Add streaming/partial-turn early dispatch pattern to AI-AND-LLM.md - #16
Open
ankit-prabhavak wants to merge 1 commit into
Open
ankit-prabhavak wants to merge 1 commit into
ankit-prabhavak wants to merge 1 commit into
Conversation
None of the existing tool/action attack classes cover timing: they assume the dispatcher acts on a complete model turn. Frameworks that stream tool-call arguments (LangChain/LangGraph agent loops among them) can dispatch a side effect before the turn is finalized, which is a distinct boundary-failure class worth naming separately.
Bangkah
approved these changes
Sep 17, 2026
Bangkah
left a comment
Bangkah
left a comment
There was a problem hiding this comment.
Clean addition, addresses a real gap in LLM agent streaming dispatch logic. No base conflicts. LGTM.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #15
Adds a new attack-class pattern under "Tool and action attack classes" covering agent dispatchers that act on partial/streaming model output rather than a finalized turn, a gap not covered by the existing tool-argument-injection, confused-deputy, action-binding, schema-disagreement, or unbounded-loop patterns.
No other file in the repo references these pattern names, so this is a self-contained, single-file addition.