agentaudit-client 1.0.0__tar.gz

agentaudit_client-1.0.0/PKG-INFO

@@ -0,0 +1,173 @@
+Metadata-Version: 2.4
+Name: agentaudit-client
+Version: 1.0.0
+Summary: Audit & Compliance SDK for AI Agents
+Home-page: https://github.com/agentaudit/agentaudit-python
+Author: AgentAudit Team
+Author-email: support@agentaudit.io
+Keywords: ai agents audit compliance langchain monitoring
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.25.0
+Provides-Extra: langchain
+Requires-Dist: langchain>=0.1.0; extra == "langchain"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# AgentAudit Python SDK
+
+Official Python SDK for the AgentAudit API — audit logging and compliance monitoring for AI agents.
+
+## Installation
+
+```bash
+pip install agentaudit-client
+```
+
+With LangChain support:
+```bash
+pip install agentaudit-client[langchain]
+```
+
+## Quick Start
+
+```python
+from agentaudit import AgentAudit
+
+# Initialize
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Log an agent action
+audit.log(
+    action="prompt_submitted",
+    prompt="What is the weather?",
+    response="It is sunny today.",
+    metadata={"model": "gpt-4", "tokens": 150}
+)
+```
+
+## LangChain Integration
+
+```python
+from langchain.callbacks import AgentAuditCallbackHandler
+from langchain.llms import OpenAI
+
+# Setup audit callback
+audit_handler = AgentAuditCallbackHandler(
+    api_key="aa_your_key_here",
+    agent_id="uuid-of-your-agent"
+)
+
+# Use with any LangChain component
+llm = OpenAI(callbacks=[audit_handler])
+llm.predict("What is the weather?")
+# Automatically logged to AgentAudit!
+```
+
+## Features
+
+- **Simple logging**: One-line audit log submission
+- **Automatic compliance**: PII detection, keyword matching, rate limiting, regex matching, sentiment analysis, custom validators
+- **Agent registration**: Track which agents are performing actions
+- **Query and export**: Retrieve audit logs with filters
+- **LangChain support**: Drop-in callback handler
+- **Type hints**: Full type annotation support
+
+## Agent-to-Agent Audit Trails
+
+Track multi-agent conversations and CrewAI workflows with distributed tracing:
+
+```python
+import uuid
+from agentaudit import AgentAudit
+
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Start a trace — e.g. when a CrewAI crew begins execution
+trace_id = str(uuid.uuid4())
+
+# Log the root event (crew start)
+root = audit.log(
+    action="crewai_crew_start",
+    trace_id=trace_id,
+    metadata={"crew": "Research Crew", "task_count": 3}
+)
+
+# Log child events (tasks, agent actions) with parent_span_id
+audit.log(
+    action="crewai_task_start",
+    trace_id=trace_id,
+    parent_span_id=root.id,
+    prompt="Research topic X",
+    metadata={"task_id": "task-1"}
+)
+
+# Query the full trace later
+# (use the HTTP client or dashboard to query by traceId)
+```
+
+### CrewAI Integration
+
+The [CrewAI observer](../../integrations/crewai/) automatically manages trace IDs and parent span IDs:
+
+```python
+from agentaudit_crewai import AgentAuditObserver
+
+observer = AgentAuditObserver(api_key="aa_key", crew_name="My Crew")
+# trace_id is generated automatically in on_crew_start
+# every event shares the same trace_id with proper parent_span_id linking
+```
+
+## Documentation
+
+Full API documentation: https://docs.agentaudit.io
+
+## License
+
+MIT
+
+---
+
+## Publishing (Maintainers Only)
+
+This package is published automatically via GitHub Actions when you push a version tag:
+
+### Prerequisites
+1. Create a [PyPI account](https://pypi.org/account/register/)
+2. Generate an API token at [pypi.org/manage/account/token](https://pypi.org/manage/account/token)
+3. Add the token to your GitHub repo: **Settings → Secrets and variables → Actions → New repository secret**
+   - Name: `PYPI_API_TOKEN`
+   - Value: your PyPI API token (starts with `pypi-`)
+
+### Publish a New Version
+```bash
+# Update version in sdk/python/setup.py
+git add sdk/python/setup.py
+git commit -m "chore: bump Python SDK to v1.0.1"
+git tag v1.0.1
+git push origin v1.0.1
+```
+
+The `publish-python.yml` workflow will automatically build and upload to PyPI.

