Add invoke_workflow operation name span by wrisa · Pull Request #3249 · open-telemetry/semantic-conventions

wrisa · 2026-01-06T20:13:37Z

Fixes #
Issue: 2912 partly

Agentic framework	Mapping to Workflow	References
Langchain/LangGraph	First chain can indicate start of the workflow	workflow agents
CrewAI	Crew kickoff can start workflow	Crew kickoff
OpenAI agents	Higher level Trace can be started as workflow	Higher trace
Custom/In-house	Multiple LLMs or agents can be grouped under a workflow	In-house

Changes

Workflow proposal https://github.com/open-telemetry/semantic-conventions/blob/b6bfc44631e28e87a0252011a8898e8098cb0ff9/docs/gen-ai/Session-and-Workflow-for-GenAI-Observability.md discussion led to suggestion of invoke workflow operation name in agent span.

Important

Pull requests acceptance are subject to the triage process as described in Issue and PR Triage Management.
PRs that do not follow the guidance above, may be automatically rejected and closed.

Merge requirement checklist

CONTRIBUTING.md guidelines followed.
Change log entry added, according to the guidelines in When to add a changelog entry.
- If your PR does not need a change log, start the PR title with [chore]
Links to the prototypes or existing instrumentations (when adding or changing conventions)

91pavan

Looks good.

zhirafovod

LGTM with some conditional notes left on the PR.

singankit · 2026-01-20T22:53:47Z

@wrisa Is there any active discussions or doc about conditional nodes and how they can be represented, especially with gen ai workflows. For example conditional edges in langgraph.

wrisa · 2026-01-21T20:09:41Z

Is there any active discussions or doc about conditional nodes and how they can be represented, especially with gen ai workflows

@singankit Not exactly, but we briefly presented step for intermediate steps like langchain's chains or CrewAi's tasks. According to SIG discussions, it seemed expensive as all the info could be captured on agent span as well and also it seemed more framework specific. If we can have more use cases like you suggested we can start the discussion maybe again.
P.S: We added assigned agents attribute in step for the chain invoking agent, crewAI's task executed by an agent and can be used for nodes in conditional edge. May be conditional edge can be a 'step' or an extension to it.

lmolkova · 2026-02-24T02:18:26Z

Summarizing the story:

LangGraph

StateGraph operations would be 'workflows`. E.g.

parallel_builder  = StateGraph(State)
...
parallel_workflow = parallel_builder.compile()
state = parallel_workflow.invoke({"topic": "cats"})   <--- this would be workflow span, no workflow name available?

alternatively it could be

@entrypoint()
def parallel_workflow(topic: str):  <--- this would be workflow span, workflow name would be the function name - `parallel_workflow`
    joke_fut = call_llm_1(topic)
   ...
    return aggregator(
        topic, joke_fut.result(), ...    ).result()

examples

OpenAI

Terminology like higher level traces OpenAI uses is not correct or applicable to OTel world, but what's important they use workflow in their docs.

    agent = Agent(name="Joke generator", instructions="Tell funny jokes.")

    with trace("Joke workflow"): #    <----- this would be workflow span, with "Joke workflow" as a name
        first_result = await Runner.run(agent, "Tell me a joke")
        second_result = await Runner.run(agent, f"Rate this joke: {first_result.final_output}")

Warning

This trace thing could mean absolutely anything, users might use it to track calls to their database (by mistake)
I would not rely on it meaning workflow - an operation that wraps calls to (presumably) multiple agents

examples

Agent wrapping agents

orchestrator_agent = Agent(
    name="orchestrator_agent",
    instructions=....,
    tools=[
        spanish_agent.as_tool(tool_name="translate_to_spanish", ...),
        french_agent.as_tool(tool_name="translate_to_french", ...),
        italian_agent.as_tool(tool_name="translate_to_italian", ...),
    ],
)
...
await Runner.run(orchestrator_agent, msg)  # <---- this one might or might not know whether it's doing orchestration

