Metadata-Version: 2.4
Name: iknowhy
Version: 0.3.0
Summary: Causal event capture for AI agents — with native PyRapide integration
License: MIT
Project-URL: Homepage, https://iknowhy.ai
Project-URL: Documentation, https://iknowhy.ai/docs-guide
Project-URL: Repository, https://github.com/bytecreeper/iknowhy-sdk
Keywords: ai,agents,causal,observability,tracing
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Libraries
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.24.0
Provides-Extra: pyrapide
Requires-Dist: pyrapide>=0.1.0; extra == "pyrapide"

# iknowhy

Python SDK for [iKnowhy.ai](https://iknowhy.ai) — the causal event intelligence platform.

Log events, trace causal chains, and surface constraint violations across your systems.

```bash
pip install iknowhy
```

## Quickstart

```python
from iknowhy import CausewayClient

client = CausewayClient(api_key="cwy_...")

# Log a causal chain: user_login → process_spawn (caused by login)
login_id = client.log("user_login", payload={"user": "alice"}, session_id="sess1")
proc_id  = client.log("process_spawn", payload={"pid": 1234}, cause_ids=[login_id])

# Query the chain
chain = client.chain(proc_id)
# [{"id": login_id, "name": "user_login", ...}, {"id": proc_id, ...}]
```

---

## PyRapide Integration

iKnowhy integrates natively with **[PyRapide](https://pypi.org/project/pyrapide/)**, the
causal event-driven architecture library for Python by [Shane Morris](https://github.com/ShaneDolphin).

PyRapide implements RAPIDE (Rapid Prototyping for Application Domain-specific Integrated
Environments), developed at Stanford University by David Luckham. It gives you first-class
tools to model, execute, and analyze causal event architectures in Python with async-native
execution, Pydantic events, and a composable pattern algebra.

iKnowhy's `PyRapideAdapter` bridges PyRapide's local causal computation into iKnowhy's
persistent event log — giving you durable storage, a web dashboard, and API access to every
causal chain your PyRapide architecture produces.

```bash
pip install iknowhy pyrapide
```

### Batch mode (after engine.run())

```python
import asyncio
from pyrapide import Engine, architecture, interface, action, module, when, Pattern, connect, get_context
from iknowhy import CausewayClient
from iknowhy.pyrapide import PyRapideAdapter

@interface
class Scanner:
    @action
    async def scan(self, target: str) -> None: ...

@interface
class Classifier:
    @action
    async def classify(self, finding: str) -> None: ...

@module(implements=Scanner)
class ScannerModule:
    async def start(self):
        ctx = get_context(self)
        ctx.generate_event("Scanner.scan", payload={"target": "192.168.1.1"})

@module(implements=Classifier)
class ClassifierModule:
    @when(Pattern.match("Scanner.scan"))
    async def on_scan(self, match):
        ctx = get_context(self)
        event = list(match.events)[0]
        ctx.generate_event("Classifier.classify",
                           payload={"finding": "open port 22"},
                           caused_by=list(match.events))

@architecture
class SecurityArch:
    scanner: Scanner
    classifier: Classifier
    def connections(self):
        return [connect(Pattern.match("Scanner.scan"), "classifier")]

async def main():
    client = CausewayClient(api_key="cwy_...")
    adapter = PyRapideAdapter(client, session_id="security-scan-001")

    arch = SecurityArch()
    engine = Engine()
    engine.bind(arch, "scanner", ScannerModule)
    engine.bind(arch, "classifier", ClassifierModule)

    comp = await engine.run(arch, timeout=5.0)

    # Upload entire computation to iKnowhy — causal links preserved
    event_ids = await adapter.flush_computation(comp)
    print(f"Logged {len(event_ids)} events to iKnowhy")

asyncio.run(main())
```

### Streaming mode (real-time via StreamProcessor)

```python
from pyrapide import StreamProcessor, InMemoryEventSource, Event
from iknowhy import CausewayClient
from iknowhy.pyrapide import PyRapideAdapter

async def main():
    client = CausewayClient(api_key="cwy_...")
    adapter = PyRapideAdapter(client, session_id="live-monitor")

    source = InMemoryEventSource("agent")
    processor = StreamProcessor()
    processor.add_source("agent", source)

    # Attach iKnowhy — events are logged in real time as they flow through PyRapide
    adapter.attach_stream(processor, session_id="live-monitor")

    # Send events; they'll appear in your iKnowhy dashboard immediately
    await source.put(Event(name="tool_call", payload={"tool": "browser"}))
    await source.close()
    await processor.run()

asyncio.run(main())
```

---

## API Reference

### `CausewayClient`

| Method | Description |
|---|---|
| `log(name, payload, session_id, cause_ids, tags)` | Log an event, returns `event_id` |
| `chain(event_id)` | Full causal ancestry for an event |
| `violations()` | Current constraint violations |
| `sessions()` | List of sessions |
| `events(session_id, name, limit)` | Query events with filters |

### `PyRapideAdapter`

| Method | Description |
|---|---|
| `flush_computation(comp, session_id, tags)` | Upload a completed PyRapide `Computation` |
| `attach_stream(processor, session_id, tags)` | Hook into a live `StreamProcessor` |
| `id_map()` | PyRapide event.id → iKnowhy event_id mapping |
| `clear()` | Reset ID map between computations |

---

## Links

- [iKnowhy Dashboard](https://iknowhy.ai)
- [API Docs](https://iknowhy.ai/docs-guide)
- [PyRapide on PyPI](https://pypi.org/project/pyrapide/) — by Shane Morris
- [PyRapide on GitHub](https://github.com/ShaneDolphin/pyrapide)
