> ## Documentation Index > Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details. # Overview > Read what a coding agent session did and what it cost. Walk one session's events call by call, with the tokens, cost and compactions of each, or roll a whole pull request up into sessions, tokens and cost per project, user and agent. ## Endpoints * [List coding agent session events](/docs/api-reference/coding-agents/list-coding-agent-session-events): every model call, compaction, rate limit and tool run of one session, in time order, with input, output, cache-read and cache-creation tokens, cost, duration and model per row. * [Get pull request coding agent usage](/docs/api-reference/coding-agents/get-pull-request-coding-agent-usage): the rollup of everything spent on a pull request over its lifetime, split by project, user and agent. Both authenticate with a project API key and read under the project's [data privacy policy](/docs/ai-governance/data-privacy): an API key resolves as a public viewer, so it reads what the policy captures and never what it restricts or drops. The same data renders in the product on the [sessions](/docs/coding-agents/sessions) and [pull requests](/docs/coding-agents/pull-requests) views, and over the command line as `langwatch session events ` and `langwatch trace transcript `.