# system-prompts-and-models-of-ai-tools
  
An interactive execute agent with a simple planning loop, tool registry, built-in tools (shell, filesystem, http, python eval), and pluggable model providers (echo, OpenAI, Ollama). Supports streaming and an optional web
> **Fork.** This README is generated by the [agentic harness](https://github.com/sahiixx/agentic-harness) and is
> **fork-local** — exclude it from any upstream pull request. Upstream docs are
> preserved in `README.original.md`.
## Table of Contents
- [Overview](#overview)
- [Quick Start](#quick-start)
- [Agentic Architecture](#agentic-architecture)
- [Model Routing](#model-routing)
- [Project Layout](#project-layout)
- [Development](#development)
- [Related Repositories](#related-repositories)
## Overview
An interactive execute agent with a simple planning loop, tool registry, built-in tools (shell, filesystem, http, python eval), and pluggable model providers (echo, OpenAI, Ollama). Supports streaming and an optional web
| | |
|---|---|
| **Stack** | python |
| **Frameworks** | anthropic, fastapi, openai |
| **Tests** | yes |
| **Commits** | 2 |
| **Last activity** | 2026-08-10 |
| **Origin** | fork of upstream |
## Quick Start
### Install
```bash
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt # or: pip install -e .
```
### Run
```bash
# Entry point not auto-detected; inspect the layout below.
```
## Agentic Architecture
This fork participates in the [sahiixx agentic harness](https://github.com/sahiixx/agentic-harness) — a shared
contract for how agents plan, act, verify, and recover across the account.
> **Fork note:** this file is fork-local. Drop it from any branch you open as a
> pull request upstream. The harness contract also lives in `AGENTS.md`.
**Signal strength:** agentic density score `1159`.
### Patterns in play
| Pattern | Role here |
|---|---|
| **Prompt Chaining** | Deterministic multi-step pipelines with known subtasks |
| **Routing** | Classify input, dispatch to the specialist path |
| **Parallelization** | Independent subtasks fan out; results aggregated |
| **Orchestrator–Workers** | Central planner decomposes dynamically |
| **Evaluator–Optimizer** | Generator/judge split with explicit rubric; bounded retry |
| **ReAct** | Interleaved reason → act → observe for adaptive tool use |
| **Reflection** | Self-critique before emitting a final answer |
### Reliability envelope
- **Bounded execution** — every loop has a max-iteration and wall-clock ceiling.
- **Tool sandboxing** — filesystem/network side effects isolated and reversible.
- **Guardrail layering** — validate at input, mid-loop, and output.
- **Context engineering** — select, compress, isolate; never grow unbounded.
- **Self-verification** — check intermediate output against constraints.
## Model Routing
Agent work in this fork routes through Azure AI Foundry. See [`AGENTS.md`](./AGENTS.md).
| Purpose | Deployment | Endpoint |
|---|---|---|
| Default / general | `gpt-5.6-sol` | `/openai/v1/chat/completions` |
| Deep reasoning | `claude-opus-5` | `/openai/v1/responses` **only** |
| Embeddings | `text-embedding-3-small` | `/openai/v1/embeddings` |
```bash
export AZURE_FOUNDRY_API_KEY=... # never commit this
export AZURE_FOUNDRY_BASE_URL=https://<resource>.openai.azure.com/openai/v1
```
> **Gotcha:** Claude deployments on Azure return `404 api_not_supported` on
> `/chat/completions`. They answer **only** via the Responses API.
## Project Layout
```
-Spawn/
AGENTS.md
ALL_FEATURES_COMPLETE.md
Amp/
Anthropic/
Augment Code/
BEST_PRACTICES.md
CHANGELOG.md
CODE_OF_CONDUCT.md
COMPARISON.md
COMPLETE_DELIVERY.md
COMPLETE_IMPLEMENTATION_REPORT.md
COMPLETE_IMPLEMENTATION_REPORT_V2.md
COMPLETION_REPORT_OCT_2_2025.md
```
## Development
```bash
ruff check . && ruff format .
gh workflow run hermes-azure-check.yml
```
Secrets live in environment variables and CI secrets — never in tracked files.
## Related Repositories
Part of a 226-repository workspace sharing one agentic contract:
- **[agentic-harness](https://github.com/sahiixx/agentic-harness)** — patterns, contracts, reference implementations
- `AGENTS.md` in every repo pins identical model routing
---
<sub>README maintained by the agentic harness · fork-local · regenerated 2026-08-10</sub>