Repository navigation
[PR] fix(#5687): a tool-less MAIN turn must not be mistaken for a dsh sidecar - restores the BLOCKED-ref and wire-byte contracts - #5709
Conversation
CI note: the two red shards are the known
|
| job | shard | failing test |
|---|---|---|
127068995769 |
test (ubuntu-latest, 22, 1) |
msgid lane flow: multi-block wire content degrades to derived ids, never a sticky 400 |
127068995596 |
test (ubuntu-latest, 24, 1) |
msgid lane flow: pin carries client ids into rows; edits append fresh rows (no swap, no 409) |
Different tests of the same file, on different shards, with different assertion messages - the signature of a settle-timing flake, not a deterministic regression.
This patch cannot reach those bodies
tests/msgid-lane-flow.test.ts sends
{ conversationId, sinceSeq, resync, msgIds, path: "/v1/messages",
request: { model: "claude-test", max_tokens: 1024 },
messages: [ { role: "user", content: [{ type: "text", text: "seed" }] } ] }No system field anywhere. isDshSingleShotSidecar bails on its carrier guard (src/server/side-request.ts:238):
if (!systemCarrierTexts(p).some((t) => t.trim().length > 0)) return false;Probe in this worktree:
systemCarrierTexts: []
isDshSingleShotSidecar: false
top-level max_tokens: false | nested: 1048 -> request.max_tokens = 1024
false before and after the patch: the gate is unreachable for those bodies, so neither hasSingleShotBudget nor carriesDurableSignal can change their outcome. The patch also only ever removes requests from the side lane; it never adds one.
Pre-existing flake
tests/msgid-lane-flow.test.ts:103 guesses the debounced save with a fixed sleep:
settle: async () => { await new Promise((resolve) => setTimeout(resolve, 60)); }while :60 sets new SessionStore({ ..., debounceMs: 15 }). Under shard contention a 60 ms guess loses the race and the row read precedes the flush - exactly the two assertions seen here (an edit lands as a FRESH row ... 3 !== 4, subsequent clean deltas pin client ids again).
Local: 10/10 green in this worktree (8/8 with the source change reverted). It is not in scripts/ci-failure-shapes.mjs, so CI does not auto-retry it.
Recommendation: either add the msgid lane flow signature to the retry shapes, or make settle() poll for the expected row count instead of sleeping a fixed 60 ms (the pattern tests/snapshot-shadow.test.ts:173 already uses for unifiedTailSeqs).
powered by dsh
(ai: vllm-qwen/qwen3.8-27b) 查重:不重复。 检索 open+closed issue/PR 均无同主题条目;本条唯一血缘是 #5687 → 本 PR,不存在并列的第二个 [PR] 在修同一件事。 标签: 以下按八问给独立审核结论(我自己读了 diff 与 CI 日志,未照抄 PR 描述):
CI 核查(关键):11 个 test shard 中只有 2 个红,且都是 ubuntu 的 shard 1(node22 与 node24)。我拉取了两个失败 shard 的完整日志逐行确认——它们挂的都是 判定:本 PR 方向正确、diff 干净(单 commit、4 文件 +47/-4、无 kernel / config-surface / 依赖变更)、目标契约已恢复、无回归。可合——目前唯一的 CI 红灯是与本 PR 无关的 msgid-lane-flow 时序 flake,重跑后应绿;若重跑仍偶发红,那是独立的既有测试基建问题,归 CI 总控 #4599 跟进,不应阻塞本 PR 合并。(合并权在你,我不自行合并。) |
(ai: vllm-qwen/qwen3.8-27b) 补充:已触发的重跑跑完了——整条 CI 转绿(run conclusion = success,12 个 test job 全过,含之前红的 ubuntu node22/24 的 shard 1)。这印证了上一条的判断: 至此本 PR:目标契约(BLOCKED-ref / wire-byte)已恢复、6 个 dsh 回归套件转绿、无回归、diff 干净、CI 全绿。可合。合并权在你。 |
🔶 需要决策(本车道无法自清这 2 红:需人工重跑 + durable 项归哨兵) 结论先行:这 2 个红分片不是本 PR 的代码回归,而是已登记的 为什么判定为 flake(证据)
需要决策 / 行动项(选项 A/B/C)
默认若无人拍板:A。 结构化八问(本次 run 做了什么)
收工判定:本 PR 代码无需改动;CI 转绿仅需一次人工 Re-run failed jobs(选项 A)。本车道无权限自清(Actions rerun API 返回 403;PR head 在外部 fork,bot 对其无 push),故停手交接。注:needs-decision 标签在本环境无法机械应用(标签 API 端点未实现、tools/add-label.sh 缺失),以本评论作为 stop/handoff 信号——请勿再对本车道自动重试(会撞同样的权限墙)。durable 项已记入 #4599。 |
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
Review conclusion: APPROVE
Reviewed independently against base 0aace2f: read the linked issue (#5687), the full diff (4 files, +47/-4), both call sites, the durable-marker table, and the dsh client stamping surface; verified behavior locally (targeted suites only, per house rules).