agentaudit_client-1.0.0/README.md

@@ -0,0 +1,135 @@
+# AgentAudit Python SDK
+
+Official Python SDK for the AgentAudit API — audit logging and compliance monitoring for AI agents.
+
+## Installation
+
+```bash
+pip install agentaudit-client
+```
+
+With LangChain support:
+```bash
+pip install agentaudit-client[langchain]
+```
+
+## Quick Start
+
+```python
+from agentaudit import AgentAudit
+
+# Initialize
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Log an agent action
+audit.log(
+    action="prompt_submitted",
+    prompt="What is the weather?",
+    response="It is sunny today.",
+    metadata={"model": "gpt-4", "tokens": 150}
+)
+```
+
+## LangChain Integration
+
+```python
+from langchain.callbacks import AgentAuditCallbackHandler
+from langchain.llms import OpenAI
+
+# Setup audit callback
+audit_handler = AgentAuditCallbackHandler(
+    api_key="aa_your_key_here",
+    agent_id="uuid-of-your-agent"
+)
+
+# Use with any LangChain component
+llm = OpenAI(callbacks=[audit_handler])
+llm.predict("What is the weather?")
+# Automatically logged to AgentAudit!
+```
+
+## Features
+
+- **Simple logging**: One-line audit log submission
+- **Automatic compliance**: PII detection, keyword matching, rate limiting, regex matching, sentiment analysis, custom validators
+- **Agent registration**: Track which agents are performing actions
+- **Query and export**: Retrieve audit logs with filters
+- **LangChain support**: Drop-in callback handler
+- **Type hints**: Full type annotation support
+
+## Agent-to-Agent Audit Trails
+
+Track multi-agent conversations and CrewAI workflows with distributed tracing:
+
+```python
+import uuid
+from agentaudit import AgentAudit
+
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Start a trace — e.g. when a CrewAI crew begins execution
+trace_id = str(uuid.uuid4())
+
+# Log the root event (crew start)
+root = audit.log(
+    action="crewai_crew_start",
+    trace_id=trace_id,
+    metadata={"crew": "Research Crew", "task_count": 3}
+)
+
+# Log child events (tasks, agent actions) with parent_span_id
+audit.log(
+    action="crewai_task_start",
+    trace_id=trace_id,
+    parent_span_id=root.id,
+    prompt="Research topic X",
+    metadata={"task_id": "task-1"}
+)
+
+# Query the full trace later
+# (use the HTTP client or dashboard to query by traceId)
+```
+
+### CrewAI Integration
+
+The [CrewAI observer](../../integrations/crewai/) automatically manages trace IDs and parent span IDs:
+
+```python
+from agentaudit_crewai import AgentAuditObserver
+
+observer = AgentAuditObserver(api_key="aa_key", crew_name="My Crew")
+# trace_id is generated automatically in on_crew_start
+# every event shares the same trace_id with proper parent_span_id linking
+```
+
+## Documentation
+
+Full API documentation: https://docs.agentaudit.io
+
+## License
+
+MIT
+
+---
+
+## Publishing (Maintainers Only)
+
+This package is published automatically via GitHub Actions when you push a version tag:
+
+### Prerequisites
+1. Create a [PyPI account](https://pypi.org/account/register/)
+2. Generate an API token at [pypi.org/manage/account/token](https://pypi.org/manage/account/token)
+3. Add the token to your GitHub repo: **Settings → Secrets and variables → Actions → New repository secret**
+   - Name: `PYPI_API_TOKEN`
+   - Value: your PyPI API token (starts with `pypi-`)
+
+### Publish a New Version
+```bash
+# Update version in sdk/python/setup.py
+git add sdk/python/setup.py
+git commit -m "chore: bump Python SDK to v1.0.1"
+git tag v1.0.1
+git push origin v1.0.1
+```
+
+The `publish-python.yml` workflow will automatically build and upload to PyPI.

