Skip to content

Implementation Plan: T5-P5-A2-WP1 — Invariant Registry Coverage Meta-Test#4143

Merged
Trecek merged 4 commits into
developfrom
t5-p5-a2-wp1-provide-a-load-bearing-meta-test-that-validates/4033
Jun 28, 2026
Merged

Implementation Plan: T5-P5-A2-WP1 — Invariant Registry Coverage Meta-Test#4143
Trecek merged 4 commits into
developfrom
t5-p5-a2-wp1-provide-a-load-bearing-meta-test-that-validates/4033

Conversation

@Trecek

@Trecek Trecek commented Jun 28, 2026

Copy link
Copy Markdown
Collaborator

Summary

Add a load-bearing meta-test at tests/arch/test_invariant_registry_coverage.py that validates every InvariantDef in INVARIANT_REGISTRY has a resolvable gate_target, non-empty required fields, and a source_doc that still contains the original prohibition prose. Three test functions plus a helper. Update tests/arch/AGENTS.md file-table with the new entry.

Closes #4033

Implementation Plan

Plan file: /home/talon/projects/autoskillit-runs/impl-20260628-082224-932884/.autoskillit/temp/make-plan/t5-p5-a2-wp1-invariant-registry-meta-test_plan_2026-06-28_090000.md

🤖 Generated with Claude Code via AutoSkillit

Token Usage Summary

Step Model count uncached output cache_read peak_ctx turns cache_write time
plan* opus[1m] 1 2.3k 33.2k 2.1M 103.0k 56 87.0k 26m 44s
verify* sonnet 1 284 55.7k 3.4M 147.0k 103 128.5k 17m 35s
implement* MiniMax-M3 1 66.3k 7.1k 1.5M 0 58 0 3m 20s
audit_impl* sonnet 1 44 7.5k 163.9k 42.2k 13 31.5k 4m 1s
prepare_pr* MiniMax-M3 1 42.0k 2.0k 152.2k 0 13 0 38s
compose_pr* MiniMax-M3 1 35.8k 1.3k 140.7k 0 13 0 30s
review_pr* sonnet 1 156 19.9k 949.2k 67.1k 43 49.6k 5m 42s
resolve_review* sonnet 1 239 18.2k 2.0M 90.4k 67 72.3k 7m 50s
Total 147.1k 145.0k 10.5M 147.0k 368.9k 1h 6m

* Step used a non-Anthropic provider; caching behavior may differ.

Token Efficiency

Step LoC Changed cache_read/LoC cache_write/LoC output/LoC
plan 0
verify 0
implement 139 10950.9 0.0 51.1
audit_impl 0
prepare_pr 0
compose_pr 0
review_pr 0
resolve_review 27 74733.0 2678.9 672.9
Total 166 63230.3 2222.1 873.5

Model Usage Breakdown

Model steps uncached output cache_read cache_write time
opus[1m] 1 2.3k 33.2k 2.1M 87.0k 26m 44s
sonnet 4 723 101.4k 6.6M 281.8k 35m 11s
MiniMax-M3 3 144.1k 10.4k 1.8M 0 4m 28s

Trecek and others added 4 commits June 28, 2026 09:06
- tests/arch/test_invariant_registry_coverage.py verifies every
  InvariantDef has a resolvable gate_target, non-empty required
  fields, and a source_doc that still contains the original
  prohibition prose anchor.
- tests/arch/AGENTS.md file-table updated with the new entry.
Without this fallback, single-word gate_target values (e.g. "autoskillit")
would silently return False despite being importable modules.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ry_entries

Avoids O(invariants × files) disk reads — content is now read once per
unique source_doc and reused for subsequent invariants sharing the same doc.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…action

A 30-char prefix may not appear verbatim in source_doc if formatting differs.
Extracting the longest word (>= 5 chars) is more distinctive and reliable.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@Trecek Trecek added this pull request to the merge queue Jun 28, 2026
Merged via the queue into develop with commit 78f755d Jun 28, 2026
3 checks passed
@Trecek Trecek deleted the t5-p5-a2-wp1-provide-a-load-bearing-meta-test-that-validates/4033 branch June 28, 2026 16:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant