fix(security): enforce stream guards and align runtime contracts - #617
Merged
Merged
Conversation
Destynova2
enabled auto-merge (squash)
September 26, 2026 10:01
Contributor
Mutation testing (PR diff sample)Informational — never blocks merge. Full matrix runs on main.
Legend: clean (no survivors), missed (inspect artifact), timed-out (25 min cap reached). Artifact: mutants-pr-results-7c5b11c44e7060a8946ab3948484711e884be087. |
Destynova2
added a commit
that referenced
this pull request
Sep 26, 2026
## 🤖 New release * `grob`: 0.36.116 -> 0.36.117 <details><summary><i><b>Changelog</b></i></summary><p> <blockquote> ## [0.36.117](v0.36.116...v0.36.117) - 2026-09-26 ### Fixed - *(security)* enforce stream guards and align runtime contracts ([#617](#617)) </blockquote> </p></details> --- This PR was generated with [release-plz](https://github.com/release-plz/release-plz/).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Security decisions on streamed responses depended on JSON formatting and transport boundaries. Output DLP could emit configured secrets before detecting them, HIT could miss tool blocks or decide on partial arguments, and cached JWT signatures outlived token expiry. Documentation and image publication also described different runtime behavior.
This change:
Validation:
Behavior to review: when output DLP is enabled, text is delivered at content-block completion rather than token by token. Matching is scoped to each text block; tool input, thinking blocks and matches across separate text blocks are outside that DLP adapter. The 1 MiB/4,096-event limits bound retained data and serialized output, not total process RSS or temporary replacement allocations.