Metadata-Version: 2.4
Name: xyglue
Version: 0.1.0
Summary: A thinking-first agent framework built on Progressive Capture Theory
Author: Luke H
License-Expression: MIT
Project-URL: Homepage, https://github.com/mintingpressbuilds/XYGLUE
Project-URL: Repository, https://github.com/mintingpressbuilds/XYGLUE
Project-URL: Issues, https://github.com/mintingpressbuilds/XYGLUE/issues
Keywords: agent,framework,thinking,ai,automation
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Classifier: Typing :: Typed
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aiosqlite>=0.19.0
Provides-Extra: ai
Requires-Dist: anthropic>=0.25.0; extra == "ai"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
Requires-Dist: mypy>=1.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Dynamic: license-file

# XYGLUE

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/downloads/)

A thinking-first agent framework that inserts a thinking layer between goal and plan, generating three ranked execution paths before any work begins.

---

## The Problem

Every agent framework does this:

```
Goal → Plan → Execute → Output
```

The plan is a single path. If it fails, you get retries. If the approach was wrong, you get a *faster wrong answer*.

Nobody stops to ask: **is the plan itself any good?**

## What XYGLUE Does Differently

XYGLUE inserts a **thinking layer** before planning. Three agents analyze the task, classify what's actually required vs. what's just convention, and generate three alternative paths — ranked from most creative to most safe.

```
                          ┌─────────────────────────────────────────┐
                          │          THINKING LAYER                 │
                          │                                         │
                          │  ┌─────────┐   Every task has a         │
                Goal ────►│  │  Scout  │   "standard" way.          │
                          │  └────┬────┘   Scout maps it.           │
                          │       │                                  │
                          │  ┌────▼──────┐ Which parts are physics  │
                          │  │ Physicist │ (must do) vs habit        │
                          │  └────┬──────┘ (just convention)?       │
                          │       │                                  │
                          │  ┌────▼──────┐ Three paths:             │
                          │  │ Architect │ A = break all habits     │
                          │  └──┬──┬──┬──┘ B = break some           │
                          │     │  │  │    C = optimized standard   │
                          └─────┼──┼──┼─────────────────────────────┘
                                │  │  │
                ┌───────────────┼──┼──┼──────────────────────┐
                │           EXECUTION LAYER                   │
                │               │  │  │                       │
                │          Path A  B  C  (with fallthrough)   │
                │               │  │  │                       │
                │           Self-healing pipeline              │
                │           20 seeded failure patterns         │
                │           Checkpointing + rollback           │
                └───────────────┼──┼──┼──────────────────────┘
                                │  │  │
                ┌───────────────┼──┼──┼──────────────────────┐
                │            CAPTURE LAYER                    │
                │                                             │
                │   Ground Tracker — records every run        │
                │   Template Library — quality ≥ 0.95,        │
                │     proven 2-3×, single failure resets      │
                └─────────────────────────────────────────────┘
                                  │
                                  ▼
                               Brief
```

**The key insight:** Most of what developers assume is "required" is actually just convention. A REST API doesn't *need* Express. Auth doesn't *need* JWT. XYGLUE's Physicist separates what's actually constrained (physics) from what's just popular (habit) — then the Architect generates paths that break the habits.

Path A breaks everything. Path C plays it safe. Path B is the pragmatic middle. The engine runs A first, and if it fails, self-heals and falls through to B, then C. You get the upside of creative approaches with the safety net of conventional ones.

---

## Installation

```bash
pip install xyglue
```

For AI-powered thinking (optional):

```bash
pip install xyglue[ai]
```

## Quick Start

```python
import asyncio
from xyglue import Engine

async def main():
    engine = Engine()
    result = await engine.run("Build a REST API for user management", mode="auto")
    print(result.brief.format())

asyncio.run(main())
```

```
✅ Complete. Path A succeeded.
🔍 Scout benchmark: web. Standard: code, database.
   2 habits broken. 0 physics respected.
```

No API key needed — every AI component has a rule-based fallback that works out of the box.

