Skip to content

[dsh] A healthy 93%-compressed image session becomes permanently uncompressed by ordinary usage: quota → model switch → attribution loss → 413 → rewind → 3,455 dead refs → compress REFUSED forever (0.1.202) | 一个健康压缩率 93% 的图片会话被普通操作永久废掉:额度→换模型→丢归因→413→撤回→… #3918

Closed

Description

@radio607

Environment

bili 0.1.202 (commit 6deb4547), plugin native lane, 127.0.0.1:18790
client DSH desktop 0.2.1-rc.2 (Electron, win32 x64, Windows 11)
upstream copilot.tencent.com / workbuddy relay → deepseek-v4.1-flash, declared 1,000,000, effective 872,000 (128k output reserve)
host RAM 15.2 GB total, 1.4 GB free at the time of the incident
config compress.externalSummary enabled (3 targets, all on one local forward gate)

Session: session-7ffc1d1c-8c3d-4966-8e0c-8cf4cee3c8f4 — an image-heavy 3D-scene development conversation, 3,550 messages, 271 image parts / 264 unique attachments / 138,965,404 B (132.5 MiB) raw = ~176.7 MiB after base64.

Summary

This session worked perfectly for days at a 93% compression ratio (inbound=43.6MiB → outbound=2.9MiB). It then became permanently uncompressible after a sequence of completely ordinary user actions:

quota exhausted → user switches model & retries → attribution lost → DIRECT (uncompressed)
                → 413 request body too large → user retries with rewind
                → 3,250 covered ids drift → 3,455 dead refs
                → every `compress` call REFUSED (view=0) forever
                → preflight death spiral, session permanently slow

None of these steps is a misuse. The user did what any user does when they hit a quota wall: switch model, retry, undo the bad turn. The result is a conversation that can never be compressed again.

Phase 1 — healthy (compression at 93%)

2026-10-18T17:43:28Z  request: 3540 msgs, inbound=43.6MiB, outbound=2.9MiB

Seconds later the upstream returned 429 and DSH surfaced QUOTA_EXCEEDED (turn 9). Compression was not the problem at this point — it was working exactly as designed.

Phase 2 — model switch → attribution loss → DIRECT uncompressed → 413

After the quota error the user switched provider/model and retried. bili then lost the session attribution and every request went out raw:

2026-10-19T04:14:36.170Z [warn] [dsh-client] bili-native-dsh: model request sent DIRECT (uncompressed)
  — takeover gate refused http://127.0.0.1:7868/inference/v1/chat/completions:
    no active initiator attribution (agentless/background lane, third-party in-process
    caller, or stale attribution after host resume?)
2026-10-19T04:15:23.251Z  … http://127.0.0.1:8897/…  (same)
2026-10-19T04:17:22.110Z  … http://127.0.0.1:8897/…  (same)
2026-10-19T04:22:48.882Z  … http://127.0.0.1:12322/… (same)

19 such DIRECT lines exist on 10-19, but most are an hourly sidecar (00:21, 01:21, 02:22, 03:22 … 09:58) and are unrelated noise. The ones that matter are the cluster at 04:14–04:22 UTC, which lines up to the second with the two 413s (Beijing time = UTC+8):

DIRECT (uncompressed) 413 in DSH Δ
04:17:22.110Z → :8897 12:19:11 = 04:19:11Z (turn 11) ~2 min
04:22:48.882Z → :12322 12:22:43 = 04:22:43Z (turn 12) ~6 s
2026-10-19 12:19:11  {"message":"request body too large","code":"CLIENT_ERROR","status":413}   (turn 11)
2026-10-19 12:22:43  {"message":"request body too large","code":"CLIENT_ERROR","status":413}   (turn 12)

And critically: zero bili log lines mention this session on 10-19. It was invisible to the proxy all day — which is exactly why nobody noticed compression had stopped.

Note the feedback loop: the bigger the session, the more the attribution loss hurts, and the more likely the user is to switch models — which is what causes the attribution loss. A 43.6 MiB session never 413s while compressed; it 413s immediately once compression silently stops.

Phase 3 — rewind → ref drift → 3,455 dead refs

The user retried and used rewind/withdraw to undo failed turns (7 times). When bili re-took over the session it found the fold anchors no longer matched:

[fold-reconcile] resent history drifted: 3250 covered id(s) missing — reanchored 3250
unannounced client history rewrite detected (1203/4998 incoming message(s) carry pre-turn refs of 4720 known)
  — marking compaction boundary (#1001)

Result: 63 blocks (46 active) that claim to cover m00001–m04397, but ~3,455 refs are dead. The token view looks healthy (271,287 / 872,000 = 31%) while the wire body stays at 44.7 MiB — i.e. the panel says "compressed" and the request is still raw. That gap is the single most misleading thing in this whole incident.

Phase 4 — compress permanently REFUSED (this is the part that never heals)

The session weighs 444 MiB resident, and bili's resident pool budget is 512 MiB:

[session] evicted session-7ffc1d1c… from resident pool (weight 466297620 bytes, 1 session(s) remain, budget 536870912 bytes)
[session] evicted session-7ffc1d1c… from resident pool (weight 449962280 bytes, 1 session(s) remain, budget 536870912 bytes)
[session] evicted session-7ffc1d1c… from resident pool (weight 449375528 bytes, 1 session(s) remain, budget 536870912 bytes)

With a second 87.5 MiB session open, 444 + 87.5 = 532 MiB > 512 MiB → the big session is evicted every single time. And an evicted session has no live message view, so compress refuses every attempt:

[acp-proxy: compress REFUSED m00004–m00016, m00120–m00123, … — no visible context
  (view=0 message(s), 5048 ref(s) mapped); refs left untouched and nothing recorded as dead
  — the view self-heals on the next model request (#3126)]

The refusal message tells the user "after the next turn you can compress the same ranges again". That advice is wrong for this session: the next turn re-evicts it, so every retry fails identically. The user retried 3 times over 40 minutes and never succeeded.

This is the core structural defect I want to report: above a certain session size, the compress tool is permanently unusable, and nothing in the UI or the error message says so. The user is left repeatedly clicking a button that cannot work, on a session that cannot shrink without that button.

Phase 5 — preflight death spiral, plus two reporting bugs

After I cleared the stale ledger (backed up and moved both origin snapshots) so the session could relearn refs, preflight rebuilt from scratch and did work — 64 real folds, 2,012,855 → 914,731 tokens, every one via externalSummary:

[external-summary] completed (preflight) 4/4 range(s); calls=4; batch=finished result=success
[Compressed m02732–m02825 → 1 block(s), ~87282 tokens saved.]
… 64 lines total …
[preflight] round 9/32: payload ~914731 tok vs window 872000 (deficit 42731), 149 viable range(s)

Then it failed anyway, 42,731 tokens short, because the 32-call summarization budget ran out:

preflight fail-fast 502 (retryable=false): context ~652251 tokens (down from ~1153146 before preflight)
  exceeds the model window 872000 (model=deepseek-v4.1-flash), with 149 compressible range(s) still visible
  and preflight compression could not bring it under: the preflight summarization budget
  (32 calls per protection regime) was exhausted before the payload fit the window.
  The over-window payload was NOT forwarded.

Two separate reporting defects are visible right there, both already filed — but they made this incident much harder to diagnose, so I'm listing them as they hit me:

  1. [preflight] Failure headline mixes calibrated size and raw stats, and labels input budget as model window #3663 — the headline mixes calibrated and raw quantities and calls the input budget the model window. Here it printed context ~652251 tokens … exceeds the model window 872000, which is self-contradictory on its face. The actual decision value in the same preflight was 914,731.
  2. [Bug][preflight] Local 413 is forgotten when the baseline becomes an estimate, reopening oversized probes #3846 — after that local 502 refusal, the next attempt forwarded on estimate only: request: 3637 msgs, inbound=44.7MiB, outbound=32.2MiB → [acp-usage] input=620921. So the refusal was not durable; a later pass reopened the oversized forward.