ADK

from google.adk.agents import LlmAgent, SequentialAgent

hello_agent = LlmAgent(model="gemini-2.5-flash",  name="hello_agent",  instruction="Your job is to creatively say hello")
bye_agent = LlmAgent(model="gemini-2.5-flash", name="bye_agent",  instruction="Your job is to creatively reply to the greeting and reply with a quip")
root_agent = SequentialAgent(name="root_agent", sub_agents=[hello_agent, bye_agent])  # <--- this could be a workflow span, it knows it wraps other agents, workflow name could be `root_agent` or `SequentialAgent` if name is optional

examples

CreaAI

also use2 workflow terminology in the docs

 crew = Crew(
            agents=self.agents,  # Automatically collected by the @agent decorator
            tasks=self.tasks,    # Automatically collected by the @task decorator.
            process=Process.sequential,
            verbose=True,
        )
crew.kickoff(inputs={"any": "input here"}) #    <----- this would be workflow span, no workflow name

examples

MS agent framework

    workflow = GroupChatBuilder(
        participants=[researcher, writer],
        intermediate_outputs=True,
        orchestrator_agent=AzureOpenAIResponsesClient(...).as_agent(
            name="Orchestrator",
            instructions="You coordinate a team conversation to solve the user's task.",
        ),
    ).build()
    workflow_agent = workflow.as_agent(name="GroupChatWorkflowAgent")
    agent_result = await workflow_agent.run(task)  #  <----- this probably should be the workflow span? Or the orchestrator? Or both?

examples

Agno

article_workflow = Workflow(
    name="Enhanced Article Creation Workflow",
    description="Automated article creation with conditional parallel research",
    steps=[article_creation_sequence],
)

full example

Let me write down more thoughts in a separate comment

lmolkova · 2026-02-24T02:39:45Z

It seems we have two types of design:

Workflow as a separate API (CrewAI, LangGraph, Agno, MS agent framework, OpenAI with @\trace annotation). Note: I didn't check if they also support calling agents from agents via tools)
Workflow as a specialized agent that is a composition of one or more agents (ADK, OpenAI Agents)

And there are several ways to address is:

Workflow is a separate operation name (not an invoke_agent)
- Pros: we can have different metrics for workflows and individual agents
- Cons:
  - not clear what to do with workflows-that-are-also-agents.
  - We can't really demand one operation name for everyone (crew ai would probably prefer kickoff - it'd be more user friendly)
Workflow is the same span as invoke_agent, gen_ai.workflow.name attribute means it's a workflow. We'll probably need a more reliable criteria.
- Pros: can model agents and workflows
- Cons: same workflow and agent metrics, might be problematic if latency is tremendously different
  We could even report

It seems there is no perfect solution. I'm going to sleep on this and let's discuss it on the call tomorrow.

aabmass

LGTM but still need to figure out relationship to agent spans imo.

