Metadata-Version: 2.4
Name: plyra-trace
Version: 2.0.2
Summary: Universal observability for AI agents — tracing, flamegraph, live graph, and cost tracking for any framework or LLM provider.
Project-URL: Homepage, https://plyraai.github.io
Project-URL: Documentation, https://plyraai.github.io/plyra-trace
Project-URL: Repository, https://github.com/plyraAI/plyra-trace
Project-URL: Issues, https://github.com/plyraAI/plyra-trace/issues
Author-email: Plyra <oss@plyra.dev>
License: Apache-2.0
License-File: LICENSE
Keywords: agentic-ai,agents,ai,langchain,llm,observability,openai,opentelemetry,tracing
Classifier: Development Status :: 3 - Alpha
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 :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: fastapi>=0.110.0
Requires-Dist: opentelemetry-api>=1.20.0
Requires-Dist: opentelemetry-exporter-otlp-proto-grpc>=1.20.0
Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.20.0
Requires-Dist: opentelemetry-proto>=1.20.0
Requires-Dist: opentelemetry-sdk>=1.20.0
Requires-Dist: protobuf>=4.25.0
Requires-Dist: pydantic>=2.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: sse-starlette>=1.6.0
Requires-Dist: typing-extensions>=4.0
Requires-Dist: uvicorn[standard]>=0.27.0
Requires-Dist: wrapt>=1.14.0
Provides-Extra: all
Requires-Dist: anthropic>=0.20.0; extra == 'all'
Requires-Dist: langchain-core>=0.1.0; extra == 'all'
Requires-Dist: litellm>=1.0.0; extra == 'all'
Requires-Dist: openai>=1.0.0; extra == 'all'
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.20.0; extra == 'anthropic'
Provides-Extra: dev
Requires-Dist: anthropic>=0.20.0; extra == 'dev'
Requires-Dist: httpx>=0.25.0; extra == 'dev'
Requires-Dist: mypy; extra == 'dev'
Requires-Dist: openai>=1.0.0; extra == 'dev'
Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'dev'
Requires-Dist: pytest-asyncio; extra == 'dev'
Requires-Dist: pytest-cov; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: ruff; extra == 'dev'
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.1.0; extra == 'langchain'
Provides-Extra: litellm
Requires-Dist: litellm>=1.0.0; extra == 'litellm'
Provides-Extra: openai
Requires-Dist: openai>=1.0.0; extra == 'openai'
Description-Content-Type: text/markdown

# plyra-trace

**Behavioral tracing for agentic AI. OTel-compatible. Framework-agnostic.**

[![License](https://img.shields.io/badge/License-Apache%202.0-2dd4bf.svg?labelColor=0d1117)](https://opensource.org/licenses/Apache-2.0)
[![Python](https://img.shields.io/badge/Python-3.11%2B-2dd4bf.svg?labelColor=0d1117)](https://www.python.org/)
[![PyPI](https://img.shields.io/pypi/v/plyra-trace?color=2dd4bf&labelColor=0d1117)](https://pypi.org/project/plyra-trace/)

---

## The Problem

LLM observability tools trace tokens and latency. But agents don't just call models—they reason, delegate, coordinate, and enforce policy. Without **agent-native tracing**, you're blind to:

- **Multi-agent handoffs** — which agent handled what, and why
- **Policy decisions** — what guards fired, what actions were blocked
- **Cross-process coordination** — how agents communicate via HTTP, queues, or MCP
- **Behavioral patterns** — ReAct loops, chain-of-thought, tree search

**plyra-trace** is the instrumentation layer that understands agent behavior as a first-class primitive. Not a vendor lock-in. Not another dashboard. Just **OpenTelemetry-native tracing with agent semantics baked in**.

---

## Install

```bash
pip install plyra-trace
```

**Requires Python 3.11+**. Works with any OTLP backend: Jaeger, Grafana Tempo, Phoenix, Langfuse, Datadog, or the future plyra collector.

---

## Quickstart

```python
import plyra_trace

# Initialize (exports to console by default — no collector needed for dev)
pt = plyra_trace.init(project="my-agent")

@plyra_trace.agent(name="researcher")
def research_agent(query: str) -> dict:
    docs = web_search(query)
    return {"docs": docs}

@plyra_trace.tool(name="web-search")
def web_search(query: str) -> list:
    return [{"title": "Result 1", "snippet": "..."}]

# Run with session + user context
with plyra_trace.session("session-abc"):
    with plyra_trace.user("user-123"):
        result = research_agent("What are the top EV companies?")

pt.shutdown()
```

**That's it.** Traces export to console (dev mode). To send to an OTLP backend:

```python
pt = plyra_trace.init(
    project="my-agent",
    endpoint="http://localhost:4318",  # Jaeger, Tempo, Phoenix, etc.
)
```

