Issues

• [bug] bedrock: uninstrument() does not remove tracing from clients created while instrumented

  bugtriage
  Arize-ai/openinference#3969 · Filter by author armanunix opened on Oct 7, 2026

• [bug] openai, google-genai: a call cancelled while waiting for the response (asyncio timeout/cancel, Ctrl-C) never ends its span

  Arize-ai/openinference#3968 · Filter by author armanunix opened on Oct 6, 2026

• [openai] trace the OpenAI Decisions API (client.decisions.create) as DECISION spans

  enhancementinstrumentation: openaiinstrumentationlanguage: jslanguage: pythontriage
  Feature

  Arize-ai/openinference#3966 · Filter by author mikeldking opened on Oct 6, 2026

• [feature request][python][google-genai] base64_image_max_length is not applied to output.value

  enhancementtriage
  Arize-ai/openinference#3958 · Filter by author kouk opened on Oct 6, 2026

• auto instrumentor for elevenlabs python sdk

  enhancementinstrumentationlanguage: pythonnew instrumentationsize:L
  Arize-ai/openinference#3956 · Filter by author caroger opened on Oct 5, 2026
  

• [bug] Agno instrumentor marks model spans OK when model calls fail

  buginstrumentation: agno
  Arize-ai/openinference#3952 · Filter by author ialisaleh opened on Oct 5, 2026
  

• [claude-agent-sdk] Token counts and cost are cumulative per session after resume (claude-agent-sdk >= 0.2.157)

  Arize-ai/openinference#3945 · Filter by author hassiebp opened on Oct 5, 2026

• [bug] bedrock: Converse llm.invocation_parameters omits additionalModelRequestFields (e.g. top_k) and includes the response stop_reason

  Arize-ai/openinference#3944 · Filter by author armanunix opened on Oct 5, 2026
  1

• [bug] bedrock: converse_stream and invoke_model_with_response_stream spans are never ended when the stream is left early (break, close(), abandoned)

  Arize-ai/openinference#3943 · Filter by author armanunix opened on Oct 5, 2026
  1

• [bug] bedrock: system prompt recorded with OPENINFERENCE_HIDE_INPUTS=true (in llm.invocation_parameters for invoke_model, and under an unprefixed message.contents key for streamed system blocks)

  Arize-ai/openinference#3933 · Filter by author armanunix opened on Oct 5, 2026

• [bug] bedrock: invoke_model body passed as a file-like object breaks invoke_model_with_response_stream (TypeError after the request is sent, span never ends) and is not traced by invoke_model

  Arize-ai/openinference#3932 · Filter by author armanunix opened on Oct 5, 2026
  1

• [bug] google-genai: generate_content_stream spans are never ended when the stream is left early (break, close(), abandoned)

  Arize-ai/openinference#3931 · Filter by author armanunix opened on Oct 4, 2026

• [bug] anthropic: stream.close() and abandoned streams never end the LLM span (sync and async)

  bugtriage
  Arize-ai/openinference#3930 · Filter by author armanunix opened on Oct 4, 2026
  1

• [bug] JS openai-agents: tool spans are never made active, so spans created inside a tool start a new trace

  Arize-ai/openinference#3925 · Filter by author selimaytac opened on Oct 2, 2026
  1

• [bug] claude-agent-sdk (JS): AGENT span prompt/total token counts exclude prompt-cache tokens

  bugtriage
  Arize-ai/openinference#3923 · Filter by author jimbobbennett opened on Oct 2, 2026

• [feature request] Add instrumentation for pi-durable

  enhancementlanguage: js
  Arize-ai/openinference#3921 · Filter by author cephalization opened on Oct 2, 2026
  

• [bug] agent-framework: duplicated messages, missing system prompt, and double-encoded tool arguments

  buglanguage: pythontriage
  Arize-ai/openinference#3912 · Filter by author jimbobbennett opened on Oct 1, 2026

• [bug] anthropic: early exit from a stream records the SDK's placeholder tool arguments ({}) as the final tool call

  bugtriage
  Arize-ai/openinference#3904 · Filter by author armanunix opened on Oct 1, 2026
  1

• auto instrumentor for livekit python sdk

  instrumentation
  Feature

  Arize-ai/openinference#3903 · Filter by author caroger opened on Oct 1, 2026
  

• [bug] pipecat: prompt token count not folded, cache_write and audio details never set

  Arize-ai/openinference#3893 · Filter by author chrikrah opened on Sep 30, 2026
  

• [bug] Agno instrumentor marks the agent/team span OK when Agno returns a failed run (RunStatus.error)

  Arize-ai/openinference#3885 · Filter by author IAmAlexander opened on Sep 30, 2026
  3

  

• Together PR #3843 drops error spans when content generators raise

  Arize-ai/openinference#3884 · Filter by author caroger opened on Sep 29, 2026
  

• [feature request] Reduce CPU cost of input/output serialization in _update_span for LangChain autoinstrumentor

  enhancementtriage
  Arize-ai/openinference#3882 · Filter by author sofia099 opened on Sep 29, 2026
  

• [bug] anthropic (python and js): document blocks are silently dropped from recorded input messages

  Arize-ai/openinference#3879 · Filter by author Harsh23Kashyap opened on Sep 29, 2026

• [feature request] Support gen_ai.system.message events in strands-agents processor

  enhancement
  Arize-ai/openinference#3878 · Filter by author AmirSaeed96 opened on Sep 28, 2026