Metadata-Version: 2.4
Name: aisquare-explainability
Version: 0.1.1
Summary: Explainability SDK for tracing, graphing, and policy auditing of AI agents
Author: AISquare
License: MIT
Project-URL: Homepage, https://github.com/AISquareHQ/aisquare-explainability
Project-URL: Documentation, https://github.com/AISquareHQ/aisquare-explainability/tree/main/docs
Project-URL: Repository, https://github.com/AISquareHQ/aisquare-explainability
Project-URL: Issues, https://github.com/AISquareHQ/aisquare-explainability/issues
Keywords: ai,agents,observability,tracing,governance,explainability
Classifier: Development Status :: 4 - Beta
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: httpx<1.0,>=0.27
Requires-Dist: aiosqlite<1.0,>=0.20
Requires-Dist: opentelemetry-sdk<2.0,>=1.24
Requires-Dist: opentelemetry-api<2.0,>=1.24
Provides-Extra: gateway
Requires-Dist: fastapi<1.0,>=0.111; extra == "gateway"
Requires-Dist: uvicorn<1.0,>=0.30; extra == "gateway"
Requires-Dist: pydantic<3.0,>=2.7; extra == "gateway"
Requires-Dist: redis<6.0,>=5.0; extra == "gateway"
Requires-Dist: neo4j<6.0,>=5.20; extra == "gateway"
Requires-Dist: asyncpg<1.0,>=0.29; extra == "gateway"
Requires-Dist: openai<2.0,>=1.30; extra == "gateway"
Requires-Dist: prometheus-client<1.0,>=0.20; extra == "gateway"
Requires-Dist: sse-starlette<3.0,>=2.0; extra == "gateway"
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
Requires-Dist: pytest-cov>=5.0; extra == "dev"
Requires-Dist: ruff>=0.4; extra == "dev"
Provides-Extra: agno
Requires-Dist: agno>=0.1; extra == "agno"
Requires-Dist: openinference-instrumentation-agno>=0.1; extra == "agno"
Dynamic: license-file

# AISquare Explainability SDK

An explainability and governance stack for AI agents. Captures execution traces from any Python agent (Agno, LangChain, plain Python), delivers them to a FastAPI gateway, and projects them into a Neo4j graph with RML semantic analysis and policy detection.

## How it works

```
Your Agent Code
    │  OpenInference / OTel spans
    ▼
SDK (aisquare_explainability_sdk/)
    │  serialised to local SQLite inbox — no gateway dependency in the hot path
    ▼
InboxSweeper (background thread)
    │  POST /v1/traces/ingest
    ▼
Gateway (FastAPI — gateway/)
    ├── Structural Worker  →  Neo4j  (Run / Span / Artifact / Policy graph)
    ├── RML Extractor      →  Postgres (claims, assumptions, evidence, inference chain)
    └── Policy Detector    →  Neo4j + Postgres (PolicyCandidate nodes, crystallization loop)
         ▼
Explainability Studio UI (modular-ai-space frontend)
```

## Repo layout

```
aisquare_explainability_sdk/   SDK — capture, inbox, sweeper, adapters, manual tracers
gateway/                        FastAPI ingest gateway + worker pipeline
graph/                          Neo4j Cypher and React Flow transformation helpers
examples/                       Runnable agent examples
docs/                           Guides, concepts, API reference
tests/                          Unit and integration tests
```

## What the SDK captures

The SDK collects two layers of signal:

**Auto-instrumentation** (zero-code): The `AgnoAdapter` installs `openinference-instrumentation-agno`, which automatically wraps every Agno agent run, LLM call, and tool invocation as an OTel span.