---

## Core Concepts

### Span Kinds

plyra-trace understands agent-specific span types. Every span has a `plyra.span.kind` attribute:

| Span Kind    | Use Case                                 | Decorator      |
|--------------|------------------------------------------|----------------|
| `AGENT`      | Autonomous reasoning block               | `@agent()`     |
| `TOOL`       | External function or API call            | `@tool()`      |
| `GUARD`      | Policy/safety check (plyra-native)       | `@guard()`     |
| `LLM`        | Language model call                      | `@llm()`       |
| `CHAIN`      | Glue code linking pipeline steps         | `@trace()`     |
| `RETRIEVER`  | Vector/document retrieval                | `@trace(kind=...)`      |
| `ROUTER`     | Agent routing/delegation (plyra-native)  | `@trace(kind=...)`      |

All spans are **OpenInference-compatible**. Both `plyra.span.kind` and `openinference.span.kind` are set automatically.

---

### Decorators

```python
@plyra_trace.trace()                    # Root span (CHAIN)
@plyra_trace.agent(name="planner")      # AGENT span
@plyra_trace.tool(name="search")        # TOOL span
@plyra_trace.guard(policy="safety")     # GUARD span
@plyra_trace.llm(model="gpt-4")         # LLM span
```

**Works with both sync and async functions.** Input/output auto-captured as JSON. Exceptions set span status to ERROR.

---

### Context Managers

Propagate session, user, metadata, and tags to all child spans:

```python
with plyra_trace.session("session-id"):
    with plyra_trace.user("user-id"):
        with plyra_trace.metadata({"tier": "enterprise"}):
            with plyra_trace.tags(["production"]):
                result = run_agent(query)
```

Context is **thread-safe** and **doesn't leak** outside the `with` block.

---

## Multi-Agent Propagation

### In-Process Handoffs

Nested decorators automatically create parent-child spans:

```python
@plyra_trace.agent(name="orchestrator")
def orchestrator(query: str):
    research = research_agent(query)  # Child span
    return analysis_agent(research)   # Child span
```

### Cross-Process Handoffs (HTTP, gRPC, Queues)

**Inject context** when calling another agent:

```python
headers = {}
plyra_trace.inject_context(
    headers,
    agent_name="orchestrator",
    handoff_reason="needs research"
)
response = httpx.post("http://agent-2/task", headers=headers, json=payload)
```

**Extract and continue** the trace on the receiving side:

```python
ctx = plyra_trace.extract_context(request.headers)
with plyra_trace.continue_trace(ctx):
    result = process_task(request.body)
```

This creates a **distributed trace** across agents. Works with HTTP, gRPC, message queues, or any carrier that supports headers.

---

## Guard Integration

Guards are **first-class citizens** in plyra-trace. Not just logged—traced as GUARD spans:

```python
from plyra_trace import GuardResult

@plyra_trace.guard(name="input-safety", policy="content-safety")
def check_input(text: str) -> GuardResult:
    triggered = "dangerous" in text.lower()
    return GuardResult(
        policy="content-safety",
        action="block" if triggered else "allow",
        triggered=triggered,
        confidence=0.95,
        details={"reason": "unsafe keyword detected"}
    )

@plyra_trace.agent(name="executor")
def executor(command: str):
    result = check_input(command)
    if result.triggered:
        return f"Blocked: {result.policy}"
    return execute(command)
```

Guard results automatically populate `guard.policy`, `guard.action`, `guard.triggered`, `guard.confidence`, and `guard.details` span attributes.

---

## OTLP Backend Compatibility

plyra-trace exports to **any OTLP-compatible backend**:

| Backend           | Protocol   | Endpoint Example                          |
|-------------------|------------|-------------------------------------------|
| Jaeger            | HTTP/gRPC  | `http://localhost:4318`                   |
| Grafana Tempo     | HTTP/gRPC  | `http://tempo:4318`                       |
| Arize Phoenix     | HTTP       | `http://localhost:6006/v1/traces`         |
| Langfuse          | HTTP       | `https://cloud.langfuse.com/api/public`   |
| Datadog           | HTTP       | `https://trace.agent.datadoghq.com`       |
| SigNoz            | HTTP/gRPC  | `http://signoz:4318`                      |

**Example with Jaeger:**

```python
pt = plyra_trace.init(
    project="my-agent",
    endpoint="http://localhost:4318",
    protocol="http/protobuf"  # or "grpc"
)
```

**Example with Grafana Cloud:**

```python
pt = plyra_trace.init(
    project="my-agent",
    endpoint="https://otlp-gateway-prod-us-central-0.grafana.net/otlp",
    headers={"Authorization": f"Basic {api_key}"}
)
```

