proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pagenaw10314 min readrelease notesintermediate

Show HN: Foremerge – Catch intent conflicts between parallel coding agents

Summary

Foremerge is an open‑source Rust CLI that lets multiple AI coding agents publish their intended semantic changes before they edit files, detecting intent conflicts that Git's line‑based merge cannot see. It stores intents in a local SQLite DB under .git and reports advisory warnings without locking files.

  • Agents publish intent (e.g., replace PaymentService) via `foremerge intent publish` and the tool checks for overlapping scopes like `symbol:PaymentService`.
  • Conflicts are advisory only; no file locks, so a crashed agent doesn't stall others, and the user decides how to resolve.
  • Installation is a one‑liner script or `cargo install`; the CLI provides `init`, `setup`, `checks`, and `doctor` commands to wire agents and define verification checks.
  • Foremerge stores coordination state in a SQLite DB inside the repository’s .git folder, making it visible to all local worktrees.

Teams using multiple AI code generators need a lightweight way to surface semantic clashes before they become hidden bugs, and Foremerge offers that without altering Git's workflow.

6/10

Related reading

  1. Build Your Own AI Agent Harness in C#, the MafClaw Live Series

    The post walks .NET developers through using Microsoft Agent Framework's harness to turn a simple IChatClient into a fully‑featured C# AI agent, showing code for tool integration, file sandboxing, approval flows, and memory, then outlines further capabilities like skills and observability.

    .NETmicrosoft.com10 minHN2
  2. How to Review AI-Generated Python Code Efficiently

    A practical five‑step workflow for reviewing AI‑generated Python code, covering intent clarification, automated quality checks (linters, type checkers, security scanners, tests), risk‑first manual reading, a checklist of common AI mistakes, and fix‑verify loops, plus a ready‑to‑use dev‑environment setup.

    Real Pythonrealpython.com26 min
  3. Changing the game: How Google uses agentic AI to secure hundreds of millions of lines of code

    Google’s AI & Infrastructure team built an agentic pipeline (Mantis) that runs pre‑submit AI‑driven scans on every code check‑in, validates findings with a fast triage agent (AST + call‑graph analysis) achieving >92% precision in <1 min, then auto‑generates fixes via a bug‑fix agent. Localized threat models and a two‑step scan cut false‑positives to ~3% and prevent hundreds of vulnerabilities eac…

    Google Cloud Bloggoogle.com4 min
  4. Constraint Decay: The Fragility of LLM Agents in Backend Code Generation

    A systematic evaluation of LLM agents generating multi‑file backend code shows a sharp drop in correctness when structural constraints (framework conventions, ORM usage, API contracts) are added. Across 100 tasks in 8 Python web frameworks, assertion pass rates fall ~27 points, with data‑layer bugs (bad queries, ORM violations) driving most failures. Mid‑size models cope with minimal frameworks (…

    arXiv cs.SE (Software Engineering)arxiv.org1 minpaperHN287197