Repository navigation
[PR] fix: preserve literal buffered SSE field semantics - #6654
ranxianglei merged 1 commit into
Conversation
(ai: vllm-qwen/qwen3.8-27b) 查重: 不重复。 Searched open PRs/issues for this parser: #6654 is the only one fixing the Independent verification (checked out head
Key correctness finding: the fix aligns the summary parser with the SSE spec and with the streaming adapters ( Behavior changes (old → new), all spec-aligned:
Action items before merge (I will not merge — human-only):
Per §7.4 this is auto-merge-eligible (single-module 结构化八问:
判定:修复正确、符合规范、测试有牙、回归风险低,符合 §7.4 自动合并条件。合并前需:rebase 到当前 master + 重触发 CI(当前 head 的 check 全为 cancelled,尚无绿)。我不合并(人工专属)。 |
4ed6fed to
dadbcd3
Compare
Closes #6652.
Problem
The buffered summary parser treats whitespace-only lines as blank event boundaries. A legal unknown field containing one space or tab therefore splits a multiline JSON event, and preflight/external summaries can fail even though the upstream response is valid. Colon-free fields are also dropped, and event names are over-trimmed.
Change
Parse a field at its first colon, remove only one optional leading space from its value, and recognize colon-free fields with empty values. Only an actually empty line dispatches an event. This follows the SSE interpretation rules. Caller-owned terminal and residual validation remain unchanged.
Validation
e5e1647ba0f92dfc36a96220f3e5c0d454218e2f; 34 controls pass.1ff89e878522f3e4d4147067973e2dc26e648923, all 211 targeted tests pass: the original 130 SSE cases plus 81 broader summary-path cases, including preflight compression, stream summaries, empty/incomplete summaries, Google/Responses summary handling, external summaries, and terminal detection.npm run typecheck,npm run build, andgit diff --checkpass. Full-suite status remains the upstream CI result.Both compression modes share this summary parser. No outgoing message shape, kernel, configuration, or persisted format changes.
Base after rebase:
1ff89e878522f3e4d4147067973e2dc26e648923. Current head:dadbcd35475b451cd2d8207c1f1cee23cecfbded. Published tree87ff0c9ebe626bb7b0ccb92c2df9e387e0a029acmatches the tested tree. The rebase changes the base only; the three-file patch is unchanged. The local targeted tests, full typecheck and build above were rerun on this rebased tree.Hosted CI follow-up
The branch has been rebased onto the current master after the maintainer review. CI run 43571794127 for the new head
dadbcd35475b451cd2d8207c1f1cee23cecfbdedhas been queued; no full-suite green result is claimed for it.For the previous head
4ed6fed50668c58b11679ac7531efa5f0e70c1f9, the maintainer reran CI run 43564467766 (attempt 2). It finished with 25 successful jobs, two failed Windows test jobs and one skipped job. All Linux test shards and both Windows/Ubuntu static gates passed. That historical run remains red and is not a verdict on the rebased head.The two previous-head failures were:
persist-metadata-fold-gatecases fail while removing openindex.dbfiles (EBUSY); the automatic retry repeats them.persist-zstdcases fail on the same open-file cleanup; the automatic retry repeats them.The exact suites and teardown cause are already covered by upstream issue #6547 and open fix PR #6561. This PR does not duplicate that work. No failure in those previous-head logs belongs to this PR's new regression cases.