Skip to content

Commit 3e5216f

Browse files
arul28claude
andauthored
docs: overhaul Mintlify site + changelog for v1.2.7 (#595)
Rebuild the public docs around ADE's real feature set (grounded in docs/features/**): correct lane model (primary lane + worktree/child/ import/attach), add Review, iOS Simulator, Automations, GitHub, and troubleshooting pages, consolidate Integrations (GitHub + Linear) and AI Connections, swap the stale green logo for the real purple brand, and wire the full /media library into the pages. Adds the v1.2.7 changelog. Docs-only — no app code touched. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
1 parent 0b83d22 commit 3e5216f

63 files changed

Lines changed: 3293 additions & 1547 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

.mintignore

Lines changed: 2 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,5 @@ docs/
1515
packages/
1616
.factory/
1717

18-
# Template files we're replacing
19-
essentials/
20-
ai-tools/
21-
api-reference/
18+
# Source-of-truth media library lives elsewhere; the docs reference the
19+
# committed copies under /media, /logo, and /favicon.png directly.

ai-tools/claude-code.mdx

Lines changed: 49 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -1,42 +1,70 @@
11
---
22
title: "Claude Code"
3-
description: "Use Claude Code as an ADE chat and worker backend."
4-
icon: "terminal"
3+
description: "Claude Code runs inside ADE through the bundled Claude Agent SDK — scoped to a lane, with permission modes and transcripts handled for you."
4+
icon: "robot"
55
---
66

7-
Claude Code can run inside ADE as a coding agent. ADE starts sessions in the selected lane, passes the right project context, and records the transcript and tool activity.
7+
<Frame>
8+
<div style={{ display: "flex", alignItems: "center", justifyContent: "center", padding: "1rem 0.5rem" }}>
9+
<img src="/media/logos/models/claude-color.svg" alt="Claude" style={{ height: "48px", background: "#fff", borderRadius: "12px", padding: "10px 16px" }} />
10+
</div>
11+
</Frame>
12+
13+
Claude Code runs inside ADE through the **bundled Claude Agent SDK** — there's no separate `claude` CLI to install. Pick a Claude model in any chat and ADE starts the session in the selected lane's worktree, applies your permission mode, streams tool calls live, and records the transcript to History.
814

915
## Setup
1016

1117
<Steps>
12-
<Step title="Install or authenticate Claude Code">
13-
Make sure the `claude` CLI works in a normal terminal.
14-
</Step>
15-
<Step title="Open Settings -> AI Providers">
16-
Refresh provider detection and verify Claude Code.
18+
<Step title="Connect Claude in Settings → AI">
19+
Sign in with a Claude subscription or paste an Anthropic API key. A green status means Claude is ready.
1720
</Step>
18-
<Step title="Start a lane chat">
19-
Choose Claude from the model/provider selector.
21+
<Step title="Pick a Claude model in chat">
22+
Open the model picker in the chat header and choose a Claude model. That session now runs on Claude.
2023
</Step>
2124
</Steps>
2225

23-
## What ADE adds
26+
## What ADE handles for you
2427

25-
- Lane-scoped working directories.
26-
- Session transcripts in History.
27-
- File and Git attribution.
28-
- Provider permission controls.
29-
- Links to PRs, Linear issues, and proof artifacts when used.
28+
<CardGroup cols={2}>
29+
<Card title="Lane-scoped worktree" icon="code-branch">
30+
Every session runs in the active lane's worktree, so Claude edits and runs commands against that task's isolated checkout.
31+
</Card>
32+
<Card title="Live transcripts" icon="comments">
33+
Tool calls, thinking, and diffs stream into chat and are saved to History.
34+
</Card>
35+
<Card title="Permission gates" icon="shield-halved">
36+
A native permission mode decides what Claude can do without asking.
37+
</Card>
38+
<Card title="In-context links" icon="link">
39+
Changes attribute to Files and Git, and link out to PRs, Linear issues, and proof when used.
40+
</Card>
41+
</CardGroup>
3042

3143
## Permission modes
3244

33-
Claude Code uses Claude's native permission model. Pick a stricter mode when exploring an unfamiliar repo, and a more permissive mode only when you trust the lane and task.
45+
Claude Code uses Claude's native permission model. Pick a stricter mode when exploring an unfamiliar repo, and a more permissive one only when you trust the lane and task.
46+
47+
<AccordionGroup>
48+
<Accordion title="The Claude permission modes" icon="shield-halved">
49+
| Mode | Behavior |
50+
|------|----------|
51+
| `default` | Claude's built-in permission flow — asks before risky operations. |
52+
| `plan` | Read-only. Writing and executing are blocked until you approve a plan. |
53+
| `acceptEdits` | File writes allowed; shell commands still require approval. |
54+
| `bypassPermissions` | Proceeds without asking. |
55+
56+
The mode can change mid-session from the permission picker. See [Permissions](/configuration/permissions) for how modes map across providers.
57+
</Accordion>
58+
<Accordion title="Where Claude runs" icon="terminal">
59+
Claude is also one of the providers you can launch as a CLI session in the Work tab, and as a CTO worker backend. Wherever it runs, it's the same bundled Claude Agent SDK against the same lane worktree — desktop, [`ade code`](/tools/ade-code), and your phone all see the session.
60+
</Accordion>
61+
</AccordionGroup>
3462

