Repository navigation
Conversation
… rejection cause Review follow-up on ranxianglei#5482. bound() collapsed only C0 + DEL before clamping, so C1 control characters survived into the appended log suffix — in particular U+0085 (NEXT LINE) and U+009C (file separator), which render as line/field breaks. A relay that echoed such a byte into attempts[].details.error.message could forge a second log field, contradicting the module's own "no newline may forge a second log field" invariant (pinned by the \r\n test). Widen the strip to C1 (U+007f-U+009f) and extend the control-shape regression test to pin NEL and file-separator. No behavior change beyond the log-line sanitization.
[bot] 🏷 查重: 不重复。本 PR 是 #4452 的活跃后续,取代已关闭未合入的 #4455;与 #3659(summary-tier 分类诊断)症状与机制均不同,与 #5007(message-count/fall-through)无关。当前仓库仅此一个 PR 做「无标记拒绝判据收窄 + 中继聚合体死因提取」。 标签: bug + scope/wiring + p3 —— 纯宿主侧日志诊断缺陷(误导告警 + 死因被截断),不涉及 kernel/存储/wire/配置面,severity 为诊断噪音级。 Review summary (for @Maziar123): Direction is sound and both changes are strictly host-side, log-only diagnostics — no retry/refold/window-learn/cache/persistence/wire/kernel impact (verified: the predicate has exactly one caller, 结构化八问
行为变更披露(旧值→新值 + 原因): 收工判定: 可合(待 CI |
…ile existence (ranxianglei#4599) The receiver fixture creates its .port file before the write lands; on a loaded runner the existsSync poll can win that race and read back an empty file, so Number("") === 0 tripped the assertion (CI: ubuntu-24 shard 2, run 42202673910 — second occurrence of this signature after PR ranxianglei#5327's one-off, recorded in ranxianglei#4599 as record-only). Poll until the content parses as a positive integer instead; the 15s deadline and the diagnostic message are unchanged.
(ai: vllm-qwen/qwen3.8-27b) 现状:PR 在 head 本轮(windows-22 shard 5 红):两个子测试红,均判定为环境负载 flake,无代码改动,重跑转绿:
前一轮(修复仍有效):ubuntu-24 s2 结构化八问:
结论:PR 全绿,待人工 merge。若 issue3654 B7 的 win32 时序预算再红,按 flake 家族台账升级处理(预算放宽/平台感知),已在 #4599 登记签名。 |
(ai: vllm-qwen/qwen3.8-27b) 当前状态(已逐项核实):分支上全部 run(含 run 42211604100 attempt=2)conclusion=success,30/30 check 绿,无待处理失败。注:镜像缓存此刻仍显示 12 项 in_progress,属轮询缓存滞后——GitHub API 直读确认均为 success,若再收到同 head 的阻塞通知按重复处理即可。 结构化八问:
结论:无待办,PR 在 |
…server module map (ranxianglei#5482 review)
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
APPROVE — 纯诊断面修复,方向正确、测试有牙、无回归。CI:旧 head 8d283b9e5 镜像缓存 30/30 success/skipped(含 static-gates/gate/lock-sync/mysql-contract);本 review 另推了一个 docs 排序小修(见文末),新 head 47d078973 CI 重跑中。
结构化八问:
- 是什么问题:#4452 家族的两个可诊断性缺陷——① master 的
isMarkerlessOverflowReject把任何「无标记 4xx」当作溢出证据,而各家中转站对畸形/schema/role 错误返回的通用体几乎一模一样 → 普通畸形请求被误报「自愈无法启动 / calibration-starved route」;② 扇出型中转站的聚合错误体把真实死因埋在attempts[last].details.error.message,永远落在日志 600 字节截断之外,日志只见外层叙事「All targets failed」。 - 什么原因导致的:① status 400 本身没有「太大」语义(只有 413 有),用「4xx + 无标记」当尺寸证据把畸形与超大两类请求混为一谈;② 日志行只保留正文前 600 字节,聚合体的外层叙事恰好占据头部。
