bug` | Risk-ranked files + suspected areas + code annotations |
| `refactor` | Structural issues + improvement opportunities |
| `generate-tests` | Untested source files + test gap analysis |
| `onboard` | Full project understanding for new agents/developers |
| `review-pr` | Changed files + architectural impact |
| `delta` | Git-changed files only — incremental context |

---

## Philosophy

**Determinism over approximation.** Every run on the same repository produces the same output. Agents, pipelines, and teams can depend on that.

**Runtime topology over file trees.** What matters is where execution starts, what calls what, and which modules are actually critical — not alphabetical file lists.

**Noise suppression by default.** Benchmark dirs, generated files, tooling configs, and docs are suppressed unless explicitly requested. Agents get signal, not inventory.

**Local-first, privacy-respecting.** No code leaves your machine. No API keys required. Analysis is fully offline.

**Composable, not monolithic.** Output is structured data. Pipe it, transform it, inject it, cache it. It's infrastructure, not a magic black box.

**Confidence-aware.** Every analysis includes a confidence summary and gap list. Agents know what they don't know.

---

## Supported languages and stacks

| Language | Package detection | Entry points | Frameworks |
|----------|-------------------|--------------|------------|
| Python | `pyproject.toml`, `requirements.txt`, `setup.py` | CLI, scripts, `__main__` | FastAPI, Django, Flask, Typer, Click |
| Node.js | `package.json`, lock files | `main`, `bin`, scripts | Express, Next.js, Fastify, NestJS, React, Vue |
| Go | `go.mod` | `main.go`, `cmd/` | Standard library, Gin, Echo |
| Rust | `Cargo.toml` | `main.rs`, `lib.rs` | Tokio, Actix, Axum |
| Java | `pom.xml`, `build.gradle` | Spring Boot, Quarkus, Micronaut | Spring, Quarkus |
| Kotlin | `build.gradle.kts` | Spring Boot, Ktor | Spring, Ktor |
| .NET / C# | `.csproj`, `.sln` | `Program.cs` | ASP.NET, Blazor |
| PHP | `composer.json` | `index.php` | Laravel, Symfony |
| Ruby | `Gemfile` | `config.ru` | Rails, Sinatra |
| Dart | `pubspec.yaml` | `main.dart` | Flutter |

Monorepos with mixed stacks are fully supported.

---

## Roadmap

**Now — Core stability**
- Ranking improvements (git churn, runtime proximity)
- Better architecture inference
- Broader language coverage

**Next — Agent integrations**
- MCP server for native Claude Code integration
- VS Code extension
- Context diffing (compare before/after changes)
- Incremental updates (delta mode improvements)

**Later — Team features**
- Shared context snapshots
- Architecture drift detection
- CI integration templates
- Governance and compliance context

> Focus is on adoption and utility. No monetization until the core is genuinely useful to the community.

---

## Contributing

We welcome contributions. See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, testing, and guidelines.

**Quick start for contributors:**
```bash
git clone https://github.com/sourcecode-ai/sourcecode
cd sourcecode
pip install -e ".[dev]"
pytest tests/
```

---

## Security

`sourcecode` analyzes local repositories. It does not transmit code, paths, or analysis results to any external service. See [SECURITY.md](SECURITY.md) for our security policy and responsible disclosure process.

---

## Privacy

Telemetry is **opt-in only** and disabled by default. If you choose to enable it, only anonymous usage metadata is collected — never code, paths, or content. See [docs/privacy.md](docs/privacy.md) for full details.

```bash
sourcecode telemetry status   # check current setting
sourcecode telemetry enable   # opt in
sourcecode telemetry disable  # opt out
```

---

## License

Apache License 2.0. See [LICENSE](LICENSE) for details.

---

<p align="center">
  Built for the age of AI coding agents.<br>
  <a href="https://github.com/sourcecode-ai/sourcecode">GitHub</a> ·
  <a href="https://pypi.org/project/sourcecode/">PyPI</a> ·
  <a href="docs/getting-started.md">Documentation</a>
</p>
