Repository Issue Activity (beta)

#3073 Expose a helper to build LangSmith URLs for OTel-ingested spans

#3128 ValidationException: An error occurred (ValidationException) when calling the ConverseStream operation: The provided model identifier is invalid. During task with name 'model' and id '${ID}'

#3080 OTEL exporter: RuntimeError "dictionary changed size during iteration" in _cleanup_stale_spans

#3071 Trace outputs silently dropped when run I/O contains a dict with tuple keys (OPT_NON_STR_KEYS gap)

#3054 usage_metadata input_cost/output_cost not reflected in prompt_cost/completion_cost on runs

#3072 Expose a public helper for OTel-safe LangSmith metadata attributes

#3096 Client initialization can fail when NO_PROXY contains IPv6 CIDR entries

#3057 Python 0.8.17 generated OpenAPI client imports undeclared runtime dependencies

#2844 Client session leaks per instance until process exit (atexit holds strong session ref)

#1761 How to disable automatic LLM inference for the "OUTPUT" column in a LangSmith experiment?

#3042 [0.7.9][Regression] type errors with [email protected]

#2826 Bug: Incompatibility between GPT-5.4 "Responses API" and UI-forced reasoning_effort parameter

#2907 [Feature Request]: SDK support for programmatic eval-to-feedback loop — close the trace-to-action gap without manual UI steps

#2552 Feature: SDK API for managing model pricing configuration

#1769 Failed to send compressed multipart ingest: Connection error caused failure to POST https://api.smith.langchain.com/runs/multipart in LangSmith API

#2962 Feature: query traces by predicates over child run fields

#3016 Add first-class SDK methods for online evaluators

#2412 BUG: Langsmith UI - OpenAI structured output in Extra Parameters

#2977 BUG: Feedback from presigned token not visible in UI

#2914 evaluate_comparative(): expose pairwise comparison URL on ComparativeExperimentResults

#2919 AgentBoundary v0.1 conformance evaluation of LangSmith — pre-publication review

#2852 DOC: on langsmith evaluate an application's intermediate steps，child_runs of the run/rootRun is null

#2936 wrapAnthropic + LANGSMITH_TRACING_MODE=otel traces don't auto-resolve in Playground

#2083 Issue: JS SDK is missing session_feedback_stats

#2923 wrapOpenAI / wrapAnthropic traces don't auto-resolve in Playground when LANGSMITH_TRACING_MODE=otel