* feat: add provider trace backend abstraction for multi-backend telemetry Introduces a pluggable backend system for provider traces: - Base class with async/sync create and read interfaces - PostgreSQL backend (existing behavior) - ClickHouse backend (via OTEL instrumentation) - Socket backend (writes to Unix socket for crouton sidecar) - Factory for instantiating backends from config Refactors TelemetryManager to use backends with support for: - Multi-backend writes (concurrent via asyncio.gather) - Primary backend for reads (first in config list) - Graceful error handling per backend Config: LETTA_TELEMETRY_PROVIDER_TRACE_BACKEND (comma-separated) Example: "postgres,socket" for dual-write to Postgres and crouton 🐙 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com> * feat: add protocol version to socket backend records Adds PROTOCOL_VERSION constant to socket backend: - Included in every telemetry record sent to crouton - Must match ProtocolVersion in apps/crouton/main.go - Enables crouton to detect and reject incompatible messages 🐙 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com> * fix: remove organization_id from ProviderTraceCreate calls The organization_id is now handled via the actor parameter in the telemetry manager, not through ProviderTraceCreate schema. This fixes validation errors after changing ProviderTraceCreate to inherit from BaseProviderTrace which forbids extra fields. 🐙 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com> * consolidate provider trace * add clickhouse-connect to fix bug on main lmao * auto generated sdk changes, and deployment details, and clikchouse prefix bug and added fields to runs trace return api * auto generated sdk changes, and deployment details, and clikchouse prefix bug and added fields to runs trace return api * consolidate provider trace * consolidate provider trace bug fix --------- Co-authored-by: Letta <noreply@letta.com>
70 lines
1.7 KiB
Python
70 lines
1.7 KiB
Python
"""Base class for provider trace backends."""
|
|
|
|
from abc import ABC, abstractmethod
|
|
from enum import Enum
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from letta.schemas.provider_trace import ProviderTrace
|
|
from letta.schemas.user import User
|
|
|
|
|
|
class ProviderTraceBackend(str, Enum):
|
|
"""Supported provider trace storage backends."""
|
|
|
|
POSTGRES = "postgres"
|
|
CLICKHOUSE = "clickhouse"
|
|
SOCKET = "socket"
|
|
|
|
|
|
class ProviderTraceBackendClient(ABC):
|
|
"""Abstract base class for provider trace storage backends."""
|
|
|
|
@abstractmethod
|
|
async def create_async(
|
|
self,
|
|
actor: "User",
|
|
provider_trace: "ProviderTrace",
|
|
) -> "ProviderTrace | None":
|
|
"""
|
|
Store a provider trace record.
|
|
|
|
Args:
|
|
actor: The user/actor creating the trace
|
|
provider_trace: The trace data to store
|
|
|
|
Returns:
|
|
The created ProviderTrace, or None if the backend doesn't return it
|
|
"""
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
async def get_by_step_id_async(
|
|
self,
|
|
step_id: str,
|
|
actor: "User",
|
|
) -> "ProviderTrace | None":
|
|
"""
|
|
Retrieve a provider trace by step ID.
|
|
|
|
Args:
|
|
step_id: The step ID to look up
|
|
actor: The user/actor requesting the trace
|
|
|
|
Returns:
|
|
The ProviderTrace if found, None otherwise
|
|
"""
|
|
raise NotImplementedError
|
|
|
|
def create_sync(
|
|
self,
|
|
actor: "User",
|
|
provider_trace: "ProviderTrace",
|
|
) -> "ProviderTrace | None":
|
|
"""
|
|
Synchronous version of create_async.
|
|
|
|
Default implementation does nothing. Override if sync support is needed.
|
|
"""
|
|
return None
|