Why I think this is a design gap, not user error

Every single trigger is normal usage:

what the user did is it reasonable? consequence
hit a quota wall yes, unavoidable —
switch model and retry yes, the obvious thing to do attribution lost → uncompressed forward → 413
rewind a failed turn yes, the obvious thing to do 3,250 covered ids drift → 3,455 dead refs
click "compress" to fix it yes, that's what the button is for permanently refused (session can't stay resident)

The failure mode is also silently irreversible: once refs drift, the token view stays plausible (31%), so nothing warns the user that the session has become permanently unable to compress. The only visible symptom is "slow and expensive", which looks like a model problem, not a compression problem.

A session that has already been compressed 63 times should not be able to fall off a cliff like this. Graceful degradation would mean: detect that a large session cannot stay resident, and either (a) say so plainly instead of suggesting a retry that cannot work, (b) allow compress to operate on the on-disk snapshot without a resident view, or (c) evict smaller sessions first so the one that needs compression can stay resident.

Relationship to existing issues

issue state covers gap
#3909 open image session permanently re-sending 48.6 MiB, fold blocked by cadence, archived images still on wire (pi lane, 503) different lane, different trigger; does not cover attribution loss → 413, nor the resident-eviction → compress REFUSED loop
#2438 open preflight compress/timeout loop on sustained mass fold-coverage loss has no graceful degrade describes the loop, not the entry into it; no resident-pool angle
#3859 + PR #3863 open no-visible-context guard bypassed for ranges overlapping active blocks, marking live refs DEAD adjacent, but here the guard did fire correctly — the problem is that it fires forever
#3137 open empty view marks request refs DEAD defense-in-depth, not the permanent-refusal UX
#3724 closed host-side rewind/undo tail truncation unhandled (summaries survive rewinds) closed, but rewind is still one of the drift sources here
#2975 open workbuddy reverse proxy can't compress — no active initiator attribution exact same mechanism as my Phase 2; owner asked for A/B evidence on 10-13, last activity 10-14, still open
#3651 / PR #3653 open / open takeover-broken banner false alarm from agentless sidecar lanes addresses banner noise; PR still unmerged, so real attribution loss still has no user-visible signal
#3872 open mid-session wire/dialect switch sends one request far beyond the declared window; no send-time size guard same class of "no byte guard before send" as my Phase 2
#3846 open local 413 forgotten when baseline becomes estimate, reopening oversized probes hit me in Phase 5
#3663 open preflight failure headline mixes calibrated/raw size, labels input budget as model window hit me in Phase 5
#3588 / #3641 closed image-offload rewrites history → fold refs break → "substrate destroyed"; root fix = "snapshot as session", identity claim by order not hash #3641 closed 2026-10-18; if the implementation is not yet in 0.1.202, this incident is a live instance of the exact defect #3641 was meant to root out

I could not find an existing issue that ties these together as one causal chain reachable by ordinary usage. That is what I am reporting.

Expected behaviour

  1. Size-aware compress: if a session cannot stay in the resident pool, say so explicitly and stop suggesting a retry that is guaranteed to fail. Better: allow compression against the persisted snapshot so the tool is not size-gated.
  2. Resident eviction policy: evict by need, not by size — a session that the user is actively asking to compress should win over an idle smaller one.
  3. Make the drift visible: when refs die, the status panel must not keep reporting a healthy compression ratio. Today 271,287 / 872,000 = 31% coexists with a 44.7 MiB raw wire body.
  4. Attribution is load-bearing but silent: losing it should degrade loudly (or better, fall back to the in-band session header chain that the server side already understands — see The D4.1F model accessed via the WorkBuddy reverse proxy cannot be compressed. | 使用workbuddy反代的D4.1F模型无法压缩 #2975's analysis). Right now the only trace is a warn line the user never sees, and the consequence is an uncompressed 43 MiB request.
  5. Durable local refusals: a local "too large" refusal must survive an estimate demotion ([Bug][preflight] Local 413 is forgotten when the baseline becomes an estimate, reopening oversized probes #3846). Otherwise the refusal is advisory.
  6. Preflight budget vs reality: when preflight has 64 successful folds and is 42,731 tokens short, running out of a hardcoded 32-call budget and returning a non-retryable 502 is a poor trade. Either extend the budget when progress is being made, or report "almost — N tokens short, retry will continue" instead of a terminal error.

What I did locally (in case it helps reproduce or triage)

  1. Appended one official DSH image/offload event (seq=9771, 269 targets) to the session log, taking 269 of 271 images off the wire. DSH accepted it, seq stayed monotonic, projection replayed correctly. This works and is worth considering as a supported path for image-heavy sessions.
  2. Backed up and moved both origin legacy snapshots so the session cold-loaded empty and relearned current refs. Preflight then produced 64 real folds — so the ledger rebuild approach works, it just does not survive the 32-call budget.
  3. After all of that the session is usable again (produces assistant messages and tool calls normally) but still sends ~44.7 MiB per round, and compress on it still cannot succeed.

Happy to run any A/B or provide further dumps — I have the full bili.log, the session's session.v4.jsonl.zstd, and the ledger backups preserved.

Activity

  1. changed the title [-][dsh] A healthy 93%-compressed image session becomes permanently uncompressed by ordinary usage: quota → model switch → attribution loss → 413 → rewind → 3,455 dead refs → compress REFUSED forever (0.1.202) | 一个健康压缩率 93% 的图片会话被普通操作永久废掉:额度→换模型→丢归因→413→撤回→3455 死 ref→compress 永远被拒[/-] [+][dsh] A healthy 93%-compressed image session becomes permanently uncompressed by ordinary usage: quota → model switch → attribution loss → 413 → rewind → 3,455 dead refs → compress REFUSED forever (0.1.202) | 一个健康压缩率 93% 的图片会话被普通操作永久废掉:额度→换模型→丢归因→413→撤回→…[/+] on Oct 20, 2026
  2. ranxianglei commented on Oct 20, 2026

    @ranxianglei
    Owner

    🤖 Powered by ework · qwen3.8-27b

    (ai: vllm-qwen/qwen3.8-27b)

    查重: 不重复(open+closed 均按失败签名检索过)。你列的关联表我逐条核了:Phase 2(归因丢失→DIRECT 不压缩)与 #2975 是同一机制、同一症状(takeover gate 无备选归因通道),并入 #2975 的 A/B/C 决策,本票不重开;Phase 3 的 id 漂移根因在 snapshot-render 谱系(#3756/#3641/#3724);持久本地拒发=#3846、标题口径混用=#3663,各有独立线程。本票自己的新机制:大会话被驻留池反复驱逐 → compress 永久 REFUSED + 误导性恢复建议 + preflight 有进展却报终局错误。检索无重复项(查重: 无)。

    标签: bug, dsh, scope/kernel, p1(核心承诺失灵——该会话压缩能力永久不可用,按 2026-10-19 修订归 p1,不降档)。

    版本核对(先定版本):你的 bili 0.1.202 = commit 6deb4547。我 diff 了 tag→master 的相关文件:src/stream.ts(refusal 逻辑)零改动,session.ts/preflight.ts/dsh-native.ts 仅有无关小改——下面的代码级结论对你的版本成立,不存在"master 已修"的情况。

    已在代码里钉死的三处缺陷(不是猜):

    1. 驱逐乒乓(src/session.ts releaseInFlight :1051-1057):每个模型请求结束后立即按字节预算回写驱逐;你的会话实测驻留 ~444 MiB + 另一会话 ~87.5 MiB > 512 MiB 预算,两个活跃会话互相驱逐,任何一次 compress 都落在"视图为空"窗口里。
    2. 误导性建议(src/stream.ts noVisibleContextRefusal :640):拒发回执固定说"等下一轮模型请求后重试即可"——对预算驱逐场景这句话永远不成立,下一轮照样被逐。这是把你卡死的直接文案。
    3. 终局误判(src/server.ts :3603-3608 + src/preflight.ts :2778):preflight 预算耗尽的 failure 不带 retryable 字段 → 一律 502 retryable=false,即使本轮已经真实折叠了 N 个 range(折叠是持久的,下一轮从更小基线继续)。你那 64 次有效折叠每次都报"终局",就是这条。

    处置计划(连贯修复,一个 PR 收口本机制族):

    • 现在就修(无需拍板):① 拒发回执区分"瞬态"(重启/临时驱逐,原文案保留)与"永久"(最后实测足迹 + 当前驻留 > 预算)——永久情形明说重试无效,并给出两条可操作出口(关掉其他会话 / 调大已存在的 sessions.residentMaxBytes,CONFIGURATION.md 已有文档)+ 日志加 PERMANENT 标记便于 grep;② preflight 有持久化进展的非确定性耗尽 → retryable=true + 消息带上"本轮已折叠 N 个 range、还差约 X token、下轮继续"。
    • 需要你拍板(选项+推荐随后给出):驱逐策略(按需求保活 vs 纯 LRU)、以及是否支持对磁盘快照做 compress(根治"消息字节只活在内存"这个结构问题)。

    PR 马上来,八问体例收尾。

  3. ranxianglei commented on Oct 20, 2026

    @ranxianglei
    Owner

    🤖 Powered by ework · qwen3.8-27b

    (ai: vllm-qwen/qwen3.8-27b)

    无决策依赖的部分已修完,两个根因方向等你拍板。 PR:#3943 (CI 运行中)

    本次修了什么(两处方言,都是「判决说谎」)

    修复 1 — 「compress 永远被拒」现在会明说「重试不会好」。
    旧拒收回执对所有情况都说「等下一轮模型请求后重试即可」。但对装不进常驻池的大会话,这个承诺永远不成立:每次模型请求结束后它都被逐出(超预算即驱逐是既有设计),视图在请求之间从不存活。现在 bili 在每次驱逐时记下该会话的实测内存占用;若「本会话占用 + 其他常驻会话 > 池预算」,拒收消息改为:此拒收不是暂时的——现在或下一轮重试都会以同样方式失败;恢复途径:关掉另一个打开的会话,或把 sessions.residentMaxBytes 提到约 X MiB 以上(按实测数字给出)并重启。操作日志同步加 PERMANENT 标记 + 三个数字。真正暂时的场景(小会话、刚重启)保持原文一字不改。

    修复 2 — preflight 预算耗尽但已有进展时,不再报「死局」。
    原来预算耗尽一律 retryable=false。但已折叠的 range 持久在会话里,下一次尝试从更小的基线继续折——事故中 64 次有效折叠(2,012,855→914,731 tok)每一轮都被判死局。现在:非确定性耗尽 且 有成功折叠 → retryable=true + 说明「N 个 range 已折叠并保留,距窗口还差约 X tokens」。零进展耗尽与确定性耗尽(含 #3461 的 413 路径)行为不变。

