@cursor/july 0.1.10 → 0.1.12

package/docs/reference/cli.md

@@ -43,6 +43,7 @@ also provide `agentkit slack help` and `agentkit github help`.
 | [`rotate-token`](#rotate-token)                         | Replace a deployment's alias token                             |
 | [`rotate-pod-credential`](#rotate-pod-credential)       | Replace a deployment's pod credential                          |
 | [`secrets`](#secrets)                                   | Manage deployment secrets                                      |
+| [`mcp oauth`](#mcp-oauth)                               | Authorize host MCP OAuth; optional `--store` to deployment secrets |
 | [`slack ...`](#slack)                                   | Set up and check Slack channels                                |
 | [`github ...`](#github)                                 | Forward, replay, and inspect GitHub webhook channels           |
 
@@ -560,6 +561,33 @@ The command returns only the masked key and revokes the old credential
 immediately. Redeploy at once to inject the replacement; the current
 pod can't authenticate to Cursor in between.
 
+## mcp oauth
+
+`mcp oauth` authorizes a `defineConnection({ url, oauth: true })`
+connection with a browser PKCE flow. Tokens are written to
+`mcp-auth.json` under the agent-serve config dir (default
+`~/.config/agent-serve`). Pass `--store` to upsert matching
+`MCP_OAUTH_<CONNECTION>_*` secrets on the hosted deployment.
+
+```bash
+agentkit mcp oauth <connection> [--dir .] [--store] [--slug <slug>] [--team <id>]
+```
+
+`<connection>` is the `agent/mcp-connections/<connection>.ts` basename.
+`--slug` defaults to the `--dir` basename. `--team` defaults to the
+signed-in account's team. You need `agentkit login` (or `--api-key`)
+before `--store`.
+
+Secret names are `MCP_OAUTH_<NAME>_ACCESS_TOKEN`,
+`_REFRESH_TOKEN`, and `_CLIENT_ID` (`<NAME>` is the connection id in
+upper snake case). Declare them in `hosting.secretNames` so deploy
+validation expects them. Secrets apply on the next deploy.
+
+Tokens are bound to the connection's resource URL. Changing the URL
+invalidates the local entry; run `mcp oauth` again.
+
+See the [Host MCP OAuth guide](../guides/mcp-oauth.md).
+
 ## secrets
 
 `secrets` manages environment secrets for a deployment.

package/docs/reference/connections.md

@@ -27,6 +27,33 @@ export default defineConnection({
 
 Tokens come from env vars. Never hardcode them in the file.
 
+## Host MCP OAuth
+
+For servers that speak OAuth, set `oauth: true` and authorize with the
+CLI. Tokens live in `~/.config/agent-serve/mcp-auth.json`. `--store`
+copies them onto the hosted deployment as `MCP_OAUTH_<NAME>_*` secrets.
+
+```ts
+export default defineConnection({
+  url: "https://mcp.example.com/inventory",
+  oauth: true,
+  hostOnly: true, // model cannot call; host.mcp still can
+});
+```
+
+```bash
+agentkit mcp oauth inventory           # browser PKCE → local mcp-auth.json
+agentkit mcp oauth inventory --store   # also upsert deployment secrets
+```
+
+Full walkthrough: [Host MCP OAuth](../guides/mcp-oauth.md). Companion
+skill: [`skills/mcp-auth/SKILL.md`](../../skills/mcp-auth/SKILL.md).
+
+Use `hostOnly: true` when only deterministic host tools should call the
+server (deploys, admin APIs). Account MCP
+(`cursorAccount: true`) stays the right choice for connectors already
+linked in the Cursor dashboard.
+
 ## Local stdio MCP server
 
 Run a local MCP server as a child process with `command`.
@@ -134,6 +161,7 @@ lazily on first use.
 
