@cursor/july 0.1.89 → 0.1.91

package/docs/reference/tools.md

@@ -100,6 +100,55 @@ typecheck will.
 Throwing inside `execute` reports an error result to the model
 (`isError: true`). The turn and the server keep running.
 
+### Declare structured output
+
+Set `outputSchema` when MCP clients need a structured result contract. Use a
+Zod schema or plain JSON Schema:
+
+```ts
+const Weather = z.object({
+  city: z.string(),
+  temperatureF: z.number(),
+});
+
+export default defineTool({
+  description: "Read the current weather.",
+  inputSchema: z.object({ city: z.string() }),
+  outputSchema: Weather,
+  async execute({ city }) {
+    return { city, temperatureF: 72 };
+  },
+});
+```
+
+The Agent SDK advertises the schema. It does not validate tool results against
+it. Plain object returns fill MCP `structuredContent` automatically. An
+envelope return must set `structuredContent` next to `content` and `isError`.
+
+Use the exported `ToolInput<TSchema>` type when another function needs the
+input type inferred from a tool schema.
+
+### Control dry-run effects
+
+Set `effect` to `"read"`, `"write"`, or a predicate over validated input.
+A dry-run session executes reads and answers writes without running their
+tool bodies. An authored tool without `effect` is treated as a write.
+
+```ts
+export default defineTool({
+  description: "Publish a release.",
+  inputSchema: z.object({ version: z.string() }),
+  effect: "write",
+  dryRunResult: ({ version }) => ({ published: false, version }),
+  async execute({ version }) {
+    return publishRelease(version);
+  },
+});
+```
+
+`dryRunResult` keeps the result shape stable. Without it, a stubbed write
+returns `"Operation acknowledged."`. Traces mark the result as stubbed.
+
 ## Define an agent tool
 
 Set `execution: "agent"` and the tool materializes as a shell script
@@ -240,9 +289,8 @@ spoofed payload can't steer it.
 Test tools with `call` before blaming prompts. If the tool's output is
 wrong, no instruction change fixes it.
 
-And gate side effects: `needsApproval` for the calls that need a
-person's sign-off, and dry-run defaults flipped by an env var for
-anything destructive.
+Gate side effects with `needsApproval`. Declare each tool's `effect` so
+dry-run sessions can execute reads and stub writes.
 
 ## What's next
 

package/docs/scaffolding-agents.md

@@ -86,8 +86,10 @@ No files change before you approve this step.
 
 A first version usually includes:
 
+- `AGENTS.md`, `.gitignore`, `package.json`, and `tsconfig.json`
 - `agent/agent.ts` for the model and runtime
 - `agent/instructions.md` for the always-on prompt
+- `agent/hooks/memory.ts` for memory guidance
 - One or two tools under `agent/tools/`
 - Any channels or MCP connections you selected
 - `evals/evals.config.ts` and one smoke eval

package/docs/templates/triage.md

@@ -67,11 +67,9 @@ curl -X POST http://127.0.0.1:3000/triage-agent/v1/channels/queue/issue \
 `POST /v1/channels/queue/issue` accepts
 `{ identifier, title?, description? }` from the playground.
 
-Hosted Cursor aliases require `X-Agent-Alias-Token`, which Linear and
-Jira cannot send. For create webhooks, self-host, set
-`LINEAR_WEBHOOK_SECRET` or `JIRA_WEBHOOK_SECRET`, and POST the signed
-body to `/v1/channels/webhook`. The channel ACKs immediately and
-coalesces retries onto the same issue.
+For create webhooks, set `LINEAR_WEBHOOK_SECRET` or
+`JIRA_WEBHOOK_SECRET`. Point the provider at the deployed alias under
+`/v1/channels/webhook`. Signed events start or resume triage for that issue.
 