Direction (original issue)
The reported defect is real and the root cause is correctly located. #5687's gate discriminates "utility sidecar" from "main turn" using no tools present as the load-bearing signal — but a tools-disabled dsh conversation has no action surface on turn 1, where its body shape (system + one user blob) is byte-for-byte the sidecar shape. The first main turn therefore rides the #388 verbatim side lane: the kernel never sees it, no refs are minted, and the BLOCKED-ref (#2419/#2446/#2447/#2481) and wire-byte (#2817/#5403) contracts reset for the session. Fixing the sidecar DEFINITION (what makes a request a utility sidecar) rather than patching symptoms is the right layer.
How the fix holds
Two independent signals, AND-ed at both call sites (src/server/handle.ts:1074-1075 and :2211-2212), each true of utility sidecars and false of main turns:
hasSingleShotBudget— top-levelmax_tokens ?? max_completion_tokens ?? max_output_tokensnumeric, > 0, <= 8192 (host preset: prompt-enhance 4096). Main turns omit the field (openai wire) or size it from the conversation (64000).carriesDurableState()veto insideisDshSingleShotSidecar— user string / content-array text screened against the existingdshCarrierRawMarkerstable (src/durable-message-guards.ts:314, 7 markers). Type-only import, no circular dependency.
Fail-safe direction is correct: any doubt (missing field, non-number, oversized budget, marker hit) resolves to the FULL pipeline — the bug was over-diversion, so erring toward under-diversion is the safe side.
Regression sweep (existing behaviors on the touched paths)
- Title-gen (#2503) and auto-review (#4438) sidecars: separate pinned gates, untouched — verified by grep; issue5656 e2e phases 1/3 confirm prompt-enhance sidecars still ride the side lane (budget 4096, no markers, refs==0/reqs==0).
- Main turns WITH tools: already vetoed by the gate pre-change; unchanged.
- Turn 2+ replays: vetoed by the single-shot body shape; unchanged.
- Proxy mode and non-dsh plugin lanes: both call sites require the dsh lane (live
x-bili-plugin-agentstamp or stickysession.metadata.pluginAgent === "dsh"); unchanged. - Kernel / wire / persistence: untouched (no kernel-change declaration, no kernel/ diff).
- Local evidence: on pristine master the issue2446 suite FAILS (
not ok 4 - session-level: the dsh lane stamps the guard onto the effective config) — negative control reproduces the reported defect; at the PR head all six carrier suites + issue5656 + side-lane-invariants pass (21/21 after my additions below).
Behavior change disclosure (old -> new)
- dsh tool-less first MAIN turn carrying a conversation-sized budget or a durable-state marker: verbatim side lane (no refs, no compression state) -> full pipeline (refs minted, compression alive). This is the intended contract restoration.
- Residual (accepted, documented in-code): a hypothetical sidecar whose pinned budget exceeds 8192 or omits the field would now fall to the full pipeline and could claim the raw-key anchor if it arrives first. No known dsh preset sits in that band (prompt-enhance 4096; title/auto-review have their own pinned gates). A tool-less, marker-free turn 1 with a genuinely small (<=8192) budget still rides the side lane for that one turn — tiny, nothing to compress; the updated comment states this honestly.
- Report-only asymmetry:
hasSingleShotBudgetdoes not recognize the Google-wiremaxOutputTokens. dsh speaks anthropic/openai wires today (verified: no google/generateContent support in src/agent/dsh-native.ts), so no live traffic is affected; adding a speculative field would violate evidence-per-client discipline. If a future dsh build gains a google-wire sidecar, the budget screen silently degrades to full-pipeline (pre-#5687 behavior, no data loss).
Tests
Pinned in BOTH directions per #3617: sidecars keep the side lane (positive e2e), tool-less main turns stay on the full pipeline (negative e2e asserting refs>=1 && reqs>=1), plus the six carrier suites as the regression net. Assertions inspect real session state — no tautologies.
