Repository navigation
skills: tri-pipeline fast path (t27b first, frontier --only seal reuse) and a t27o skill (Closes #10541) - #10542
Merged
Merged
Conversation
…e) and a t27o skill (Closes #10541) tri-pipeline: t27b test for the inner loop (rust_std.t27 0.89 s against 94 s for t27c test-report), t27c frontier --only for unchanged specs (REUSE = the sealed verdict stands; 5 specs in about 5 s), test-report once as the final gate, symlinked release binaries instead of rebuilds, t27b exit codes, the sandbox ZIG cache trap, git add -f for gen files; drop the stale "tri test does not yet fail on vacuous" (#10507 landed). t27o: where its truth lives, making a refusal class convertible and measuring it, --check, the loop tick for #10522, tonight's traps. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
gHashTag
enabled auto-merge (squash)
October 18, 2026 16:47
9 of 10 tasks
This was referenced Oct 18, 2026
Merged
gHashTag
disabled auto-merge
October 18, 2026 17:26
Contributor
… the scratchpad (Closes #10541) #10538 failed the required own-language check with +9/-0 hand lines in cli/tri/src/main.rs: check_budget refuses a diff whose counted foreign lines gain more than they lose, on top of the 40/80 cap. tri-pipeline says so under PRs; the t27o skill adds the numstat one-liner. The scratchpad was wiped on a session resume (worktrees, cargo target, measurements); $TMPDIR survived, so loop worktrees live there. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
gHashTag
enabled auto-merge (squash)
October 18, 2026 17:41
3 tasks done
This was referenced Oct 18, 2026
Merged
Contributor
PR DashboardGenerated at: 2026-10-18 18:38:06 UTC
Summary
Seal Status
|
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
2 participants
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.
Closes #10541. Part of #10522. Owner request 2026-10-18: use t27b and the t27c seal to go faster, and keep it in the skills.
What
.claude/skills/tri-pipeline/SKILL.md-- "One spec, end to end -- fast path first": a table of the five steps with measured costs (t27b test 0.89 s vs t27c test-report 94 s on rust_std.t27;t27c frontier --onlyreused 5 of 5 sealed verdicts in about 5 s), then: symlink existing release binaries instead of rebuilding, t27b's exit codes and which are verdicts (the rule ist27b_outcomeinledger.t27, t27o: --check judges with t27b test first (0.89 s vs 94 s), t27c test-report only when t27b cannot judge #10525 / PR t27o --check: t27b test judges first, t27c test-report only when t27b cannot (Closes #10525) #10538), the sandbox ZIG cache trap (BLOCKED / refused seal),git add -ffor a#[path]-included gen file. The stale line "tri test does not yet fail on vacuous" is gone (tri test: refuse vacuous passes -- report.t27 reads the "vacuous passes N of M" line (Closes #10497) #10507 landed)..claude/skills/t27o/SKILL.md(new): where t27o's truth lives, how to make a refusal class convertible (test first, t27b loop, regenerate, seal, measure before/after), how to measure coverage honestly (per-file time cap; root refusals vs the cascade),--check, the loop tick for [EPIC] t27o overnight loop: dogfood on the roadmap repos, t27b-fast checks, refusal classes, competitors (feeds #10486 M2) #10522 next to the analog loop, and the sandbox traps met tonight (.claude/skillsnot writable from the session worktree,--no-track, gh TLS, auto-merge by GraphQL).Checks
python3 -I tools/check_documented_commands_exist.py: ok, 138 deadtrimentions = the recorded ceiling (no new one).t27b test,t27c frontier --only ... --list,t27c test-report,t27c seal --save/--verify,t27c gen-rust,tri t27o,t27c dupes).🤖 Generated with Claude Code