Repository navigation
Develop - #4
Merged
Merged
Develop#4
Conversation
A tinylib sandbox with seven AGENTS.md rules (CLAUDE.md is a symlink to the same file), four tasks that each tempt a different rule, a runner that gives every run a fresh copy with its own venv and git repo, and an analyzer that scores each manifest run from its session log. Marked as a legacy pilot harness: it measures adherence only, and the README lists its limits.
… init --from - keeptrue ablate plan/run/report (experimental): frozen Git snapshots and standalone verifiers, paired leave-one-unit-out slots, a bounded Codex runner behind a zero-cost OS-sandbox preflight, and offline HTML/JSON/ Markdown reports with task-weighted paired effects. An offline synthetic demo runs in CI. - Missing token/time observations stay unknown in adapters and reports; per-success costs are withheld when coverage is partial. - init --from abstains on conditional or unsupported instructions, keeps scoped parent text and skips fenced examples; config rejects duplicate or blank rule IDs. - Codex execution records no longer hide unrelated denied or unmatched calls; Claude partial/full snapshots no longer inflate final-message length. - A Ctrl-C during verification now stops the run loop instead of launching the next paid slot. - docs/instruction-experiments.md and docs/validation-status.md.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.