Repository navigation
[PR] fix(stream): keep requested ref numbers in stale-ref compress receipts - #6714
Conversation
When every requested ref is above the session frontier, the failure receipt scrubbed the endpoints to a bare [stale-ref], so the caller could not tell which refs it used. Emit a number-preserving marker ([stale-ref:00010]) instead: the range diagnostic stays readable while the bare mNNNNN token never reaches the client-persisted receipt, so the ranxianglei#2146 echo channel stays dead. Fixes ranxianglei#6712
(ai: vllm-qwen/qwen3.8-27b) 查重: 不重复 — PR #6714 is the only open PR targeting #6712; no other open PR touches this scrub path (searched open PRs for the issue number and for stale-ref titles — the only adjacent work, #2742/#5985, is closed and different in focus). Review of PR #6714 (head Direction (issue #6712) — verified real. The scrub at Regression review — existing behaviors on the touched path, item by item:
Code — Tests — teeth verified locally: both new tests FAIL against pre-fix CI (live, mirror cache 12:21 UTC): 0 failures — 9 success, 12 skipped, 9 queued (guard lanes still running). Labels (judged on the PR's own diff): Note: the issue's secondary point (startId throws where endId clamps above the frontier) lives in 八问 (PR 审核):
判定: 可合(mergeable) — 方向对、无回归、测试有牙(修复前红/修复后绿已本地验证)、diff 干净(3 文件,+102/−2,每行都在目的内)。等 9 个排队中的 CI lane 全绿 + 人工 review;合并由人执行。 |
|
Closes pair #6712 was auto-closed by the batch merge. Superseded by #6765 (merged to master as 8a70e1e). Your commit 42fd2ff is in master verbatim — same content, same authorship, only the object ID changed (the batch used a real Thanks for the fix — it is live in master from 8a70e1e onward. |
What broke
When every requested ref sits above the session frontier (the usual aftermath of a mid-conversation model switch), the compress failure receipt scrubbed the endpoints to a bare
[stale-ref]. Therange ...:line readrange [stale-ref]..[stale-ref], so the caller could not tell which refs it used and could not self-correct.What changed
src/stream.ts: the scrub marker now keeps the ref number ([stale-ref:00010]). The baremNNNNNtoken still never reaches the client-persisted receipt, so the dsh内部问题 出现这个错误后,重启dsh可以发消息 但陷入无限压缩失败 #2146 echo channel stays dead.tests/issue6712-compress-receipt-stale-refs.test.ts; the dsh内部问题 出现这个错误后,重启dsh可以发消息 但陷入无限压缩失败 #2146 marker assertion updated to the new shape (the no-bare-ref invariant is unchanged).How verified
Note: the issue's secondary point (startId throws where endId clamps above the frontier) lives in
kernel/src/boundaries.ts, so it needs the kernel-side process and is not in this PR.Fixes #6712