 Continue with these pages:
 
+- [Host MCP OAuth](../guides/mcp-oauth.md): `mcp oauth`, `--store`, `hostOnly`
 - [Agent-to-agent](../guides/agent-to-agent.md): peers in depth
 - [Tools](./tools.md): authored tools that wrap MCP connections
 - [Webhooks](../guides/webhooks.md): calling MCP connections from handlers

package/docs/reference/prompt.md

@@ -0,0 +1,47 @@
+---
+title: "prompt"
+description: "Dedented multi-line strings for tool descriptions, reminder prompts, channel context, and errors."
+---
+
+# `prompt`
+
+Authoring helper for long strings that live next to indented TypeScript:
+tool descriptions, reminder `prompt` fields, GitHub channel `context`,
+and error messages.
+
+```ts
+import { prompt } from "@cursor/july";
+// or: import { prompt } from "@cursor/july/prompt";
+```
+
+## `prompt\`…\``
+
+Returns a single dedented string. Common leading whitespace is stripped;
+a leading newline after the opening backtick is dropped so the usual
+multiline form stays readable in source.
+
+```ts
+throw new Error(prompt`
+  It is outside business hours (Mon–Fri 9am–5pm ET).
+  Use request_author_approval, or pass approval=human_request.
+`);
+```
+
+Blank lines inside the body are preserved. Relative indentation after the
+common prefix is kept (handy for nested bullet lists).
+
+When interpolating multi-line values (for example a list of services), give
+those lines the same indent as the `prompt` body so dedent stays consistent.
+
+## `prompt.lines\`…\``
+
+Same dedent rules, but returns `string[]` — one entry per line. Use this
+where an API wants separate lines (for example GitHub channel `context`):
+
+```ts
+context: prompt.lines`
+  Merged PR detected: ${pr.url} by ${author}.
+
+  Call plan_deploy, then follow its nextStep.
+`
+```

package/docs/reference/tools.md

@@ -39,6 +39,27 @@ code that runs it. With a Zod `inputSchema`, the input is validated before
 `execute` runs and the input type is inferred. A plain JSON Schema
 object is forwarded as-is and the input arrives as raw JSON.
 
+For multi-line descriptions, reminder prompts, and error messages, use
+[`prompt`](./prompt.md) so the string can sit indented with the surrounding
+TypeScript:
+
+```ts
+import { prompt } from "@cursor/july";
+import { defineTool } from "@cursor/july/tools";
+import { z } from "zod";
+
+export default defineTool({
+  description: prompt`
+    Inspect a pull request before approval.
+    Prefer this over guessing from the title alone.
+  `,
+  inputSchema: z.object({ prUrl: z.string().url() }),
+  async execute({ prUrl }) {
+    return { prUrl };
+  },
+});
+```
+
 ### The `ctx` parameter
 
 `execute` receives a `ctx` with the runtime accessors:

package/docs/troubleshooting.md

@@ -63,6 +63,17 @@ Match your symptom below. Keep the commands as `agentkit`; see
 | The bot ignores ordinary channel posts | Default engagement is mentions and DMs only. Enable `engagement.channelPosts` with an allowlist, and subscribe the app to `message.channels` / `message.groups`. |
 | Approve / Deny buttons do nothing | Re-import a Slack app manifest with interactivity enabled. Channels that post approval cards need `toolApprovals: true` (and `interactivity: true` when you compose events by hand). |
 
+## What if host MCP OAuth fails?
+
+| What you see | What to do |
+| --- | --- |
+| `must be defineConnection({ url, oauth: true })` | The connection file needs `oauth: true`, or you passed the wrong connection name to `agentkit mcp oauth`. |
+| Local auth works; hosted calls unauthorized | Run `agentkit mcp oauth <name> --store`, confirm names with `agentkit secrets list <slug>`, then redeploy. |
+| Model asks for `mcp_auth` or IDE MCP for a privileged server | That connection is likely `hostOnly`. Call it from a host tool via `ctx.host.mcp`, and update instructions. |
+
+See [Host MCP OAuth](./guides/mcp-oauth.md) and
+[`skills/mcp-auth/SKILL.md`](../skills/mcp-auth/SKILL.md).
+
 ## What if schedules, reminders, or approvals stall?
 
