@cursor/july 0.1.109 → 0.1.112

package/dist/docs/llms.txt

@@ -4,63 +4,40 @@
 
 ## Overview
 
-- [Agent SDK documentation](/docs/index.md): Build and run Cursor agents with tools, approvals, channels, and evals.
+- [Agent SDK](/docs/index.md): Build, test, and deploy agents as code on Cursor's agent harness.
 
 ## Getting started
 
-- [Building agents with agents](/docs/building-with-agents.md): Use the built-in skills to have a coding agent create, verify, and improve your agent.
-- [How the Agent SDK works](/docs/concepts.md): Understand projects, sessions, event streams, channels, and runtimes in plain language.
-- [Deployment](/docs/deployment.md): Deploy the Agent SDK with Cursor-managed hosting or on infrastructure you control.
-- [One FileSystem for every Agent SDK agent](/docs/design/filesystem.md)
-- [Replacing `runtime: "local" | "cloud"` with a code interface](/docs/design/runtime-abstraction.md)
-- [Evals](/docs/evals.md): Write defineEval cases that gate an agent's trajectory, run them with agent-sdk eval locally and in CI, and lock every kept improvement with a regression check.
-- [Hillclimbing](/docs/hillclimbing.md): Improve an agent one measured round at a time, with the hillclimb skill running the loop with you.
-- [Build your first PR reviewer](/docs/quickstart.md): Create an agent that reviews pull requests by complexity, approves safe changes, and handles GitHub webhook events.
-- [Scaffold an agent with Cursor](/docs/scaffolding-agents.md): Use the bundled create-agent skill to plan, build, and verify a new agent.
-- [Storage](/docs/storage.md): Point the Agent SDK's durable storage at a backend you own with defineStorage.
-- [Fix common agent problems](/docs/troubleshooting.md): Match what you see to a cause, then read a session trace when you need more detail.
+- [Build with a coding agent](/docs/building-with-agents.md): Delegate Agent SDK creation, capability work, verification, and measured improvement to a coding agent.
+- [Deployment](/docs/deployment.md): Deploy an Agent SDK project from Git with Cursor-managed hosting, or run one secure process on your own infrastructure.
+- [Evals](/docs/evals.md): Protect agent decisions with fixed inputs, trajectory assertions, and regression checks that run locally or in CI.
+- [Hillclimbing](/docs/hillclimbing.md): Improve one agent behavior at a time by measuring fixed inputs, changing one lever, and locking each win with an eval.
+- [Build a PR reviewer](/docs/quickstart.md): Create an agent that reviews pull requests by complexity, approves safe changes, and handles GitHub webhook events.
+- [Fix common agent problems](/docs/troubleshooting.md): Match the symptom to one corrective action, then inspect the session trace when the first fix is not enough.
 
 ## Templates
 
 - [Review pull requests with owners policies](/docs/templates/agentic-owners.md): Scaffold the agent, commit .agentic-owners policies, and let it risk-tier PRs, request the owners, and approve what the policy allows.
-- [Keep AGENTS.md current from last week's work](/docs/templates/agents-md.md): Scaffold the agent, pick a repo and Slack channels, dispatch the weekly job, and deploy.
-- [Keep a code wiki current after merge](/docs/templates/code-wiki.md): Scaffold the agent, pick repos, replay a merged PR, and deploy.
-- [Record a walkthrough from a collected PR](/docs/templates/demo.md): Scaffold the agent, seed the PR on the host, record a walkthrough, and comment the result.
-- [Talk to your Grok Bot agents](/docs/templates/grokbot-agents.md): Scaffold the agent, name the Grok Bot agents it may reach, and consult them from its own conversation.
 - [Fix pull requests on a Cursor cloud VM](/docs/templates/pr-autofixer.md): Scaffold the agent, point it at your repos, and opt in to auto-fix a PR.
-- [Answer security questions in Slack](/docs/templates/security-help.md): Scaffold the agent, connect Slack, and answer from your skills. Paste a GitHub pull request for a first look.
 - [Review pull requests for exploitable bugs](/docs/templates/security-reviewer.md): Scaffold the agent, pick repos, replay a PR, and deploy.
+- [Review pull requests for structural code quality](/docs/templates/thermo-quality-review.md): Scaffold the agent, deploy it, and open a PR.
+- [Review pull requests for bugs and breakage](/docs/templates/thermo-review.md): Scaffold the agent, deploy it, and open a PR.
 - [Triage Linear or Jira issues in place](/docs/templates/triage.md): Scaffold the agent, point it at an existing ticket, tune the rubric, run evals, and deploy.
 
