Skip to content

Add auto-instrumentation and MCP tracing - #20

Merged
nikhilvdev merged 1 commit into
mainfrom
feat/phase-15-auto-instrumentation-mcp
Sep 27, 2026
Merged

nikhilvdev merged 1 commit into
mainfrom
feat/phase-15-auto-instrumentation-mcp

Conversation

@nikhilvdev

Copy link
Copy Markdown
Owner

This change adds provider auto-instrumentation for Anthropic, OpenAI, and LiteLLM so SDK calls emit logger.llm_call(...) without call-site changes. It also adds the OpenAI Agents SDK adapter and MCP trace propagation utilities that carry trace_id and meta.mcp.* across client/server boundaries. The record schema and migration docs were updated to include meta.mcp.run_id, and tests cover the new adapters and instrumentation paths.

Summary

Checklist

  • ruff check . passes
  • mypy logquill passes (--strict on the public API)
  • pytest passes, and new surface area has test coverage
  • Public API additions are documented in README.md with a runnable example
  • CHANGELOG.md has an entry under Unreleased
  • If this touches the cross-language contract (levels, logger methods,
    record shape, transport/plugin contracts, config shape) shared with
    logquill-js, a matching tracking issue/PR is opened there

Scope

This change adds provider auto-instrumentation for Anthropic, OpenAI, and LiteLLM so SDK calls emit `logger.llm_call(...)` without call-site changes. It also adds the OpenAI Agents SDK adapter and MCP trace propagation utilities that carry `trace_id` and `meta.mcp.*` across client/server boundaries. The record schema and migration docs were updated to include `meta.mcp.run_id`, and tests cover the new adapters and instrumentation paths.
@nikhilvdev
nikhilvdev merged commit e26dc05 into main Sep 27, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant