feat(langchain): emit GenAI request attributes

[Jackson Weber (JacksonWeber)]

Summary

• emit available GenAI request parameters from LangChain extra.invocation_params on chat spans
• derive gen_ai.output.type from explicit output types and structured response formats, restricted to the documented text, json, and image values
• accept OpenAI-style snake_case and provider/LangChain camelCase input aliases while emitting only OpenTelemetry gen_ai.* attribute names
• preserve typed provider values without coercing numeric or boolean strings

Attributes

• gen_ai.output.type
• gen_ai.request.temperature
• gen_ai.request.top_p
• gen_ai.request.top_k
• gen_ai.request.max_tokens
• gen_ai.request.frequency_penalty
• gen_ai.request.presence_penalty
• gen_ai.request.seed
• gen_ai.request.stop_sequences
• gen_ai.request.stream

Input normalization

• supports OpenAI-style keys such as top_p, max_completion_tokens, frequency_penalty, and response_format
• supports camelCase keys exposed by LangChain provider integrations, including Google's documented maxOutputTokens, topK, topP, and stopSequences
• maps provider response-format aliases such as json_object and json_schema to json, and b64_json and url to image
• ignores unsupported output types, malformed values, non-integer integer attributes, and string representations of numeric or boolean values

Validation

• LangChain unit, tracer, and functional suites pass
• A365 exporter and span-processor suites pass
• lint, formatting, and build pass
• live Azure OpenAI invocation validated against Application Insights using @langchain/openai 1.5.5 and @langchain/core 1.2.3; the ingested span retained expected typed values for temperature, top-p, max tokens, penalties, seed, stop sequences, stream, and JSON output type

A365 compatibility

• the Agent365 exporter copies span attributes into its OTLP-like payload without renaming or coercion
• added a regression test proving the complete new attribute set retains its string, number, boolean, and string-array types in the A365 payload
• gen_ai.request.temperature, gen_ai.request.top_p, and gen_ai.request.max_tokens are already defined by the upstream Agent365 JS constants
• all emitted keys and types follow the current OpenTelemetry GenAI semantic conventions; A365 identity partitioning and message truncation behavior are unchanged

Upstream assessment

Current LangChain.js exposes these values as raw callback invocation_params but does not map them to OpenTelemetry gen_ai.* attributes, so the distro remains the appropriate implementation layer.

[Copilot]

Pull request overview

Warning

Copilot couldn't run its full agentic review because it didn't start before the timeout. Make sure your repository has a runner available, or add a copilot-code-review.yml file specifying one with the runs-on attribute. See the docs for more details.

Adds LangChain instrumentation support for emitting GenAI request-related OpenTelemetry attributes (including output type) from extra.invocation_params, with validation/normalization and expanded unit test coverage.

Changes:

• Introduces new GenAI semantic convention constants for request parameters and gen_ai.output.type.
• Adds setRequestAttributes to LangChain utils and wires it into the LangChain tracer.
• Expands unit tests to cover mapping/normalization and exporter payload preservation.

Reviewed changes

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

Show a summary per file

File	Description
test/internal/unit/genai/langchain/utils.test.ts	Adds focused unit tests for setRequestAttributes mapping/validation behavior.
test/internal/unit/genai/langchain/tracer.test.ts	Verifies tracer emits request attributes/output type onto spans.
test/internal/unit/a365/agent365Exporter.test.ts	Ensures A365 exporter payload preserves new GenAI attributes.
src/genai/semconv.ts	Defines new gen_ai.* attribute constants used by instrumentation.
src/genai/instrumentations/langchain/utils.ts	Implements request attribute extraction, normalization, and type validation.
src/genai/instrumentations/langchain/tracer.ts	Hooks request attribute setting into span creation flow.
CHANGELOG.md	Documents the new instrumentation feature under Unreleased.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Radhika Gupta (rads-1996)]

where did the other checks go? Is it a github issue?

[Jackson Weber (JacksonWeber)]

where did the other checks go? Is it a github issue?

Interesting, yeah. There were issues with github actions yesterday. Let me fix this one.

[Radhika Gupta (rads-1996)]

LGTM. The entire test suite is however not being run still.

[Jackson Weber (JacksonWeber)]

LGTM. The entire test suite is however not being run still.

We don't currently have perf or integration tests for this project. Need to migrate them over from others. Have a follow up task for this.