- 影响范围与严重程度:纯日志诊断面——无数据丢失、无线协议变化、无恢复行为变化。受影响者 = 排查上游拒绝的运维。旧行为:经通用体中转站的每个畸形请求都触发假警报(噪音+误导方向);新行为:无标记 400 不再告警。代价(有意披露):Cherry Studio 类网关把溢出 400 改写为通用体时失去这条提示——重复 400 模式在日志里仍然可见,功能级修复属 #4452/#4455 的 owner 决策机制,不在本 PR 范围;无标记 413 照旧告警。
- 怎么修复的:① 谓词收窄到仅 413(413 的 HTTP 语义就是载荷过大);② 新增只读模块
src/server/rejection-diagnostics.ts:≤64KiB 正文才解析,只读一条attempts[].details.error.message(顶层或error信封下),从尾部取最后一个可用 attempt,终局 attempt 沉默时回退到最近的有信息量的前序并标reported而非terminal(存在不等于因果),经共享redactSecretsInText洗凭证,折叠全部 C0/C1 控制符+空白(防日志行伪造),300 字符上限,有则追加到← upstream行、无则与原行逐字节一致。 - 是否有回归问题:无。触碰路径既有行为逐项清点:
inspectContextOverflow标记解析/窗口学习/image-count wall——未动;relay non-2xx 路径(errBody 缓冲、armOverflowShrink/armFailureShrink、strict-echo 学习、throttle governor feed、dumpRejectedBody、verbatim passthrough)——未动;恢复决策全部以标记为准,不依赖新谓词与新后缀(纯诊断,代码注释亦如此声明);← upstream行格式纯增量、缺席时逐字节一致(单测双向钉住);grep 确认旧 400 警告文案全仓仅 relay.ts:1599 一处产出、无其他测试 pin 依赖它。高危模式逐项过:fail-fast 未变吞错(JSON.parse 失败→返回 undefined→无后缀,诚实降级)、阈值漂移无(64KiB/300 字符是带注释意图的新常量,未挪用既有值)、输出格式变化已按第 3 问披露。 - 是否破坏缓存:不涉及——缓存/重试/增量游标/去重键均未触碰。
- 是否改了设计方向:否。无新配置面、无线/持久化/kernel 变更;模块边界干净(一个新文件 + relay.ts 单调用点)。
- 是否引入新配置:无。
测试有效性:tests/rejection-diagnostics.test.ts 18 例是真行为测试(正/负双向 + 对抗输入:NEL U+0085 等 C1 控制符、bearer/sk- 凭证形状、超 64KiB 正文、UTF-8 字节预算 vs UTF-16 长度、非对象 attempts 条目、嵌套 error.attempts 信封、空/非字符串消息回退);issue4452-markerless-reject.test.ts 更新保持 #3617 门纪律(双向断言保留,400 翻负例 + 新增 MALFORMED_BODY 负例);issue5152 flake 修复(port 文件竞态:轮询有效端口值而非 existsSync)是干净的 CI 协调小修(#4599),与本 PR 目的相容。diff 整洁:8 个文件全部服务本 PR 目的,CHANGELOG 与 architecture 文档同步在内。
已顺手修:reference/architecture.md 的 server 模块图把 rejection-diagnostics.ts 排在 relay.ts 之后,违反该块字母序惯例(rej < rel)——已换位,commit 47d078973(docs-only,CI 重跑中)。
判定:可合并(merge 留给人工)。
|
(ai: vllm-qwen/qwen3.8-27b) 已顺手修:reference/architecture.md server 模块图排序——rejection-diagnostics.ts 按字母序应在 relay.ts 之前 + commit 47d0789(docs-only,CI 重跑中) |
(ai: vllm-qwen/qwen3.8-27b) 新提交 47d0789(模块图字母序,docs-only)已核实,CI 已全绿。 本轮做了什么:
八问:
结论:PR 在 head 47d0789 全绿,可合并(合并按流程由人工执行)。 |
# Conflicts: # CHANGELOG.md
(ai: vllm-qwen/qwen3.8-27b) 冲突解决完成,PR 恢复可合并状态且 CI 全绿。 本次把 过程要点:
八问:
结论:冲突清零、CI 全绿,PR 已就绪等待人工合并(head=f423c8ef18)。合并按规则由人工执行。 |
[bot] 🏷 过期重复触发,本轮零改动、零重跑,只做核验。 冲突解决工作在本线程上方(floor 22)已完成:merge commit 本轮核验结果(逐项实测):
八问:
结论:PR 在 head |
[ework] CI fix verified green ✓ |
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
Round 2 — new head f423c8ef1 is a clean merge of upstream/master
This round adds no new code from the author: the only new commit is a merge of upstream/master (58a87962) into the previously-reviewed head (47d078973, which I approved last round). I re-verified that the merge did not disturb the fix.