 | What you see | What to do |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cursor/july",
-  "version": "0.1.10",
+  "version": "0.1.12",
   "description": "(early alpha) Filesystem-first framework for defining Cursor agents as markdown and TypeScript and serving them over channels with the Cursor SDK.",
   "license": "SEE LICENSE IN LICENSE.md",
   "repository": {
@@ -103,6 +103,13 @@
       "import": "./dist/hooks.js",
       "default": "./dist/hooks.js"
     },
+    "./prompt": {
+      "anysphere-source": "./src/prompt.ts",
+      "bun": "./src/prompt.ts",
+      "types": "./dist/prompt.d.ts",
+      "import": "./dist/prompt.js",
+      "default": "./dist/prompt.js"
+    },
     "./evals": {
       "anysphere-source": "./src/evals.ts",
       "bun": "./src/evals.ts",
@@ -213,4 +220,4 @@
     "vitest": "^4.0.18",
     "zustand": "^5.0.9"
   }
-}
+}

package/skills/create-agent/SKILL.md

@@ -15,8 +15,9 @@ Stand up one new agent project via a short interview, scaffold it, get
 channels working
 with the user, prove a turn runs end-to-end, and set up the improvement loop.
 Sibling skills: `framework-map` for orientation, `setup-slack` for Slack
-wiring, `github` for webhook-driven agents, `evals` for the eval API,
-`ab` for live A/B metrics, `hillclimb` for iteration once the agent runs.
+wiring, `mcp-auth` for host MCP OAuth, `github` for webhook-driven
+agents, `evals` for the eval API, `ab` for live A/B metrics, `hillclimb`
+for iteration once the agent runs.
 
 Read `framework-map/SKILL.md` first if you haven't; treat the package
 `AGENTS.md` and `README.md` as ground truth for
@@ -91,7 +92,10 @@ Defaults that make first cuts good:
 - **Tool per file**, filename = tool name the model sees. Prefer
   `execution: "server"` with a zod `inputSchema`; use `execution: "agent"`
   (script) only when the tool must run where the agent runs (or runtime is
-  cloud). Gate side-effecting tools with `needsApproval: true`.
+  cloud). Gate side-effecting tools with `needsApproval: true`. For long
+  tool descriptions, reminder prompts, channel `context`, and errors, use
+  `prompt\`…\`` / `prompt.lines\`…\`` from `@cursor/july` (dedents indented
+  multi-line strings).
 - **Env prefix** for Slack tokens = upper-snake slug (`my-agent` →
   `MY_AGENT_SLACK_*`); `agentkit slack init` derives it for you.
 - **Host prep beats model wandering:** when the purpose has a deterministic

package/skills/framework-map/SKILL.md

@@ -139,6 +139,7 @@ folder mounts every sibling agent too.
 - Live A/B metrics → `packages/agent-serve/skills/ab/SKILL.md`
 - GitHub webhooks → `packages/agent-serve/skills/github/SKILL.md`
 - Slack → `packages/agent-serve/skills/setup-slack/SKILL.md`
+- Host MCP OAuth → `packages/agent-serve/skills/mcp-auth/SKILL.md`
 - Local triage → `packages/agent-serve/skills/debug/SKILL.md`
 - Measured improvement → `packages/agent-serve/skills/hillclimb/SKILL.md`
 - Dogfood / deploy → `packages/agent-serve/skills/operate/SKILL.md`