**Manual tracers** (governance-grade): Seven context-manager tracers you can add to any Python code — framework-agnostic:

| Tracer | Purpose |
|--------|---------|
| `AgentRunTracer` | Wraps a full agent run as the root span |
| `LLMCallTracer` | Records an LLM inference call with I/O and token counts |
| `ToolCallTracer` | Records a tool invocation with parameters, result, and errors |
| `RetrievalTracer` | Records a RAG retrieval with documents and scores |
| `HumanInterventionTracer` | Records a human-in-the-loop review or correction |
| `RoutingTracer` | Records a routing/delegation decision with selected and rejected paths |
| `MemoryTracer` | Records memory read/write operations |

The manual tracers also provide decorators: `@trace_tool` and `@trace_retrieval`.

## What the gateway adds

The gateway worker pipeline runs after each trace is ingested:

- **Structural projection**: Every span becomes a `Run`, `Span`, `Artifact`, or policy node in Neo4j with typed edges (`CONTAINS`, `EXECUTED`, `PRODUCED`, `CONSUMED`, `FLAGGED_AS`).
- **RML extraction**: GPT-4o-mini analyzes AGENT and LLM spans to produce claims, assumptions, evidence attribution, inference chain, and policy triggers. Confidence is a blended score: 40% LLM-reported + 60% deterministic structural signals.
- **Policy detection**: Recurring system-prompt instructions are counted across traces. When an instruction exceeds the occurrence threshold it is promoted to a `PolicyCandidate` node for human review and activation.

## Data model

**Neo4j nodes**: `Studio`, `Run`, `Span`, `Event`, `Artifact`, `Agent`, `Tool`, `Human`, `PolicyCandidate`, `Policy`

**Neo4j relationships**: `HOSTS`, `CONTAINS`, `NEXT`, `EXECUTED`, `INTERVENED`, `CONSUMED`, `PRODUCED`, `REFERENCES`, `FLAGGED_AS`, `PROPOSES`

**Postgres tables**: `ingest_batches`, `trace_states`, `processed_traces`, `rml_analyses`, `policy_observations`, `artifact_content`, `extraction_failures`, `studio_config`

**SDK local durability**: SQLite inbox (`explainability_inbox.db`)

## Local setup

### 1. Install dependencies

```bash
pip install -e ".[dev,agno]"
```

### 2. Start infrastructure

```bash
docker compose up -d
```

Starts Neo4j (bolt://localhost:7687), Postgres (localhost:5433), and Redis (localhost:6379).

### 3. Configure environment

Copy `.env.example` to `.env` and fill in the required values:

```bash
# Database
NEO4J_URI=bolt://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=password
POSTGRES_DSN=postgresql://postgres:postgres@localhost:5433/explainability
REDIS_URL=redis://localhost:6379/0

# Auth
ENV=development
ALLOW_TEST_AUTH_BYPASS=true

# SDK → gateway
EXPLAINABILITY_GATEWAY_URL=http://127.0.0.1:8000
EXPLAINABILITY_API_KEY=test-key

# LLM extraction
OPENAI_API_KEY=sk-...
EXTRACTOR_MODEL=gpt-4o-mini
```

### 4. Run the gateway

```bash
uvicorn gateway.main:app --host 0.0.0.0 --port 8000
```

Health checks:

```bash
curl http://127.0.0.1:8000/live    # → {"status":"ok"}
curl http://127.0.0.1:8000/ready   # → {"neo4j":"ok","postgres":"ok","redis":"ok"}
```

### 5. Run an example

```bash
python examples/basics/openai_chat.py
```

### 6. Start the frontend

The UI lives in the `modular-ai-space` repository:

```bash
cd ../modular-ai-space
npm install
npm run dev:localdev    # http://localhost:3001
```

## SDK usage

```python
import aisquare_explainability_sdk as sdk

# Reads EXPLAINABILITY_GATEWAY_URL and EXPLAINABILITY_API_KEY from environment
sdk.init_from_env(service_name="my-agent")

# Run your agent — Agno is auto-instrumented, all spans captured automatically
agent.print_response("...")

# IMPORTANT for short-lived scripts: flush ensures traces reach the gateway
# before the process exits. Long-running services don't need this.
sdk.flush()
```

