feat(rules): add side-effect bounds rules (batch 1) - #162
Merged
Merged
Conversation
ivanpaghubasan
requested review from
ericksondelacruz,
jhumel-code and
sairenchristianbuerano
September 28, 2026 07:13
sairenchristianbuerano
approved these changes
Sep 28, 2026
Adds side_effect_bounds.yaml to the openai_sdk, pydantic_ai, mcp, and langchain packs: OAI-030/031, PYD-014, MCP-030, LC-025. Flags tools where the model chooses the recipient or amount of a side effect with no visible bound (severity high, confidence 0.5). Mirrored byte-for-byte from the engine fixture. No manifest or schema change; existing predicates only.
ivanpaghubasan
force-pushed
the
feat/p0-side-effect-bounds-batch1
branch
from
September 29, 2026 06:06
099b642 to
695d282
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds side_effect_bounds.yaml to the openai_sdk, pydantic_ai, mcp, and langchain packs: OAI-030/031, PYD-014, MCP-030, LC-025. Flags tools where the model chooses the recipient or amount of a side effect with no visible bound (severity high, confidence 0.5).
Mirrored byte-for-byte from the engine fixture. No manifest or schema change; existing predicates only.