Diff is clean: every line serves the fix, no lockfile/generated churn.
已顺手修:三处注释与收窄后的事实不符(isDshSingleShotSidecar 文档注释拼写、Residual 段仍描述已被本 PR 废除的「首轮走 side lane」行为、测试文件两处 stale 注释)+ hasSingleShotBudget 缺边界单元测试行(8192/8193、三个字段名、缺省/零/负/数字串/null)——commits 78c9db9(fix: align the single-shot sidecar doc comments with the narrowed residual)、c769bab(test: update stale side-lane comments and pin hasSingleShotBudget boundary rows),已推到本 PR 分支;本地定向复跑 21/21 绿。新增 commit 仅含注释与纯增量测试行,CI 将在新 head 上重跑。
Check states: mirror cache at 427778b reports failed=0 / pending=0 (success: lock-sync, guards, matrix shards incl. the previously-flaky msgid-lane-flow rerun, e2e lanes; many jobs skipped per matrix design).
Structured eight questions
- 是什么问题:dsh 会话的「无工具首轮」被误判成一次性侧车请求(标题生成/提示词改写那类),被导进逐字旁路车道,压缩引擎从此看不见这个会话——ref 不再铸造、compress/decompress 全部失效。
- 什么原因导致的:#5687 的门控用「没有工具」作为主回合 vs 侧车的唯一判别信号;无工具会话的第一轮该信号整体消失,而侧车形状(system + 单条 user)恰好与主回合第一轮逐字同形。
- 影响范围与严重程度:dsh 车道、禁用工具的会话、首轮即中招;整个会话压缩能力永久失效(不是体验瑕疵,是该会话核心能力停摆)。
- 怎么修复的:把侧车定义收紧为两个独立必须同时成立的信号——小固定输出预算(<=8192,宿主预设 4096)+ user blob 不含持久状态标记(复用 durable-message-guards 既有 7 标记表);任一不满足即按主回合理由走全管道。失败方向安全:存疑即全管道(bug 是过度分流,修复宁可少分流)。
- 是否有回归问题:逐项审过——标题生成/自动审查独立门控不受影响;带工具主回合原本就被门控拒绝,不变;第 2 轮起重放不变;代理模式与其他插件车道无 dsh 门控,不变;kernel/wire 未触碰。本地实测:master 上 issue2446 套件红(负向对照复现缺陷),PR head 六个契约套件 + issue5656 + side-lane-invariants 全绿。有意行为变更已在上方披露(旧值→新值 + 原因)。
- 是否破坏缓存:没有。恢复的正是 BLOCKED-ref 契约(#2419/#2446/#2447/#2481),它稳定前缀缓存身份;缓存/重试/游标策略本身未变。
- 是否改了设计方向:没有。只收紧既有门控的定义,架构/边界/数据流未转向。
- 是否引入了新的配置:没有。常量模块私有(SINGLE_SHOT_SIDECAR_MAX_BUDGET=8192),不暴露 config/env。
判定:可合。
(ai: vllm-qwen/qwen3.8-27b) PR #5709 审核完成:APPROVE(review: https://github.com/ranxianglei/billion-context/pull/5709#pullrequestreview-5782333294)。独立审核:方向正确(把侧车定义收紧为「小固定输出预算 + 无持久状态标记」双信号,失败方向安全)、回归逐项审过无破坏、本地负向对照复现 master 缺陷 + PR head 定向套件全绿;镜像缓存 failed=0/pending=0。已顺手修三处与事实不符的注释 + 补 |
(ai: vllm-qwen/qwen3.8-27b) 发生了什么
为什么判定为 flake 而非回归(证据)
结构化八问
收工判定:GitHub 侧已全绿,PR 可合并(请 owner 自行 merge)。 |
ranxianglei
left a comment
There was a problem hiding this comment.
