Fiddler LangGraph SDK
1.3
1.3.1
February 5, 2026
Enhancements
Automatic Span Flush on Exit:
FiddlerClientnow registers anatexithandler to automatically flush and shut down the tracer provider when the process exits, reducing span loss from in-memory buffering.Explicit Flush and Shutdown Methods: New
force_flush(timeout_millis)andshutdown()methods onFiddlerClientfor explicit control over span export.shutdown()is idempotent and safe to call multiple times.Asyncio Support: New
aflush()andashutdown()async methods run flush and shutdown in a thread pool, avoiding event loop blocking in asyncio applications.Context Manager Support:
FiddlerClientcan now be used as a context manager (with FiddlerClient(...) as client:) to ensure automatic shutdown on exit.
Bug Fixes
Fixed Pydantic Double-Encoding: Corrected JSON serialization of Pydantic models to use
model_dump()instead ofmodel_dump_json(), preventing double-encoded JSON strings in span attributes.Deduplicated Retriever Span Attributes: Removed duplicate
TYPEandTOOL_NAMEattribute assignments in theon_retriever_startcallback.Replaced
print()withlogging: Allprint()calls injsonl_capture.pynow use the standardloggingmodule for proper log management.
1.3.0
January 21, 2026
Enhancements
OpenTelemetry Version Upgrade: Updated OpenTelemetry dependencies to version 1.39.1/0.60b1 for improved performance and compatibility:
opentelemetry-api: now supports up to 1.39.1opentelemetry-sdk: now supports up to 1.39.1opentelemetry-instrumentation: now supports up to 0.60b1opentelemetry-exporter-otlp-proto-http: now supports up to 1.39.1
1.2
1.2.0
January 14, 2026
Enhancements
Removed Hardcoded OpenTelemetry Limits: Removed hardcoded default values for span limits and batch span processor configuration. The SDK now relies on OpenTelemetry SDK's built-in defaults, simplifying configuration and ensuring consistency with standard OpenTelemetry defaults.
Enhanced LangGraph Tracing with Full Message History: Introduced comprehensive message lifecycle tracking with two new span attributes:
gen_ai.input.messages: Captures the complete message history provided as input to the LLM, including system, user, assistant, and tool messagesgen_ai.output.messages: Captures the output messages generated by the LLM, including tool calls and finish_reason when availableBoth attributes are aligned with GenAI semantic conventions for standardized observability
Extracted Message History from Strands Span Events: Added support for extracting
gen_ai.input.messagesandgen_ai.output.messagesfrom Strands span events (emitted as events rather than attributes) and storing them as span-level attributes in ClickHouse for unified querying and analysis.
1.0
1.0.0
December 6, 2025
Breaking Changes
Moved
add_session_attributesto Tracing Module: Theadd_session_attributes()method has been relocated from the Core module to the Tracing module to co-locate session management functions with related tracing utilities.Old import:
from fiddler_langgraph.core.attributes import add_session_attributesNew import:
from fiddler_langgraph.tracing.instrumentation import add_session_attributesMigration: Update import statements in your code. No functional changes—all behavior remains identical.
Impact: Existing code using the old import path will fail with ImportError
0.1
0.1.1
Previous Release
Initial release of Fiddler LangGraph SDK.