…ow span support for LlamaIndex AgentWorkflow and CrewAI (#705) *Description of changes:* - Add `invoke_workflow` span for LlamaIndex `AgentWorkflow.run()` and CrewAI `Crew.kickoff()` following the OTel GenAI semantic conventions [open-telemetry/semantic-conventions#3249](open-telemetry/semantic-conventions#3249) - Add `invoke_agent` span for LlamaIndex workflow agent steps, merging ReAct iterations into one span per agent - Suppress `jinja2` instrumentation in agent observability mode to reduce trace noise from LlamaIndex template rendering - Bump LlamaIndex minimum from `0.10.44` to `0.13.0` Testing: - Unit tests added - E2E testing with CrewAI and LLamaIndex: ``` WARNING:root:LLM event emitted outside call context - generating fallback call_id { "name": "chat gpt-4", "context": { "trace_id": "0x9e7cb9200dc4e94da082ca558872ff3b", "span_id": "0xbb52e545f367b9ac", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x9886147b550546f6", "start_time": "2026-04-02T19:31:11.176007Z", "end_time": "2026-04-02T19:31:11.178020Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "chat", "gen_ai.provider.name": "openai", "gen_ai.request.model": "gpt-4", "gen_ai.system_instructions": "[{\"type\": \"text\", \"content\": \"You are Greeter. You are a friendly greeter.\\nYour personal goal is: Greet people\"}]", "gen_ai.input.messages": "[{\"role\": \"user\", \"parts\": [{\"type\": \"text\", \"content\": \"\\nCurrent Task: Greet World\\n\\nThis is the expected criteria for your final answer: A greeting.\\nyou MUST return the actual complete content as the final answer, not a summary.\"}]}]", "gen_ai.output.messages": "[{\"role\": \"assistant\", \"parts\": [{\"type\": \"tool_call\", \"name\": \"get_greeting\", \"arguments\": {\"name\": \"World\"}}], \"finish_reason\": \"tool_call\"}]", "gen_ai.response.model": "gpt-4", "gen_ai.usage.input_tokens": 1, "gen_ai.usage.output_tokens": 1 }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "execute_tool get_greeting", "context": { "trace_id": "0x9e7cb9200dc4e94da082ca558872ff3b", "span_id": "0x16c12ef0f504dd8f", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x9886147b550546f6", "start_time": "2026-04-02T19:31:11.178242Z", "end_time": "2026-04-02T19:31:11.178453Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "execute_tool", "gen_ai.tool.type": "function", "gen_ai.tool.name": "get_greeting", "gen_ai.tool.description": "Tool Name: get_greeting\nTool Arguments: {\n \"properties\": {\n \"name\": {\n \"title\": \"Name\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"name\"\n ],\n \"title\": \"Get_Greeting\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\nTool Description: Get a greeting for someone", "gen_ai.provider.name": "openai", "gen_ai.request.model": "gpt-4", "gen_ai.tool.call.arguments": "{\"name\": \"World\"}", "gen_ai.tool.call.result": "\"Hello World!\"" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "chat gpt-4", "context": { "trace_id": "0x9e7cb9200dc4e94da082ca558872ff3b", "span_id": "0x672dbb753d2a9c19", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x9886147b550546f6", "start_time": "2026-04-02T19:31:11.178651Z", "end_time": "2026-04-02T19:31:11.180069Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "chat", "gen_ai.provider.name": "openai", "gen_ai.request.model": "gpt-4", "gen_ai.system_instructions": "[{\"type\": \"text\", \"content\": \"You are Greeter. You are a friendly greeter.\\nYour personal goal is: Greet people\"}]", "gen_ai.input.messages": "[{\"role\": \"user\", \"parts\": [{\"type\": \"text\", \"content\": \"\\nCurrent Task: Greet World\\n\\nThis is the expected criteria for your final answer: A greeting.\\nyou MUST return the actual complete content as the final answer, not a summary.\"}]}, {\"role\": \"assistant\", \"parts\": [{\"type\": \"tool_call\", \"id\": \"call_1\"}]}, {\"role\": \"tool\", \"parts\": [{\"type\": \"tool_call_response\", \"id\": \"call_1\", \"response\": \"Hello World!\"}]}, {\"role\": \"user\", \"parts\": [{\"type\": \"text\", \"content\": \"Analyze the tool result. If requirements are met, provide the Final Answer. Otherwise, call the next tool. Deliver only the answer without meta-commentary.\"}]}]", "gen_ai.output.messages": "[{\"role\": \"assistant\", \"parts\": [{\"type\": \"text\", \"content\": \"Thought: I now know the final answer\\nFinal Answer: Hello World!