3563
<CardGroup cols={2}>
36-
<Card title="Agent chat" icon="comments" href="/chat/overview">
37-
Run Claude in a lane.
38-
</Card>
3964
<Card title="AI providers" icon="brain" href="/configuration/ai-providers">
40-
Configure provider defaults.
65+
Connect each agent and set defaults.
66+
</Card>
67+
<Card title="Agent chat" icon="comments" href="/chat/overview">
68+
Run Claude in a lane and watch tool calls stream.
4169
</Card>
4270
</CardGroup>

ai-tools/cursor.mdx

Lines changed: 40 additions & 84 deletions
Original file line numberDiff line numberDiff line change
@@ -1,98 +1,54 @@
11
---
2-
title: "Cursor Integration"
3-
description: "Use Cursor as an agent provider in ADE — launch sessions, route models, and track work through the Cursor SDK."
2+
title: "Cursor"
3+
description: "Run Cursor as an agent provider in ADE through the Cursor SDK — one of ADE's five agents, scoped to a lane."
44
icon: "arrow-pointer"
55
---
66

7-
## Overview
7+
[Cursor](https://cursor.com) runs inside ADE as one of its five agent providers, alongside Claude Code, Codex, Factory Droid, and OpenCode. ADE drives Cursor's agent through the official **Cursor SDK** — ADE owns the lane scope, permissions, and system prompt; the SDK owns the model and tool execution.
88

9-
ADE integrates with [Cursor](https://cursor.com) in two ways:
9+
## Connect Cursor
1010

11-
1. **Launch Cursor from ADE** — open your project or a lane's worktree in Cursor from the Run tab
12-
2. **Cursor as an agent provider** — use Cursor's AI agent as a chat provider inside ADE via the Cursor SDK
11+
Cursor chat authenticates with an API key. Add a Cursor API key in **Settings → AI**, or set `CURSOR_API_KEY` in the environment ADE launches from — ADE accepts either.
1312

14-
The SDK integration means Cursor's agent capabilities are available directly in ADE's chat interface, alongside Claude, Codex, and other providers. You can switch between providers per-session.
15-
16-
---
17-
18-
## Requirements
19-
20-
| Requirement | Details |
21-
|------------|---------|
22-
| **Cursor installed** | Cursor desktop app must be installed to launch Cursor from ADE |
23-
| **Cursor SDK auth** | Cursor chat requires `CURSOR_API_KEY` or a Cursor API key saved in ADE Settings |
24-
| **Authentication** | ADE uses API-key authentication for Cursor chat. Cursor desktop sign-in is only needed for launching the editor. |
25-
26-
ADE checks Cursor API-key authentication during onboarding and in **Settings → AI**. When `CURSOR_API_KEY` is present, ADE recognizes it as a valid authentication signal. You can also save the key in ADE's encrypted provider settings.
27-
28-
---
29-
30-
## Launching Cursor from ADE
31-
32-
Open the **Run** tab and click the **Cursor** launcher. ADE opens the current project (or the selected lane's worktree) in Cursor as a separate application window.
33-
34-
The session is linked back to the active lane for tracking. File changes made in Cursor appear in the lane's diff view as soon as they are saved.
35-
36-
---
37-
38-
## Cursor as an agent provider
39-
40-
When Cursor API-key auth is configured, ADE can use Cursor as a chat provider through the **Cursor SDK**.
41-
42-
### How it works
43-
44-
1. ADE starts an isolated SDK worker for the active lane
45-
2. The worker creates or resumes a Cursor SDK agent with the selected model
46-
3. Chat messages are routed through SDK runs, and Cursor has access to the `ade` CLI for ADE workflows
47-
4. Model discovery queries Cursor SDK metadata for available models and capabilities
48-
49-
### Selecting Cursor in chat
50-
51-
In any Agent Chat session, use the **model selector** in the chat header to choose a Cursor-provided model. Models discovered from Cursor appear alongside Claude, GPT, and other configured providers.
52-
53-
### Model discovery
54-
55-
ADE queries Cursor for its available models at startup and caches the result. The discovered models appear in:
56-
- The chat model selector
57-
- The worker run model configuration
58-
- The unified model selector throughout the app
59-
60-
### Session behavior
61-
62-
| Behavior | Details |
63-
|----------|---------|
64-
| **Session lifecycle** | Managed by the Cursor SDK pool; sessions are reused when possible |
65-
| **Event mapping** | SDK events are mapped to ADE's chat event model for consistent UI |
66-
| **ADE CLI access** | The `ade` CLI is on `PATH` so Cursor agents can call ADE lane, git, PR, and action tools |
67-
| **Interrupts** | Supported via SDK run cancel |
68-
69-
---
70-
71-
## Connection status
72-
73-
ADE shows Cursor's connection status in **Settings → AI**:
74-
75-
| Status | Meaning |
76-
|--------|---------|
77-
| **Connected** (green) | Cursor API key found and ready |
78-
| **Not authenticated** (amber) | Cursor API key is missing or invalid |
79-
| **Not found** (gray) | Cursor desktop is not detected for editor launch |
80-
81-
---
82-
83-
## Troubleshooting
13+
Once connected, ADE discovers Cursor's available models and they appear in the model picker alongside every other provider. Pick one in any chat header to route that session through Cursor.
8414