    结构化八问

    1. 是什么问题:健康压缩率 93% 的图片会话被普通操作永久废掉的过程中,两处判决对用户/宿主说谎——拒收回执承诺了一个永远不会到来的自愈;preflight 在明明有进展时宣布终局。
    2. 什么原因导致的:① 大会话的活内存占用只在常驻期间可测,逐出后无任何记录,拒收逻辑只能给统一的「会自愈」承诺——驱逐机制本身是按设计的空闲缓存策略,但其后果(永久乒乓)对所有人不可见。② fail-fast 判决只看「这次是否压进窗口」,不看「这次是否取得了进展」;折叠跨轮持久,判决却当作一次性。
    3. 影响范围与严重程度:p1。触发条件 = 会话活占用 + 其他常驻会话 > 512MiB 默认预算(图片重会话极易命中);后果 = 该会话永远无法再压缩、每轮裸发原始历史(事故 44.7MiB/轮)、高概率 413、成本失控。修复 1 不改变触发条件,只让判决诚实并给出出口;修复 2 只改该条 preflight 路径的错误响应语义。
    4. 怎么修复的:驱逐时刻记录实测占用(咨询性 map,上限 256 条,非承重)→ 拒收时计算「本会话能否在请求之间存活」→ 按情形分支文案;fail-fast 尾部加一个 progressContinues 条件翻转 retryable 并追加进展说明。
    5. 是否有回归问题:逐项审过——暂时性拒收文案字节级不变([bug] 大会话 compress 持续失败:ctx has 0 message(s) 时所有 ref 被判悬空(cannot-anchor),报错归因误导 #3126 六测全绿);零进展/确定性 preflight 路径不变(Three issues found during real-model stress testing: WS passthrough can't connect — HTTP upstream is guaranteed to die; | 真模型压测发现的三个问题:WS 直通连不上 HTTP 上游必死、超限时死锁+紧急提示风暴、compress 激活本身太重 #3461、preflight-multi-range、preflight-fail-fast、模型压缩输出是输入的数倍 #1841 futility、[Evidence] pi 车道切供应商(同 modelId)后 fold 不随会话迁移:裸上下文 2.23MB(≥298K est tokens)被 preflight 10 秒拒 3 次;账面 ≤157K 与裸水位背离 10.5h #2847 doom、[Bug] Codex 额度中断后恢复长会话,preflight SSE 摘要为空并持续 502 #726 cooldown 全绿,共 60 个定向测试过);驱逐行为本身未动(LRU 选择逻辑零改动,只在删除后加一行记录);无新配置面。
    6. 是否破坏缓存:否。两处都不碰前缀缓存/折叠提交逻辑;修复 2 只改错误响应体,超窗 payload 依旧不转发。
    7. 是否改了设计方向:否。不动驱逐策略、不动持久化格式、不动 kernel。这是诊断诚实 + 判决诚实。
    8. 是否引入新配置:无。仅引用既有的 sessions.residentMaxBytes / BILI_SESSION_RESIDENT_MAX_BYTES(CONFIGURATION.md en/zh 已收录)。

    合并判定:单模块范围的判决映射修正 + 双向回归测试齐备,但 retryable false→true 属错误语义变更(§7.4「fallback/默认值变更是产品决策」),请你人工合并:#3943

    等你拍板的两项(本事故的根因方向)

    决策 1 — 驱逐策略(你的预期行为 2)

    • 选项 A(维持现状 LRU):零成本。代价是多会话工作负载下大会话持续乒乓——但修复 1 之后用户知道为什么、怎么解。影响面:无新增;回归风险:无。
    • 选项 B(按需驱逐):discharge 时优先逐出「闲置且小」的会话,保护正在被压缩/刚折叠过的会话。影响面:releaseInFlight/evictOldest 的选择逻辑,哪个会话被逐出会微妙变化(磁盘状态兜底,数据安全)。回归风险:驱逐顺序变化可能影响多会话缓存命中分布,需要一轮 e2e 观察。
    • 推荐 A:B 是优化不是修复——修复 1 后失败模式可见且可解;等真实数据看看乒乓频率再决定是否值得做 B。

    决策 2 — 快照式压缩(你的预期行为 1b,真正的根治)

    • 病灶:消息字节只存在于内存,而压缩依赖视图常驻。对超预算会话,这个依赖结构性无法满足——修复 1 只是把这件事说清楚了。
    • 选项 A(持久层存消息原文):pluginMessages 随状态落盘(存储格式扩展;图片 base64 使磁盘占用显著增长——事故会话 176.7MiB,zstd 后仍数十 MiB)。此后即使被逐出也能对着磁盘快照压缩,永久拒收这一类病从结构上消失。影响面:persist 格式版本 + 存储体积;回归风险:格式演进需走既有迁移纪律,中等。
    • 选项 B(不存,维持现状 + 修复 1):零存储成本;大会话仍需「关别的会话/调预算」才能压缩。影响面:无;回归风险:无。
    • 选项 C(折中):仅对超过阈值(如 >50% 预算)的会话落盘消息原文,控制磁盘增长。复杂度中等,多一条格式分支。
    • 推荐 A(在意磁盘就选 C):这是唯一消除该故障域而非让它可见的选项,且与 Snapshot rendering: proxy-lane outbound is now rendered authoritatively server-side; existing sessions are immune to ker | 快照渲染:proxy 车道出站从服务端正史渲染,存量会话对内核升级免疫(#3752 根治) #3756 D 车道「服务端正史不应依赖内存驻留」的方向一致。涉及存储格式演进,按约定先拍板再动工。

