docs(agents): collapse aggregate validation guidance - #54
Merged
Conversation
Member
Author
|
Deep self-review confirmed tools/validate.py already owns contracts, schemas, syntax, audits, collection, licensing, and runtime packaging, so removing duplicated command prose preserves coverage. Main-branch validation is green; no open finding remains. |
zoeyrose
added a commit
to atrinik/atrinik
that referenced
this pull request
Aug 9, 2026
## Summary - Make root AGENTS a durable ownership and safety router, preserve the new preview-first cleanup contract from #293, and establish docs/PROVENANCE.md as the canonical grant registry. - Split the multi-repository migration procedure into an on-demand reference, remove unconditional broad reads, correct stale C/protocol/content/runtime/scenario routes, and shrink discovery metadata. - Add a dependency-free guidance inventory with byte ceilings and tests for budgets, local pointers, canonical provenance, and stale-route regressions. ## Exact o200k_base results Counts are repository-owned text, excluding chat/tool envelopes. Prompt cases were cross-checked with codex debug prompt-input; ordinary-root catalog paths are normalized from the review-worktree path. | Scenario | Issue baseline | Final | Reduction | | --- | ---: | ---: | ---: | | Wrapper startup | 2,819 | 1,557 | 44.8% | | Wrapper + multi-repository skill | 7,002 | 2,905 | 58.5% | | Wrapper + multi + runtime + scenario | 8,339 | 3,572 | 57.2% | | Standalone classic/server startup | 3,474 | 1,751 | 49.6% | | Skill catalog at ordinary wrapper root | 575 | 354 | 38.4% | Replacement AGENTS raw-text counts are client 1,918 to 975; server 2,501 to 967; protocol 2,643 to 987; editor 2,155 to 859; renderer 2,046 to 883; content-toolkit 1,918 to 763; and website 1,914 to 858. ## Coordinated owning-repository PRs - atrinik/client#48 - atrinik/server#73 - atrinik/protocol#19 - atrinik/editor#21 - atrinik/renderer#27 - atrinik/content-toolkit#15 - atrinik/website#13 - atrinik/classic#35 - atrinik/content#54 (main) - atrinik/content#53 (1.x) ## Validation - 267 wrapper tests under coverage; 77% combined statement/branch coverage - compileall, manifest validation, all seven skill validators, guidance inventory, cleanup dry-run, and git diff --check - profile-aware supply-chain audit with the classic review worktree and clean current tools checkout - complete validators in every replacement and content checkout; classic import/root/release/protocol/libatrinik/ShellCheck/Actionlint validation Coordinates #294. Runtime launch is not applicable to guidance-only orchestration changes; component build, packaging, GPU, content collection, and policy paths were validated in their owning repositories.
|
🎉 This PR is included in version 2.0.2 🎉 The release is available on:
Your semantic-release bot 📦🚀 |
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
1 participant
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.
Summary
Validation