 ## Guides
 
-- [Agent-to-agent](/docs/guides/agent-to-agent.md): Every agent is an MCP server. Peer MCP connections let one agent delegate to another that keeps its own tools, sessions, and context.
-- [Bitbucket](/docs/guides/bitbucket.md): Wake your agent from pull requests, comments, and pushes on Bitbucket Cloud or Bitbucket Data Center.
-- [Cursor cloud agents](/docs/guides/cloud-agents.md): Let an agent-sdk agent hand coding work to Cursor cloud agents and steer them: mount the extension, pick the repositories it may touch, and decide what needs approval.
-- [Convert a Cursor Automation](/docs/guides/convert-automation.md): Export a dashboard Automation into a local Agent SDK project, then review, validate, and run it.
-- [GitHub](/docs/guides/github.md): Wake your agent from pull requests, CI, and comments by pulling Cursor SCM events, with fixtures and replay for local tests.
-- [GitLab](/docs/guides/gitlab.md): Wake your agent from GitLab merge requests, notes, pipelines, and pushes on GitLab.com or self-managed GitLab.
-- [Cursor Grok Bot agents](/docs/guides/grokbot-agents.md): Let an agent-sdk agent talk to your Grok Bot agents: mount the extension, name the bots it may reach, and decide what needs approval.
-- [Human-in-the-loop](/docs/guides/human-in-the-loop.md): Gate a tool call on human approval: park it, resolve it from the playground, HTTP, or Slack, and keep the turn alive throughout.
-- [Self-improvement](/docs/guides/improve.md): Mount improve so an agent can change its own instructions, skills, and tools through a pull request a one-off cloud agent opens.
-- [Host MCP OAuth](/docs/guides/mcp-oauth.md): Authorize defineConnection({ url, oauth: true }) with agent-sdk mcp oauth, store tokens locally, and push MCP_OAUTH_* secrets to hosted deployments.
-- [OpenTelemetry](/docs/guides/opentelemetry.md): Push session, turn, and tool traces from the serve process to an OTLP collector you run.
-- [Slack](/docs/guides/slack.md): Run a Socket Mode Slack bot from the dashboard wizard, or import an app you own.
-- [Webhooks & custom channels](/docs/guides/webhooks.md): Give the agent its own HTTP surface: validated routes, sessions keyed to your domain, and replies delivered back out.
-
-## Skills
-
-- [Create an Agent SDK agent](/docs/skills/create-agent.md): Scaffold a new Agent SDK agent: short AskQuestion interview, then verify a turn and hand off to hillclimb. Use when creating a new agent. Ask only what the invoking message left open.
-- [Debugging the Agent SDK locally](/docs/skills/debug.md): Diagnose a misbehaving local Agent SDK agent: blank playground, missing sessions, failed reads, webhook 401s, 403/409, lost approvals. Use when a project runs but behaves wrong locally.
-- [Deploy an Agent SDK agent](/docs/skills/deploy.md): Deploy or redeploy an Agent SDK project to Cursor-managed hosting with an attached service account. Use when asked to deploy, redeploy, publish, or update a hosted Agent SDK agent.
-- [Agent SDK evals](/docs/skills/evals.md): Author and run defineEval cases. Use when writing, fixing, seeding, or hillclimbing evals. Ask whether to generate samples or take uploaded data. Materialize API-backed fixtures first.
-- [Agent SDK framework map](/docs/skills/framework-map.md): Orient on Agent SDK layout, local vs cloud runtime, sessions, and invariants (Node not Bun, root evals/, typecheck after tsx). Use when creating, editing, or running a project with agent/agent.ts.
-- [GitHub channels in the Agent SDK](/docs/skills/github.md): Build and test GitHub-driven Agent SDK agents: githubChannel hooks (auth turn vs host task), cursorAccount / --cursor-events, and local test tiers (fixtures, replay, forward). Use when wiring GitHub events or debugging delivery.
-- [Agent SDK hillclimb](/docs/skills/hillclimb.md): Improve one existing Agent SDK agent: pin fixtures, measure, change one lever, remeasure, lock the win with an eval. Use when an agent already runs and needs better results.
-- [Coding-agent skills](/docs/skills/index.md): Task guides that ship with the Agent SDK for scaffolding, deployment, evals, channels, and hillclimbing.
-- [Host MCP OAuth](/docs/skills/mcp-auth.md): Authorize host MCP OAuth for defineConnection({ url, oauth: true }): agent-sdk mcp oauth, local tokens, --store, advertiseTools, egress. Use when wiring or debugging MCP auth.
-- [Agent SDK OpenTelemetry (`defineOtel`)](/docs/skills/otel.md): Wire OpenTelemetry export (defineOtel, OTLP env, traces/metrics/logs, ctx.host.otel). Use when adding collector export or custom metrics.
-- [Setup Slack for the Agent SDK](/docs/skills/setup-slack.md): Wire Slack to an Agent SDK agent. Mint a dedicated Socket Mode app with slack create, then doctor and smoke. Use slack init --manual only when the user owns the Slack app. Use when adding Slack.
+- [Agent-to-agent](/docs/guides/agent-to-agent.md): Let one Agent SDK agent consult an independent specialist, continue its session, or call its deterministic tools.
+- [Bitbucket](/docs/guides/bitbucket.md): Review pull requests, answer comments, and triage pushes on Bitbucket Cloud or Data Center.
+- [Cursor cloud agents](/docs/guides/cloud-agents.md): Mount an extension that lets your agent delegate repository work, inspect the result, and steer or stop the cloud agent.
+- [Convert a Cursor Automation](/docs/guides/convert-automation.md): Turn a dashboard Automation into an Agent SDK project, then reconnect its actions and triggers.
+- [GitHub](/docs/guides/github.md): Let your agent read pull requests and CI, then write back reviews, comments, and checks.
+- [GitLab](/docs/guides/gitlab.md): Review merge requests, answer notes, and triage failed pipelines on GitLab.com or self-managed GitLab.
+- [Cursor Grok Bot agents](/docs/guides/grokbot-agents.md): Mount an extension that lets your agent consult named Grok Bot agents, wait for long replies, and interrupt work.
+- [Self-improvement](/docs/guides/improve.md): Let an agent propose a change to its own source through a branch and pull request, with review and deployment kept separate.
+- [Host MCP OAuth](/docs/guides/mcp-oauth.md): Authorize a private MCP server locally, constrain its tools, and carry its credentials onto a hosted agent.
+- [OpenTelemetry](/docs/guides/opentelemetry.md): Send agent traces and metrics to an OTLP collector, follow one conversation, and add domain telemetry.
+- [Slack](/docs/guides/slack.md): Wake your agent from mentions, DMs, and watched posts, then reply in the thread.
+- [Webhooks & custom channels](/docs/guides/webhooks.md): Receive provider events, keep one conversation per domain object, and deliver agent replies back out.
 
