Skip to content

v0.6.0

Choose a tag to compare

View all tags
@kiloloop-claude kiloloop-claude released this 20 Mar 07:54
· 4 commits to main since this release
v0.6.0
7d62cac
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's New

Changed

  • README rewritten as a conversion page with real-data hero examples, human-multiplier compression ratios, and curated worked examples
  • Updated METR threshold model fleet: Opus 4.6 (90m), GPT-5.4 (60m), Gemini 3.1 Pro (45m), Sonnet 4.6 (30m), Haiku 4.5 (15m). Legacy keys preserved
  • Updated model key aliases: claude→opus_4_6, codex→gpt_5_4, gemini→gemini_3_1_pro, sonnet→sonnet_4_6, haiku→haiku_4_5
  • Fixed frontier model tier resolution to correctly disambiguate by agent name
  • Updated pyproject.toml description to "Know what an AI task will cost before you run it"

Added

  • examples/ directory with 5 curated worked examples: coding-s, coding-m, research, documentation, multi-agent

Full Changelog: https://github.com/kiloloop/agent-estimate/blob/main/CHANGELOG.md

Assets 2
Loading