---

## Programmatic Span Creation

When decorators aren't enough, use `SpanBuilder`:

```python
from plyra_trace import SpanBuilder, SpanKind

with SpanBuilder("orchestrator-step", kind=SpanKind.AGENT) as span:
    span.set_input({"query": "analyze competitors"})
    span.set_agent(name="orchestrator", framework="custom")
    
    result = do_complex_work()
    
    span.set_output(result)
    span.add_event("checkpoint", attributes={"step": 1})
```

---

## Semantic Conventions

plyra-trace extends [OpenInference semantic conventions](https://arize-ai.github.io/openinference/spec/semantic_conventions.html) with agent-native attributes:

### Agent Attributes (plyra-native)

- `agent.name` — Agent identifier
- `agent.framework` — `"langgraph"`, `"crewai"`, `"autogen"`, etc.
- `agent.pattern` — `"ReAct"`, `"Chain-of-Thought"`, `"Tree-of-Thoughts"`
- `agent.handoff.from` — Source agent in a handoff
- `agent.handoff.to` — Target agent in a handoff
- `agent.handoff.reason` — Why the handoff occurred
- `agent.handoff.protocol` — `"http"`, `"grpc"`, `"mcp"`, `"queue"`

### Guard Attributes (plyra-native)

- `guard.policy` — Policy name (e.g., `"content-safety"`)
- `guard.action` — `"allow"`, `"block"`, `"redact"`, `"flag"`, `"modify"`
- `guard.triggered` — Boolean: was the guard triggered?
- `guard.confidence` — Float [0.0, 1.0]
- `guard.details` — JSON string with structured details
- `guard.provider` — `"plyra-guard"`, `"guardrails-ai"`, `"nemo-guardrails"`

### Standard OpenInference Attributes

All standard OpenInference attributes are fully supported:
- `input.value`, `output.value`, `input.mime_type`, `output.mime_type`
- `llm.model_name`, `llm.provider`, `llm.token_count.*`
- `tool.name`, `tool.description`, `tool.parameters`
- `session.id`, `user.id`, `metadata`, `tag.tags`

---

## Compatibility with Existing Instrumentation

### OpenInference

plyra-trace uses the **same semantic conventions as OpenInference**. Spans created by OpenInference auto-instrumentation (e.g., LlamaIndex, LangChain via Phoenix) work seamlessly with plyra-trace.

### OpenLLMetry (Traceloop)

Use the compatibility processor to normalize OpenLLMetry spans:

```python
from plyra_trace.compat import OpenLLMetrySpanProcessor

pt = plyra_trace.init(
    project="my-agent",
    endpoint="http://localhost:4318",
    span_processors=[OpenLLMetrySpanProcessor()]
)
```

---

## Examples

- [**basic_agent.py**](examples/basic_agent.py) — Single agent with console output
- [**multi_agent.py**](examples/multi_agent.py) — Multi-agent orchestration
- [**with_guard.py**](examples/with_guard.py) — Guard integration

Run examples:

```bash
python examples/basic_agent.py
```

---

## Development

```bash
# Install uv if not already installed
pip install uv

# Sync dependencies
uv sync --all-extras

# Run tests
uv run pytest

# Lint
uv run ruff check .
uv run ruff format .

# Build
rm -rf dist/ && uv build
```

---

## Roadmap

**v0.1** (current):
- ✅ Core SDK with decorators, context managers, span builders
- ✅ OTLP export (HTTP + gRPC)
- ✅ OpenInference semantic conventions
- ✅ Agent-native attributes (guards, handoffs, routing)

**v0.2** (planned):
- Auto-instrumentation for LangGraph, CrewAI, AutoGen
- Async context propagation improvements
- Streaming span export
- MCP (Model Context Protocol) propagation

**v1.0** (future):
- plyra collector with agent-aware sampling
- GuardRails integration
- Policy event correlation

---

## License

Apache 2.0. See [LICENSE](LICENSE).

---

## Links

- **Documentation**: [plyraai.github.io/plyra-trace](https://plyraai.github.io/plyra-trace)
- **PyPI**: [pypi.org/project/plyra-trace](https://pypi.org/project/plyra-trace)
- **GitHub**: [github.com/plyraAI/plyra-trace](https://github.com/plyraAI/plyra-trace)
- **Issues**: [github.com/plyraAI/plyra-trace/issues](https://github.com/plyraAI/plyra-trace/issues)
- **Plyra Stack**:
  - [plyra-guard](https://github.com/plyraAI/plyra-guard) — Action middleware for policy enforcement
  - [plyra-memory](https://github.com/plyraAI/plyra-memory) — Persistent structured memory

---

Built with ❤️ by the Plyra team. Questions? [oss@plyra.dev](mailto:oss@plyra.dev)
