Document Seqera AI dev CLI setup in cloud docs

platform-cloud/docs/seqera-ai/authentication.md

@@ -23,10 +23,10 @@ seqera login
 
 This will:
 
-1. Open your default browser to the Seqera login page
-1. Prompt you to sign in with your Seqera Platform credentials
-1. Automatically capture the authentication token
-1. Display a success message in your terminal
+1. Open your default browser to the Seqera login page.
+1. Prompt you to sign in with your Seqera Platform credentials.
+1. Automatically capture the authentication token.
+1. Display a success message in your terminal.
 
    ```
    [Login] Starting Seqera CLI authentication...
@@ -55,6 +55,36 @@ seqera ai
 
 When this environment variable is set, the CLI skips the OAuth login flow and uses the provided token directly.
 
+### Point a development build at the hosted Seqera AI backend
+
+If you are testing a development build of the CLI against the hosted production Seqera AI service, set the following environment variables before starting `seqera ai`.
+
+| Variable | Purpose | Example value |
+| --- | --- | --- |
+| `SEQERA_AI_BACKEND_URL` | Seqera AI backend endpoint used by the CLI | `https://ai-api.seqera.io` |
+| `SEQERA_AUTH_DOMAIN` | Platform API base URL used for browser-based login | `https://cloud.seqera.io/api` |
+| `SEQERA_AUTH_CLI_CLIENT_ID` | OAuth client ID for the Seqera AI CLI | `seqera_ai_cli` |
+| `TOWER_ACCESS_TOKEN` | Platform personal access token used instead of browser login | `<PLATFORM_ACCESS_TOKEN>` |
+
+Use the OAuth login flow:
+
+```bash
+export SEQERA_AUTH_DOMAIN=https://cloud.seqera.io/api
+export SEQERA_AUTH_CLI_CLIENT_ID=seqera_ai_cli
+export SEQERA_AI_BACKEND_URL=https://ai-api.seqera.io
+seqera ai
+```
+
+Use a Platform personal access token instead of browser login:
+
+```bash
+export TOWER_ACCESS_TOKEN=<PLATFORM_ACCESS_TOKEN>
+export SEQERA_AI_BACKEND_URL=https://ai-api.seqera.io
+seqera ai
+```
+
+You only need `SEQERA_AUTH_DOMAIN` and `SEQERA_AUTH_CLI_CLIENT_ID` when using the OAuth login flow.
+
 ### Log out
 
 To sign out from the current session, run:

platform-cloud/docs/seqera-ai/get-started.md

@@ -29,6 +29,8 @@ To get started with Seqera AI:
 
     See [Authentication](./authentication.md) for a comprehensive authentication guide.
 
+    If you are testing a development build of the CLI against the hosted production Seqera AI service, set `SEQERA_AI_BACKEND_URL=https://ai-api.seqera.io` first. See [Authentication](./authentication.md#point-a-development-build-at-the-hosted-seqera-ai-backend) for the full environment variable reference.
+
 
 1. Start Seqera AI:
 

platform-cloud/docs/seqera-ai/installation.md

@@ -22,6 +22,12 @@ Seqera Cloud users receive $20 in free credits to get started with Seqera AI. [C
 npm install -g seqera
 ```
 
+Install the development build:
+
+```bash
+npm install -g seqera@dev
+```
+
 Verify your installation:
 
 ```bash
@@ -34,6 +40,10 @@ seqera --version
 npm update -g seqera
 ```
 
+### Developer configuration
+
+See [Authentication](./authentication.md#point-a-development-build-at-the-hosted-seqera-ai-backend) for the complete environment variable reference and OAuth versus token-based examples.
+
 ### Install agent integrations
 
 Install Seqera AI as a skill for your coding agent:

platform-cloud/docs/seqera-ai/modes.md

@@ -48,9 +48,9 @@ Toggle modes during a session with `Shift+Tab`.
 
 You can also:
 
-- Check the current mode in the composer footer
-- Run `/status` to view the current mode alongside session and LSP status
-- Use `/help` to see mode-aware command guidance
+- Check the current mode in the composer footer.
+- Run `/status` to view the current mode alongside session and LSP status.
+- Use `/help` to see mode-aware command guidance.
 
 ## Goal mode
 
@@ -62,10 +62,10 @@ Goal mode is a persistent workflow for longer tasks. Set a goal with:
 
 When goal mode is active, Seqera AI:
 
-- Keeps working toward the same objective over multiple model attempts
-- Automatically continues if more work is needed
-- Stops when the goal is complete or the goal attempt limit is reached
-- Switches approval mode to `full` so work can continue without repeated prompts
+- Keeps working toward the same objective over multiple model attempts.
+- Automatically continues if more work is needed.
+- Stops when the goal is complete or the goal attempt limit is reached.
+- Switches approval mode to `full` so work can continue without repeated prompts.
 
 Goal mode commands:
 
@@ -82,9 +82,9 @@ Seqera AI currently gives goal mode up to **3 model attempts** before it stops a
 
 | Shortcut | Action |
 |----------|--------|
-| `Shift+Tab` | Toggle between build mode and plan mode |
-| `Ctrl+Enter` | If your terminal supports it, interrupt the current response and send a queued follow-up immediately |
-| `Esc` | Clear a queued follow-up or interrupt the current response |
+| `Shift+Tab` | Toggle between build mode and plan mode. |
+| `Ctrl+Enter` | If your terminal supports it, interrupt the current response and send a queued follow-up immediately. |
+| `Esc` | Clear a queued follow-up or interrupt the current response. |
 
 ## Examples
 

platform-cloud/docs/seqera-ai/nextflow-lsp.md

@@ -11,9 +11,9 @@ Seqera Cloud users receive $20 in free credits to get started with Seqera AI. [C
 
 When you ask Seqera AI to help with code in your workspace, it uses language server (LSP) context to provide:
 
-- Explanations for errors and warnings in your code
-- Context-aware completions and suggestions
-- Better navigation and understanding across project files
+- Explanations for errors and warnings in your code.
+- Context-aware completions and suggestions.
+- Better navigation and understanding across project files.
 
 For Nextflow projects, this includes diagnostics and code intelligence for scripts and config files.