@cursor/july 0.1.29 → 0.1.31

package/docs/example-agents/codebase-wiki.md

@@ -88,8 +88,8 @@ GitHub. Its only side effects are wiki files on the serve host.
 ## Validate the surface
 
 ```bash
-agentkit validate --dir examples/codebase-wiki
-agentkit info --dir examples/codebase-wiki --json
+agent-sdk validate --dir examples/codebase-wiki
+agent-sdk info --dir examples/codebase-wiki --json
 ```
 
 The manifest should report four server tools, one skill, one schedule,
@@ -100,9 +100,9 @@ and the authored GitHub channel.
 Replay a real merged PR as a closed delivery:
 
 ```bash
-agentkit dev examples/codebase-wiki
+agent-sdk dev examples/codebase-wiki
 
-agentkit github replay https://github.com/owner/repo/pull/123 \
+agent-sdk github replay https://github.com/owner/repo/pull/123 \
   --dir examples/codebase-wiki --action closed
 ```
 
@@ -118,7 +118,7 @@ section, and a changelog line citing the PR. Deterministic digest
 preparation works without a model turn:
 
 ```bash
-agentkit call ingest_pr \
+agent-sdk call ingest_pr \
   --dir examples/codebase-wiki \
   --input '{"pr":"https://github.com/owner/repo/pull/123"}'
 ```
@@ -128,7 +128,7 @@ the model to change nothing.
 
 ## Run the daily digest
 
-The schedule fires at 07:00 UTC. Under `agentkit dev`, trigger it by
+The schedule fires at 07:00 UTC. Under `agent-sdk dev`, trigger it by
 hand:
 
 ```bash
@@ -143,8 +143,8 @@ always count; a digest only claims a quiet day when no entry qualifies.
 ## Run the evals
 
 ```bash
-agentkit eval --dir examples/codebase-wiki --list
-agentkit eval --dir examples/codebase-wiki ingest/update-existing
+agent-sdk eval --dir examples/codebase-wiki --list
+agent-sdk eval --dir examples/codebase-wiki ingest/update-existing
 ```
 
 The cases seed a temp wiki through `CODEBASE_WIKI_DIR` and build

package/docs/example-agents/codeowners-review.md

@@ -96,8 +96,8 @@ the same session through the `pr:<label>` continuation token.
 ## Validate the surface
 
 ```bash
-agentkit validate --dir examples/codeowners-review
-agentkit info --dir examples/codeowners-review --json
+agent-sdk validate --dir examples/codeowners-review
+agent-sdk info --dir examples/codeowners-review --json
 ```
 
 The manifest should report two server tools, one skill, one subagent,
@@ -106,9 +106,9 @@ and the authored GitHub channel.
 ## Inspect routing without a model turn
 
 ```bash
-agentkit call list_review_areas --dir examples/codeowners-review --input '{}'
+agent-sdk call list_review_areas --dir examples/codeowners-review --input '{}'
 
-agentkit call prepare_review \
+agent-sdk call prepare_review \
   --dir examples/codeowners-review \
   --input '{"pr":"fixture:multi-area"}'
 ```
@@ -123,7 +123,7 @@ adapt `reviews/REVIEWERS`.
 ## Review the planted fixture
 
 ```bash
-agentkit dev examples/codeowners-review
+agent-sdk dev examples/codeowners-review
 ```
 
 In the playground:
@@ -146,7 +146,7 @@ Review a real PR the same way:
 Or replay one as a webhook delivery:
 
 ```bash
-agentkit github replay https://github.com/owner/repo/pull/123 \
+agent-sdk github replay https://github.com/owner/repo/pull/123 \
   --dir examples/codeowners-review --action opened
 ```
 
@@ -162,8 +162,8 @@ APPROVE only when every non-advisory area approved.
 ## Run the evals
 