\"}], \"finish_reason\": \"stop\"}]", "gen_ai.response.model": "gpt-4", "gen_ai.usage.input_tokens": 1, "gen_ai.usage.output_tokens": 1 }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "invoke_agent Greeter", "context": { "trace_id": "0x9e7cb9200dc4e94da082ca558872ff3b", "span_id": "0x9886147b550546f6", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x03496a39dc7be2d7", "start_time": "2026-04-02T19:31:11.175538Z", "end_time": "2026-04-02T19:31:11.180400Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "invoke_agent", "gen_ai.agent.name": "Greeter", "gen_ai.agent.id": "6e4c0852-87ae-4be5-b11d-df203ead6cb6", "gen_ai.agent.description": "Greet people", "gen_ai.system_instructions": "You are a friendly greeter.", "gen_ai.provider.name": "openai", "gen_ai.request.model": "gpt-4" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "invoke_workflow GreetingCrew", "context": { "trace_id": "0x9e7cb9200dc4e94da082ca558872ff3b", "span_id": "0x03496a39dc7be2d7", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": null, "start_time": "2026-04-02T19:31:11.168711Z", "end_time": "2026-04-02T19:31:11.183189Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "invoke_workflow", "gen_ai.workflow.name": "GreetingCrew", "gen_ai.agent.id": "7eebdca4-e295-464a-a1d7-329998e02f93", "gen_ai.tool.definitions": "[{\"type\": \"function\", \"name\": \"get_greeting\", \"description\": \"Tool Name: get_greeting\\nTool Arguments: {\\n \\\"properties\\\": {\\n \\\"name\\\": {\\n \\\"title\\\": \\\"Name\\\",\\n \\\"type\\\": \\\"string\\\"\\n }\\n },\\n \\\"required\\\": [\\n \\\"name\\\"\\n ],\\n \\\"title\\\": \\\"Get_Greeting\\\",\\n \\\"type\\\": \\\"object\\\",\\n \\\"additionalProperties\\\": false\\n}\\nTool Description: Get a greeting for someone\", \"parameters\": {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"name\"], \"title\": \"Get_Greeting\", \"type\": \"object\"}}]" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } ``` ``` { "name": "chat us.anthropic.claude-sonnet-4-20250514-v1:0", "context": { "trace_id": "0xc626744ad1f2632500b94131f23f6090", "span_id": "0x09ec58e5f0a11a30", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x20887e9dbe3d8c5d", "start_time": "2026-04-02T19:30:48.591392Z", "end_time": "2026-04-02T19:30:49.060111Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.request.model": "us.anthropic.claude-sonnet-4-20250514-v1:0", "gen_ai.provider.name": "aws.bedrock", "gen_ai.request.temperature": 0.1, "gen_ai.request.max_tokens": 200, "gen_ai.tool.definitions": "[\"tools\", \"toolChoice\"]", "gen_ai.operation.name": "chat", "gen_ai.system_instructions": "[{\"type\": \"text\", \"content\": \"You are a pet records specialist. Use tools to look up pets.\"}]", "gen_ai.input.messages": "[{\"role\": \"user\", \"parts\": [{\"type\": \"text\", \"content\": \"Look up pet PET001\"}]}]" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=7f63a06d-196f-4fed-8272-a074eb2bc9eb Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=340d5fb1-46b6-4bb0-b88c-2c9e6d8a5638 Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=0e630fb1-4428-46b0-a4f3-e56cffaed0a5 Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=8a09f7fa-893a-4627-9242-b3f697e854a5 Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=fbc0f545-5b57-4fd4-87e2-4f4896241fb6 Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=511d0877-d42d-45e0-bac4-2f08c91c3fee Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=21f1c125-fbf2-4754-b41c-36c2bfaea374 Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=4bf025d9-ff17-421b-97c5-d231f3bdc8ac Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=be322542-33af-4d71-8d7b-08be813b6c6c Open span is missing for span_id=BedrockConverse.astream_chat-3e1d0f16-6d83-46d3-9337-b02e89091539, event_id=b6dcac60-dfab-40c7-a1c9-53cd7fa51664 { "name": "execute_tool lookup_pet", "context": { "trace_id": "0xc626744ad1f2632500b94131f23f6090", "span_id": "0x2ac5b771c3a2286c", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x33756b5d86a90ed0", "start_time": "2026-04-02T19:30:50.387954Z", "end_time": "2026-04-02T19:30:50.388194Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "execute_tool", "gen_ai.tool.description": "Look up a pet by ID", "gen_ai.tool.name": "lookup_pet", "gen_ai.tool.call.arguments": "{\"pet_id\": \"PET001\"}", "gen_ai.tool.call.result": "{\"pet_id\": \"PET001\", \"name\": \"Buddy\", \"species\": \"dog\", \"breed\": \"Golden Retriever\"}" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "chat us.anthropic.claude-sonnet-4-20250514-v1:0", "context": { "trace_id": "0xc626744ad1f2632500b94131f23f6090", "span_id": "0xcb946943a01edace", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x20887e9dbe3d8c5d", "start_time": "2026-04-02T19:30:50.389761Z", "end_time": "2026-04-02T19:30:50.390160Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.request.model": "us.anthropic.claude-sonnet-4-20250514-v1:0", "gen_ai.provider.name": "aws.bedrock", "gen_ai.request.temperature": 0.1, "gen_ai.request.max_tokens": 200, "gen_ai.tool.definitions": "[\"tools\", \"toolChoice\"]", "gen_ai.operation.name": "chat", "gen_ai.system_instructions": "[{\"type\": \"text\", \"content\": \"You are a pet records specialist. Use tools to look up pets.\"}]", "gen_ai.input.messages": "[{\"role\": \"user\", \"parts\": [{\"type\": \"text\", \"content\": \"Look up pet PET001\"}]}, {\"role\": \"assistant\", \"parts\": [{\"type\": \"text\", \"content\": \"I'll look up the pet with ID \\\"PET001\\\" for you.\"}]}, {\"role\": \"tool\", \"parts\": [{\"type\": \"text\", \"content\": \"{\\\"pet_id\\\": \\\"PET001\\\", \\\"name\\\": \\\"Buddy\\\", \\\"species\\\": \\\"dog\\\", \\\"breed\\\": \\\"Golden Retriever\\\"}\"}]}]" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=f522e128-e10c-4e24-90b4-08be4f6cbbfc Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=dccab180-dc82-4a14-af1b-284d086ab1f8 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=2707786f-1c4c-40aa-bde1-e0cb21eccba1 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=be99782a-ddca-4faf-a706-a42c18904c8e Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=496fdd2e-4e6d-4ca4-a9fe-64f6f62e68f2 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=6aadad22-90de-43bc-8907-f4d931f18665 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=fc5e72d8-551a-4cf6-98b0-faae7936437b Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=3a533ea8-1cdd-4f9b-961d-46354a7c644b Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=13db4508-66b3-47da-bde0-876d1135995f Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=5c5244dd-be41-4fae-8439-441b3b6eb2b4 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=4d59f5cb-cd98-44d0-93be-f4116621c54a Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=815a1216-59fc-410c-9268-3ae1291071f2 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=50b7dff5-059d-4fd6-943e-d3d51a829f46 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=db6e6dc9-628e-4527-a8a9-9eb84e2e1e34 Open span is missing for span_id=BedrockConverse.astream_chat-b958be4d-e3c0-4f55-99ba-7bc31488ed5a, event_id=20f94aa2-8d0e-4efa-bd75-edf58ae61d37 Failed to detach context Traceback (most recent call last): File "/Users/liustve/aws-otel-python-instrumentation/AgentsStudioForTriton/pet-clinic-agents/.venv/lib/python3.12/site-packages/opentelemetry/context/__init__.py", line 155, in detach _RUNTIME_CONTEXT.detach(token) File "/Users/liustve/aws-otel-python-instrumentation/AgentsStudioForTriton/pet-clinic-agents/.venv/lib/python3.12/site-packages/opentelemetry/context/contextvars_context.py", line 53, in detach self._current_context.reset(token) ValueError: <Token var=<ContextVar name='current_context' default={} at 0x105b93ec0> at 0x115cb9280> was created in a different Context { "name": "invoke_agent RecordsAgent", "context": { "trace_id": "0xc626744ad1f2632500b94131f23f6090", "span_id": "0x20887e9dbe3d8c5d", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": "0x33756b5d86a90ed0", "start_time": "2026-04-02T19:30:48.589952Z", "end_time": "2026-04-02T19:30:51.620018Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "invoke_agent", "gen_ai.agent.name": "RecordsAgent", "gen_ai.system_instructions": "You are a pet records specialist. Use tools to look up pets." }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } { "name": "invoke_workflow pet_records_search", "context": { "trace_id": "0xc626744ad1f2632500b94131f23f6090", "span_id": "0x33756b5d86a90ed0", "trace_state": "[]" }, "kind": "SpanKind.INTERNAL", "parent_id": null, "start_time": "2026-04-02T19:30:48.490262Z", "end_time": "2026-04-02T19:30:51.620132Z", "status": { "status_code": "OK" }, "attributes": { "gen_ai.operation.name": "invoke_workflow", "gen_ai.workflow.name": "pet_records_search" }, "events": [], "links": [], "resource": { "attributes": { "telemetry.sdk.language": "python", "telemetry.sdk.name": "opentelemetry", "telemetry.sdk.version": "1.40.0", "service.name": "unknown_service" }, "schema_url": "" } } ``` By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

github-actions · 2026-05-05T16:42:12Z

This PR contains changes to area(s) that do not have an active SIG/project and will be auto-closed:

gen-ai

Such changes may be rejected or put on hold until a new SIG/project is established.

Please refer to the Semantic Convention Areas
document to see the current active SIGs and also to learn how to kick start a new one.

Added invoke workflow operation name to agent span

0fab1d9

github-actions Bot added the area:gen-ai label Jan 6, 2026

wrisa added 3 commits January 6, 2026 12:14

Added PR number

2d18644

Added invoke workflow operation name

8ab0313

Added invoke workflow operation name to other spans

98ad936

JWinermaSplunk reviewed Jan 12, 2026

View reviewed changes

Comment thread model/gen-ai/registry.yaml

Comment thread model/gen-ai/spans.yaml Outdated

added extends

e92eb27

wrisa marked this pull request as ready for review January 12, 2026 20:45

wrisa requested review from a team as code owners January 12, 2026 20:45

resolved conflicts with main branch

0b45e67

91pavan reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/registry.yaml Outdated

zhirafovod reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/registry.yaml Outdated

zhirafovod reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml Outdated

zhirafovod reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml Outdated

fixed typo and removed framework

88c356c

zhirafovod approved these changes Jan 13, 2026

View reviewed changes

lmolkova reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/registry.yaml

lmolkova reviewed Jan 13, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml

addressed comments

333ac6f

kamphaus reviewed Jan 20, 2026

View reviewed changes

Comment thread model/gen-ai/registry.yaml Outdated

wrisa added 2 commits January 20, 2026 08:51

corrected note

af63c87

fixed typo

a033559

lmolkova reviewed Jan 20, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml

kamphaus reviewed Jan 20, 2026

View reviewed changes

Comment thread .chloggen/genai-invoke-workflow-operation-name.yaml Outdated

singankit approved these changes Jan 20, 2026

View reviewed changes

Comment thread .chloggen/genai-invoke-workflow-operation-name.yaml Outdated

wrisa mentioned this pull request May 5, 2026

Add metrics for workflow open-telemetry/semantic-conventions-genai#74

Open

updated changelog with issue

7a757e6

wrisa changed the title ~~Added invoke workflow operation name to agent span~~ Add invoke workflow operation name to agent span Feb 20, 2026

wrisa changed the title ~~Add invoke workflow operation name to agent span~~ Add invoke_workflow operation name span Feb 20, 2026

lmolkova moved this from Untriaged to Awaiting codeowners approval in Semantic Conventions Triage Feb 20, 2026

wrisa added 2 commits February 23, 2026 14:19

removed extends

4800324

corrected numbers

106a51c

aabmass approved these changes Feb 24, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml

Comment thread model/gen-ai/spans.yaml

wrisa added 3 commits February 25, 2026 08:48

fixed table

983f0ac

Merge branch 'main' into invoke-workflow-agent-span

8c31298

fixed definition

abfcbd8

lmolkova approved these changes Mar 3, 2026

View reviewed changes

TaoChenOSU reviewed Mar 3, 2026

View reviewed changes

Comment thread docs/gen-ai/gen-ai-agent-spans.md Outdated

TaoChenOSU reviewed Mar 3, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml Outdated

lmolkova reviewed Mar 3, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml Outdated

singankit mentioned this pull request Mar 4, 2026

REQUEST: New membership for singankit open-telemetry/community#3307

Closed

6 tasks

wrisa mentioned this pull request Mar 5, 2026

Add workflow type in genai utils open-telemetry/opentelemetry-python-contrib#4310

Merged

11 tasks

lmolkova reviewed Mar 9, 2026

View reviewed changes

Comment thread model/gen-ai/spans.yaml Outdated

Comment thread model/gen-ai/spans.yaml Outdated

updated description

04f5384

lmolkova added this pull request to the merge queue Mar 9, 2026

Merged via the queue into open-telemetry:main with commit fd03200 Mar 9, 2026
17 of 18 checks passed

github-project-automation Bot moved this from In Progress to Done in GenAI Semantic Conventions and Instrumentation libraries Mar 9, 2026

Copilot AI mentioned this pull request Mar 10, 2026

Support invoke_workflow as an equivalent parent span to invoke_agent in FunctionInvokingChatClient dotnet/extensions#7382

Merged

5 tasks

liustve mentioned this pull request Apr 2, 2026

feat(crewai-instrumentor, llamaindex-instrumentor): add invoke_workflow span support for LlamaIndex AgentWorkflow and CrewAI aws-observability/aws-otel-python-instrumentation#705

Merged

clongbupt mentioned this pull request Apr 8, 2026

feat(gen-ai): Add alibaba semconv workflow alibaba/loongsuite-semantic-conventions#4

Closed

3 tasks

github-actions Bot added the triage:rejected:declined label May 5, 2026

Conversation

wrisa commented Jan 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Changes

Merge requirement checklist

Uh oh!

Uh oh!

Uh oh!

91pavan left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

zhirafovod left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

singankit commented Jan 20, 2026

Uh oh!

wrisa commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lmolkova commented Feb 24, 2026

LangGraph

OpenAI

Agent wrapping agents

ADK

CreaAI

MS agent framework

Agno

Uh oh!

lmolkova commented Feb 24, 2026

Uh oh!

aabmass left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

github-actions Bot commented May 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

wrisa commented Jan 6, 2026 •

edited

Loading

wrisa commented Jan 21, 2026 •

edited

Loading