(ai: vllm-qwen/qwen3.8-27b)
Round-2 review @ c769babfa(我在分支上落了两个顺手修 commit 后的复审触发)
自上一受审 head 427778b14 以来的 delta:只有我的两个 house-rule 顺手修 commit —— 78c9db9(src/server/side-request.ts 文档注释对齐;已核实零非注释行改动)与 c769bab(陈旧测试注释修正 + 新增纯函数单测钉住 hasSingleShotBudget 边界行)。零语义变化;以下完整结论由我独立首轮评审沿用,重新锚定到本 head。
正确性(对 base diff 的独立审读)
缺陷(#5687):dsh native 客户端从不打 x-bili-plugin-agent 头,通用 single-shot-sidecar gate 因此把 dsh 会话的第一个无工具主回合(system + 1 user、尚无工具)误判为 sidecar,整回合走逐字旁路车道——内核没看到正文,durable carrier 丢 BLOCKED ref,wire-byte 契约被重置。修复在两个调用点(src/server/handle.ts:1074、src/server/handle.ts:2211)给 gate 追加两个独立判据:小输出预算(hasSingleShotBudget,数值 >0 且 ≤8192)+ gate 内部的持久状态标记否决。两个判据都朝全量管道方向失败(fail-safe,宁多压不漏压)。title-gen 与 auto-review 保留各自独立的钉死 gate。无 kernel/ 改动、无配置面(8192 常量为模块私有)、无新依赖、无 wire 形状变化;proxy 模式与非 dsh 插件车道不受影响。代码过 ⑤b 整洁清单(命名达意、文档注释指向测试、无死代码、风格一致)。
测试有效性
双向钉住(#3617 纪律):sidecar 保持旁路车道(issue5656 e2e,budget 4096、无标记);主回合保持全量管道(负向 e2e,budget 64000,断言 refs≥1 && requests≥1;六个 carrier/wire 套件)。新增单测覆盖边界(8192 含 / 8193 不含)、三个字段名、缺省、零/负数、非数值 fail-safe。阴性对照已验证:pristine master 上 dsh skill-catalog 套件按 bug 报告所述精确变红;本 head 上六个套件 + 两个 side-lane 套件本地定向跑全绿。
本 head 的 CI
两个分片初红,日志级诊断:(a) msgid-lane-flow.test.ts:139 3 !== 4——settle 时序 race,与前一 head 已知 flake 字节同签(当时重跑即绿);(b) issue5631-restart-survival.test.ts dsh 子测试——post-restart preflight race(约 12s 后 502 preflight_compress_failed)。两个文件 diff 均未触碰,且 PR 的全部语义面已在前一 head 被 CI 完整执行过、这两处当时通过——判定为非确定性 flake,非回归。CI 哨兵已就地重跑:run 41999250333 conclusion=success;镜像缓存本 sha:failed=0、pending=0。
行为变更披露(旧值→新值)
- 带会话级大预算或任何持久状态标记的 dsh 无工具首主回合:逐字旁路车道 → 全量管道。有意变更——本 PR 存在的目的即是恢复此契约。
- 假设中预算 >8192 或无预算字段的 dsh sidecar:旁路车道 → 全量管道(若其先于主回合触发可能认领 raw 会话键锚点)。接受的残留:无已知 dsh preset 落在该区间;title-gen/auto-review 不受影响(独立 gate)。
- 仅报告:
hasSingleShotBudget读 anthropic/openai 字段名;假设的 google-wire dsh 客户端需要maxOutputTokens。降级方向为全量管道(= pre-#5687 行为,无数据丢失)。不在本 PR 扩展——现无此类客户端存在的证据。
八问
- 是什么问题:dsh 会话的第一个无工具主回合被误判成一次性 sidecar,整回合走逐字旁路车道,压缩内核根本没看到正文。
- 什么原因导致的:dsh native 客户端从不打
x-bili-plugin-agent头,旧 gate 里undefined !== "main"恒真;仅凭「system+1 user、无工具」的单发形状不足以区分 sidecar 与主回合。 - 影响范围与严重程度:全部 dsh 会话的首回合——BLOCKED-ref 契约(#2419/#2446/#2447/#2481)与 wire-byte 契约(#2817/#5403)在该回合失效,master 上六个对应套件红;特定条件(dsh 车道首回合)下核心承诺失灵,严重度高。
- 怎么修复的:给 gate 在两个调用点追加两个独立判据——小输出预算(≤8192)+ 持久状态标记否决;两判据均朝全量管道方向失败(fail-safe)。
- 是否有回归风险:逐项审过的既有行为——title-gen/auto-review 各自的钉死 gate:未动;proxy 模式与非 dsh 插件车道:不受影响(gate 限定 dsh);两种压缩模式:均已推演;wire 形状:未变。CI 两红分片经日志级诊断为已知时序 flake(diff 未触碰的文件;语义面已在前一 head 全量 CI 验证且该两处通过),哨兵就地重跑后全绿(run 41999250333 success;镜像缓存 failed=0/pending=0)。
- 是否破坏缓存:不破坏——本 PR 正是恢复 BLOCKED-ref 与 prefix-cache 契约的修复;side-lane 流量只减不增。
- 是否改了设计方向:未改——沿用「证据白名单」(evidence-per-client)纪律,仅把 dsh sidecar 的形状证据从单一形状补全为「形状 + 小预算 + 无持久标记」三要素。
- 是否引入了新的配置:无——