 `record_triage` comments on the issue in the continuation key, not
 whatever identifier the model copies out of the ticket body.

package/docs/troubleshooting.md

@@ -41,7 +41,7 @@ Match your symptom below. Keep the commands as `agent-sdk`; see
 
 | What you see | What to do |
 | --- | --- |
-| `409` on a follow-up message | Refresh the `continuationToken` (it rotates on each accepted follow-up), wait if the session is busy, or confirm the session is a chat session (task and schedule sessions are not followable). |
+| `409` on a follow-up message | Refresh the `continuationToken` or confirm the session is a chat session. Task sessions do not accept follow-ups. |
 | `409 session_busy` on `call --session` | Wait for the model turn to finish, or omit `--session` for a one-off call. |
 | `403` on stream or follow-up | Use the same auth identity that created the session. Off localhost, pass `--bearer-token` and send it on every request. |
 | Works on localhost; blocked through a tunnel or LAN | Default auth allows only direct loopback callers. Share the host with `--bearer-token <secret>` (or authored `bearerAuth`). Use `--allow-anonymous` only on a trusted private network. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cursor/july",
-  "version": "0.1.89",
+  "version": "0.1.91",
   "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": {
@@ -225,6 +225,7 @@
     "node": ">=22.13"
   },
   "dependencies": {
+    "@bazel/runfiles": "6.5.0",
     "@cursor/sdk": "1.0.28",
     "@modelcontextprotocol/sdk": "1.25.1",
     "@octokit/auth-app": "^7.2.0",

package/skills/create-agent/SKILL.md

@@ -59,11 +59,11 @@ questions, concrete options, the recommended option listed first and labeled
 
 | Question | Options | Guidance |
 | --- | --- | --- |
-| **Runtime** | `local` (default) · `cloud` | Local = Cursor SDK harness on this machine; server tools, skills, sandbox seeds, and tool approvals all work. Cloud = Cursor cloud agents; needs `cloud.repos`, no server tools/skills/sandbox seeds (instructions are prepended to the first prompt). Recommend local unless the purpose needs a repo checkout on a cloud VM. |
+| **Runtime** | `local` (default) · `cloud` | Local runs on this machine. Cloud runs on a Cursor cloud agent and needs `cloud.repos`. Server tools and skills work on both. Tool approvals and sandbox seeds are local only. Recommend local unless the purpose needs a cloud checkout. |
 | **Model** | `grok-4.5` with `effort=high`, `fast=true` (default) · Other model id | Effort and fast are params, not id suffixes: `{ id: "grok-4.5", params: [{ id: "effort", value: "high" }, { id: "fast", value: "true" }] }` — the SDK rejects suffix-style ids. |
 | **Channels** (multi) | playground + HTTP API only (always mounted) · Slack · GitHub webhooks · custom webhook · schedule (cron) | Slack has two connections: the Cursor-hosted connection (`cursorAccount: true` — zero Slack admin, recommended default) and a dedicated Socket Mode app (own bot user + one app/token pair per agent; needed for channel watching or approval buttons). When Slack is picked, resolve the connection with the Step 0 gate in `setup-slack/SKILL.md` — either fold its AskQuestion into this round or ask it before channel setup; default to Cursor-hosted when you cannot ask. GitHub verifies `X-Hub-Signature-256` when a secret is set. Discord/Teams packs do not exist yet — offer custom webhook instead. |
 | **MCP connections** (multi) | none · remote server (URL + header auth) · local stdio server · Cursor account connectors · Other | One file per server under `agent/mcp-connections/`; filename = server name. Do not name an account connection `cursor.ts` (collides with the IDE `cursor` namespace); use `account.ts`. Tokens via env vars, never hardcoded. Connections serve the model and host code (`ctx.host.mcp`). If the model should call them by name on local turns, set `advertiseTools: true`. Set `hostOnly: true` only when host tools call the server and the playground must not. |
-| **Capabilities** (multi) | server tools · agent tools (scripts) · skills · subagents · hooks · sandbox seed files · tool approvals (HITL) · evals (recommend) | Server tools, skills, sandbox seeds, approvals are local-runtime only. Agent tools (`execution: "agent"`) work on both runtimes. Always recommend at least one smoke eval. |
+| **Capabilities** (multi) | server tools · agent tools (scripts) · skills · subagents · hooks · sandbox seed files · tool approvals (HITL) · evals (recommend) | Always recommend at least one smoke eval. |
 
 Close the round with a one-screen plan — chosen options plus the file tree you
 intend to create — and a final gate: "Scaffold it" / "Adjust something". Only
@@ -144,9 +144,8 @@ agent-sdk init ./<slug>
 
 `init` writes `package.json` (with `typescript` dev deps and a
 `check` script), `tsconfig.json`, `AGENTS.md`, `.gitignore`, `agent/agent.ts`,
-`agent/instructions.md`, a demo `agent/tools/echo.ts`, and empty capability
-folders (`skills/`, `channels/`, `evals/`, …) each with a `.gitkeep`; existing
-files are left alone (`exist`) and missing ones are filled in. It then
+`agent/instructions.md`, a demo `agent/tools/echo.ts`, and
+`agent/hooks/memory.ts`. Existing files are left alone (`exist`). It then
 runs `npm install`, and when the host is unsigned runs `login` and waits
 before printing `cd` (when needed) and `agent-sdk dev`. Then shape it to the
 plan:
@@ -261,8 +260,8 @@ loop starts deterministic.
 
 - Interview → plan gate → scaffold → verify → channel setup → hillclimb
   handoff. Do not skip verification because the files "look right".
-- Fill blanks yourself; re-ask only when an answer contradicts the framework
-  (e.g. server tools on cloud runtime — `validate` warns about these).
+- Fill blanks yourself. Re-ask only when an answer contradicts the framework,
+  such as approval-gated tools on the cloud runtime.
 - Do not deploy, post to real Slack/GitHub surfaces beyond the smoke tests the
   user asked for, or commit without being asked.
 - Keep the first cut reviewable: if the plan grows past ~10 files, cut scope

package/skills/framework-map/SKILL.md

@@ -77,10 +77,11 @@ the serve host; `runtime: "cloud"` runs them on Cursor cloud agents
 
 | Capability | local | cloud |
 | --- | --- | --- |
-| Server tools (`execution: "server"`), approvals | yes | **no** |
+| Server tools (`execution: "server"`) | yes | yes on managed hosting; self-hosted needs `--public-url` |
+| Tool approvals | yes | no |
 | Agent tools (`execution: "agent"` scripts) | yes | yes |
-| Skills | yes | yes (Agent Store native discovery) |
-| sandbox seeds | yes | only if in the cloud repo |
+| Skills | yes | yes |
+| sandbox seeds | yes | no |
 | Instructions | `AGENTS.md` in session workspace | prepended to first prompt |
 | Checkout of a repo/PR | you arrange it | the VM carries it |
 
@@ -93,9 +94,8 @@ scale, use cloud and keep the host to routing, briefs, and bookkeeping.
 
 Two handles, two owners:
 
-- **continuationToken** — channel-owned conversation key. Same token =
-  same durable session (a Slack `channelId:threadTs`, a `pr:owner/repo#N`).
-  Rotates on each accepted HTTP follow-up; stale tokens get `409`.
+- **continuationToken:** credential for continuing a conversation. HTTP
+  follow-ups rotate it; stale tokens get `409`.
 - **sessionId** — runtime-owned handle for streaming/inspection
   (`GET /v1/session/:id/stream?startIndex=N`, durable NDJSON replay).
 

