Agent
Based on actual testing (tooned check, tooned pipe, tooned index, streaming scenarios, edge cases) and codebase exploration (crates/tooned-json/src/lib.rs, crates/tooned-convert/src/lib.rs, crates/tooned-metrics/src/store.rs, crates/tooned-cli/src/config.rs).
Agent
Agent "toon-context-proof" from w0wl0lxd/tooned, covering toon hook — backend flow and what the backend does.
Agent
A model given a TOON tool result extracts values by reading the header and rows directly. It does not need a toon → json conversion step; it maps the header/row structure to the question as it would for CSV or Markdown tables.
Agent
This document records actual test results from running tooned commands on real fixtures, streaming scenarios, index/metrics surfaces, and model comprehension validation. All results come from the current binary (tooned CLI) and agent CLI tests with swe-1.7-max, glm-5.2 (high), not simulated or estimated.
Agent
When tooned is installed as a PostToolUse hook with tool result replacement (updatedToolOutput for Claude Code / OpenCode / Kilo / Pi; continue: false + reason for Codex), the model receives only the TOON encoding. The original JSON is not in that context item.
Agent
tooned hook run operates as a PostToolUse command hook. The result format depends on the agent family.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: