Repository navigation
Conversation
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Contributor
🤖 CI report🚨 Trunk lane — universal laneThis PR is assigned to the universal lane. It cannot merge in parallel with other PRs, so it can take longer to merge. Ask dev-ex if you think this is wrong. ✅ Duplication (Python) — cleanNew Python code duplication introduced by this branch. Fails at 70+ tokens in app code, or 150+ tokens when both copies live in test files. Advisory while the gate proves itself: extract a shared helper instead of copying. ✅ Duplication (TypeScript) — cleanNew TypeScript code duplication introduced by this branch. Fails at 70+ tokens in app code, or 150+ tokens when both copies live in test files. Advisory while the gate proves itself: extract a shared helper instead of copying. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
AGENTS.mdin full, so each line added to it costs every task./editing-agents-mdstates a target of under 200 lines, and no check enforces it.Changes
test_agents_md_size_budget.py, fails when the rootAGENTS.mdexceeds 23,000 bytes..agents/guide or a skill, or cut an older line./editing-agents-mdnow names the test, replaces the 200-line target with it, and asks for a reason in the PR before anyone raises the budget.repo_invariantsCI filter already matchesAGENTS.md, so an edit to the file runs the test.Note
Stacked on #123122. That PR comes from a fork, so its head sits in this repo as
stack/slim-root-agentsto give this PR a clean diff. Retarget tomasteronce #123122 merges.How did you test this code?
Test rationale: the new test catches the root file growing past its budget. No existing test checks the size. The tag invariant checks only the content.
Release status
Docs update
None. The
/editing-agents-mdskill carries the budget rule.🤖 Agent context
Autonomy: Human-driven (agent-assisted)
Agent: Claude Code, Claude Opus 5.5 (
claude-opus-5-5)hogli agent:usage) and feat(agents): hint on resume when a session's context is large and cold #123369 (SessionStart hint)./editing-agents-md,/writing-tests,/writing-pr-descriptions.AGENTS.md.🤖 Generated with Claude Code