package/skills/setup-slack/SKILL.md

@@ -303,7 +303,7 @@ a mention), opt in explicitly:
 export default slackChannel({
   engagement: {
     channelPosts: {
-      allow: ["#issues-cursor-desktop"], // explicit allowlist; no wildcard exists
+      allow: ["#issues-cursor-desktop"], // use ["*"] for every joined channel
       posts: "top-level",       // default — thread replies never dispatch
       debounceMs: 15_000,       // optional: edits settle, deletes cancel
     },

package/src/ab.ts

@@ -14,7 +14,7 @@
  * sample/snapshot export lives on the `defineStorage` `abs` table.
  *
  * ```ts
- * import { defineAB, splitBySessionHash } from "@anysphere/agent-serve/ab";
+ * import { defineAB, splitBySessionHash } from "@cursor/july/ab";
  *
  * export default defineAB({
  *   name: "concise-instructions",

package/src/artifacts.ts

@@ -10,7 +10,7 @@
  *
  * ```ts
  * import { z } from "zod";
- * import { defineArtifacts } from "@anysphere/agent-serve/artifacts";
+ * import { defineArtifacts } from "@cursor/july/artifacts";
  *
  * export default defineArtifacts({
  *   kinds: {

package/src/bin/agent-serve.ts

@@ -61,6 +61,7 @@ import {
 import { cmdManifest } from "../internal/cli-manifest.js";
 import {
   CLI_COMMAND_NAME as CLI,
+  formatCliVersion,
   PACKAGE_NAME,
   packageVersion,
 } from "../internal/distribution.js";
@@ -135,7 +136,7 @@ Usage:
   ${CLI} logout
   ${CLI} whoami      [--json]
   ${CLI} update
-  ${CLI} version
+  ${CLI} version     [--json]
   ${CLI} deploy      [--dir <path>] [--slug <slug> | --all] [--team <id>] [--json]
                           [--no-wait] [--repo <url>] [--ref <ref>]
                           [--path <agentPath>] [--cursor-events-repo <owner/name>]...
@@ -205,7 +206,7 @@ Commands:
               prompt. --json is machine-readable and never blocks on
               login. No directory: print the setup guide.
   convert-automation
-              Export a Cursor Automation into an agentkit project. <url> is
+              Export a Cursor Automation into an agentsdk project. <url> is
               the dashboard URL (…/automations/<uuid> or
               …/custom-agents/<uuid>) or a bare uuid. Fetches the definition
               with your Cursor credentials, writes the converted files into
@@ -258,7 +259,9 @@ 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).
+  version     Print the ${PACKAGE_NAME} version this CLI will use and exit
+              (also --version / -V). Text is the version number; --json
+              prints { name, version, cli }.
   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
@@ -292,7 +295,7 @@ Agent loop:
   ${CLI} dev .
 
 Options:
-  --version, -V      Print the installed version and exit.
+  --version, -V      Print the version number and exit.
   --dir             Project root (defaults to the current directory).
   --port             Port to listen on (default 3000). When the default is
                      taken, serve tries the next free port and prints a notice.
@@ -400,7 +403,7 @@ Options:
   --skip-report      eval: ignore reporters from evals.config.ts / eval files.
   --no-stream        run/eval: silence live progress on stderr (JSON still prints).
   --json             JSON output (init/convert-automation/install-skills/
-                     info/chat/eval/logs/
+                     info/chat/eval/logs/version/
                      sessions/session/github; run defaults to JSON). logs:
                      NDJSON progress/log events. session: trajectory JSON
                      (not raw events).
@@ -474,7 +477,7 @@ async function main(argv: string[]): Promise<number> {
     return command === undefined ? 1 : 0;
   }
   if (command === "version" || command === "--version" || command === "-V") {
-    await writeStdout(`${CLI} ${packageVersion()}\n`);
+    await writeStdout(formatCliVersion({ json: restIn.includes("--json") }));
     return 0;
   }
 
@@ -574,9 +577,14 @@ async function main(argv: string[]): Promise<number> {
       "no-artifacts": { type: "boolean", default: false },
       "skip-report": { type: "boolean", default: false },
       "max-concurrency": { type: "string" },
+      version: { type: "boolean", short: "V", default: false },
     },
   });
   const dir = values.dir ?? ".";
+  if (values.version === true) {
+    await writeStdout(formatCliVersion({ json: values.json === true }));
+    return 0;
+  }
 
   // Best-effort, cached, and silent on failure. `update` does its own fresh
   // lookup, --json runs stay quiet for machine consumers, and `mcp` skips it
@@ -1301,8 +1309,14 @@ async function main(argv: string[]): Promise<number> {
         loadLocalEnv();
         // Model turns need a Cursor credential. Prompt login before listen
         // so the first playground turn does not fail with a late auth error.
+        // `--allow-anonymous` is the hosted trust boundary (alias token /
+        // freeze bake): skip the login gate so health can bind without a
+        // key. v1 hosted injects CURSOR_API_KEY at exec; freeze bind drops
+        // CURSOR_API_KEY / CURSOR_API_KEY_FILE onto the listening process.
+        // Self-hosted omit the flag and still fail-fast unsigned on a TTY-less host.
         const loginExit = await ensureCursorLogin({
           apiKey: values["api-key"],
+          allowAnonymous: values["allow-anonymous"] === true,
         });
         if (loginExit !== 0) {
           return { kind: "login-failed", exitCode: loginExit };

package/src/channels/slack/channel-watch.ts

@@ -2,7 +2,7 @@
  * Opt-in channel watch: dispatch on posts in allowlisted channels.
  *
  * Filtering rules (the anti-slop guarantees):
- * - Only explicitly allowlisted channels are watched — no wildcard.
+ * - Only configured channels are watched; `"*"` opts into every channel.
  * - Top-level posts only by default; thread replies never dispatch unless
  *   `posts: "all"` is configured.
  * - Posts that @mention the bot are skipped here (the `app_mention` path

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

@@ -233,7 +233,7 @@ export function slackChannel<const Name extends string = string>(
     const entries = channelPosts.allow.filter((entry) => entry.trim() !== "");
     if (entries.length === 0) {
       throw new Error(
-        "slackChannel engagement.channelPosts.allow must list at least one channel (id or #name); there is no wildcard watch."
+        'slackChannel engagement.channelPosts.allow must list at least one channel (id, #name, or "*").'
       );
     }
   }

package/src/channels/slack/types.ts

@@ -324,10 +324,8 @@ export type SlackBlockActionHandler = (
   | Promise<SlackDispatchDecision | null | undefined>;
 
 /**
- * Opt-in channel watch: dispatch on posts in explicitly allowlisted
- * channels without requiring an @mention. There is deliberately no
- * "every channel the bot is in" wildcard — watching a channel is a
- * per-channel decision.
+ * Opt-in channel watch: dispatch on posts in configured channels without an
+ * @mention. Use `"*"` for every channel the bot has joined.
  */
 export interface SlackChannelPostsOptions {
   /**

package/src/channels.ts

@@ -9,7 +9,7 @@
  * and are mounted under `/v1/channels/<name>`:
  *
  * ```ts
- * import { defineChannel, POST } from "@anysphere/agent-serve/channels";
+ * import { defineChannel, POST } from "@cursor/july/channels";
  * import { z } from "zod";
  *
  * export default defineChannel({

package/src/connections.ts

@@ -8,7 +8,7 @@
  * `hostOnly: true` to keep it off the model (still on `host.mcp`).
  *
  * ```ts
- * import { defineConnection } from "@anysphere/agent-serve/connections";
+ * import { defineConnection } from "@cursor/july/connections";
  *
  * export default defineConnection({
  *   url: "https://mcp.linear.app/mcp",