What I checked at the new head:
- Core fix files are byte-identical to the approved head:
src/server/rejection-diagnostics.ts,tests/rejection-diagnostics.test.ts,tests/issue4452-markerless-reject.test.ts,tests/issue5152-owner-beat-survives-host-stall.test.ts. src/util.ts—isMarkerlessOverflowRejectstill narrowed tostatus === 413 && !markerwith its full rationale comment; master's independent +17 lines (the #5613 calibrated token ratio, a SGLang pattern) do not touch it.src/server/relay.ts— master rewrote this file heavily (+613/-86); the PR's wiring survived intact and coherent: import :76, theisMarkerlessOverflowRejectelse-if branch :2056-2068, and theterminalCauseappend :2112-2113.errBodyis buffered before use (:2028-2033). The predicate still has exactly ONE consumer repo-wide — master added no second call site.CHANGELOG.md— both PR bullets intact;reference/architecture.md— the module-map ordering fix from last round survived master's docs reorg (rejection-diagnostics.tsstill alphabetically beforerelay.ts).- No leftover conflict markers anywhere; CI is green on this head (30/30, 0 failed);
mergeable: true.
The original analysis stands: narrowing the markerless-reject diagnosis to 413-only is correct (an unmarked 400 is the generic malformed/schema bucket across relays and carries no size evidence), and the bounded, credential-scrubbed terminal-cause suffix is read-only diagnostics that leaves the log line byte-identical when absent. No new findings this round.
结构化八问(本轮 = 合并 master 后的复核)
- 是什么问题:本轮没有新的代码改动,只是把已评审的分支合并到最新的 upstream/master;要复核的是「这次合并有没有破坏上一轮已批准的修复」。
- 什么原因导致的:不是缺陷,是常规操作——master 前进了(含对 relay.ts 的大幅重写),作者把 master 合进来保持分支最新、避免合并冲突。
- 影响范围与严重程度:无外部影响。逐文件核对确认 PR 的修复逻辑在合并后原样保留,行为与上一轮批准时完全一致。
- 怎么修复的:无需修复。我做的只是验证——核心文件字节级比对、谓词唯一消费方复查、冲突标记扫描、新 head 的 CI 状态。
- 是否有回归问题:无。
isMarkerlessOverflowReject仍只有 relay.ts 一处消费;恢复类决策(refold/emergency-shrink/window-learn)依旧按溢出标记驱动、未被触碰;日志行在无 attempts[] 时与原实现逐字节一致。master 对 relay.ts 的重写属 master 自身变更(各自 PR 单独评审),本 PR 未引入任何语义漂移。 - 是否破坏缓存:不涉及。纯诊断面,不触碰缓存/重试/增量游标。
- 是否改了设计方向:不涉及。仍为「只读诊断」定位,不改重试判定与响应字节。
- 是否引入了新的配置:不涉及。无新增 env/config/默认值。
结论:可合并(merge 留给人工)。
[bot] 🏷 再次收到「merge state: dirty」通知,本轮实测为过期快照——当前无冲突、无红项,零改动。 本次不依赖缓存,直接读 GitHub API(单次 GET,非轮询):
八问:
给 owner 的两点提示:① PR 仍处 draft 状态,需作者(@Maziar123)un-draft 后才能合并;② 若同 head 的 dirty 通知继续重复出现,建议检查 blocker 检测器的快照刷新逻辑(本会话已两次对同一绿色 head 误报)。合并按规则由人工执行。 |
(ai: vllm-qwen/qwen3.8-27b) Round 2 done @ head f423c8e: new commit is a pure merge of upstream/master into the previously-approved head; verified the fix logic survived byte-for-byte (predicate 413-only + single relay consumer, terminalCause wiring coherent inside master's relay rewrite, docs/CHANGELOG intact, no conflict markers) and CI is green 30/30 — APPROVE re-posted (review id 5852867457), no new findings, awaiting human merge. |
[ework] CI fix verified green ✓ |
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
Round 3 — new head b16ec584d is again a clean merge of upstream/master
Same shape as last round: the only new commit merges origin/master (dc041dd1) into the previously-approved head f423c8ef1. The PR's own contribution is unchanged (same 8 files, +364/-30).
What I checked at the new head:
- All four core fix files byte-identical to the approved head:
src/server/rejection-diagnostics.ts,tests/rejection-diagnostics.test.ts,tests/issue4452-markerless-reject.test.ts,tests/issue5152-owner-beat-survives-host-stall.test.ts;src/util.tsalso unchanged this round (predicate stillstatus === 413 && !marker, :582). src/server/relay.ts— master's delta this round (+16/-25) lives entirely inforwardCaptured(#5765 blockOps system-prompt gate, #6150 fold-point relocation removal) and the import block; none of it touches the PR's region. The wiring survives intact: import :76, markerless branch :2055,terminalCauseappend :2111.CHANGELOG.md+3 /reference/architecture.md+1 are other PRs' entries; the module-map ordering fix still holds (rejection-diagnostics.ts:30 beforerelay.ts:31).- No conflict markers; PR touches no
kernel/**and carries nokernel-change:declaration; all test lanes complete on this head with 0 failures (a few fast static gates were still queued in CI at review time — they passed on both prior heads of identical content).
No new findings. The original analysis and verdict stand.
结构化八问(本轮 = 再次合并 master 后的复核)
- 是什么问题:无新问题。本轮唯一新提交是把分支合并到最新 master,要确认的是合并没有破坏已批准的修复。
- 什么原因导致的:常规同步——master 又前进了一个窗口(#5765 blockOps 门、#6150 移除 fold-point 重定位等),作者合入以保持可合并性。
- 影响范围与严重程度:无外部影响;PR 修复逻辑逐字节保留,行为与此前两轮批准时一致。
- 怎么修复的:无需修复,仅验证——核心文件字节比对、relay.ts 增量逐 hunk 核对(全部落在 forwardCaptured/import,与 PR 代码区无交集)、冲突标记扫描、CI 状态读取。
- 是否有回归问题:无。谓词仍仅 relay.ts 一处消费;恢复类决策仍按溢出标记驱动;日志行在无 attempts[] 时逐字节不变。master 自身变更由各自 PR 评审负责,本 PR 未引入语义漂移。
- 是否破坏缓存:不涉及。纯诊断面。
- 是否改了设计方向:不涉及。
- 是否引入了新的配置:不涉及。(本轮合入的 #5765
compress.blockOps门是 master 上的独立变更,非本 PR 内容。)
结论:可合并(merge 留给人工)。
(ai: vllm-qwen/qwen3.8-27b) Round 3 done @ head b16ec58: again a pure merge of upstream/master (dc041dd) into the approved head — PR contribution byte-identical, relay.ts master-delta confined to forwardCaptured/imports (#5765/#6150), no kernel involvement, test lanes 0 failures — APPROVE re-posted (review id 5858206213), no new findings, awaiting human merge. |
[ework] CI fix verified green ✓ |
1 similar comment
[ework] CI fix verified green ✓ |
[ework] CI fix verified green ✓ |
# Conflicts: # CHANGELOG.md
[bot] 🏷 本轮是真实冲突(与之前两次过期误报不同):作者已自行 merge 过 master 并把分支推进到 过程:
八问:
结论:冲突清零,PR 在 head |
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
Round 4 — new head 47b85cf2f is again a clean merge of upstream/master
Same shape as the last two rounds: the only new commit merges upstream/master (259cd876) into the previously-approved head b16ec584d. The PR's own contribution is unchanged (same 8 files, +364/-30).
What I checked at the new head:
- All code/test files of the fix byte-identical to the approved head:
src/server/rejection-diagnostics.ts,src/server/relay.ts(untouched this round), all three test files. src/util.ts— master added an unrelatedtrailingSystemRunStarthelper (#5432, aftersystemToUser); the PR'sisMarkerlessOverflowRejectis untouched (:581-582, stillstatus === 413 && !marker) and still has exactly one consumer (relay.ts :2055).CHANGELOG.md+7 /reference/architecture.md+4/-1 are other PRs' entries (toml-integer.ts,mdrender.tsmap rows); the module-map ordering fix still holds (rejection-diagnostics.tsbeforerelay.ts).- No conflict markers; PR touches no
kernel/**and carries nokernel-change:declaration; CI 29/30 lanes complete with 0 failures (one windows test shard still running at review time — it passed on all three prior heads of identical content).
