uselemma

Review a GitHub pull request, reconcile prior inline review threads, resolve fixed findings, and post new inline comments without editing code or managing the PR.

Review code changes across a repository and report findings without editing, committing, or managing PRs. Use when evaluating a branch, pull request, or diff for behavior, tests, organization, code quality, readability, duplication, maintainability, and security.

Use when adding a new LLM call to a service, or wiring an existing service to the company LiteLLM proxy so its calls get logged to ClickHouse. Triggers when the user mentions calling Claude/GPT/an LLM, "instrument" or "add observability" to LLM calls, switching from a direct provider SDK to the proxy, or asks how to send tags. Don't use this for general LLM-coding questions unrelated to our proxy.

Use when the user asks a cost, usage, latency, or attribution question about LLM calls — e.g. "what did feature X cost last month", "spend by model", "p95 latency for our summarization endpoint", "which prompt version is most expensive", "how much did customer Y spend on Claude". Also use for debugging a specific past LLM call by request ID, or for offline evals against historical traffic. Queries the `litellm_logs` table in ClickHouse Cloud via the ClickHouse MCP.

Integrate Lemma AI observability tracing into a codebase. Use when adding Lemma tracing, fixing missing or malformed traces, adding tool calls, generations, trace handles, thread/user context, Vercel AI SDK, OpenAI Agents SDK, LangChain, LangGraph, Langfuse side-by-side installs, or debugging Lemma trace delivery and trace shape.

Integrate Lemma AI observability tracing into a codebase. Use when adding Lemma tracing, fixing missing or malformed traces, adding tool calls, generations, trace handles, thread/user context, Vercel AI SDK, OpenAI Agents SDK, LangChain, LangGraph, Langfuse side-by-side installs, or debugging Lemma trace delivery and trace shape.