builder@DESKTOP-QADGF36:~/Workspaces/myTest$ curl -fsSL https://opencode.ai/install | bash

Installing opencode version: 1.15.10
■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■ 100%
Successfully added opencode to $PATH in /home/builder/.bashrc

                                 ▄
█▀▀█ █▀▀█ █▀▀█ █▀▀▄ █▀▀▀ █▀▀█ █▀▀█ █▀▀█
█░░█ █░░█ █▀▀▀ █░░█ █░░░ █░░█ █░░█ █▀▀▀
▀▀▀▀ █▀▀▀ ▀▀▀▀ ▀  ▀ ▀▀▀▀ ▀▀▀▀ ▀▀▀▀ ▀▀▀▀


OpenCode includes free models, to start:

cd <project>  # Open directory
opencode      # Run command

For more information visit https://opencode.ai/docs


builder@DESKTOP-QADGF36:~/Workspaces/myTest$

  "permission": {
    "edit": "allow"
  },

builder@bosgamerz9:~$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 24.04.2 LTS
Release:        24.04
Codename:       noble
builder@bosgamerz9:~$ curl -fsSL https://opencode.ai/install | bash

Installing opencode version: 1.15.10
■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■ 100%
Successfully added opencode to $PATH in /home/builder/.bashrc

                                 ▄
█▀▀█ █▀▀█ █▀▀█ █▀▀▄ █▀▀▀ █▀▀█ █▀▀█ █▀▀█
█░░█ █░░█ █▀▀▀ █░░█ █░░░ █░░█ █░░█ █▀▀▀
▀▀▀▀ █▀▀▀ ▀▀▀▀ ▀  ▀ ▀▀▀▀ ▀▀▀▀ ▀▀▀▀ ▀▀▀▀


OpenCode includes free models, to start:

cd <project>  # Open directory
opencode      # Run command

For more information visit https://opencode.ai/docs

builder@bosgamerz9:~/Workspaces/mytest$ ls -ltra
total 8
drwxrwxr-x 8 builder builder 4096 May 25 14:43 ..
drwxrwxr-x 2 builder builder 4096 May 25 14:43 .

Create or update `AGENTS.md` for this repository.
The goal is a compact instruction file that helps future OpenCode sessions avoid mistakes and ramp up quickly. Every line should answer: "Would an agent likely miss this without help?" If not, leave it out.
User-provided focus or constraints (honor these):
with path set to /home/builder/Workspaces/mytest
## How to investigate
Read the highest-value sources first:
- `README*`, root manifests, workspace config, lockfiles
- build, test, lint, formatter, typecheck, and codegen config
- CI workflows and pre-commit / task runner config
- existing instruction files (`AGENTS.md`, `CLAUDE.md`, `.cursor/rules/`, `.cursorrules`, `.github/copilot-instructions.md`)
- repo-local OpenCode config such as `opencode.json`
If architecture is still unclear after reading config and docs, inspect a small number of representative code files to find the real entrypoints, package boundaries, and execution flow. Prefer reading the files that explain how the system is wired together over random leaf files.
Prefer executable sources of truth over prose. If docs conflict with config or scripts, trust the executable source and only keep what you can verify.
## What to extract
Look for the highest-signal facts for an agent working in this repo:
- exact developer commands, especially non-obvious ones
- how to run a single test, a single package, or a focused verification step
- required command order when it matters, such as `lint -> typecheck -> test`
- monorepo or multi-package boundaries, ownership of major directories, and the real app/library entrypoints
- framework or toolchain quirks: generated code, migrations, codegen, build artifacts, special env loading, dev servers, infra deploy flow
- repo-specific style or workflow conventions that differ from defaults
- testing quirks: fixtures, integration test prerequisites, snapshot workflows, required services, flaky or expensive suites
- important constraints from existing instruction files worth preserving
Good `AGENTS.md` content is usually hard-earned context that took reading multiple files to infer.
## Questions
Only ask the user questions if the repo cannot answer something important. Use the `question` tool for one short batch at most.
Good questions:
- undocumented team conventions
- branch / PR / release expectations
- missing setup or test prerequisites that are known but not written down
Do not ask about anything the repo already makes clear.
## Writing rules
Include only high-signal, repo-specific guidance such as:
- exact commands and shortcuts the agent would otherwise guess wrong
- architecture notes that are not obvious from filenames
- conventions that differ from language or framework defaults
- setup requirements, environment quirks, and operational gotchas
- references to existing instruction sources that matter
Exclude:
- generic software advice
- long tutorials or exhaustive file trees
- obvious language conventions
- speculative claims or anything you could not verify
- content better stored in another file referenced via `opencode.json` `instructions`
When in doubt, omit.
Prefer short sections and bullets. If the repo is simple, keep the file simple. If the repo is large, summarize the few structural facts that actually change how an agent should work.
If `AGENTS.md` already exists at `/`, improve it in place rather than rewriting blindly. Preserve verified useful guidance, delete fluff or stale claims, and reconcile it with the current codebase.

