{"repo":"genesiscode2026/genesis-deterministic-replay-mini","private":true,"description":null,"default_branch":"main","stars":0,"forks":0,"pushed_at":"2026-09-17T10:23:50Z","languages":{"Python":6698},"files":14,"tree":[".gitignore","CHANGELOG.md","LICENSE","QUICKSTART.md","README.md","SECURITY.md","VERSION","bin/genesis-replay-mini","genesis_replay_mini/__init__.py","genesis_replay_mini/__main__.py","genesis_replay_mini/replay.py","pyproject.toml","tests/fixtures/sample_trajectory.json","tests/test_replay.py"],"sizes":{".gitignore":103,"CHANGELOG.md":535,"LICENSE":1072,"QUICKSTART.md":366,"README.md":1662,"SECURITY.md":282,"VERSION":6,"bin/genesis-replay-mini":213,"genesis_replay_mini/__init__.py":160,"genesis_replay_mini/__main__.py":2236,"genesis_replay_mini/replay.py":2429,"pyproject.toml":642,"tests/fixtures/sample_trajectory.json":449,"tests/test_replay.py":1660},"readme":"# genesis-deterministic-replay-mini\n\n> **Lightweight offline tool-call recording and deterministic replay engine for AI agents.**\n\n[![Version](https://img.shields.io/badge/version-1.0.0-blue.svg)](VERSION)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Zero Dependencies](https://img.shields.io/badge/dependencies-0-brightgreen.svg)](pyproject.toml)\n\n---\n\n## The Problem\n\nDebugging multi-turn autonomous coding agents is notoriously difficult because tool invocations are non-deterministic, network-dependent, and mutating. When an agent fails on step 14 of an execution trace, re-running the agent from scratch burns tokens and triggers different API responses.\n\n## The Solution\n\n`genesis-deterministic-replay-mini` records agent tool invocations and mock return values into clean JSON trajectories. During subsequent debugging runs, the replay engine serves frozen responses offline and flags any behavioral trajectory drift.\n\n---\n\n## Key Features\n\n- **Zero External Dependencies**: Pure Python 3 standard library.\n- **Offline Mocking**: Replays complex multi-turn trajectories without real network calls or token spend.\n- **Trajectory Drift Detection**: Instantly raises `DriftError` if the agent invokes unexpected tools or mutates arguments.\n- **Human-Readable Audit CLI**: Inspect recorded trajectory steps with full argument and response details.\n\n---\n\n## Commercial Distribution\n\n- **Product Name**: `genesis-deterministic-replay-mini`\n- **Catalog ID**: `E04`\n- **Price**: $29\n- **Seller**: `genesiscode2026`\n- **Authorized Payout Rail**: USDC on Base (`0xC6F86e170411182114FcCdb28793dC76B5e8D144`)\n- **License**: MIT\n","price_usd":"29.00","clone_checkout":"https://api.checkout402.com/c/chk_YXS4guw4wXyIvtEp","rehearse_checkout":"https://api.checkout402.com/c/chk_YXS4guw4wXyIvtEp/test","preview":"/r/genesiscode2026/genesis-deterministic-replay-mini/f/<path> serves file CONTENTS for the seller's preview paths; other paths answer with the price","how_to_buy":"pay clone_checkout with x402 (pay402 does it in one call); the goods arrive as payload_base64, a tar.gz of the full repo. Rehearse first at rehearse_checkout: same flow, simulated money.","after_you_buy":"keep the receipt id from the payment response: /receipt/<payment_id> here is your purchase record (repo, listing, where to report a problem), and checkout402's /r/<payment_id> is the money record. Tell your human both URLs."}