tatlock/src/core/logging_config.py

"""
Structured logging configuration using structlog.

Deeply integrates with FastAPI/uvicorn's built-in logging to provide
seamless structured logs across the entire application stack.
"""
import logging
import logging.config
import sys
from contextlib import asynccontextmanager
from datetime import datetime, timezone
from typing import Any, AsyncIterator

import structlog
from structlog.types import EventDict, Processor

from .config import config


def add_timestamp(logger: Any, method_name: str, event_dict: EventDict) -> EventDict:
    """Add ISO 8601 timestamp to log entries."""
    event_dict["timestamp"] = datetime.now(timezone.utc).isoformat()
    return event_dict


def add_log_level(logger: Any, method_name: str, event_dict: EventDict) -> EventDict:
    """Add log level to event dict."""
    event_dict["level"] = method_name.upper()
    return event_dict


def extract_from_record(logger: Any, method_name: str, event_dict: EventDict) -> EventDict:
    """
    Extract extra fields from logging.LogRecord for standard library integration.

    This allows standard Python logging calls to include structured data:
    logger.info("request received", extra={"user_id": "123", "path": "/api"})
    """
    record = event_dict.get("_record")
    if record is not None:
        # Extract custom fields from record
        for key, value in record.__dict__.items():
            if key not in {
                "name", "msg", "args", "created", "filename", "funcName",
                "levelname", "levelno", "lineno", "module", "msecs",
                "message", "pathname", "process", "processName", "relativeCreated",
                "thread", "threadName", "exc_info", "exc_text", "stack_info",
                "taskName"
            }:
                event_dict[key] = value

    return event_dict


def configure_logging() -> None:
    """
    Configure structured logging with deep FastAPI/uvicorn integration.

    - Replaces all Python logging with structlog
    - FastAPI, uvicorn, and app logs all use same format
    - JSON format for production, pretty console for development
    - Preserves log levels and exception handling
    """
    # Determine processors based on log format
    shared_processors: list[Processor] = [
        structlog.contextvars.merge_contextvars,
        structlog.stdlib.add_logger_name,
        add_log_level,
        add_timestamp,
        structlog.stdlib.PositionalArgumentsFormatter(),
        structlog.processors.StackInfoRenderer(),
        extract_from_record,
    ]

    if config.log_format == "json":
        # JSON format for production
        structlog.configure(
            processors=[
                structlog.stdlib.filter_by_level,
                *shared_processors,
                structlog.stdlib.ProcessorFormatter.wrap_for_formatter,
            ],
            logger_factory=structlog.stdlib.LoggerFactory(),
            wrapper_class=structlog.stdlib.BoundLogger,
            cache_logger_on_first_use=True,
        )

        formatter = structlog.stdlib.ProcessorFormatter(
            processors=[
                structlog.stdlib.ProcessorFormatter.remove_processors_meta,
                structlog.processors.format_exc_info,
                structlog.processors.JSONRenderer(),
            ],
            foreign_pre_chain=shared_processors,
        )
    else:
        # Console format for development
        structlog.configure(
            processors=[
                structlog.stdlib.filter_by_level,
                *shared_processors,
                structlog.stdlib.ProcessorFormatter.wrap_for_formatter,
            ],
            logger_factory=structlog.stdlib.LoggerFactory(),
            wrapper_class=structlog.stdlib.BoundLogger,
            cache_logger_on_first_use=True,
        )

        formatter = structlog.stdlib.ProcessorFormatter(
            processors=[
                structlog.stdlib.ProcessorFormatter.remove_processors_meta,
                structlog.dev.ConsoleRenderer(colors=True),
            ],
            foreign_pre_chain=shared_processors,
        )

    # Configure Python's logging to use structlog
    handler = logging.StreamHandler(sys.stdout)
    handler.setFormatter(formatter)

    # Set up root logger
    root_logger = logging.getLogger()
    root_logger.handlers.clear()
    root_logger.addHandler(handler)
    root_logger.setLevel(logging.getLevelName(config.LOG_LEVEL))

    # Configure specific loggers
    for logger_name in [
        "uvicorn",
        "uvicorn.access",
        "uvicorn.error",
        "fastapi",
        "tatlock",
    ]:
        logger = logging.getLogger(logger_name)
        logger.handlers.clear()
        logger.propagate = True
        logger.setLevel(logging.getLevelName(config.LOG_LEVEL))


def get_logger(name: str) -> structlog.stdlib.BoundLogger:
    """
    Get a structured logger instance.

    Works seamlessly with both structlog and standard logging calls:
    - logger.info("message", key="value") - structlog style
    - logger.info("message", extra={"key": "value"}) - standard logging style

    Args:
        name: Logger name (typically __name__)

    Returns:
        Configured structlog BoundLogger

    Example:
        >>> logger = get_logger(__name__)
        >>> logger.info("user_request", user_id="123", action="search")
        >>> logger.info("standard log", extra={"request_id": "abc"})
    """
    return structlog.get_logger(name)


@asynccontextmanager
async def log_operation(
    operation: str,
    initial_context: dict[str, Any] | None = None,
    logger_name: str = "tatlock.operations"
) -> AsyncIterator[dict[str, Any]]:
    """
    Context manager for automatic operation timing and logging.

    Args:
        operation: Operation name (e.g., "steward_analysis", "tool_call")
        initial_context: Initial metadata to log
        logger_name: Logger name for this operation

    Yields:
        Context dict that can be updated during operation

    Example:
        >>> async with log_operation("steward_analysis", {"user_id": "123"}) as ctx:
        ...     # Do work
        ...     ctx["recommendation_count"] = 3
        ...     # Automatically logs duration and context on exit
    """
    logger = get_logger(logger_name)
    context = initial_context or {}
    context["operation"] = operation

    start_time = datetime.now(timezone.utc)
    logger.info("operation_started", **context)

    try:
        yield context

        # Success case
        duration = (datetime.now(timezone.utc) - start_time).total_seconds()
        context["duration_seconds"] = duration
        context["success"] = True
        logger.info("operation_completed", **context)

    except Exception as e:
        # Error case
        duration = (datetime.now(timezone.utc) - start_time).total_seconds()
        context["duration_seconds"] = duration
        context["success"] = False
        context["error"] = str(e)
        context["error_type"] = type(e).__name__
        logger.error("operation_failed", **context, exc_info=True)
        raise


def get_uvicorn_log_config() -> dict[str, Any]:
    """
    Get uvicorn logging configuration that integrates with structlog.

    Use this when starting uvicorn:
    uvicorn.run(app, log_config=get_uvicorn_log_config())

    Returns:
        Uvicorn-compatible logging configuration dict
    """
    return {
        "version": 1,
        "disable_existing_loggers": False,
        "formatters": {
            "default": {
                "()": structlog.stdlib.ProcessorFormatter,
                "processors": [
                    structlog.stdlib.ProcessorFormatter.remove_processors_meta,
                    structlog.processors.JSONRenderer() if config.log_format == "json"
                    else structlog.dev.ConsoleRenderer(colors=True),
                ],
            },
        },
        "handlers": {
            "default": {
                "formatter": "default",
                "class": "logging.StreamHandler",
                "stream": "ext://sys.stdout",
            },
        },
        "loggers": {
            "uvicorn": {"handlers": ["default"], "level": config.LOG_LEVEL},
            "uvicorn.error": {"handlers": ["default"], "level": config.LOG_LEVEL},
            "uvicorn.access": {"handlers": ["default"], "level": config.LOG_LEVEL},
        },
    }


# Initialize logging on module import
configure_logging()