package/skills/mcp-auth/SKILL.md

@@ -0,0 +1,138 @@
+---
+name: agentkit-mcp-auth
+description: >-
+  Authorize host MCP OAuth for defineConnection({ url, oauth: true }):
+  agentkit mcp oauth, local mcp-auth.json, --store deployment secrets,
+  hostOnly, and egress. Read when wiring or debugging MCP auth.
+---
+
+# Host MCP OAuth (mcp auth)
+
+Use this skill when a human asks to authorize a remote MCP server on an
+agentkit host, store credentials for Cursor-managed hosting, or debug
+`host.mcp` auth failures for `oauth: true` connections.
+
+Sibling skills: `framework-map` for layout, `create-agent` when scaffolding,
+`debug` for unrelated local failures, `operate` for deploy/secrets ops.
+
+Docs: `docs/guides/mcp-oauth.md`, `docs/reference/connections.md`,
+`docs/reference/cli.md#mcp-oauth`.
+
+## When to use host OAuth vs account MCP
+
+| Need | Use |
+| --- | --- |
+| Connector already in Cursor dashboard (Linear, Notion, …) | `defineConnection({ cursorAccount: true, servers: […] })` |
+| Remote URL that speaks OAuth; host must hold tokens | `defineConnection({ url, oauth: true })` + this skill |
+| Static bearer / API key | `headers` / env on a plain `{ url }` connection |
+
+Prefer `hostOnly: true` when only host tools / channel handlers should
+call the server (admin APIs, privileged writes). The model will not see
+those tools.
+
+## Goal checklist
+
+- [ ] `agent/mcp-connections/<name>.ts` with `url` + `oauth: true` (+ `hostOnly` if privileged)
+- [ ] `hosting.secretNames` lists `MCP_OAUTH_<NAME>_{ACCESS_TOKEN,REFRESH_TOKEN,CLIENT_ID}` when you will `--store`
+- [ ] Hosted engines that reach non-bootstrap hosts declare `hosting.egressDomains`
+- [ ] Local: `agentkit mcp oauth <name>` succeeds
+- [ ] Hosted: `agentkit mcp oauth <name> --store` then redeploy; `secrets list` shows the names
+
+## Phase 0 — Author the connection (agent)
+
+```ts
+// agent/mcp-connections/inventory.ts
+import { defineConnection } from "@cursor/july/connections";
+
+export default defineConnection({
+  url: "https://mcp.example.com/inventory",
+  oauth: true,
+  hostOnly: true,
+  description: "Privileged inventory MCP; call via ctx.host.mcp only.",
+});
+```
+
+In `agent/agent.ts`:
+
+```ts
+hosting: {
+  egressDomains: ["mcp.example.com"], // if hosted + non-bootstrap host
+  secretNames: [
+    "MCP_OAUTH_INVENTORY_ACCESS_TOKEN",
+    "MCP_OAUTH_INVENTORY_REFRESH_TOKEN",
+    "MCP_OAUTH_INVENTORY_CLIENT_ID",
+  ],
+},
+```
+
+Naming: connection file `inventory.ts` → env prefix `MCP_OAUTH_INVENTORY`.
+Do **not** put `CURSOR_*` or hosted-storage names in `secretNames`.
+
+Wire privileged calls through host tools:
+
+```ts
+await ctx.host.mcp.callTool("inventory", "list_warehouses", {
+  region: input.region,
+});
+```
+
+Update instructions so the model does not hunt IDE MCP namespaces or
+`mcp_auth` for `hostOnly` servers.
+
+## Phase 1 — Local authorize (agent + human)
+
+```bash
+cd <agent-project>
+agentkit mcp oauth <connection>
+```
+
+Human completes the browser login. Callback:
+`http://localhost:8787/callback`. Tokens:
+`~/.config/agent-serve/mcp-auth.json` (or `$AGENT_SERVE_CONFIG_DIR`).
+
+Already authorized → command prints that and exits 0. URL change →
+re-run; resource URL binding drops the old entry.
+
+## Phase 2 — Store on the deployment (agent + human)
+
+Requires `agentkit login` (or `CURSOR_API_KEY`) and deploy rights.
+
+```bash
+agentkit mcp oauth <connection> --store [--slug <slug>] [--team <id>]
+agentkit secrets list <slug>
+agentkit deploy   # or your usual deploy; secrets apply next deploy
+```
+
+`--store` upserts access (required), refresh (if present), and client id
+(if present). It does not remove unrelated secrets.
+
+## Phase 3 — Verify (agent)
+
+Local:
+
+```bash
+agentkit validate --dir .
+agentkit call <tool-that-uses-host.mcp> --dir .
+# or exercise the same path from the playground
+```
+
+Hosted: confirm egress allowlist includes the MCP host, secrets exist,
+redeploy completed, then exercise the same host tool once.
+
+## Failure table
+
+| Symptom | Fix |
+| --- | --- |
+| `must be defineConnection({ url, oauth: true })` | Wrong connection name, or missing `oauth: true` |
+| `Unknown MCP connection` | Filename under `agent/mcp-connections/` must match CLI arg |
+| Callback hang | Free port 8787; finish browser flow on this machine |
+| Hosted 401 / unauthorized | `secrets list`; re-run `--store`; redeploy |
+| Model invents `mcp_auth` / IDE MCP | Connection is `hostOnly`; fix instructions + use host tools |
+| Tokens ignored after URL edit | Expected; run `mcp oauth` again for the new resource URL |
+
+## Don't
+
+- Don't put raw OAuth tokens in git or in connection source files
+- Don't add `BUGBOTDB_URL` / `AGENT_SERVE_DEPLOYMENT_ID` to `secretNames`
+- Don't use Bun for the CLI (use Node / `tsx`)
+- Don't expect `--store` alone to restart a running engine; redeploy