$ bunx opencode-supermemory@latest install --no-tui

$ cat ~/.config/opencode/opencode.json | head -n10
{
  "$schema": "https://opencode.ai/config.json",
  "permission": {
    "edit": "allow"
  },
  "provider": {
    "ollama143": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "http://192.168.1.143:11434/v1"

builder@builder-Lenny16:~/Workspaces/mytest2$ ls -ltra
total 20
drwxrwxr-x 15 builder builder 4096 May 25 16:02 ..
-rw-rw-r--  1 builder builder   97 May 26 07:09 README.md
-rw-rw-r--  1 builder builder   50 May 26 07:26 requirements.txt
-rw-rw-r--  1 builder builder  515 May 26 07:26 server.py
drwxrwxr-x  2 builder builder 4096 May 26 07:26 .

builder@builder-Lenny16:~/Workspaces/mytest2$ cat Dockerfile
# Docker Setup

This repository contains the necessary files to build and run a Docker container for `mytest2`.

## Building the Image

To build the Docker image, navigate to the project root and execute:
---bash
docker build -t mytest2 .
---

## Running the Container

After building, you can run the container with:
---bash
docker run --name mytest2_container -dit mytest2
---

## Usage

You can interact with the running container using:
---bash
docker exec -it mytest2_container /bin/sh
---

---

## Contributing

We welcome contributions! Please follow these guidelines:
1. Fork the repository.
2. Create a new branch for your feature: `git checkout -b feature/YourFeature`.
3. Make changes and commit them: `git commit -m "Add descriptive commit message"`.
4. Push to your fork: `git push origin feature/YourFeature`.
5. Open a Pull Request against the main branch.

### Code of Conduct

This project adheres to a [Code of Conduct](CODE_OF_CONDUCT.md). By participating, you agree to uphold these guidelines.

$ npm install -g cline

builder@bosgamerz9:~/Workspaces/mytest$ cline

Session Summary
  ID        1779793430569_u5y6s
  Duration  526s
  Model     ollama:qwen3:8b
  CWD       /home/builder/Workspaces/mytest
  Messages  6
  Cost      $0.00
  Continue  cline --id 1779793430569_u5y6s

builder@bosgamerz9:~/Workspaces/mytest$ cat AGENTS.md
## AGENTS

### Overview

This section provides an overview of the agents and their roles in the repository.

### Agents

#### 1. Cline
- **Role**: Main AI coding agent
- **Responsibilities**: Assisting users with coding tasks, generating code, testing, and maintaining code quality.
- **Functions**: Code generation, testing, file manipulation, and system interaction.

#### 2. Helper Agents
- **Role**: Sub-agents or teammates that assist with specialized tasks.
- **Responsibilities**: Performing focused tasks such as testing, documentation, and system monitoring.
- **Functions**: Task delegation, system monitoring, and documentation.

### Teammates

#### 1. Documentation Agent
- **Role**: Assisting with documentation and maintaining code quality.
- **Responsibilities**: Generating and updating documentation for code changes.
- **Functions**: Documentation generation, code quality checks.

#### 2. Testing Agent
- **Role**: Ensuring the correctness of code changes.
- **Responsibilities**: Writing and running tests for new features and bug fixes.
- **Functions**: Test generation, test execution, and test reporting.

### Conclusion

This repository uses a team of agents to ensure code quality, maintain documentation, and streamline development tasks.