 ```bash
-agentkit eval --dir examples/codeowners-review --list
-agentkit eval --dir examples/codeowners-review review/multi-area
+agent-sdk eval --dir examples/codeowners-review --list
+agent-sdk eval --dir examples/codeowners-review review/multi-area
 ```
 
 `review/multi-area` gates the whole pipeline: `prepare_review` runs, at

package/docs/example-agents/concierge.md

@@ -6,7 +6,7 @@ description: "Delegate weather requests through a peer MCP connection while each
 # Compose agents with a concierge
 
 Concierge answers general questions itself and sends every weather question
-to the weather agent. The connection is one file. Agentkit turns the target
+to the weather agent. The connection is one file. The Agent SDK turns the target
 agent's MCP endpoint into tools the concierge can call.
 
 Use this example when two agents are useful on their own and one should
@@ -51,7 +51,7 @@ comparison.
    classifies packing advice as weather-related.
 3. The model calls `weather.ask` with the city, timeframe, units, and the
    complete question.
-4. Agentkit creates an MCP-channel session inside `weather-agent`.
+4. The Agent SDK creates an MCP-channel session inside `weather-agent`.
 5. Weather agent calls its own Open-Meteo tools and returns a reply.
 6. If the turn exceeds the bounded MCP wait, `ask` returns
    `status: "running"`. Concierge calls `weather.check` with the returned
@@ -87,8 +87,8 @@ isn't mounted.
 From `packages/agent-serve`, validate both projects:
 
 ```bash
-agentkit validate --dir examples/concierge
-agentkit validate --dir examples/weather-agent
+agent-sdk validate --dir examples/concierge
+agent-sdk validate --dir examples/weather-agent
 ```
 
 Don't serve the repository's whole `examples/` directory for this proof.
@@ -108,7 +108,7 @@ cp -R examples/weather-agent/agent/{tools,skills,mcp-connections,subagents,sched
   "$PAIR_DIR/weather-agent/agent/"
 cp -R examples/weather-agent/mcp "$PAIR_DIR/weather-agent/"
 cp examples/weather-agent/package.json "$PAIR_DIR/weather-agent/"
-agentkit dev "$PAIR_DIR"
+agent-sdk dev "$PAIR_DIR"
 ```
 
 The host resolves the peer after it knows every mount. The local peer URL is
@@ -120,7 +120,7 @@ credential for both model turns.
 Send a weather request to the running Concierge:
 
 ```bash
-agentkit chat \
+agent-sdk chat \
   --url http://127.0.0.1:3000/concierge \
   --message "What should I pack for Paris tomorrow?"
 ```
@@ -136,7 +136,7 @@ separate session on the `mcp` channel with live weather tool calls.
 Now send a general request:
 
 ```bash
-agentkit chat \
+agent-sdk chat \
   --url http://127.0.0.1:3000/concierge \
   --message "Give me three ideas for a quiet weekend."
 ```
@@ -155,7 +155,7 @@ the second question needs facts or choices from the first.
 
 ## Keep delegation bounded
 
-Agentkit rejects unknown peer slugs and self-references during startup. It
+The Agent SDK rejects unknown peer slugs and self-references during startup. It
 doesn't stop a cycle across several valid peers. If agent A delegates all work
 to B and B delegates all work to A, they can recurse.
 
@@ -175,12 +175,12 @@ Local turns reach peers over loopback. A cloud VM can't reach the serve
 host's loopback address. Set a public URL when a cloud agent needs the peer:
 
 ```bash
-agentkit serve --dir "$PAIR_DIR" \
+agent-sdk serve --dir "$PAIR_DIR" \
   --public-url https://agents.example.com \
   --bearer-token "$AGENT_TOKEN"
 ```
 
-Agentkit attaches the bearer token to peer calls. Without `--public-url`,
+The Agent SDK attaches the bearer token to peer calls. Without `--public-url`,
 cloud turns omit peer connections and the server logs a warning.
 
 ## Compose your own pair

package/docs/example-agents/fsd.md

@@ -41,7 +41,7 @@ execution, event wakes, and timed follow-ups.
 2. The root model calls `drive_pr` with the PR, mode, and optional hint.
 3. The tool calls `ctx.send("drive", ...)` with a per-session `cloud` block
    to attach the PR.
-4. Agentkit creates or resumes the `drive` session keyed by
+4. The Agent SDK creates or resumes the `drive` session keyed by
    `pr:owner/repo#N`.
 5. The remote runtime provisions the agent and emits `agent.bound`.
 6. The enrollment hook writes PR affinity and calls the workflow backend to
@@ -119,9 +119,9 @@ long-lived host.
 ## Validate without starting remote work
 
 ```bash
-agentkit validate --dir examples/fsd
-agentkit info --dir examples/fsd --json
-agentkit github events --dir examples/fsd --json
+agent-sdk validate --dir examples/fsd
+agent-sdk info --dir examples/fsd --json
+agent-sdk github events --dir examples/fsd --json
 ```
 
 These commands inspect discovery and declared GitHub events. They don't
@@ -158,7 +158,7 @@ authoritative mode.
 Run the host:
 
 ```bash
-agentkit dev examples/fsd
+agent-sdk dev examples/fsd
 ```
 
 From chat:
@@ -168,7 +168,7 @@ From chat:
 Or call the coordinator tool:
 
 ```bash
-agentkit call drive_pr \
+agent-sdk call drive_pr \
   --dir examples/fsd \
   --input '{"pr":"https://github.com/owner/repo/pull/123","mode":"suggest"}'
 ```
@@ -270,7 +270,7 @@ Development mode doesn't fire reminder timers automatically. Dispatch one
 through the dev reminder endpoint for a manual proof, or use non-dev `serve`
 to run the 30-minute cadence.
 