    相关线程(未重复劳动)

    标签维持首报:bug + dsh + scope/kernel + p1(核心承诺失灵:健康压缩会话被普通操作永久废掉)。

  4. ranxianglei commented on Oct 20, 2026

    @ranxianglei
    Owner

    🤖 Powered by ework · qwen3.8-27b

    (ai: vllm-qwen/qwen3.8-27b)

    CI 小修:首推的 head 上 unused-exports 门禁红了——新加的 ResidentPressure 接口只有模块内使用(跨模块只消费函数返回的推断类型),已去掉 export 一词(af0956b5e,独立标注 commit),本地门禁 + typecheck 复跑全绿,已推上 PR 分支。核心测试矩阵在新 head 上运行中。

  5. added a commit that references this issue on Oct 21, 2026
  6. ranxianglei commented on Oct 21, 2026

    @ranxianglei
    Owner

    四组件修复全部进 master,关闭:

    1. P2 归因丢失(DIRECT 裸发/413 的入口):[PR] dsh: session identity rides the request object (llm/stream attribution, #4082) #4101 llm/stream 会话身份随请求对象 + [PR] dsh: negotiated session recall for unattributed retries (#4082) #4094 指纹桥兜底——重试/切模型不再裸发。
    2. P3 rewind → 3255 id 漂移 → 死 ref:快照渲染栈(Snapshot rendering: proxy-lane outbound is now rendered authoritatively server-side; existing sessions are immune to ker | 快照渲染:proxy 车道出站从服务端正史渲染,存量会话对内核升级免疫(#3752 根治) #3756 引擎 + Snapshot as session reconstruction: identity claim order takes priority, message hash demoted to reference signal (root- | 快照即会话重构:身份认领顺序优先,消息哈希降级为参考信号(根治 #3588/#3640 一类误判) #3641/[PR] fold anchoring doctrine: order over hash — shape churn, image offload, host truncation stop reading as destruction (#3641) #3644 教义 + Snapshot rendering identity signature does not include message ID: duplicate short messages silently truncate history (m | 快照渲染身份签名不含消息 id:重复短消息会静默截断历史(开灰度前必须修) #3812 接缝加固)——服务端正史渲染出站,客户端字节漂移不再拆会话;影子对账([PR] Snapshot Rendering Shadow Reconciliation: The outbound snapshot engine defaults to dry-run; alerts are raised only for m | 快照渲染影子对账:出站快照引擎默认干跑,机械可证错误才报警 #3865)默认开收证据。
    3. P4 常驻池驱逐 → compress REFUSED 永久死:[PR] compress-from-store: evicted sessions fold against the unified-store view instead of refusing forever (#3982) #3983 compress-from-store——被驱逐会话对着统一存储视图折叠,拒绝回执不再谎称会自愈。
    4. P5 预算耗尽报死局:[PR] fix: name permanent resident-eviction compress refusals and keep progressing preflight exhaustion retryable (#3918) #3943 拒收诚实化——有进展的预算耗尽标 retryable,不再一次判死。

    验收状态:相关测试族全绿(llm-stream 4/4、recall 2/2、native-intercept 64/64、compress-from-store 4/4、eviction honesty 8/8);CI 全绿。老会话的已损形状(如 rewind 后的死 ref)在新版首次加载时走快照/词袋认领自愈,内容不丢(CCR 保底)。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions