Add LangChain workflow span support and refactor LLM invocation

[wrisa]

Description

WIP - adding agent invocation as well.

• Introduces support for tracing LangChain workflow-level operations (first chain) via the callback handler.
• Adds start/stop workflow invocation tracking alongside the existing LLM inference spans.
• Refactors the callback handler to adress changes in #feat(util-genai): refactor and make API smaller and more user-friendly #4391.
• Adds opentelemetry-util-genai as an explicit dependency in pyproject.toml.
• Includes a workflow example (examples/workflow/main.py)
• Comprehensive tests covering chain execution tracing.

See sample workflow and inference spans below,

Fixes # (issue)

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• Test A

Does This PR Require a Core Repo Change?

• Yes. - Link to PR:
• No.

Checklist:

See contributing.md for styleguide, changelog guidelines, and more.

• Followed the style guidelines of this project
• Changelogs have been updated
• Unit tests have been added
• Documentation has been updated

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds workflow-level tracing for LangChain (top-level chain runs) and refactors LLM span creation to use the newer GenAI invocation APIs, including an example and expanded test coverage.

Changes:

• Add workflow invocation (INTERNAL span) start/stop/error handling via on_chain_* callbacks.
• Refactor LLM spans to use InferenceInvocation (start_inference(), stop(), fail()), and introduce workflow invocation tracking.
• Add opentelemetry-util-genai dependency plus a LangGraph workflow example and new tests.

Reviewed changes

Copilot reviewed 7 out of 8 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
instrumentation-genai/opentelemetry-instrumentation-langchain/tests/test_workflow_chain.py	Adds unit tests validating workflow span creation, CSA propagation, and error/no-op paths.
instrumentation-genai/opentelemetry-instrumentation-langchain/src/opentelemetry/instrumentation/langchain/invocation_manager.py	Makes invocation state nullable to support runs without an associated GenAI invocation.
instrumentation-genai/opentelemetry-instrumentation-langchain/src/opentelemetry/instrumentation/langchain/callback_handler.py	Implements workflow spans for chains and migrates LLM handling to InferenceInvocation.
instrumentation-genai/opentelemetry-instrumentation-langchain/pyproject.toml	Updates core instrumentation dependency and adds explicit opentelemetry-util-genai dependency.
instrumentation-genai/opentelemetry-instrumentation-langchain/examples/workflow/requirements.txt	Adds dependencies for the new workflow example.
instrumentation-genai/opentelemetry-instrumentation-langchain/examples/workflow/main.py	Adds a LangGraph StateGraph workflow example that invokes an LLM node.
instrumentation-genai/opentelemetry-instrumentation-langchain/CHANGELOG.md	Notes the new workflow span support/refactor in the changelog.

[Copilot]

Nested chains are recorded in the invocation manager with invocation=None, but on_chain_end() returns early when the invocation is missing/non-WorkflowInvocation. If parent_run_id is not present in the manager (e.g., out-of-order callbacks or partial instrumentation), this creates orphaned entries that will never be cleaned up. Consider deleting the invocation state on on_chain_end() / on_chain_error() when get_invocation() returns None (or when it’s not a WorkflowInvocation), or avoid storing state at all when the parent is unknown.