@pageai/ralph-loop 1.17.0 → 1.20.0

package/.agent/STEERING.md

@@ -29,8 +29,6 @@ This sandbox runs emulated aarch64 Linux. Apply as needed:
      Fix: `rm -rf node_modules/<corrupt-pkg> && npm install --ignore-scripts`
      Re-scan until clean. Only then start the dev server.
 
-- **If using TanStack Start:** Check that `src/integrations/tanstack-query/root-provider.tsx` has a default export wrapping children with `QueryClientProvider`. The starter template ships without it, causing a 500 on load.
-
 ## Main Tasks
 
 Install dependencies (using the sequence above), then install Playwright system dependencies: `sudo npx playwright install-deps chromium 2>&1`. Allow up to 10 minutes for tasks to complete.

package/README.md

@@ -1,6 +1,6 @@
 # A Ralph Wiggum Loop implementation that works™
 
-[![@pageai/ralph-loop version](https://img.shields.io/npm/v/@pageai/ralph-loop?label=npm&style=flat)](https://github.com/pageai-pro/ralph-loop)
+[![@pageai/ralph-loop version](https://img.shields.io/npm/v/@pageai/ralph-loop?label=npm&style=flat)](https://www.npmjs.com/package/@pageai/ralph-loop)
 
 Ralph is a long-running AI agent loop. Ralph automates software development tasks by iteratively working through a task list until completion. This allows for long running agent loops, effectively enabling AI to code for days at a time.
 
@@ -25,6 +25,7 @@ This is an implementation that actually works, containing a hackable script so y
   - [Promise Tags](#promise-tags)
   - [Exit Codes](#exit-codes)
 - [Structure](#structure)
+- [Continued Development](#continued-development)
 - [Skills](#skills)
   - [Available Skills](#available-skills)
   - [Skills Directory Structure](#skills-directory-structure)
@@ -33,6 +34,8 @@ This is an implementation that actually works, containing a hackable script so y
   - [Vitest configuration](#vitest-configuration)
   - [Running with a different agentic CLI](#running-with-a-different-agentic-cli)
   - [Starting from scratch](#starting-from-scratch)
+  - [Debugging](#debugging)
+- [How to inspect the sandbox and debug](#how-to-inspect-the-sandbox-and-debug)
 - [License](#license)
 
 ---------------------------------
@@ -257,6 +260,24 @@ Ralph uses semantic tags to communicate status:
 └── skills/             # Shared skills (source of truth)
 ```
 
+## Continued Development
+
+As Ralph implements tasks, you might notice that you want some tweaks, features or even bug fixes.<br/>
+To do so, you need to continue using the `prd-creator` skill to update the PRD and task list.
+
+For example:
+
+```
+I would like to expand the PRD. Use the prd-creator skill to create these tasks:
+
+- there is a bug in X that should be fixed by doing Y
+- create a new feature that implement Z
+
+etc.
+```
+
+It's fine to add multiple tasks at once.
+
 ## Skills
 
 Skills are reusable agent capabilities that provide specialized knowledge and workflows. The canonical source is `.agent/skills/`, which is symlinked to multiple agent tool directories for compatibility.
@@ -419,6 +440,38 @@ npm i @vitejs/plugin-react @testing-library/dom @testing-library/jest-dom @testi
 
 It is recommended that you add skills for your specific language and framework. See [skills.sh](https://skills.sh) to discover existing skills.
 
+### Debugging
+
+## How to inspect the sandbox and debug
+
+You might be wondering... if this is not a Docker container, how can you see what's going on inside Docker!?
+How to debug/install things?
+
+That's quite straightforward.
+
+You first need to run:
+
+```bash
+docker sandbox list
+```
+
+Note down the name of the sandbox, e.g. `claude-ralph-loop`.
+
+And then you can run bash into any of the sandboxes like so:
+```bash
+docker sandbox exec -it <sandbox-name> bash # e.g. docker sandbox exec -it claude-ralph-loop bash
+```
+
+And you have full control over the sandbox, just like a regular container. You can install packages, run commands, etc.
+
+You can also also run Claude Code inside the sandbox (make sure to navigate to the project directory first).
+
+```bash
+docker sandbox exec -it <sandbox-name> bash
+cd /path/to/your/project # this is the same path as the path in the root machine, e.g. /Users/your-username/Documents/your-project
+claude
+```
+
 ## License
 
 MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pageai/ralph-loop",
-  "version": "1.17.0",
+  "version": "1.20.0",
   "publishConfig": {
     "access": "public"
   },

package/ralph.sh

@@ -98,7 +98,7 @@ $(cat $SCRIPT_DIR/.agent/PROMPT.md)"
   export PROMPT_CONTENT
   export DOCKER_DEFAULT_PLATFORM=linux/amd64 # Needed for Playwright.
 
-  script -q "$OUTPUT_FILE" bash -c 'docker sandbox run claude . -- --model opus --output-format stream-json --verbose -p "$PROMPT_CONTENT"' >/dev/null 2>&1 &
+  script -q "$OUTPUT_FILE" bash -c 'docker sandbox run claude . -- --effort max --model opus --output-format stream-json --verbose -p "$PROMPT_CONTENT"' >/dev/null 2>&1 &
   AGENT_PID=$!
 
   # Track position in output file for incremental reading