**Last Updated**: 5/26/2026builder@bosgamerz9:~/Workspaces/mytest$

builder@DESKTOP-QADGF36:~/Workspaces/mytest2$ cline

Session Summary
  ID        1779793718556_3kd9r
  Duration  270s
  Model     ollama:gemma4:e4b
  CWD       /home/builder/Workspaces/mytest2
  Messages  17
  Cost      $0.00
  Continue  cline --id 1779793718556_3kd9r

builder@DESKTOP-QADGF36:~/Workspaces/mytest2$ cat AGENTS.md
# Agent Guide: MyTest2 Repository Instructions

This file serves as a highly condensed, machine-readable guide for AI agents working in this repository. Every line documents a process, command, or convention that an agent might otherwise guess incorrectly or miss entirely. **Follow this guide strictly.**

## 🚀 Getting Started & Setup
*   **Installation:** Always run `npm ci` (or `yarn install --frozen-lockfile`) to ensure dependencies match the lockfile exactly. Do not rely on `npm install`.
*   **Environment:** The system requires the `NODE_ENV` to be set to `development` for local server startups, even if the build process uses `production`.
*   **Required Tools:** Ensure `eslint`, `prettier`, and `typescript` are installed as dev dependencies.

## 🏗️ Development Workflow & Commands
*   **Pre-flight Check Order:** When debugging or making changes, the required command order is critical and must be followed: `(1) lint -> (2) typecheck -> (3) test`. Never skip a step.
    1.  **Linting (Style Check):** Run `npm run lint:fix` first to automatically correct style issues. Failure here means a structural style problem exists.
    2.  **Type Checking (Structural Check):** Run `npm run typecheck`. This is a *compile-time* check and does not test runtime execution, but it catches incorrect API usage or missing types.
    3.  **Testing (Execution Check):** Only run `npm test` *after* linting and typechecking pass successfully. This ensures the test environment is clean.

*   **Running Single Tests:** To focus verification, use the specific test utility provided by the framework (e.g., `npx jest --only-tests="Feature X Test"`). Passing the test name/file path is mandatory.

## 🧩 Architecture & Boundaries
*   **Monorepo Structure:** This repository is structured as a mono-repo. The core application logic resides in the `src/` directory. Specific libraries/modules are located in `packages/`.
*   **Entry Point:** The main application entry point is located at `src/index.js` (or `src/main.ts`).
*   **Data/Models:** All primary data models and interfaces are defined in `src/models/`. **Do not** write business logic directly in these files; they are purely declarative.
*   **Service Layer:** Business logic MUST be encapsulated within the `services/` directory. Services are responsible for coordinating model interactions and external API calls.

## 🔧 Toolchain Quirks & Gotchas
*   **Database Migrations:** Running database changes requires the dedicated migration step: `npm run db:migrate`. This runs *before* any testing suite that depends on the updated schema.
*   **Generated Code:** Files within `src/generated/` or `packages/utils/generated/` are *never* to be edited manually. They are the output of the codegen process.
*   **Mocking:** When writing integration tests, always use the `MockService` class located in `test/mocks/` to control external dependencies (e.g., payment gateways, third-party APIs).

## ⛔ Exclusions
*   Do not rely on simple `npm run dev` for production readiness validation. It is only for local development.
*   If a feature involves state or side effects, the implementation should use the `EventBus` pattern documented in `src/utils/event.js`, not direct global modification.

builder@DESKTOP-QADGF36:~/Workspaces/mytest2$ ls
CONTRIBUTING.md  Dockerfile  README.md  mcp_server.py  requirements.txt  src
builder@DESKTOP-QADGF36:~/Workspaces/mytest2$ tree .
.
├── CONTRIBUTING.md
├── Dockerfile
├── README.md
├── mcp_server.py
├── requirements.txt
└── src
    └── tools
        └── hello_world_tool.py

2 directories, 6 files

$ npm install -g --force --ignore-scripts @earendil-works/pi-coding-agent

builder@builder-Lenny16:~/Workspaces/mytest2$ cat Dockerfile
# Use an official Python runtime as a parent image
FROM python:3.11-slim

# Set the working directory in the container
WORKDIR /app

# Copy the requirements file and install dependencies
# This step is cached unless requirements.txt changes
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the rest of the application code
COPY server.py .

# Expose the port the application runs on (from server.py: port 5000)
EXPOSE 5000

# Command to run the application
# We use the python command structure defined in server.py
CMD ["python", "server.py"]

$ sudo ubuntu-drivers install
$ sudo reboot