traceloop/openllmetry

View on GitHub

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Stars: 7.4k
Forks: 1.1k
Open beginner issues: 9
Indexed issues: 122
Avg merge: 8d 14h
Merged PRs (30d): 2

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 17, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: help wanted good first issue

Beginner friendly Everything

Open All

122 open issues indexed

Responses API streaming crashes with 'AsyncStream' object has no attribute 'id' when using .with_raw_response Open

Difficulty 3/5 1-2 days Newbie friendliness 74/100

traceloop/openllmetry#4476 · Opened Sep 16, 2026
Responses API: completed responses are never removed from the global `responses` dict Open

Difficulty 4/5 3-5 days Newbie friendliness 68/100

traceloop/openllmetry#4473 · 1 comment · Opened Sep 15, 2026
🐛 Bug Report: gen_ai.bedrock.guardrail.activation counts every Bedrock call Open

Difficulty 2/5 1-3 hours Newbie friendliness 86/100

traceloop/openllmetry#4471 · Opened Sep 15, 2026
🐛 Bug Report: MCP client send_request is @dont_throw'd, so a tracing error returns None and breaks the tool call Open

Difficulty 4/5 3-5 days Newbie friendliness 72/100

traceloop/openllmetry#4463 · Opened Sep 7, 2026
anthropic: reasoning-token subset not emitted — cross-provider reasoning cost invisible Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

traceloop/openllmetry#4458 · 1 comment · Opened Sep 3, 2026
LangchainTool definition missing Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

traceloop/openllmetry#4454 · 1 comment · Opened Sep 1, 2026
🐛 Bug Report: CrewAI: LLM.call wrap never fires on crewai >= 1.x native providers, so no LLM span is emitted Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

traceloop/openllmetry#4453 · 1 comment · Opened Sep 1, 2026
🚀 Feature: CrewAI: instrument BaseTool.run to emit tool-execution spans Open

Difficulty 4/5 3-5 days Newbie friendliness 64/100

traceloop/openllmetry#4452 · 1 comment · Opened Sep 1, 2026
🐛 Bug Report: crewai instrumentation reports scope version 0.36.0 on 0.62.3 spans Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

traceloop/openllmetry#4450 · Opened Sep 1, 2026
Same cached Claude call via anthropic vs bedrock packages emits different gen_ai.usage.input_tokens — which is intended? Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

traceloop/openllmetry#4449 · Opened Sep 1, 2026
🐛 Bug Report: `langgraph_utils.extract_graph_structure` drops `gen_ai.workflow.nodes` when node ids are str subclasses Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

traceloop/openllmetry#4447 · Opened Sep 1, 2026
🐛 Bug Report: list-valued association properties crash metrics, and silently drop gen_ai.output.messages Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

traceloop/openllmetry#4436 · 2 comments · Opened Aug 20, 2026
🐛 Bug Report: NotGiven sentinel leak in Anthropic instrumentation Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

traceloop/openllmetry#4431 · 1 comment · Opened Aug 20, 2026
🐛 Bug Report: [OpenAI] Non-ASCII characters are escaped in `gen_ai.input.messages`, `gen_ai.tool.definitions`, and `gen_ai.output.messages` attributes Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

traceloop/openllmetry#4426 · 1 comment · Opened Aug 18, 2026
🐛 Bug Report: Groq streaming calls record no token or duration metrics Open

Difficulty 4/5 3-5 days Newbie friendliness 72/100

traceloop/openllmetry#4419 · Opened Aug 13, 2026
🐛 Bug Report: streaming choice events use the drained generator instead of the last chunk Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

traceloop/openllmetry#4417 · Opened Aug 13, 2026
🐛 Bug Report: dont_throw has no effect on async functions in VertexAI instrumentation Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

traceloop/openllmetry#4414 · Opened Aug 12, 2026
🐛 Bug Report: Unsupported mcp==2.x module 'streamablehttp_client' Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

traceloop/openllmetry#4413 · Opened Aug 12, 2026
Annotation.create() cannot tell a caller the write didn't land Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

traceloop/openllmetry#4404 · Opened Aug 5, 2026
Annotation.create() cannot tell a caller the write didn't land Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

traceloop/openllmetry#4402 · Opened Aug 5, 2026
🐛 Bug Report: Anthropic instrumentation fails to instrument beta async streams Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

traceloop/openllmetry#4388 · 1 comment · Opened Jul 30, 2026
🐛 Bug Report: LangGraph instrumentation incorrectly marks successful astream() executions as ERROR due to GeneratorExit Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

traceloop/openllmetry#4385 · 1 comment · Opened Jul 28, 2026
Bug: @agent leaks gen_ai.agent.name into subsequent spans Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

traceloop/openllmetry#4378 · Opened Jul 26, 2026
🐛 Bug Report: MCP client instrumentation never propagates trace context for ordinary tool calls (regression from #3179) Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

traceloop/openllmetry#4374 · 1 comment · Opened Jul 22, 2026
Bug: HTTP CLIENT spans not nested under gen_ai spans (start_span vs start_as_current_span) Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

traceloop/openllmetry#4365 · Opened Jul 14, 2026
🐛 Bug Report: [anthropic] Streaming spans drop gen_ai.response.finish_reasons and gen_ai.output.messages for turns with empty content Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

traceloop/openllmetry#4362 · 2 comments · Opened Jul 13, 2026
LangChain: bare tool loop without a workflow span produces one trace per invocation — expected? docs note? Open