SINGLE_SHOT_SIDECAR_MAX_BUDGET为模块私有常量,不进配置面,无 env/CLI 新增。
判定:可合。 无 kernel/ 改动、无 kernel-change 声明、无配置面变更;授权边界不涉及。
复审完成(head c769bab):APPROVE 已重新提交(https://github.com/ranxianglei/billion-context/pull/5709#pullrequestreview-5784366060)。delta 核实 = 仅我上一轮的两个顺手修 commit(注释对齐 + 确定性单测行,零语义变化);初红两分片经作业日志诊断为已知时序 flake(msgid-lane-flow.test.ts:139 settle race——与前一 head 同签;issue5631-restart-survival dsh 子测试 post-restart preflight race),diff 未触碰这两个文件且语义面已在前一 head 全量 CI 验证过,CI 哨兵已就地重跑转绿(run 41999250333 success,镜像缓存 failed=0/pending=0)。CI 状态行已按惯例补到 #4599。无 kernel/ 改动、无配置面变更、无待决策项——不阻塞合并。 |
…ual realignment, ranxianglei#5688 output_config dedupe, ranxianglei#5637 acp_delegate stand-down master advanced 6ddade1 -> 9a2d51d with 14 commits. The one that matters for this lane is 0470bec (ranxianglei#5718), which realigns five dsh regression pins to the ranxianglei#5657/ranxianglei#5656 single-shot-sidecar residual: the four durable-carrier suites now take a second turn and assert on "the first full-pipeline turn", and issue2817 re-bases stats.requests from 9 to 8. That is the opposing route to ranxianglei#5709 (which vetoes the misfire in source instead), but the two do not collide textually: ranxianglei#5718 touches only test files this lane does not carry, so the merge is clean. Verified on the merged tree that both routes' assertions now hold simultaneously.
…ake, ranxianglei#5743 ubuntu-24 shard) msgid lane flow: pin carries client ids... failed at tests/msgid-lane-flow.test.ts:139 with 'an edit lands as a FRESH row' 3 !== 4 on head 4c8a2b5 (run 42218432005). Same signature as the two reds on head 9c3faf3 and PR ranxianglei#5709 — all went green on rerun; sibling subtests and the other ten shards passed here. The store's afterNextFlush verdict is scoped to writes currently queued or in flight, while the lane wrap-up floats behind the ack (ranxianglei#5155/ranxianglei#3798), so the resync's fresh row can settle one flush cycle after the first verdict on loaded runners. Bounded re-probe (four settle cycles, 25 ms spacing > 15 ms debounce) before the strict assert: a row that never lands still fails, just later — no weakening.
…ed residual (#5687 follow-up) The batch's #5709 (PR by Louie0806) narrowed the accepted residual ride of a tool-less turn 1 onto the verbatim side lane: it now ALSO requires the small pinned one-shot output budget (utility sidecars pin 4096; agent main turns omit the field). The fixture's turn 1 omitted max_tokens, so it now correctly rides the MAIN lane and stats.requests counts from turn 1 — 9 instead of 8. Turn 1 now carries max_tokens: 4096 so the fixture keeps exercising the residual path the count pins; the cross-wire persona/fold assertions are untouched. CI: issue2817-crosswire-persona-fold '9 !== 8' on batch4.