package/src/evals.ts

@@ -7,7 +7,7 @@
  * `t.messageIncludes(...)`, or `t.check(value, includes(...))`.
  *
  * ```ts
- * import { defineEval, includes } from "@anysphere/agent-serve/evals";
+ * import { defineEval, includes } from "@cursor/july/evals";
  *
  * // One datapoint — id is the file path (evals/weather/nyc.eval.ts → weather/nyc)
  * export default defineEval({

package/src/hooks.ts

@@ -6,7 +6,7 @@
  * transcripts to your own database). Handlers are observe-only.
  *
  * ```ts
- * import { defineHook } from "@anysphere/agent-serve/hooks";
+ * import { defineHook } from "@cursor/july/hooks";
  *
  * export default defineHook({
  *   events: {

package/src/index.ts

@@ -1,12 +1,12 @@
 /**
- * @anysphere/agent-serve
+ * @cursor/july
  *
  * Filesystem-first framework for Cursor agents: define an agent as markdown
  * and TypeScript files under an `agent/` directory, and serve it over
  * channels with the Cursor SDK as the execution harness.
  *
  * ```ts
- * import { serve } from "@anysphere/agent-serve";
+ * import { serve } from "@cursor/july";
  *
  * const handle = await serve(".", { port: 3000 });
  * console.log(`agent listening on ${handle.url}`);

package/src/internal/cli-convert-automation.ts

@@ -1,6 +1,6 @@
 /**
  * `agent-serve convert-automation <url>` — export a Cursor Automation into
- * an agentkit project.
+ * an agentsdk project.
  *
  * Fetches the automation's workflow from the backend export endpoint
  * (Bearer user API key, same credential chain as deploy), runs the pure

package/src/internal/cli-cursor.ts

@@ -148,10 +148,12 @@ export async function cmdLogin(options: CursorCliOptions): Promise<number> {
 /**
  * Gate for commands that need a Cursor credential before they can do useful
  * work (`serve`, `dev`, interactive `init`). Already-signed-in hosts
- * (`--api-key` / `CURSOR_API_KEY` / stored login) return immediately.
- * Otherwise an interactive host runs {@link cmdLogin}; a non-interactive
- * one (CI, Docker) fails fast with {@link SIGN_IN_HINT} instead of polling
- * a browser that will never open.
+ * (`--api-key` / `CURSOR_API_KEY` / `CURSOR_API_KEY_FILE` / stored login) return immediately.
+ * Hosted `--allow-anonymous` (v1 alias-token engines and v2 freeze bake)
+ * skips this gate so health/manifest can bind without a Cursor key.
+ * Self-hosted omit the flag: an interactive host runs {@link cmdLogin};
+ * a non-interactive one (CI, Docker) fails fast with {@link SIGN_IN_HINT}
+ * instead of polling a browser that will never open.
  */
 export async function ensureCursorLogin(
   options: {
@@ -161,6 +163,12 @@ export async function ensureCursorLogin(
      * TTY.
      */
     interactive?: boolean;
+    /**
+     * `serve --allow-anonymous`: listen without a Cursor credential.
+     * Model turns still fail later if a key is required; freeze only
+     * needs `/v1/health` and `/v1/manifest`.
+     */
+    allowAnonymous?: boolean;
     /** Test seam. */
     login?: (options: CursorCliOptions) => Promise<number>;
   } = {}
@@ -169,6 +177,9 @@ export async function ensureCursorLogin(
   if (resolved !== undefined) {
     return 0;
   }
+  if (options.allowAnonymous === true) {
+    return 0;
+  }
   const interactive = options.interactive ?? process.stderr.isTTY === true;
   if (!interactive) {
     process.stderr.write(`Not signed in to Cursor. ${SIGN_IN_HINT}\n`);
@@ -243,12 +254,14 @@ function formatIdentity(identity: CursorIdentity): string {
   return name === "" ? `${email}${team}` : `${name} <${email}>${team}`;
 }
 
-function describeSource(source: "option" | "env" | "login"): string {
+function describeSource(source: "option" | "env" | "file" | "login"): string {
   switch (source) {
     case "option":