agentaudit_client-1.0.0/agentaudit/__init__.py

@@ -0,0 +1,252 @@
+"""
+AgentAudit Python SDK
+Drop-in audit logging for AI agents.
+"""
+
+import requests
+from typing import Optional, Dict, Any, List
+from dataclasses import dataclass
+
+
+@dataclass
+class AuditLog:
+    """Represents an audit log entry."""
+    id: str
+    action: str
+    agent_id: Optional[str]
+    prompt: Optional[str]
+    response: Optional[str]
+    metadata: Optional[Dict[str, Any]]
+    compliance_flags: List[str]
+    created_at: str
+
+
+@dataclass
+class GuardrailResult:
+    """Result of a compliance guardrail check."""
+    allowed: bool
+    action: str
+    violations: List[str]
+    severity: str
+    audit_log_id: Optional[str] = None
+
+
+class AgentAudit:
+    """
+    AgentAudit client for submitting audit logs and managing agents.
+    """
+    
+    def __init__(
+        self,
+        api_key: str,
+        base_url: str = "https://agentaudit-api-production.up.railway.app/api/v1",
+        agent_id: Optional[str] = None
+    ):
+        self.api_key = api_key
+        self.base_url = base_url.rstrip("/")
+        self.agent_id = agent_id
+        self.session = requests.Session()
+        self.session.headers.update({
+            "X-API-Key": api_key,
+            "Content-Type": "application/json"
+        })
+    
+    def guardrail(
+        self,
+        action: str,
+        prompt: Optional[str] = None,
+        response: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent_id: Optional[str] = None,
+        trace_id: Optional[str] = None,
+        parent_span_id: Optional[str] = None
+    ) -> GuardrailResult:
+        """
+        Real-time compliance check. Intercepts agent output before delivery.
+        
+        Usage:
+            result = audit.guardrail(
+                action="prompt_submitted",
+                prompt=user_input,
+                response=agent_output
+            )
+            if not result.allowed:
+                raise ValueError(f"Blocked: {result.violations}")
+        """
+        payload = {
+            "action": action,
+            "agentId": agent_id or self.agent_id,
+            "checkType": "realtime"
+        }
+        if prompt:
+            payload["prompt"] = prompt
+        if response:
+            payload["response"] = response
+        if metadata:
+            payload["metadata"] = metadata
+        if trace_id:
+            payload["traceId"] = trace_id
+        if parent_span_id:
+            payload["parentSpanId"] = parent_span_id
+        
+        resp = self.session.post(
+            f"{self.base_url}/audit-logs",
+            json=payload
+        )
+        resp.raise_for_status()
+        data = resp.json()
+        
+        flags = data.get("complianceFlags", [])
+        severity = "critical" if any("PII" in f or "block" in f.lower() for f in flags) else "warning"
+        action_result = "block" if severity == "critical" and flags else ("flag" if flags else "allow")
+        
+        return GuardrailResult(
+            allowed=action_result != "block",
+            action=action_result,
+            violations=flags,
+            severity=severity,
+            audit_log_id=data.get("id")
+        )
+    
+    def log(
+        self,
+        action: str,
+        prompt: Optional[str] = None,
+        response: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent_id: Optional[str] = None,
+        trace_id: Optional[str] = None,
+        parent_span_id: Optional[str] = None
+    ) -> AuditLog:
+        """
+        Submit an audit log entry.
+        
+        Args:
+            action: The action performed (e.g., "prompt_submitted", "tool_executed")
+            prompt: The input prompt (optional)
+            response: The output response (optional)
+            metadata: Additional structured data (optional)
+            agent_id: Override the default agent ID (optional)