8515
<AccordionGroup>
86-
<Accordion title="Cursor not detected" icon="circle-question">
87-
ADE checks standard installation paths for the Cursor desktop app when launching the editor. If Cursor is installed in a non-standard location, open the project directly from Cursor or add the app to the standard Applications location.
16+
<Accordion title="How the SDK provider works" icon="gear">
17+
When a Cursor key is configured, ADE runs the official `@cursor/sdk` in a Node worker pool. The worker creates or resumes a Cursor SDK agent with the selected model in the active lane's worktree, and routes chat turns through SDK runs. Sessions are pooled and reused, SDK events map to ADE's chat event model, and interrupts cancel the run. Because the `ade` CLI is on `PATH`, Cursor agents can call ADE's lane, git, PR, and action tools.
18+
</Accordion>
19+
<Accordion title="Connection status" icon="signal">
20+
ADE shows Cursor's status in **Settings → AI**:
21+
22+
| Status | Meaning |
23+
|--------|---------|
24+
| **Connected** (green) | Cursor API key found and ready. |
25+
| **Not authenticated** (amber) | Cursor API key is missing or invalid. |
8826
</Accordion>
89-
<Accordion title="Authentication failed" icon="lock">
90-
Add a Cursor API key in **Settings → AI Providers** or set `CURSOR_API_KEY` in the environment used to launch ADE.
27+
<Accordion title="Cursor Agent CLI in the Work tab" icon="terminal">
28+
You can also launch the `cursor-agent` CLI as a tracked terminal session in the Work tab. ADE probes `cursor-agent` for CLI-only models and merges them into the picker, so the chat-vs-CLI distinction stays clear. This needs the `cursor-agent` binary on your `PATH`.
9129
</Accordion>
92-
<Accordion title="Models not appearing" icon="list">
93-
Model discovery runs at ADE startup. If you installed Cursor after starting ADE, restart ADE or go to **Settings → AI** and click **Refresh** to re-run model discovery.
30+
<Accordion title="Cursor Cloud agents" icon="cloud">
31+
Kick off Cursor's hosted cloud agents from ADE and follow them in a lane:
32+
33+
```bash
34+
ade cursor cloud agents list --text
35+
ade cursor cloud agents create --repo https://github.com/owner/repo --prompt "fix flaky test" --auto-pr
36+
```
37+
38+
The chat panel can open a cloud agent as an ADE chat (replies still run in the cloud) or jump to it on cursor.com.
9439
</Accordion>
95-
<Accordion title="Session errors" icon="circle-exclamation">
96-
If SDK sessions fail, check that the Cursor API key is configured and that the selected model is available. Check ADE's developer logs (**Settings → Developer → Log file**) for detailed SDK worker errors.
40+
<Accordion title="Troubleshooting" icon="circle-question">
41+
- **Authentication failed** — add a Cursor API key in **Settings → AI**, or set `CURSOR_API_KEY` in ADE's launch environment.
42+
- **Models not appearing** — discovery serves last-known-good rows and revalidates in the background. If Cursor was just connected, restart ADE or refresh in **Settings → AI**.
43+
- **Session errors** — confirm the key is valid and the selected model is available; check developer logs at **Settings → Developer → Log file**.
9744
</Accordion>
9845
</AccordionGroup>
46+
47+
<CardGroup cols={2}>
48+
<Card title="AI providers" icon="brain" href="/configuration/ai-providers">
49+
Connect each agent and set defaults.
50+
</Card>
51+
<Card title="Agent chat" icon="comments" href="/chat/overview">
52+
Run Cursor in a lane and compare it with other providers.
53+
</Card>
54+
</CardGroup>

0 commit comments

Comments
 (0)