 ## Reference
 
@@ -69,14 +46,14 @@
 - [Channels](/docs/reference/channels.md): The authoring reference for defineChannel, the built-in HTTP channel, route schemas, handler args, and the auth policies.
 - [CLI](/docs/reference/cli.md): Commands and common flags for local development, running servers, and Cursor-managed hosting.
 - [MCP Connections](/docs/reference/connections.md): Pull in tools from MCP servers: remote, stdio, the signed-in Cursor account's connectors, and peer agents.
-- [Extensions](/docs/reference/extensions.md): Mount a package of agent contributions or a Cursor plugin under a namespace with one file, adjust what it contributes, and author your own as a directory laid out like agent/.
+- [Evals](/docs/reference/evals.md): Reference for eval discovery, cases, assertions, judges, configuration, fixtures, reporters, and runner output.
+- [Extensions](/docs/reference/extensions.md): Mount a namespaced package of tools, skills, connections, and other agent capabilities, then inspect or override what it adds.
 - [Hooks](/docs/reference/hooks.md): Observe-only subscribers to the session event stream: audit logs, metrics, transcript mirrors, derived state.
 - [HTTP API](/docs/reference/http-api.md): Public session, discovery, and channel routes callers use.
 - [Instructions](/docs/reference/instructions.md): The always-on system prompt: authoring forms, how it reaches the model on each runtime, and what makes instructions hold up.
 - [Playground](/docs/reference/playground.md): The built-in web UI: chat with streaming, Try buttons and slash commands, session replay, approvals, and dev-mode dispatch.
 - [Project layout](/docs/reference/project-layout.md): The folder structure under agent/ and the path-derived naming rule.
 - [prompt](/docs/reference/prompt.md): Dedented multi-line strings for tool descriptions, reminder prompts, channel context, and errors.
-- [Turn result](/docs/reference/result.md): Run host code on the final assistant text when a turn finishes. Throw to fail the turn.
 - [Schedules & reminders](/docs/reference/schedules.md): Cron-driven runs defined at deploy time, and per-session durable wakes created at runtime.
 - [Sessions, events, and streaming](/docs/reference/sessions.md): Understand how conversations continue, how events stream, and where session data lives.
 - [Skills](/docs/reference/skills.md): On-demand procedures the model loads only when relevant, in three authoring forms.