## Two Modes

| Mode | What happens |
|------|--------------|
| **`semi`** (default) | Jarvis-style. Shows you the Brief with all three paths. You pick one. |
| **`auto`** | Full autonomous. Runs Path A → heals → falls through to B → C. |

```python
# Semi: review before executing
engine = Engine()
result = await engine.run("Build a REST API")
print(result.brief.format())            # See the thinking
final = await engine.approve(result, path="A")

# Auto: just run it
result = await engine.run("Build a REST API", mode="auto")
```

## Three Controls

| Control | Options | What it does |
|---------|---------|--------------|
| `mode` | `semi`, `auto` | Pause for approval or run autonomously |
| `divergence` | `low`, `medium`, `high` | How aggressively Path A breaks from convention |
| `learning` | `supervised`, `auto` | Whether proven templates auto-promote or need your approval |

```python
engine = Engine(
    api_key="sk-ant-...",       # Optional: AI-powered thinking
    mode="semi",
    divergence="high",
    learning="supervised",
    agents={                     # Custom agent names (shown in Brief)
        "scout": "Recon",
        "physicist": "Newton",
        "architect": "Blueprint",
    },
)
```

## The Thinking Layer

Three agents run in sequence before any execution happens:

### Scout

Maps the **benchmark** — how is this task typically done? What tools, patterns, and sequence does everyone use? Also identifies cross-domain components that *could* apply but typically don't.

### Physicist

Classifies every element the Scout found as either:
- **Physics** — can't change. Auth is required. TCP handshakes happen. Rate limits exist.
- **Habit** — just convention. REST is a choice. Express is a choice. PostgreSQL is a choice.

The Physicist is aggressive. Most things developers assume are necessary are just conventional.

### Architect

Generates three paths from the classified map:

| Path | Strategy | Risk | Confidence |
|------|----------|------|------------|
| **A** | Maximum divergence. Break every habit. Pull cross-domain solutions. | High | Lower |
| **B** | Informed hybrid. Break habits selectively where the payoff is clear. | Medium | Medium |
| **C** | Optimized benchmark. The conventional approach, but enhanced. The floor. | Low | Higher |

## The Healing Pipeline

When a step fails during execution, XYGLUE doesn't just retry blindly:

```
Failure → Detect → Classify → Match Pattern → Apply Fix → Retry
```

1. **Detector** classifies the error (timeout, auth, rate limit, network, etc.)
2. **Pattern Library** checks 20 seeded patterns for a known fix (fast path)
3. **Diagnoser** runs rule-based or AI diagnosis if no pattern matches (slow path)
4. **Fix** is applied and the step retries

Successful AI-diagnosed fixes get learned as new patterns. Patterns that fail lose confidence and eventually get evicted. The library improves over time.

## The Capture Layer

Every run is recorded by the **Ground Tracker** — what was the benchmark, which constraints were classified, which path won, what failed and why.

The **Template Library** is intentionally strict:
- Quality threshold: **0.95** (non-negotiable)
- Must score 0.95+ on **2-3 separate runs** to be promoted
- A **single failure resets** the validation counter

A library of 50 proven templates beats a library of 5,000 unvalidated ones.

## Custom Tools

```python
from xyglue import Tool, ToolResult

class MyTool(Tool):
    @property
    def name(self) -> str:
        return "my_tool"

    async def execute(self, params: dict) -> ToolResult:
        return ToolResult(success=True, output="done")

engine = Engine()
engine.register_tool(MyTool())
```

## Project Structure

```
xyglue/
  __init__.py          # Public API: Engine, RunResult, Brief, Tool, etc.
  config.py            # EngineConfig with all settings
  engine.py            # Main orchestrator (thinking → execution → capture)
  sdk.py               # Public Engine wrapper (one import, one class)
  storage.py           # SQLite persistence layer
  thinking/            # Scout, Physicist, Architect agents
  goal/                # Goal processing, normalization, entity extraction
  plan/                # Plan models + checkpoint management
  execute/             # Step executor with timeout, retry, fallback
  heal/                # Failure detection → diagnosis → pattern match → fix
  learn/               # Pattern library + 20 seed patterns
  capture/             # Ground tracker + template library
  brief/               # Brief output formatting
  tools/               # Tool ABC, ToolResult, MockTool, ToolRegistry
```

## Requirements

- Python 3.11+
- `aiosqlite>=0.19.0` (only required dependency)
- `anthropic>=0.25.0` (optional, for AI-powered thinking)

## Contributing

1. Fork the repo and create a feature branch
2. Install dev dependencies: `pip install -e ".[dev]"`
3. Make changes
4. Run checks:
   ```bash
   pytest                    # 263 tests
   ruff check xyglue/       # Lint
   mypy xyglue/             # Type check
   ```
5. Open a pull request

See [CLAUDE.md](CLAUDE.md) for code conventions and how to add features.

## License

[MIT](LICENSE) -- Copyright (c) 2026 Luke H