       return "explicit --api-key / serve({ apiKey })";
     case "env":
       return "CURSOR_API_KEY environment variable";
+    case "file":
+      return "CURSOR_API_KEY_FILE (task bind)";
     case "login":
       return `stored login (${credentialsFilePath()})`;
   }

package/src/internal/cli-deploy.ts

@@ -28,6 +28,7 @@ import { readDeployTemplate } from "./cursor-agent-template.js";
 import {
   type AgentkitDeployAccepted,
   type AgentkitDeployStatus,
+  type AgentkitStopAccepted,
   AgentServeDeployClient,
   type DeleteAccepted,
   type DeployAccepted,
@@ -1187,11 +1188,25 @@ export async function cmdStop(
   if (typeof ctx === "number") {
     return ctx;
   }
-  let accepted: StopAccepted;
+  // Stop takes only a slug, so there is no manifest to dispatch on (unlike
+  // deploy). The v2 agentkit control plane goes first: v1 endpoints refuse
+  // `architecture: "v2"` slugs with a 409 rather than a 404, so v1-first
+  // could not fall through. A v2 404 (including an older backend without
+  // the agentkit mount) falls back to the v1 stop.
+  let architecture: "v1" | "v2" = "v2";
+  let accepted: StopAccepted | AgentkitStopAccepted;
   try {
-    accepted = await ctx.client.stopDeployment({ teamId: ctx.teamId, slug });
+    accepted = await ctx.client.stopAgentkit({ teamId: ctx.teamId, slug });
   } catch (error) {
-    return renderApiError(error, ctx.err);
+    if (!(error instanceof DeployApiError) || error.status !== 404) {
+      return renderApiError(error, ctx.err);
+    }
+    try {
+      accepted = await ctx.client.stopDeployment({ teamId: ctx.teamId, slug });
+      architecture = "v1";
+    } catch (v1Error) {
+      return renderApiError(v1Error, ctx.err);
+    }
   }
   if (ctx.noWait) {
     if (ctx.json) {
@@ -1201,11 +1216,16 @@ export async function cmdStop(
     }
     return 0;
   }
-  let detail: DeploymentDetail;
+  let detail: DeploymentDetail | AgentkitDeployStatus;
   try {
-    detail = await pollUntil(ctx, slug, new Set(["stopped"]), () =>
-      ctx.client.getDeployment({ teamId: ctx.teamId, slug })
-    );
+    detail =
+      architecture === "v2"
+        ? await pollUntil(ctx, slug, new Set(["stopped"]), () =>
+            ctx.client.getAgentkitDeploy({ teamId: ctx.teamId, slug })
+          )
+        : await pollUntil(ctx, slug, new Set(["stopped"]), () =>
+            ctx.client.getDeployment({ teamId: ctx.teamId, slug })
+          );
   } catch (error) {
     return renderApiError(error, ctx.err);
   }

package/src/internal/convert-automation/convert-workflow.ts

@@ -1,5 +1,5 @@
 /**
- * Pure Workflow → agentkit project converter.
+ * Pure Workflow → agentsdk project converter.
  *
  * Maps an exported Cursor automation (proto3 workflow JSON + enriched MCP
  * server list) to project files, warnings, and setup steps. No I/O, no
@@ -185,7 +185,7 @@ function renderInstructions(
 }
 
 /**
- * Strip Cursor-backend prompt markup that means nothing in agentkit:
+ * Strip Cursor-backend prompt markup that means nothing in agentsdk:
  * `@[label](action:...)` action tokens become their label text, and
  * unresolvable `%%INLINECODE<n>%%` storage placeholders are flagged (their
  * content is not in the export).
@@ -972,7 +972,7 @@ function emitSlackChannel(
         ? "channel-created"
         : "reaction-added";
     out.warnings.push(
-      `Slack ${kind} trigger has no agentkit equivalent — its config is inlined as a comment in ${path}; handle the Slack event yourself on a dedicated Socket Mode app.`
+      `Slack ${kind} trigger has no agentsdk equivalent — its config is inlined as a comment in ${path}; handle the Slack event yourself on a dedicated Socket Mode app.`
     );
   }
   let reactionDropped = false;
