Skip to content

agents.md

Latest commit

 

History

History
112 lines (84 loc) · 4.57 KB

agents.md

File metadata and controls

112 lines (84 loc) · 4.57 KB

Agent Instructions

Coding Guidelines

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is over complicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove preexisting dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multistep tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Tooling

Package Management

  • The package manger for the project is uv
  • Make uv add for core dependencies, uv add --dev for developer dependencies, and add optional features to groups
  • It is also possible to remove packages using uv remove

Conventions

Python

  • The targets python versions greater than or equal to 3.12
  • Given the project targets a more modern python, use functionality such as:
    • The walrus operator (:=)
    • Modern type hints (dict)
    • Type parameters class MyClass[T: MyParent]: ...
    • The Self type for return types (from typing import Self)
  • Type annotations:
    • Do not annotate self parameters - the type is implicit
    • Use Self for return types when returning the instance
    • Example: def add_item(self, item: str) -> Self: ... (note: no type on self)
  • Classes and data structures:
    • Use @dataclass (from dataclasses) instead of manually defining __init__ for data-holding classes
    • Consider using slots=True for memory efficiency and attribute access protection
    • Use kw_only=True to require keyword arguments for better readability at call sites
    • Use frozen=True for immutable data structures
    • Example: @dataclass(slots=True, kw_only=True, frozen=True)
    • When NOT to use dataclass:
      • Inheriting from non-dataclass parents (can cause MRO and initialization issues)
      • Need for __new__ method (for singleton patterns, custom object creation)
      • Complex property logic with getters/setters that transform data
      • Need for __init_subclass__ or metaclass customization
      • Classes with significant behavior/methods (prefer traditional classes for these)
    • When to use dataclass:
      • Simple data containers with minimal logic
      • Configuration objects, DTOs (Data Transfer Objects), result types
      • Immutable value objects (use frozen=True)
      • When you want automatic __eq__, __repr__, __hash__ implementations
  • Prefer importing using from x import y instead of import x
  • Import local modules using the full path (ex: from my_project.my_module import MyClass)
  • Don't use docstrings, instead add inline comments only in places where there is complex or easily breakable logic
  • For type aliases, prefer Python's modern syntax: type MyAlias = SomeType (PEP 695 style), especially in new code.
  • URL construction:
    • Use urllib.parse methods for URL manipulation (don't use string concatenation or f-strings for query params)
    • Use urlencode() for query parameters
    • Use urlparse() and urlunparse() for URL composition
    • Example: urlunparse((parsed.scheme, parsed.netloc, parsed.path, "", urlencode(params), ""))
    • This ensures proper encoding and avoids common URL injection vulnerabilities