Repository navigation
[PR] fix: egress fuse and doom gates price the prompt mass, not the whole outbound body (#6844 #7013 #7088) - #7092
ranxianglei wants to merge 10 commits into
Conversation
📦 Built Package ArtifactBranch: Latest build — install this exact versionnpm install -g billion-context@0.0.10900-pr.7092.1da8f04This exact version is immutable and reproducible. The rolling Recent builds (commit → version)
Download artifact
tar xzf billion-context-pr7092.tgz
npm install -g packageInstall instructions are refreshed on each push. |
(ai: vllm-qwen/qwen3.8-27b) 查重: 不重复 — 本线程即修复 PR 本身。同主题在途 PR 核对: #7016 已被本 PR 完整包含(两个 commit 以 标签: 源 PR 已带 Review — independent audit of the diff (not the issue's conclusions)Direction (①): correct, root-cause level. The meter priced the wrong quantity: the window budget applies to prompt mass, but all three gates (egress fuse, both preflight measured tiers, side-request guard) compared the WHOLE outbound body against the window. DSH's model-hidden Code (③): verified against the PR head (
Regression (②): existing behaviors on the touched paths, item by item: byte-floor fallback for unparseable bodies — kept; message-count gate — kept; output-budget read — kept; fail-fast 413 for a genuinely over-window prompt — kept and pinned by the new negative e2e (1.2M-CJK prompt + 2 MiB upload still dooms, upstream sees zero calls); the only semantic change is the gate criterion itself (whole-body → prompt mass), disclosed old→new in the PR body. No fail-fast→swallow, no threshold/timing drift, no cache/retry impact — the fix actually unblocks the watermark-deadlock path the aggregation thread describes. Tests (④): real teeth. Two new e2e cases through the live proxy pin BOTH directions (#3617): 8 MiB Diff (⑤/⑤b): 9 files, +335/−47, every line in scope; no whitespace churn, no generated/lock files; naming, comments (why, with issue refs), and style match the file. Findings (minor, PR-body only — I cannot edit the source PR body, owner to amend before merge if desired):
Local verification: targeted suites 79/79 green (the 8 files the PR lists, run on the PR head) + 八问
判定: 可合(mergeable,base 即当前 master;CI 0 失败/11 pending,待远端全量绿即可由 owner 合并;合并后请 owner 关闭被取代的 #7016 与 #6860)。两条 minor 发现均在 PR 正文层面(缺 model-facing 顶标、#6860 commit 引用笔误),不阻塞,留 owner 酌情修订。 |
|
真实 DSH 生产流量验证了本 PR 的方向,
两个建议:
一个待确认点(不在本 PR 改动文件里):客户端本地 doom gate 走的是 |
(ai: vllm-qwen/qwen3.8-27b) 感谢真实生产流量数据 —— 它独立印证了本 PR 的计量方向: 关于两条建议:
关于待确认点(客户端本地 doom gate): 我已对照代码逐行核实,判断准确 ——
这属本 PR 之外的另一条代码路径(客户端字节估算 vs 服务端 token 分解,不同故障域),且是否改 price prompt mass 是设计决策(客户端 gate 的 cheap-first 字节估算是有意的,见 native-intercept.ts:941-956 注释),需 owner 拍板。按"顺提"规则我已单独立项跟踪: 判定不变: 可合。 CI 现已全绿(10 success / 20 skipped / 0 failed / 0 pending)。待确认点已转出本线程跟踪,属 #7090 根因家族的另一故障域,由 owner 决定是否并入 #7090 清单或单列修复。 |
60edc7c to
4763ab5
Compare
ZzXxYy1234
left a comment
There was a problem hiding this comment.