+            trace_id: Trace ID for agent-to-agent audit trails (optional)
+            parent_span_id: Parent span ID for chain tracking (optional)
+            
+        Returns:
+            AuditLog: The created audit log entry
+        """
+        payload = {
+            "action": action,
+            "agentId": agent_id or self.agent_id,
+        }
+        
+        if prompt is not None:
+            payload["prompt"] = prompt
+        if response is not None:
+            payload["response"] = response
+        if metadata is not None:
+            payload["metadata"] = metadata
+        if trace_id is not None:
+            payload["traceId"] = trace_id
+        if parent_span_id is not None:
+            payload["parentSpanId"] = parent_span_id
+        
+        resp = self.session.post(
+            f"{self.base_url}/audit-logs",
+            json=payload
+        )
+        resp.raise_for_status()
+        data = resp.json()
+        
+        return AuditLog(
+            id=data["id"],
+            action=data["action"],
+            agent_id=data.get("agentId"),
+            prompt=data.get("prompt"),
+            response=data.get("response"),
+            metadata=data.get("metadata"),
+            compliance_flags=data.get("complianceFlags", []),
+            created_at=data["createdAt"]
+        )
+    
+    def register_agent(
+        self,
+        name: str,
+        agent_type: str = "custom",
+        description: Optional[str] = None,
+        config: Optional[Dict[str, Any]] = None
+    ) -> Dict[str, Any]:
+        """Register a new agent and return its ID."""
+        payload = {
+            "name": name,
+            "type": agent_type,
+        }
+        if description:
+            payload["description"] = description
+        if config:
+            payload["config"] = config
+        
+        resp = self.session.post(
+            f"{self.base_url}/agents",
+            json=payload
+        )
+        resp.raise_for_status()
+        return resp.json()
+    
+    def query_logs(
+        self,
+        action: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        start_date: Optional[str] = None,
+        end_date: Optional[str] = None,
+        page: int = 1,
+        limit: int = 20
+    ) -> Dict[str, Any]:
+        """Query audit logs with filters."""
+        params = {"page": page, "limit": limit}
+        if action:
+            params["action"] = action
+        if agent_id:
+            params["agentId"] = agent_id
+        if start_date:
+            params["startDate"] = start_date
+        if end_date:
+            params["endDate"] = end_date
+        
+        resp = self.session.get(
+            f"{self.base_url}/audit-logs",
+            params=params
+        )
+        resp.raise_for_status()
+        return resp.json()
+    
+    def get_alerts(
+        self,
+        is_resolved: Optional[bool] = None,
+        severity: Optional[str] = None
+    ) -> List[Dict[str, Any]]:
+        """Get compliance alerts."""
+        params = {}
+        if is_resolved is not None:
+            params["isResolved"] = str(is_resolved).lower()
+        if severity:
+            params["severity"] = severity
+        
+        resp = self.session.get(
+            f"{self.base_url}/alerts",
+            params=params
+        )
+        resp.raise_for_status()
+        return resp.json()
+
+
+class AgentAuditCallback:
+    """
+    Callback-style integration for frameworks that support callbacks.
+    Automatically logs all agent actions.
+    """
+    
+    def __init__(self, api_key: str, agent_id: Optional[str] = None):
+        self.client = AgentAudit(api_key=api_key, agent_id=agent_id)
+    
+    def on_action(self, action: str, **kwargs):
+        """Log an action with optional prompt/response/metadata."""
+        return self.client.log(action=action, **kwargs)

agentaudit_client-1.0.0/agentaudit_client.egg-info/PKG-INFO

@@ -0,0 +1,173 @@
+Metadata-Version: 2.4
+Name: agentaudit-client
+Version: 1.0.0
+Summary: Audit & Compliance SDK for AI Agents
+Home-page: https://github.com/agentaudit/agentaudit-python
+Author: AgentAudit Team
+Author-email: support@agentaudit.io
+Keywords: ai agents audit compliance langchain monitoring
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.25.0
+Provides-Extra: langchain
+Requires-Dist: langchain>=0.1.0; extra == "langchain"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# AgentAudit Python SDK
+
+Official Python SDK for the AgentAudit API — audit logging and compliance monitoring for AI agents.
+
+## Installation
+
+```bash
+pip install agentaudit-client
+```
+
+With LangChain support:
+```bash
+pip install agentaudit-client[langchain]
+```
+
+## Quick Start
+
+```python
+from agentaudit import AgentAudit
+
+# Initialize
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Log an agent action
+audit.log(
+    action="prompt_submitted",
+    prompt="What is the weather?",
+    response="It is sunny today.",
+    metadata={"model": "gpt-4", "tokens": 150}
+)
+```
+
+## LangChain Integration
+
+```python
+from langchain.callbacks import AgentAuditCallbackHandler
+from langchain.llms import OpenAI
+
+# Setup audit callback
+audit_handler = AgentAuditCallbackHandler(
+    api_key="aa_your_key_here",
+    agent_id="uuid-of-your-agent"
+)
+
+# Use with any LangChain component
+llm = OpenAI(callbacks=[audit_handler])
+llm.predict("What is the weather?")
+# Automatically logged to AgentAudit!
+```
+
+## Features
+
+- **Simple logging**: One-line audit log submission
+- **Automatic compliance**: PII detection, keyword matching, rate limiting, regex matching, sentiment analysis, custom validators
+- **Agent registration**: Track which agents are performing actions
+- **Query and export**: Retrieve audit logs with filters
+- **LangChain support**: Drop-in callback handler
+- **Type hints**: Full type annotation support
+
+## Agent-to-Agent Audit Trails
+
+Track multi-agent conversations and CrewAI workflows with distributed tracing:
+
+```python
+import uuid
+from agentaudit import AgentAudit
+
+audit = AgentAudit(api_key="aa_your_key_here")
+
+# Start a trace — e.g. when a CrewAI crew begins execution
+trace_id = str(uuid.uuid4())
+
+# Log the root event (crew start)
+root = audit.log(
+    action="crewai_crew_start",
+    trace_id=trace_id,
+    metadata={"crew": "Research Crew", "task_count": 3}
+)
+
+# Log child events (tasks, agent actions) with parent_span_id
+audit.log(
+    action="crewai_task_start",
+    trace_id=trace_id,
+    parent_span_id=root.id,
+    prompt="Research topic X",
+    metadata={"task_id": "task-1"}
+)
+
+# Query the full trace later
+# (use the HTTP client or dashboard to query by traceId)
+```
+
+### CrewAI Integration
+
+The [CrewAI observer](../../integrations/crewai/) automatically manages trace IDs and parent span IDs:
+
+```python
+from agentaudit_crewai import AgentAuditObserver
+
+observer = AgentAuditObserver(api_key="aa_key", crew_name="My Crew")
+# trace_id is generated automatically in on_crew_start
+# every event shares the same trace_id with proper parent_span_id linking
+```
+
+## Documentation
+
+Full API documentation: https://docs.agentaudit.io
+
+## License
+
+MIT
+
+---
+
+## Publishing (Maintainers Only)
+
+This package is published automatically via GitHub Actions when you push a version tag:
+
+### Prerequisites
+1. Create a [PyPI account](https://pypi.org/account/register/)
+2. Generate an API token at [pypi.org/manage/account/token](https://pypi.org/manage/account/token)
+3. Add the token to your GitHub repo: **Settings → Secrets and variables → Actions → New repository secret**
+   - Name: `PYPI_API_TOKEN`
+   - Value: your PyPI API token (starts with `pypi-`)
+
+### Publish a New Version
+```bash
+# Update version in sdk/python/setup.py
+git add sdk/python/setup.py
+git commit -m "chore: bump Python SDK to v1.0.1"
+git tag v1.0.1
+git push origin v1.0.1
+```
+
+The `publish-python.yml` workflow will automatically build and upload to PyPI.

agentaudit_client-1.0.0/agentaudit_client.egg-info/SOURCES.txt

@@ -0,0 +1,8 @@
+README.md
+setup.py
+agentaudit/__init__.py
+agentaudit_client.egg-info/PKG-INFO
+agentaudit_client.egg-info/SOURCES.txt
+agentaudit_client.egg-info/dependency_links.txt
+agentaudit_client.egg-info/requires.txt
+agentaudit_client.egg-info/top_level.txt

agentaudit_client-1.0.0/agentaudit_client.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

agentaudit_client-1.0.0/agentaudit_client.egg-info/requires.txt

@@ -0,0 +1,9 @@
+requests>=2.25.0
+
+[dev]
+pytest>=7.0
+black
+mypy
+
+[langchain]
+langchain>=0.1.0

agentaudit_client-1.0.0/agentaudit_client.egg-info/top_level.txt

@@ -0,0 +1 @@
+agentaudit

agentaudit_client-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

agentaudit_client-1.0.0/setup.py

@@ -0,0 +1,33 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="agentaudit-client",
+    version="1.0.0",
+    description="Audit \u0026 Compliance SDK for AI Agents",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    author="AgentAudit Team",
+    author_email="support@agentaudit.io",
+    url="https://github.com/agentaudit/agentaudit-python",
+    packages=find_packages(),
+    install_requires=[
+        "requests>=2.25.0",
+    ],
+    extras_require={
+        "langchain": ["langchain>=0.1.0"],
+        "dev": ["pytest>=7.0", "black", "mypy"],
+    },
+    python_requires=">=3.8",
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+    ],
+    keywords="ai agents audit compliance langchain monitoring",
+)