-The reminder's `run` handler lives in memory. After a host restart, agentkit
+The reminder's `run` handler lives in memory. After a host restart, the Agent SDK
 disarms it with `handler_lost_on_restart`; a later drive or webhook path can
 arm a fresh handler. Persisted reminder metadata alone doesn't keep the check
 running.

package/docs/example-agents/index.md

@@ -1,9 +1,9 @@
 ---
-title: "Choose the right agentkit example"
+title: "Choose the right Agent SDK example"
 description: "Compare all twelve example agents by runtime, channels, tools, state, and the framework pattern each one teaches."
 ---
 
-# Choose the right agentkit example
+# Choose the right Agent SDK example
 
 The examples progress from one-channel assistants to durable, event-driven
 workflows. Start with the smallest agent for your use case. Each guide
@@ -13,7 +13,7 @@ design.
 The source projects live under
 [`examples/`](../../examples/). Run the commands below from
 `packages/agent-serve`. See [Run the CLI](../README.md#run-the-cli) if the
-`agentkit` command isn't installed.
+`agent-sdk` command isn't installed.
 
 ## Compare the examples
 
@@ -34,7 +34,7 @@ The source projects live under
 
 ## Pick a learning path
 
-Use this order when you want to learn agentkit one capability at a time:
+Use this order when you want to learn the Agent SDK one capability at a time:
 
 1. Start with [Weather agent](./weather-agent.md) to explore the filesystem
    conventions and local runtime.
@@ -60,7 +60,7 @@ Use this order when you want to learn agentkit one capability at a time:
 
 All examples require:
 
-- Node 22.13 or newer. Don't run agentkit under Bun.
+- Node 22.13 or newer. Don't run the Agent SDK under Bun.
 - Workspace dependencies installed.
 - An agent-runtime credential for model turns.
 
@@ -83,11 +83,11 @@ Each guide lists its own credentials, services, and side effects.
 Discovery commands don't start a model turn:
 
 ```bash
-agentkit validate --dir examples/weather-agent
-agentkit info --dir examples/weather-agent --json
+agent-sdk validate --dir examples/weather-agent
+agent-sdk info --dir examples/weather-agent --json
 ```
 
-Start one development server with `agentkit dev examples/<name>`.
+Start one development server with `agent-sdk dev examples/<name>`.
 Concierge depends on Weather agent, so its guide creates an isolated
 two-project mount. Don't mount the whole examples directory to test one
 agent; several advanced examples subscribe to live GitHub events.

package/docs/example-agents/knowledge-base.md

@@ -82,8 +82,8 @@ Nothing else. The wiki is created on first write.
 ## Validate the surface
 
 ```bash
-agentkit validate --dir examples/knowledge-base
-agentkit info --dir examples/knowledge-base --json
+agent-sdk validate --dir examples/knowledge-base
+agent-sdk info --dir examples/knowledge-base --json
 ```
 
 The manifest should report three server tools, one skill, and one
@@ -92,15 +92,15 @@ schedule.
 ## Exercise the store without a model turn
 
 ```bash
-agentkit call wiki_write \
+agent-sdk call wiki_write \
   --dir examples/knowledge-base \
   --input '{"page":"staging-database","content":"# Staging database\n\n- Port: 6432 (recorded 2026-07-19)\n"}'
 
-agentkit call wiki_search \
+agent-sdk call wiki_search \
   --dir examples/knowledge-base \
   --input '{"query":"6432"}'
 
-agentkit call wiki_read --dir examples/knowledge-base --input '{}'
+agent-sdk call wiki_read --dir examples/knowledge-base --input '{}'
 ```
 
 Invalid page ids fail fast. Try `{"page":"../escape"}` and the tool
@@ -109,7 +109,7 @@ returns the validation error instead of touching the filesystem.
 ## Prove recall across sessions
 
 ```bash
-agentkit dev examples/knowledge-base
+agent-sdk dev examples/knowledge-base
 ```
 
 Teach it something in the playground:
@@ -132,7 +132,7 @@ source of truth.
 
