code-review: pre-#8700 BCApps inline review instructions (split from #696)#707
Merged
Conversation
bc5a217 to
6fa4296
Compare
…o code-review prompt (gated by custom_instructions)
added 5 commits
June 29, 2026 10:42
…_prompt; revert agent reorder
haoranpb
reviewed
Jun 29, 2026
added 2 commits
June 29, 2026 16:19
Drop the inline-instructions prompt-gating scaffolding (config.yaml block, prompt._category_context CODE_REVIEW context, and its test). That wiring stays on experiment branches; main only carries the 6 domain checklist md files as dormant assets plus the benchmark version bump.
haoranpb
reviewed
Jun 29, 2026
haoranpb
approved these changes
Jun 29, 2026
This was referenced Jun 29, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Splits the old-inline (pre-#8700) review-knowledge arm out of #696 so it can merge independently. This is plain content consumed by the existing custom-instructions pipeline — no bespoke code, fully consistent with BC-Bench's main flow.
Why
#696 also contains the live BCQuality arm (bespoke clone/filter/entry.md wiring) which is paused pending a review of how BCApps consumes BCQuality. The inline arm has no such risk, so it should land first.
Changes
src/bcbench/agent/shared/instructions/microsoft-BCApps/: the pre-#8700 BCApps review checklists (accessibility, performance, privacy, security, style, upgrade) + AGENTS.md, consumed as custom instructions via the existingsetup_instructions_from_configflow.Safety
instructions.enabled: false; the files only take effect when an experiment opts in. No change to bug-fix / test-generation / vanilla code-review.Generated with the help of GitHub Copilot.