package/src/bin/agent-serve.ts

@@ -51,7 +51,10 @@ import {
   cmdStop,
   type DeployCliOptions,
 } from "../internal/cli-deploy.js";
-import { CLI_COMMAND_NAME as CLI } from "../internal/distribution.js";
+import {
+  CLI_COMMAND_NAME as CLI,
+  packageVersion,
+} from "../internal/distribution.js";
 import { clearTerminal, stdoutPalette } from "../internal/terminal-style.js";
 import { cmdUpdate, warnIfOutdated } from "../internal/update-check.js";
 import type { AgentProject, AgentServeHandle } from "../types.js";
@@ -93,6 +96,7 @@ Usage:
                           | --url <baseUrl> [--bearer-token <t>]
   ${CLI} mcp install [--name <serverName>] [--print] [--json]
                           (same target flags as mcp)
+  ${CLI} mcp oauth   <connection> [--dir <path>] [--store] [--slug <slug>]
   ${CLI} eval        [--dir <path>] [evalId...] [--list] [--json]
                           [--tag <tag>]... [--verbose] [--timeout-ms <n>]
                           [--no-stream] [--no-wait]
@@ -106,6 +110,7 @@ Usage:
   ${CLI} logout
   ${CLI} whoami      [--json]
   ${CLI} update
+  ${CLI} version
   ${CLI} deploy      [--dir <path>] [--slug <slug> | --all] [--team <id>] [--json]
                           [--no-wait] [--repo <url>] [--ref <ref>]
                           [--path <agentPath>] [--cursor-events-repo <owner/name>]...
@@ -170,7 +175,9 @@ Commands:
               --url targets a running server. stdout is reserved for the
               MCP wire. \`mcp install\` writes the matching entry into
               ~/.cursor/mcp.json (--print to preview; --name to override
-              the server name).
+              the server name). \`mcp oauth <connection>\` runs host PKCE
+              for defineConnection({ url, oauth: true }); \`--store\` upserts
+              MCP_OAUTH_<NAME>_* secrets on the hosted deployment.
   eval        Run filesystem evals under evals/**/*.eval.ts (streams on a TTY).
               Default: ephemeral local harness against evals on disk. Pass
               --prod to kick off the batch on the team's hosted deployment
@@ -194,6 +201,7 @@ Commands:
   whoami      Show which Cursor account powers this host (and why).
   update      Upgrade this install to the latest published version (detects
               global npm/pnpm/yarn/bun installs and project dependencies).
+  version     Print the installed ${CLI} version and exit (also --version / -V).
   deploy      Deploy onto Cursor's managed agent-serve hosting, then wait for
               the engine to come up. --repo/--ref/--path stay available;
               inside an agent git checkout they are inferred when omitted
@@ -224,6 +232,7 @@ Agent loop:
   ${CLI} dev .
 
 Options:
+  --version, -V      Print the installed version and exit.
   --dir             Project root (defaults to the current directory).
   --port             Port to listen on (default 3000).
   --host             Host to bind (default 127.0.0.1).
@@ -354,6 +363,10 @@ async function main(argv: string[]): Promise<number> {
     process.stdout.write(HELP);
     return command === undefined ? 1 : 0;
   }
+  if (command === "version" || command === "--version" || command === "-V") {
+    process.stdout.write(`${CLI} ${packageVersion()}\n`);
+    return 0;
+  }
 
   // `session --events` means "dump raw events" (boolean). Rewrite so it does
   // not collide with run/trajectory's `--events <file.ndjson>` string flag.
@@ -409,6 +422,7 @@ async function main(argv: string[]): Promise<number> {
       "mount-path": { type: "string" },
       "base-url": { type: "string" },
       print: { type: "boolean", default: false },
+      store: { type: "boolean", default: false },
       transport: { type: "string" },
       prefix: { type: "string" },
       "no-prefix": { type: "boolean", default: false },
@@ -508,7 +522,8 @@ async function main(argv: string[]): Promise<number> {
 
     case "mcp": {
       const { cmdMcp } = await import("../internal/cli-mcp.js");
-      return cmdMcp(positionals[0], {
+      const mcpSub = positionals[0];
+      return cmdMcp(mcpSub, {
         dir,
         slug: values.slug,
         team: values.team,
@@ -519,6 +534,8 @@ async function main(argv: string[]): Promise<number> {
         name: values.name,
         print: values.print,
         json: values.json,
+        store: values.store,
+        oauthConnection: mcpSub === "oauth" ? positionals[1] : undefined,
       });
     }
 

package/src/channels/github/github-channel.ts

@@ -116,6 +116,7 @@ const githubPullRequestPayloadSchema: z.ZodType<GitHubPullRequestPayload> =
       title: z.string(),
       body: z.string().nullable().optional(),
       draft: z.boolean().optional(),
+      merged: z.boolean().optional(),
       user: z
         .object({
           login: z.string().min(1).optional(),
@@ -330,6 +331,7 @@ export function parseGitHubPullRequestEvent(args: {
       ? {}
       : { baseSha: payload.pull_request.base.sha }),
     draft: payload.pull_request.draft ?? false,
+    merged: payload.pull_request.merged === true,
     ...(payload.pull_request.user?.login === undefined
       ? {}
       : { authorLogin: payload.pull_request.user.login }),

package/src/channels/github/types.ts

@@ -148,6 +148,8 @@ export type GitHubPullRequestPayload = {
     title: string;
     body?: string | null;
     draft?: boolean;
+    /** Present on real webhook payloads; false/undefined when not merged. */
+    merged?: boolean;
     user?: {
       login?: string;
       id?: number;
@@ -182,6 +184,8 @@ export interface GitHubPullRequestEvent {
   baseRef: string;
   baseSha?: string;
   draft: boolean;
+  /** True when the PR was merged (from the webhook payload). */
+  merged: boolean;
   authorLogin?: string;
 }
 

package/src/channels/slack/cursor-account.ts

@@ -167,6 +167,8 @@ export async function dispatchCursorSlackEnvelope(args: {
     credentials: runtime.credentials,
     host: args.host,
     log,
+    evalCommandsEnabled: runtime.options.evalCommands !== false,
+    cursorAgentName: envelope.agentName,
     ...(args.hasContinuationSession === undefined
       ? {}
       : { hasContinuationSession: args.hasContinuationSession }),