Difficulty 2/5 1-3 hours Newbie friendliness 65/100

traceloop/openllmetry#4347 · 2 comments · Opened Jul 3, 2026
Mapping external AI-task receipt IDs into LLM trace/span metadata Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

traceloop/openllmetry#4340 · 6 comments · Opened Jul 1, 2026
🐛 Bug Report: opentelemetry-semantic-conventions-ai 0.5.2 missing from pypi Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

traceloop/openllmetry#4291 · 1 comment · Opened Jun 19, 2026
fix: open() calls missing encoding='utf-8' may crash on non-UTF-8 systems Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

traceloop/openllmetry#4286 · 1 comment · Opened Jun 17, 2026
Bedrock: global. cross-region inference profile resolves to vendor "global", dropping span attributes Open

Difficulty 2/5 1-3 hours Newbie friendliness 86/100

traceloop/openllmetry#4234 · Opened Jun 13, 2026
🚀 Feature: Ollama instrumentation missing inference metadata attributes in spans Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

traceloop/openllmetry#4192 · 3 comments · Opened May 26, 2026
🐛 Bug Report: TRACELOOP_TRACING_ENABLED does not match Traceloop.init(enabled) parameter behavior Open

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

traceloop/openllmetry#4191 · Opened May 26, 2026
feat: add support for TRACELOOP_TRACE_CONTENT=false in mcp instrumentor Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

traceloop/openllmetry#4188 · 1 comment · Opened May 25, 2026
🐛 Bug Report: GenerationSpanData missing response field causes _extract_response_attributes to never execute Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

traceloop/openllmetry#4157 · 3 comments · Opened May 19, 2026
🐛 Bug Report: cuid dependency raises sonatype issue sonatype-2023-2645 Open

Difficulty 3/5 1-2 days Newbie friendliness 65/100

traceloop/openllmetry#4155 · Opened May 18, 2026
Best-practice: anonymize secrets in VCR test cassettes (+ minor SDK jinja2 trust-boundary comment) Open

Difficulty 3/5 1-2 days Newbie friendliness 52/100

traceloop/openllmetry#4150 · Opened May 14, 2026
Proposal: standardize gen_ai.security.threat.* event and attribute names in semantic-conventions-ai Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

traceloop/openllmetry#4096 · Opened May 9, 2026
🚀 Feature: Suggestion: Add beginner-friendly example for LLM tracing Open

good first issue

Difficulty 3/5 1-2 days Newbie friendliness 72/100

traceloop/openllmetry#4069 · 13 comments · Opened Apr 30, 2026
🐛 Bug Report: MCP `InstrumentedStreamWriter.send()` assumes dict-shaped `request.result` and can fail for object/model results Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

traceloop/openllmetry#4038 · Opened Apr 20, 2026
🚀 Feature: langchain 1.0+ support Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

traceloop/openllmetry#3834 · 3 comments · Opened Mar 20, 2026
🐛 Bug Report: TypeError: cannot pickle '_thread.RLock' object during on_tool_start in langchain instrumentor Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

traceloop/openllmetry#3518 · 1 comment · Opened Dec 12, 2025
🐛 Bug Report: `opentelemetry-instrumentation-qdrant` is incompatible with `qdrant-client` version `1.16.1` Open

good first issue help wanted

Difficulty 3/5 1-2 days Newbie friendliness 48/100

traceloop/openllmetry#3492 · 13 comments · 2 reactions · Opened Dec 4, 2025
[RFC] Semantic Conventions for AI Agent Observability Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

traceloop/openllmetry#3460 · 32 comments · Opened Nov 23, 2025
🚀 Feature: Add prompt caching for Bedrock Converse Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

traceloop/openllmetry#3337 · 3 comments · Opened Aug 22, 2025
Add OpenAI reasoning attributes to telemetry data Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

traceloop/openllmetry#3257 · 4 comments · Opened Aug 14, 2025
🐛 Bug Report: httpx and other instrumentations are not playing well with langchain instrumentation Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

traceloop/openllmetry#3214 · 2 comments · Opened Aug 2, 2025
🐛 Bug Report: long inputs / outputs are omitted Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

traceloop/openllmetry#3211 · 1 comment · Opened Jul 31, 2025
🚀 Feature: OpenLLMetry for JAVA Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

traceloop/openllmetry#3200 · 6 comments · 2 reactions · Opened Jul 29, 2025
🚀 Feature: Instrument more query_* methods Open

Difficulty 2/5 1-3 hours Newbie friendliness 58/100

traceloop/openllmetry#3174 · 2 comments · Opened Jul 25, 2025

traceloop/openllmetry

Get new issues in your inbox