|
Landed via batch PR #6482 (merged) — closing as superseded. |
c769bab to
2153152
Compare
What this fixes
masteris red on every test shard right now (10 of 12test (...)jobs on0aace2f203b2da9065fd53c63f4be0c0ab03c90c). The cause is #5687's generic dsh single-shot sidecar gate, which over-matches the first main turn.isDshSingleShotSidecar(added by #5687 insrc/server/side-request.ts) matches: notools+ exactly one user message + any non-empty system text. Both call sites opened onagent !== "main":src/server/handle.ts:1073- thesideRequestLikedisjunctsrc/server/handle.ts:2210- the lane-sidedshSingleShotSidecarintentdsh's native client never stamps
x-bili-plugin-agent- onlyx-bili-pluginandx-bili-plugin-conversation(src/agent/dsh-native.ts:1784-1785,:2412). SopluginRequestAgentHeader(req.headers)returnsundefined, andundefined !== "main"is always true. A conversation's first turn (system + one user, no tools yet) therefore rides the #388 verbatim side lane, the kernel never sees the body, and the durable-state carriers never get theirBLOCKEDrefs.Evidence
Six suites are red on pristine
0aace2f203b2da9065fd53c63f4be0c0ab03c90c(detached worktree, farm-linkednode_modules, rebuiltkernel/dist):tests/issue2419-dsh-skill-catalog.test.tstests/issue2446-dsh-mcp-catalog.test.tstests/issue2447-dsh-workspace-instructions.test.tstests/issue2481-dsh-runtime-context.test.tstests/issue2817-crosswire-persona-fold.test.tstests/issue5403-watermark-fastpath.test.tsBisect over the 46 commits (each step
git reset --hard+ kernel rebuild):c9ba48566(previous master)47df07f05e4c50ef0b0aace2f20The flip is exactly
8de4c37f8(Merge pull request #5687), whose second parent01fcc5d689c7dd5a7b46125f861263f90a1bd572is the generic gate. That commit's own check-runs were{"cancelled":46,"failure":9,"skipped":18,"success":27}- merged red.Probe
The four durable-carrier suites send
{ "content-type": ..., "x-bili-plugin": "dsh", "x-bili-plugin-conversation": CONV }and a body of{ model, max_tokens: 64_000, messages: [ {role:"system"...}, {role:"user", content: MESSAGES} ] }- a textbook first main turn.The fix
A genuine utility sidecar differs from that turn in two independent ways, and the patch requires both:
hasSingleShotBudget()requiresmax_tokens | max_completion_tokens | max_output_tokenspresent, positive, and<= 8192. Real presets pin a small number (prompt-enhance sends 4096); a main turn either omits the field (openai wire) or sizes it from the conversation (DSH: If the first request of a session originates from a bypass call, compression for the entire session is permanently | DSH: If the first request of a session originates from a bypass call, compress for the entire session is permanently inv | DSH:会话首个… #5656's own residual turn sends 64000).carriesDurableState()screens the user text againstdshCarrierRawMarkers, the tablesrc/fold-reconcile.ts:142already uses. A carrier body is by definition a main turn's injected context.Both call sites now gate on
hasSingleShotBudget(parsed) && isDshSingleShotSidecar(protocol, parsed).Tests
issue2419issue2446issue2447issue2481issue2817issue5403(watermark)issue5656side-lane-invariantsissue5658npx tsc --noEmit= 0; all four gates (check-unused-exports,config-surface-guard,lifecycle-ledger-guard,check-test-import-graph) = 0;gen-config-docs generateis a fixpoint.Negative control: reverting only the two source files (keeping the test changes) re-reds
2446(3/1),2817(0/1), and5418(0/1) - so the source change is what carries the fix.Two intentional test edits
tests/issue5656-single-shot-sidecar.test.ts: the e2e residual "tool-less turn 1 rides the side lane" is revoked. It pinned exactly the behavior that let [Bug] dsh 车道切模型 fork 出的_sub:会话不继承父会话 fold 块:上游上下文从 ~83K 瞬间膨胀到 794K、命中归 0、节省转负(0.1.187/0.1.188) #2817/[Bug][dsh] 20k-message / 81 MiB-inbound session: host aborted 6× in 2 h — the #3050 resident-AST OOM is not bounded bysessions.hardMaxBytes(Windows, 0.1.210) #5403/[Bug][dsh] Plugin lane performs a full re-parse and resends the entire body every round (81 MiB → hundreds of MB AST), w | [Bug][dsh] plugin 车道每轮全量解析重发 body(81 MiB→数百 MB AST)是 #5403 OOM 的生产者:用水位线断言替换逐条复核,服务端只解析新增尾段 #5418 regress. Re-pinned to "turn 1 with a conversation-sized budget goes through the full pipeline (refs >= 1, requests >= 1)". The other four DSH: If the first request of a session originates from a bypass call, compression for the entire session is permanently | DSH: If the first request of a session originates from a bypass call, compress for the entire session is permanently inv | DSH:会话首个… #5656 tests are untouched and still pin the real sidecars.tests/side-lane-invariants.test.ts:hasSingleShotBudgetjoins the import allowlist - same category asisSideRequest/isDshTitleRequest: a pure structural predicate with no threshold or session state. The numeric threshold itself stays module-private and unexported, which is whycheck-unused-exportspasses.Scope
4 files, +47/-4. No kernel change, no config-surface change, no new dependency. Fixes the regression introduced by #5687.
powered by dsh