 The `gardener` schedule fires at 06:00 UTC and rewrites the wiki for
 consistency: merge near-duplicate pages, rebuild `index`, and flag
-facts older than 90 days. Under `agentkit dev`, timers don't auto-fire.
+facts older than 90 days. Under `agent-sdk dev`, timers don't auto-fire.
 Trigger it by hand:
 
 ```bash
@@ -142,8 +142,8 @@ curl -s -X POST http://127.0.0.1:3000/knowledge-base/v1/dev/schedules/gardener
 ## Run the evals
 
 ```bash
-agentkit eval --dir examples/knowledge-base --list
-agentkit eval --dir examples/knowledge-base knowledge/recall
+agent-sdk eval --dir examples/knowledge-base --list
+agent-sdk eval --dir examples/knowledge-base knowledge/recall
 ```
 
 The eval file seeds a temp directory through `KNOWLEDGE_BASE_DIR`

package/docs/example-agents/oncall.md

@@ -27,7 +27,7 @@ instead of answering every message.
    through; the agent's own posts always stay dropped.
 3. The handler reacts 👀 on the alert post and sets "Investigating…"
    typing. The reaction is the lock-in signal: this alert has an owner.
-4. Agentkit creates a session keyed to the alert's thread and dispatches
+4. The Agent SDK creates a session keyed to the alert's thread and dispatches
    immediately. New alerts get no debounce.
 5. The agent reads the alert, gathers evidence, and posts findings to the
    thread once it has a hypothesis.
@@ -137,8 +137,8 @@ Channel watching is Socket Mode only, so this example uses a dedicated
 app:
 
 ```bash
-agentkit slack init --dir examples/oncall --name "Oncall" --channel-posts
-agentkit slack doctor --prefix ONCALL
+agent-sdk slack init --dir examples/oncall --name "Oncall" --channel-posts
+agent-sdk slack doctor --prefix ONCALL
 ```
 
 The generated manifest subscribes to `message.channels` and
@@ -157,9 +157,9 @@ thread.
 ## Validate and start the server
 
 ```bash
-agentkit validate --dir examples/oncall
-agentkit info --dir examples/oncall --json
-agentkit dev examples/oncall
+agent-sdk validate --dir examples/oncall
+agent-sdk info --dir examples/oncall --json
+agent-sdk dev examples/oncall
 ```
 
 The info output lists four server tools and the watched channel on the
@@ -186,7 +186,7 @@ own posts never loop, and replies coalesce behind the quiet window.
 The smoke eval spends a model turn:
 
 ```bash
-agentkit eval --dir examples/oncall smoke --json
+agent-sdk eval --dir examples/oncall smoke --json
 ```
 
 It checks identity and the reminder-tool route lexically. It doesn't prove

package/docs/example-agents/security-reviewer.md

@@ -102,9 +102,9 @@ The active names live beside the orchestration in
 ## Validate the discovered agent
 
 ```bash
-agentkit validate --dir ../../factory/security-reviewer
-agentkit info --dir ../../factory/security-reviewer --json
-agentkit eval --dir ../../factory/security-reviewer --list
+agent-sdk validate --dir ../../factory/security-reviewer
+agent-sdk info --dir ../../factory/security-reviewer --json
+agent-sdk eval --dir ../../factory/security-reviewer --list
 ```
 
 The manifest should show four server tools, two authored channels, one
@@ -129,15 +129,15 @@ calls below when a no-post proof must be enforced.
 Call each stage and pass `postComment: false` yourself:
 
 ```bash
-agentkit call prepare_review \
+agent-sdk call prepare_review \
   --dir ../../factory/security-reviewer \
   --input '{"prUrl":"https://github.com/owner/repo/pull/123"}'
 
-agentkit call run_reviewers \
+agent-sdk call run_reviewers \
   --dir ../../factory/security-reviewer \
   --input '{"runId":"<run-id>"}'
 
-agentkit call finalize_review \
+agent-sdk call finalize_review \
   --dir ../../factory/security-reviewer \
   --input '{"runId":"<run-id>","postComment":false}'
 ```
@@ -154,7 +154,7 @@ stages can open the prepared `runId`.
 Run the dev server:
 
