Repository navigation
Conversation
cmp0xff
force-pushed
the
doc-agent-accountability
branch
2 times, most recently
from
September 26, 2026 21:07
70bbadb to
41ad7f0
Compare
4 of 6 tasks
3 tasks done
Co-authored-by: claude-sonnet-5-5 <noreply@anthropic.com>
cmp0xff
force-pushed
the
doc-agent-accountability
branch
from
October 31, 2026 10:41
41ad7f0 to
e44ada1
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
pandas-stubs' AGENTS.md has no disclosure rule for AI drive-by PRs, no "don't speak for the user" rule and no PR-sync rule, and contributors here are not bound by pandas' AI policy.
This adapts pandas-dev/pandas#66767 and pandas-dev/pandas#68313 to this repository: a three-field AI disclosure (Tool / Model / Reasoning effort), an "Interactions on GitHub" scope, and rules for keeping the PR in sync.
Stubs-specific additions: the agent drafts pandas-dev/pandas issues in chat instead of opening them, and the PR body must report whether
poe test_allpassed on head and list new checker ignores (the #1953 failure).poetry run poe test_allon the head commit and it passes.AGENTS.md, I fully reviewed the result, and I quote any AI output in comments with>or a code fence.AI disclosure
AI Implementation Plan
Single commit on
doc-agent-accountability, rebased onto upstream/main (cmp0xff/pandas-stubs@e44ada15).Revision after review of the earlier version (four disclosure fields,
deepseek-v4-pro):Model versiondropped (listed IDs already carry the version);Modelis taken from the harness and equals the commit trailer. "Why a fixed list" reworded so it no longer asks the agent to guess the closest identity.poe test_allcheckbox added; deleting the AI part removes the heading too.Out of scope (follow-up): leftover pandas-isms in AGENTS.md ("unless benchmarks are requested", whatsnew/benchmarks via the contributing_codebase link).
To do:
🤖 Generated with Claude Code