veris-ai 1.5.0

A Python package for Veris AI tools

Veris AI Python SDK

A Python package for Veris AI tools with simulation capabilities and FastAPI MCP (Model Context Protocol) integration.

Quick Reference

Purpose: Tool mocking, tracing, and FastAPI MCP integration for AI agent development
Core Components: tool_mock • jaeger_interface • braintrust_tracing • fastapi_mcp
Deep Dive: Module Architecture • Testing Guide • Usage Examples
Source of Truth: Implementation details in src/veris_ai/ source code

Installation

# Base package
uv add veris-ai

# With optional extras
uv add "veris-ai[dev,fastapi,instrument]"

Installation Profiles:

• dev: Development tools (ruff, pytest, mypy)
• fastapi: FastAPI MCP integration
• instrument: Braintrust/OpenTelemetry tracing

Import Patterns

Semantic Tag: import-patterns

# Core imports (base dependencies only)
from veris_ai import veris, JaegerClient

# Optional features (require extras)
from veris_ai import braintrust_tracing  # Requires [instrument]

Complete Import Strategies: See examples/README.md for five different import approaches, conditional features, and integration patterns.

Configuration

Semantic Tag: environment-config

Variable	Purpose	Default
VERIS_ENDPOINT_URL	Mock server endpoint	Required
VERIS_MOCK_TIMEOUT	Request timeout (seconds)	90.0
ENV	Set to "simulation" for mock mode	Production
VERIS_SERVICE_NAME	Tracing service name	Auto-detected
VERIS_OTLP_ENDPOINT	OpenTelemetry collector	Required for tracing

Configuration Details: See src/veris_ai/tool_mock.py for environment handling logic.

Tracing Integration

Semantic Tag: distributed-tracing

Parallel tracing to Braintrust and Jaeger/OpenTelemetry for monitoring and evaluation.

from veris_ai import braintrust_tracing

# Enable dual tracing
braintrust_tracing.instrument(service_name="my-service", otlp_endpoint="http://localhost:4317")

Session Management: Automatic session ID extraction from bearer tokens. Manual session control via veris.set_session_id() and veris.clear_session_id().

Implementation Details: See src/veris_ai/braintrust_tracing.py for instrumentation logic.

Function Mocking

Semantic Tag: tool-mocking

Core Decorators

from veris_ai import veris

# Mock mode: Returns simulated responses in ENV=simulation
@veris.mock()
async def your_function(param1: str, param2: int) -> dict:
    """Function documentation for LLM context."""
    return {"result": "actual implementation"}

# Spy mode: Executes function but logs calls/responses
@veris.mock(mode="spy")
async def monitored_function(data: str) -> dict:
    return process_data(data)

# Stub mode: Returns fixed value in simulation
@veris.stub(return_value={"status": "success"})
async def get_data() -> dict:
    return await fetch_from_api()

Behavior: In simulation mode, decorators intercept calls to mock endpoints. In production, functions execute normally.

Implementation: See src/veris_ai/tool_mock.py for decorator logic and API integration.

FastAPI MCP Integration

Semantic Tag: fastapi-mcp

Expose FastAPI endpoints as MCP tools for AI agent consumption using HTTP transport.

from fastapi import FastAPI
from veris_ai import veris

app = FastAPI()

# Enable MCP integration with HTTP transport
veris.set_fastapi_mcp(
    fastapi=app,
    name="My API Server",
    include_operations=["get_users", "create_user"],
    exclude_tags=["internal"]
)

# Mount the MCP server with HTTP transport (recommended)
veris.fastapi_mcp.mount_http()

Key Features:

• HTTP Transport: Uses Streamable HTTP protocol for better session management
• Automatic schema conversion: FastAPI OpenAPI → MCP tool definitions
• Session management: Bearer token → session ID mapping
• Filtering: Include/exclude operations and tags
• Authentication: OAuth2 integration

Transport Protocol: The SDK uses HTTP transport (via mount_http()) which implements the MCP Streamable HTTP specification, providing robust connection handling and fixing session routing issues with concurrent connections.

Configuration Reference: See function signature in src/veris_ai/tool_mock.py for all set_fastapi_mcp() parameters.

Utility Functions

Semantic Tag: json-schema-utils

from veris_ai.utils import extract_json_schema

# Schema extraction from types
user_schema = extract_json_schema(User)  # Pydantic models
list_schema = extract_json_schema(List[str])  # Generics

Supported Types: Built-in types, generics (List, Dict, Union), Pydantic models, TypedDict, forward references.

Implementation: See src/veris_ai/utils.py for type conversion logic.

Development

Semantic Tag: development-setup

Requirements: Python 3.11+, uv package manager

# Install with dev dependencies
uv add "veris-ai[dev]"

# Quality checks
ruff check --fix .    # Lint and format
pytest --cov=veris_ai # Test with coverage

Testing & Architecture: See tests/README.md for test structure, fixtures, and coverage strategies. See src/veris_ai/README.md for module architecture and implementation flows.

Module Architecture

Semantic Tag: module-architecture

Core Modules: tool_mock (mocking), jaeger_interface (trace queries), braintrust_tracing (dual tracing), utils (schema conversion)

Complete Architecture: See src/veris_ai/README.md for module overview, implementation flows, and configuration details.

Jaeger Trace Interface

Semantic Tag: jaeger-query-api

from veris_ai.jaeger_interface import JaegerClient

client = JaegerClient("http://localhost:16686")
traces = client.search(service="veris-agent", tags={"error": "true"})

Complete Guide: See src/veris_ai/jaeger_interface/README.md for API reference, filtering strategies, and architecture details.

---

License: MIT License - see LICENSE file for details.