@@ -995,7 +995,7 @@ function emitSlackChannel(
   }
   if (reactionDropped) {
     out.warnings.push(
-      "The Slack trigger marked triggering messages with a completion reaction; agentkit has no completion-reaction option, so that signal is lost unless agent/instructions.md tells the agent to add the reaction itself via Slack tools."
+      "The Slack trigger marked triggering messages with a completion reaction; agentsdk has no completion-reaction option, so that signal is lost unless agent/instructions.md tells the agent to add the reaction itself via Slack tools."
     );
   }
   if (socketMode) {
@@ -1042,8 +1042,8 @@ function emitSlackChannel(
     if (blocksUnauthenticated) {
       out.warnings.push(
         includeBotPosts
-          ? "Some Slack watches only fired for authenticated Cursor users while others allowed anyone; agentkit has one bot-post setting per channel, so the export keeps bot posts ENABLED (the open watches depend on them) and the authenticated-only watches lose both their sender gate and their bot exclusion. Split the channels or add an onChannelPost gate."
-          : "The Slack trigger only fired for authenticated Cursor users (linked accounts on the owning team); agentkit has no equivalent sender gate, so the exported watch dispatches for ANY channel member (bot posts stay excluded). Add an onChannelPost gate in the channel if that matters."
+          ? "Some Slack watches only fired for authenticated Cursor users while others allowed anyone; agentsdk has one bot-post setting per channel, so the export keeps bot posts ENABLED (the open watches depend on them) and the authenticated-only watches lose both their sender gate and their bot exclusion. Split the channels or add an onChannelPost gate."
+          : "The Slack trigger only fired for authenticated Cursor users (linked accounts on the owning team); agentsdk has no equivalent sender gate, so the exported watch dispatches for ANY channel member (bot posts stay excluded). Add an onChannelPost gate in the channel if that matters."
       );
     }
     const engagement: string[] = [];
@@ -1309,9 +1309,9 @@ const ACTION_STEPS: Partial<Record<keyof ActionJson, string>> = {
   resolveReviewThreads:
     "Verify: resolve_review_threads — no built-in equivalent; resolve threads via the GitHub GraphQL API in a hook or tool.",
   microsoftTeams:
-    "Verify: microsoft_teams post — agentkit has no Teams channel; wire the Microsoft Teams API yourself.",
+    "Verify: microsoft_teams post — agentsdk has no Teams channel; wire the Microsoft Teams API yourself.",
   readMicrosoftTeams:
-    "Verify: read_microsoft_teams — agentkit has no Teams tools; wire the Microsoft Teams API yourself.",
+    "Verify: read_microsoft_teams — agentsdk has no Teams tools; wire the Microsoft Teams API yourself.",
 };
 
 interface SlackIntegrationState {
@@ -1375,7 +1375,7 @@ function behaviorSteps(
   const disabled = workflow.disabledDefaultTools ?? [];
   if (disabled.length > 0) {
     steps.push(
-      `Verify: disabled_default_tools (${disabled.join(", ")}) — agentkit has no default automation tools; enforce the equivalent restriction in agent/instructions.md.`
+      `Verify: disabled_default_tools (${disabled.join(", ")}) — agentsdk has no default automation tools; enforce the equivalent restriction in agent/instructions.md.`
     );
   }
   return steps;

package/src/internal/convert-automation/types.ts

@@ -1,5 +1,5 @@
 /**
- * Types for `convertWorkflow` — the pure automation → agentkit project
+ * Types for `convertWorkflow` — the pure automation → agentsdk project
  * converter behind `agent-serve convert-automation`.
  *
  * The workflow arrives as generic proto3 JSON (lowerCamelCase field names,