Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
SGLang can emit startup settings as
server_args={...}. Hyperloom currently recognizes onlyserver_args=ServerArgs(...), leaving the observed model/configuration identity empty and the same-configuration reference unverified when launch arguments are unavailable. Read both forms through the existing identity field allowlist and literal-value bounds.The parser handles wrapped records, nested values and quoted delimiters, caps log reads, and treats malformed or excessively deep expressions as unavailable evidence. Identity records continue to describe observed settings without supplying launch argv. This repairs evidence collection; it does not change benchmark acceptance thresholds or claim a performance improvement.
pytest -q -n 2 -m "not critic_agent_e2e and not robustness_agent_e2e and not targeted_build_e2e") completed with 22,754 passed, 55 skipped and four failures. All four reproduce on unchanged base2cc382a8: three robustness idle-observation tests andtest_a_restart_past_the_limit_becomes_terminal(missingfinal.json). No new test failures were identified.git diff --checkpass. Mypy reports the identical baseline diagnostic set (920 errors across 156 files), with none added.CHANGELOG.mdentry under[Unreleased]: yes.