TL;DR: Agents won’t loop autonomously in long multi-round tasks. They keep asking “should I continue?” Worse: from round 2 onward, the agent quietly merged the protocol’s mandatory five-role separation into four. Clean formatting hid the violation. This isn’t context compression. It’s protocol drift: systematic degradation in long-horizon tasks. Part 1 of 3. Part 2: Deep Root Causes June 11, 8 PM I told my agent to run a Ralph Review Loop on six module test plans. This is a multi-round review protocol I defined in my open-source tool tdd-pipeline [1]: each round dispatches independent subagents to find issues, locate files, confirm defects, and evaluate fixes. The loop stops after two consecutive rounds with zero Critical/High/Medium (CHM) findings. The protocol was unambiguous: “Fixes do not require user confirmation.” ...

This is the Day 7 exercise for Week 2 of the “AI Path: Level Up Guide” series. Complete Day 6: Batch Processing Practice first. In Day 6, you wrote a batch processing script that works. Pick a scenario, walk the folder, call the API, save the results. It all runs smoothly until you try it for real. But that script runs in an idealized environment. Real networks are not ideal. Have you hit any of these with your script? ...

This is the Day 6 exercise for Week 2 of the “AI Path: Level Up Guide” series. Complete Day 5: Teach Your Script to Read More File Formats first, then come back here to work through Day 6. In Day 5: Teach Your Script to Read More File Formats, you built the read_file() function and the skeleton of a batch script. Your script recognizes files in various formats now. But you haven’t run a full pipeline from start to finish yet. You still need to pick a scenario, call the API, and save the results. That loop is missing. ...

This is Day 5 of Week 2 in the “AI Path L1→L2 Upgrade Guide” exercises. Read Part 2 first, then come back here. The batch_summarize.py script from Part 2 handles .md and .txt files. But real files come in many more formats. PDF reports, Word contracts, CSV data tables, JSON config files. They’re sitting on your desktop right now, and the script can’t touch them. Today’s goal: write a read_file() function that picks the right reader based on file extension, then plug it into the Part 2 batch script. ...

This is Part 2 of the “AI Path L1→L2 Upgrade Guide” series. Complete Part 1 and the first three days of exercises (Day 1, Day 2, Day 3) before continuing. Part 1 taught you to make one API call. Today you’re going bigger: make your program ask AI 100 questions. Manually pasting text into a chat window 100 times is grunt work. Writing a 10-minute script to automate the task is worth it. You get the time back. ...

This is the Day 3 companion exercise. Complete Day 1 first. Part 1 covers the theory (“Understanding API Parameters”). Today you verify it with your own eyes. Part 1 explained parameters in theory. But theory without practice is just noise. Today you run three experiments and see for yourself how parameters affect output. Setup Make sure your Day 1 project still works: uv run python hello_api.py If the AI replies, your environment is ready. All experiments below build on this code. ...

This is Part 2 of When Your AI Coding Tool Needs Three Configs. Part 1 covered the config design, file structure, and orchestration philosophy. This article focuses on fallback mechanisms. omo = oh-my-openagent, oms = oh-my-opencode-slim. Model and provider names are anonymized as provider-a/model-x etc. Why Bother Understanding Fallback omo and oms both support fallback: automatic switching to backup when the primary model is unavailable. But their mechanisms differ completely: omo is a multi-layer pipeline that degrades step by step; oms uses startup model selection + runtime abort retry. You need to understand this difference to configure a reliable chain. ...

This is the Day 2 companion exercise. Complete Day 1 first. Yesterday you ran your first API call through DeepSeek’s official API. Today you do one thing: switch to a different platform, change two parameters in the same code, and run it again. You’ll see that learning one platform’s API means you’ve learned them all, as long as they’re compatible with the OpenAI interface. What Is an Aggregator Platform An aggregator platform is a middle layer. You register one account, top up once, and get access to dozens of AI models (OpenAI, Anthropic, Google, etc.) without signing up at each official platform separately. ...

Why I Need Three OpenCode Configs I have three opencode.json files in my ~/.config/opencode/ directory. The reason is simple: I wanted to run oh-my-openagent (omo from here on) and oh-my-opencode-slim (oms from here on) side by side, comparing them to understand where each one’s boundaries lie. omo is the full version—it comes with a batch of built-in agents (Sisyphus, Atlas, Prometheus, Oracle, Explore, Librarian, Metis, Momus, etc.), plus the ones I register on demand. The core is the fallback chain and the Sisyphus orchestrator: throw a refactoring task at Sisyphus, and it breaks the task down for Prometheus to plan, Atlas to execute the plan and distribute subtasks, Explore to search code, Oracle to analyze, then Sisyphus aggregates the results. oms is the slim version—it also has an orchestrator as the main agent responsible for executing tasks, but the difference is in the review phase: oms uses council multi-model consensus, where multiple councillors review results in parallel, and the Council agent synthesizes outputs from all councillors to reach a final conclusion. ...

This is the Day 1 companion exercise for the AI Path L1→L2 Upgrade Guide. Read Part 1 first, then come back here to practice. Today you do exactly one thing: run hello_api.py from Part 1 and see AI reply in your terminal. Prerequisites Complete these steps from Part 1 (skip if already done): Register a DeepSeek developer account (Part 1, “Register for API Accounts”) Get your API key and save it to a .env file (Part 1, “API Key Safety”) Install uv and Python 3.12 (Part 1, “Install Python”) Create a virtual environment and install dependencies (Part 1, “Create a Virtual Environment”) Confirm your project directory looks like this: ...