package/src/channels/slack/dispatch.ts

@@ -6,6 +6,10 @@ import type { HostContext, JsonValue, SendMessageFn } from "../../types.js";
 import { buildSlackBinding, slackContinuationKey } from "./api.js";
 import { firstLineTitle, maybeSetThreadTitle } from "./assistant.js";
 import type { ChannelPostWatcher } from "./channel-watch.js";
+import {
+  handleSlackEvalDirective,
+  parseSlackEvalDirective,
+} from "./eval-directive.js";
 import type { EventIdDedupe } from "./event-id-dedupe.js";
 import {
   formatSlackContextBlock,
@@ -82,6 +86,13 @@ export interface SlackInboundDispatchDeps {
   ) => Promise<string | undefined>;
   /** Cancel the active turn + clear coalesced nudges for this continuation. */
   interruptContinuation?: (continuationToken: string) => Promise<boolean>;
+  /**
+   * When false, skip the built-in `eval` directive. Defaults to true when
+   * `host.evals` is present.
+   */
+  evalCommandsEnabled?: boolean;
+  /** cursorAccount agent name stripped before `eval` directive parsing. */
+  cursorAgentName?: string;
 }
 
 function triggeringMergeMessage(
@@ -114,6 +125,12 @@ export async function dispatchInboundMessage(args: {
   interruptContinuation?: (continuationToken: string) => Promise<boolean>;
   log?: SlackLog;
   eventId?: string;
+  evalCommandsEnabled?: boolean;
+  /**
+   * cursorAccount agent display name — stripped before parsing `eval …`
+   * (`OncallBuddy eval list`).
+   */
+  cursorAgentName?: string;
 }): Promise<void> {
   const { message, kind } = args;
   const log = args.log ?? defaultSlackLog;
@@ -168,6 +185,34 @@ export async function dispatchInboundMessage(args: {
     return;
   }
 
+  // Built-in eval directive: run playground batches without an agent turn.
+  const evalCommandsEnabled = args.evalCommandsEnabled !== false;
+  const evalParseOptions =
+    args.cursorAgentName === undefined || args.cursorAgentName === ""
+      ? undefined
+      : { agentName: args.cursorAgentName };
+  const evalDirective =
+    evalCommandsEnabled && args.host.evals !== undefined
+      ? (parseSlackEvalDirective(message.text, evalParseOptions) ??
+        parseSlackEvalDirective(message.markdown, evalParseOptions))
+      : null;
+  if (evalDirective !== null && args.host.evals !== undefined) {
+    log.info("eval directive", {
+      kind,
+      channel: message.channelId,
+      thread_ts: message.threadTs,
+      continuation,
+      event_id: args.eventId,
+      directive: evalDirective.kind,
+    });
+    await handleSlackEvalDirective({
+      directive: evalDirective,
+      evals: args.host.evals,
+      binding,
+    });
+    return;
+  }
+
   if (message.ts === message.threadTs) {
     await maybeSetThreadTitle({
       botToken: args.credentials?.botToken,
@@ -393,6 +438,8 @@ export function dispatchInboundFromEventBody(
         credentials: deps.credentials,
         host: deps.host,
         log,
+        evalCommandsEnabled: deps.evalCommandsEnabled,
+        cursorAgentName: deps.cursorAgentName,
         ...(deps.hasContinuationSession === undefined
           ? {}
           : { hasContinuationSession: deps.hasContinuationSession }),
@@ -431,6 +478,8 @@ export function dispatchInboundFromEventBody(
         credentials: deps.credentials,
         host: deps.host,
         log,
+        evalCommandsEnabled: deps.evalCommandsEnabled,
+        cursorAgentName: deps.cursorAgentName,
         ...(deps.hasContinuationSession === undefined
           ? {}
           : { hasContinuationSession: deps.hasContinuationSession }),