eval-core 0.3.0

A testing framework for LLM agents: prompt-based test cases with built-in assertions on tool calls, parameters, and text/math output — bring your own harness.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14

# Build output.
/target

# rustfmt backup files.
**/*.rs.bk

# Claude Code local tooling + project instructions — not part of the published crate.
/.claude/
/CLAUDE.md

# NOTE on Cargo.lock: a *library* may omit Cargo.lock from version control (downstream consumers
# resolve their own lockfile). We intentionally do NOT ignore it here — committing Cargo.lock makes
# `cargo test`/CI fully reproducible and is harmless for a lib. Delete this note (and add
# `Cargo.lock`) only if you decide to follow the leave-it-out convention instead.