---
title: "Chapter 07: The Harness"
description: "Understand why you train agentic loop behavior, then build a ~200-line single-tool harness pointed at your OpenAI-compatible server."
type: lesson
order: 7
chapter: "03-trajectories"
---

# Chapter 07: The Harness

## Objective

Build the smallest possible agent harness (~200 lines, **one** tool) pointed at the Chapter 06 server. Goal of Part 3 overall: fine-tune the 1B until it emits **syntactically valid tool calls** — not smart ones, valid ones.

---

## Concept: Behavior, not knowledge

You are **not** fine-tuning the model on your code. **You are fine-tuning it on the shape of agentic behavior.**

Codebase knowledge belongs in context at runtime — bake it into weights and you retrain when the code changes, and it hallucinates moved APIs. What small models are bad at, and what *is* stably trainable, is the loop:

> take a task → emit a well-formed tool call → read the result → reason → call again → stop when done → report

That procedure is learnable. That is what we train.

### The minimal harness

One tool:

```text
read_file(path) -> string
```

Loop:

1. System prompt describing the tool and output protocol  
2. User task  
3. Model emits a tool call  
4. Harness parses, executes, appends result  
5. Repeat until final answer or step cap  

Point it at the [Chapter 06](/fine-tune-local-agent/02-the-pipeline/06-serve-and-automate/) OpenAI-compatible endpoint.

### Protocol rule

Use a simple protocol (JSON block or XML tags) you can parse with a regex and validate. **The system prompt must be identical between training and inference.** Mismatch silently destroys everything downstream.

---

## Concept check

**Q1.** Why train the *loop* (tool-call shape, stop when done) instead of embedding the whole repo into the weights?

**Q2.** Why must the system prompt match exactly between training data and live harness runs?

<details>
<summary>Concept answer key — attempt first</summary>

## Answer key (concept)

### Q1

**Model answer:** Repo facts go stale and belong in context; the stable trainable skill is agentic procedure (call tools, use results, stop).

**Pass criteria:** behavior vs knowledge; staleness or retrieval

### Q2

**Model answer:** The model learns the protocol from the system text; a different prompt at inference is a different task and validity collapses.

**Pass criteria:** train/serve protocol identity

</details>

---

## Gate: Confirm the server is up

Smoke-test the Chapter 06 endpoint with a simple `curl` chat completion. **Pass:** HTTP 200 and a completion body.

If the server is down, fix that before writing harness code.

---

## Gate: Build the one-tool harness

Implement `harness.py` (name flexible):

- OpenAI-compatible client → your local URL  
- Parse tool calls for `read_file` only  
- Execute against a **small sandbox directory** (not your whole home folder)  
- Step cap  
- Print the final answer  

**Pass:** one hand-written task like “What is the first line of README.md?” completes with a real `read_file` call when you force or mock a good model response — or when using a strong teacher URL if you already have one.

Walk through parse failures with your tutor; do not jump to logging yet.

---

## Check your understanding

**Q3.** Why start with **one** tool instead of the full coding toolset?

**Q4.** “Valid tool call” vs “correct answer to the user’s question” — which is Part 3’s primary metric, and why start there?

<details>
<summary>Answer key — attempt every question first</summary>

## Answer key

### Q3

**Model answer:** Each tool multiplies protocol surface and required examples; one tool proves the loop and logging path first.

**Pass criteria:** protocol surface / complexity control

### Q4

**Model answer:** Validity first — syntax/protocol is the wide-open gap on small models; correctness comes after the model can speak tool language.

**Pass criteria:** validity/protocol before smart answers

</details>

---

[← Part 3 Index](/fine-tune-local-agent/03-trajectories/) · [Next: Chapter 08 →](/fine-tune-local-agent/03-trajectories/08-the-logger/)