 ```bash
-agentkit dev ../../factory/security-reviewer
+agent-sdk dev ../../factory/security-reviewer
 ```
 
 Open the printed playground and start a review. The custom
@@ -164,7 +164,7 @@ It refreshes every 500 ms while the stage runs. Each row shows a reviewer
 module's state, candidates, reviewed areas, and failure. A second section
 shows triage jobs and confirmed or rejected counts.
 
-This is an authored playground extension. Agentkit discovers it by the tool
+This is an authored playground extension. The Agent SDK discovers it by the tool
 name, so the generic `run_reviewers` chip becomes a domain-specific view
 without changing the framework playground.
 
@@ -192,7 +192,7 @@ findings, accounting, and audit events.
 
 ## Separate session storage from review artifacts
 
-`defineStorage` + `cursorHostedStorage` sends agentkit session and event records
+`defineStorage` + `cursorHostedStorage` sends Agent SDK session and event records
 to Cursor-hosted Bugbot storage through the control-plane proxy. Security
 Reviewer sets `restore: "off"` so startup doesn't load old review sessions in
 bulk. A continuation lookup can still fetch a needed session.
@@ -234,7 +234,7 @@ The channel currently accepts two configured repositories. It wakes on
 Inspect its event surface:
 
 ```bash
-agentkit github events \
+agent-sdk github events \
   --dir ../../factory/security-reviewer \
   --json
 ```
@@ -243,7 +243,7 @@ Replay reaches the full publishing path:
 
 ```bash
 TEST_PR_URL=https://github.com/your-org/allowlisted-test-repo/pull/123
-agentkit github replay \
+agent-sdk github replay \
   "$TEST_PR_URL" \
   --dir ../../factory/security-reviewer \
   --action opened
@@ -256,7 +256,7 @@ status and may post findings.
 ## Inspect the eval before running it
 
 ```bash
-agentkit eval --dir ../../factory/security-reviewer --list
+agent-sdk eval --dir ../../factory/security-reviewer --list
 ```
 
 The case reads pinned metadata from the committed fixture and checks for all

package/docs/example-agents/slack-agent.md

@@ -31,7 +31,7 @@ status updates, and suggested prompts.
 1. A user mentions the agent or sends the host app a direct message naming
    it.
 2. The Slack relay selects this channel by its single-token `agentName`.
-3. Agentkit maps the Slack channel and thread timestamp to a continuation
+3. The Agent SDK maps the Slack channel and thread timestamp to a continuation
    key.
 4. The local harness runs with
    [`instructions.md`](../../examples/slack-agent/agent/instructions.md).
@@ -45,7 +45,7 @@ or tool routing.
 
 | File | Purpose |
 | --- | --- |
-| [`package.json`](../../examples/slack-agent/package.json) | Declares the example package and agentkit dependency. |
+| [`package.json`](../../examples/slack-agent/package.json) | Declares the example package and Agent SDK dependency. |
 | [`agent/agent.ts`](../../examples/slack-agent/agent/agent.ts) | Names the agent and selects the model. The omitted `runtime` defaults to local. |
 | [`agent/instructions.md`](../../examples/slack-agent/agent/instructions.md) | Sets the always-on response style. |
 | [`agent/channels/slack.ts`](../../examples/slack-agent/agent/channels/slack.ts) | Connects the signed-in host account to Slack. |
@@ -64,8 +64,8 @@ You need:
 Sign in and confirm the active account:
 
 ```bash
-agentkit login
-agentkit whoami
+agent-sdk login
+agent-sdk whoami
 ```
 
 The selected transport owns Slack credential setup. See the
@@ -75,9 +75,9 @@ options.
 ## Validate and start the server
 
 ```bash
-agentkit validate --dir examples/slack-agent
-agentkit info --dir examples/slack-agent --json
-agentkit dev examples/slack-agent
+agent-sdk validate --dir examples/slack-agent
+agent-sdk info --dir examples/slack-agent --json
+agent-sdk dev examples/slack-agent
 ```
 
 The dev command prints the playground URL. It also mounts the Slack channel
@@ -85,7 +85,7 @@ and waits for relayed messages.
 
 In Slack, address the configured host app and router name, then send:
 
-> `<host-app mention> <router name>` Explain agentkit in three bullets.
+> `<host-app mention> <router name>` Explain the Agent SDK in three bullets.
 
 Reply in the generated thread:
 
@@ -101,8 +101,8 @@ Every project gets the built-in HTTP channel even when no HTTP file exists.
 Run a one-shot turn through it:
 
 ```bash
-agentkit run --dir examples/slack-agent \
-  --message "Explain agentkit simply."
+agent-sdk run --dir examples/slack-agent \
+  --message "Explain the Agent SDK simply."
 ```
 
 The same project also exposes an MCP endpoint. Since this agent has no server