No new findings. The original analysis and verdict stand.
结构化八问(本轮 = 再次合并 master 后的复核)
- 是什么问题:无新问题。本轮唯一新提交是把分支合并到最新 master,要确认的是合并没有破坏已批准的修复。
- 什么原因导致的:常规同步——master 又前进了一个窗口(#6455/#6458/#5432 等),作者合入以保持可合并性。
- 影响范围与严重程度:无外部影响;PR 修复逻辑逐字节保留,行为与此前几轮批准时一致。
- 怎么修复的:无需修复,仅验证——PR 文件逐字节比对、util.ts 增量核对(纯新增 #5432 helper,与谓词无交集)、冲突标记扫描、CI 状态读取。
- 是否有回归问题:无。谓词仍仅 relay.ts 一处消费;恢复类决策仍按溢出标记驱动;日志行在无 attempts[] 时逐字节不变。master 自身变更由各自 PR 评审负责,本 PR 未引入语义漂移。
- 是否破坏缓存:不涉及。纯诊断面。
- 是否改了设计方向:不涉及。
- 是否引入了新的配置:不涉及。
结论:可合并(merge 留给人工)。
(ai: vllm-qwen/qwen3.8-27b) Round 4 done @ head 47b85cf: again a pure merge of upstream/master (259cd87) into the approved head — PR contribution byte-identical, util.ts delta is only the unrelated #5432 helper, relay.ts untouched, no kernel involvement, CI 29/30 lanes green (0 failures, 1 shard still running) — APPROVE re-posted (review id 5881854717), no new findings, awaiting human merge. |
[bot] 🏷 又一条过期「dirty」通知——冲突已在本线程上一轮解决(merge commit
八问:
给 owner 的提示:① PR 仍是 draft,需作者(@Maziar123)un-draft 后才能合并;② 本会话已四次收到同一绿色 head 的 dirty 误报(前两次在 |
[bot] 🏷 第五次同一状态误报,零改动。 本轮实测:镜像 head= 八问:
结论:PR 在 |
[ework] CI fix verified green ✓ |
1 similar comment
[ework] CI fix verified green ✓ |
|
Landed via batch PR #6482 (merged) — closing as superseded. |
… rejection cause Review follow-up on ranxianglei#5482. bound() collapsed only C0 + DEL before clamping, so C1 control characters survived into the appended log suffix — in particular U+0085 (NEXT LINE) and U+009C (file separator), which render as line/field breaks. A relay that echoed such a byte into attempts[].details.error.message could forge a second log field, contradicting the module's own "no newline may forge a second log field" invariant (pinned by the \r\n test). Widen the strip to C1 (U+007f-U+009f) and extend the control-shape regression test to pin NEL and file-separator. No behavior change beyond the log-line sanitization. (cherry picked from commit c749eb8)
Problem
An unmarked HTTP 400 was treated as size evidence, and a bounded outer-body preview could hide a nested provider rejection.
Change
Only unmarked413 is markerless size evidence. Positive overflow-marker detection and recovery decisions are unchanged. A shared read-only helper selects the last usable attempts[].details.error.message from direct or error-wrapped aggregates, labels an earlier informative attempt as reported rather than terminal, and appends a bounded diagnostic. Parsing is capped at64KiB UTF8; output is capped at300 characters, control/whitespace collapsed, and existing credential redaction applied. No raw body dump or recursive arbitrary cause walk.
Verification
Candidate3896863d:25 targeted runtime checks passed, plus TypeScript, unused-export and test-import-graph gates. A separate direct API smoke distinguished markerless 400 from413 and retained a nested schema cause. Local coverage is not an all-platform/full-suite CI claim.
Scope and related work
Host diagnostics only; no kernel, persistence-schema, wire or retry-policy change. Related:#4452 and closed/unmerged#4455; this narrows the older predicate and adds bounded nested-cause extraction. #5007 is a distinct message-count/fall-through mechanism and is not resolved here. This does not establish historical failure attribution or make arbitrary provider text a general privacy-safe payload.