### Manual instrumentation (any framework)

```python
import aisquare_explainability_sdk as sdk

sdk.init_from_env()

with sdk.AgentRunTracer(agent_name="MyAgent", run_id="abc-123") as run:
    run.set_input("User query")

    with sdk.LLMCallTracer(model="gpt-4o-mini", provider="openai") as llm:
        response = call_openai(...)
        llm.set_input_messages([{"role": "user", "content": "..."}])
        llm.set_output_messages([{"role": "assistant", "content": response}])
        llm.set_token_counts(prompt=100, completion=50)

    with sdk.RoutingTracer(decision_type="tool_selection") as rt:
        rt.set_selected("web_search", reason="Query requires fresh data")
        rt.set_rejected([{"name": "cached_search", "reason": "Cache is stale"}])

    run.set_output("Agent final answer")

sdk.flush()
```

## Examples

| File | What it shows |
|------|---------------|
| `examples/basics/openai_chat.py` | Simplest traced Agno agent |
| `examples/agents/deep_nesting.py` | 3-level agent delegation team |
| `examples/agents/multi_agent_branching.py` | Multi-agent research team |
| `examples/agents/routing_decision.py` | Tool routing and conditional paths |
| `examples/agents/tool_heavy_workflow.py` | Many tool calls in one run |
| `examples/governance/error_handling.py` | Error nodes (red) in graph |
| `examples/governance/policy_detection.py` | 3 runs → policy candidate detection |
| `examples/governance/policy_workflow.py` | Full detect → review → activate cycle |
| `examples/governance/e2e_governed_workflow.py` | Complete governed workflow with activation |
| `examples/streaming/monitor_execution.py` | SSE-based live execution monitoring |

## API surface

**Ingest:**
```
POST /v1/traces/ingest
Authorization: Bearer <api-key>
Content-Type: application/json
```

**Studio UI reads:**
```
GET  /v1/studios/{id}/ui/runs
GET  /v1/studios/{id}/ui/runs/{run_id}
GET  /v1/studios/{id}/ui/runs/{run_id}/graph?mode=span|event
GET  /v1/studios/{id}/ui/runs/{run_id}/xtrace
GET  /v1/studios/{id}/ui/runs/{run_id}/rml
GET  /v1/studios/{id}/ui/runs/{run_id}/nodes/{node_id}
GET  /v1/studios/{id}/ui/policies
GET  /v1/studios/{id}/ui/agents
GET  /v1/studios/{id}/ui/setup
GET  /v1/studios/{id}/artifacts/{artifact_id}
```

**Policy management:**
```
PATCH /v1/studios/{id}/policies/{fingerprint}/activate
PATCH /v1/studios/{id}/policy-config
```

**Admin:**
```
GET  /metrics
GET  /v1/admin/worker-health
GET  /v1/admin/circuit-breakers
POST /v1/admin/recover
GET  /v1/admin/extraction/failures
GET  /v1/admin/policy-candidates
```

## Documentation

Guides:
- [Getting started](docs/getting-started.md) — full local setup walkthrough
- [Quickstart (5 min)](docs/guides/quickstart-5min.md) — first trace fast
- [SDK usage guide](docs/guides/sdk-usage.md) — manual instrumentation patterns

Reference:
- [SDK API reference](docs/reference/sdk-api.md) — all SDK classes and functions
- [REST API reference](docs/reference/rest-api.md) — all gateway endpoints

Concepts:
- [RML](docs/concepts/rml.md) — Reasoning Markup Language
- [Policy system](docs/concepts/policy-system.md) — detection and enforcement
- [Graph modes](docs/concepts/graph-modes.md) — span vs event views
- [Architecture](docs/architecture.md) — system design

## Tests

```bash
python -m pytest -q
python -m ruff check .
```

Docker-backed integration test:

```bash
RUN_DOCKER_INTEGRATION=1 python -m pytest tests/test_integration_stack.py -q
```

## License

MIT