逐行读了 PR head(4763ab5 fix: show the dominating other-field's byte size in the measured-doom 413)。结论:方向正确,服务端三个消费点(egress fuse / post-compress recheck / side-request guard)都改到了,回归测试也覆盖了「大非 prompt 字段放行」与「prompt 真超窗仍然拦」两个方向。我用真实 DSH 流量核对过,数值吻合:
wireChars=9,947,234
messages:2,561,750 | system:92,785 | tools:2,498 | dsh_session_log:7,275,441 | dsh_plugin_packages:14,564
旧口径 2,395,536 tokens → 413
新口径 prompt ≈ 736K < 1,048,576 → 放行
四条建议,按重要性排序:
1. handle.ts:1874 的 rawInputTokens 仍按整 body 计价
session.metadata.rawInputTokens = estimateRawBodyTokens(parsed) + imageTokensInParsedBody(...)如果这个值参与 usage baseline / preflight 触发(usageGradeInputBaseline 那条链),那么 DSH 这类会话里它仍是 ~2.4M,而 fuse 现在量到 736K——同一份 body 两套口径。建议确认消费方;若它只是「原始体积」指标,建议改名(如 rawBodyTokens)或加注释,避免后续维护者拿它当窗口依据。
2. otherTop 在 responses / google 协议下会把 prompt 字段标成 non-prompt
estimateRawBodyBreakdown 的分桶是 openai/anthropic 形状:input、instructions(responses)、systemInstruction(google)都落在 bucket 3(other),但同时 isPrompt=true。于是 otherTop 会列出它们,而 measuredBreakdownClause 会给整条 other 贴上 "(non-prompt, excluded from the window budget)" —— 对这两种协议是错误描述,排查时会把一个 prompt 字段当成 host 上传字段。建议 otherTop 只收集 isPrompt === false 的字段,或在元素里带 prompt: boolean。
3. PROMPT_BODY_KEYS[protocol] 取不到时 fail-open
measuredOutbound 与 side-request.ts:959 都直接索引 PROMPT_BODY_KEYS[protocol]。若运行时协议串超出联合类型(头部推断、新协议上线),得到 undefined → prompt = 0 → fuse 永不触发。建议 undefined 时回退 estimateRawBodyTokens(parsed)(整 body,保守方向),或至少 log 一次。
4. 建议补一条贴近真实形态的边界回归
现有测试已覆盖「8MB upload + 小 prompt 放行」与「1.2M CJK prompt + 2MB upload 拦」。建议再加一条混合断言,把「剔除」和「没剔过头」一次钉死:
- 2.5MB
messages(≈710K tok)+ 92KBsystem+ 7.3MBdsh_session_log,窗口 1,048,576 → 放行; - 把同一份 7.3MB 内容搬进
messages→ 仍然 413。
一点范围外提醒
客户端本地 doom gate(src/agent/native-intercept.ts:957 的 bodyOverWindowDetail,整体字节 ÷4 ×1.14)在同一份 body 上仍会算 ~2.4M,proxy 不可用 / 侧请求路径上会本地误拒。那条已单独登记,由 owner 决定并入本根因还是单列;这里只提醒它和本 PR 是「同一根因、不同代码路径」。
|
更正我上面 review 的第 1 条:我把 全仓(含 kernel/plugins,排除 node_modules)只有两处引用:
而且 GC 是 opt-in( 所以实际影响只有一个、且方向安全:如果用户开了 GC,DSH 这类会话因为 upload 字段被算进 结论:这条不需要在本 PR 里改,最多在 |
|
第 2 条的实测影响面,已经跑出来了:只影响 413 文案,不影响判定数学;但文案在 google / responses 两种协议下自相矛盾。 影响面:全仓只有两个消费者用 按 PR 的实现原样复算(1.2M CJK 字符): 问题在于:google/responses 的 prompt 键( 最小修法(不改变判定数学)给 const nonPrompt = b.otherTop.filter(e => !e.prompt);
const promptInOther = b.other - nonPrompt.reduce((s, e) => s + e.tokens, 0);
const top = nonPrompt[0];
const other = b.other > 0
? promptInOther > 0
? `other ~${fmt(b.other)} (of which prompt ~${fmt(promptInOther)} — IS counted in the window budget; top non-prompt field: ${top ? `${top.field} ~${fmt(top.tokens)} tokens` : "none"})`
: `other ~${fmt(b.other)} (non-prompt, excluded from the window budget; top field: ${top.field} ~${fmt(top.tokens)} tokens ≈ ${fmt(top.bytes)} B)`
: `other ~${fmt(b.other)} (non-prompt, excluded from the window budget)`;这样 anthropic 的文案一字不变( 建议补的断言在现有 #7013 的 e2e 里各加一个 google / responses 形态:断言 413 的 message 不包含 如果 owner 认为 |
|
Follow-up on my review item ③ ( Sources of
So What is still worth hardening (opt-in, no behavior change for valid configs): The client-side counterpart of this family is already tracked in #7106, so no new issue from me. |
|
Concretizing my review item ② (google/responses prompt fields mislabeled as non-prompt) with a patch on top of this PR's head (4763ab5): Before — a google body whose …i.e. the 413 names the excluded bucket as the reason, while Patch (one commit,
Verification (from the patch branch):
I don't want to open a second PR for the same domain (#7106 already tracks the client-side half), so this is posted as a ready-to-apply patch; happy to turn it into a stacked PR if you prefer that over cherry-picking. |
|
Opened the PR-shaped path after all: #7118 — Merge order: land #7092 first, then #7118 rebases onto master cleanly (it is one commit on top of |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) 逐条回复 + 状态更新: ccfee8a(re-bucketing)取代 otherPrompt — 确认。prompt 键归入命名桶后 m00222(413 措辞自相矛盾) — 证实为真,ccfee8ad99 从根上修复:对 google/responses,prompt 字段(contents/input/systemInstruction/instructions)原先落入 anthropic 命名的 m00223(PROMPT_BODY_KEYS 加固) — 已顺手修掉,push 为 2257410:三个 gate 调用点(measuredOutbound、measured doom tier、sideRequestGuard)统一走新 m00209(rawInputTokens 更正) — 结论正确,已核实: CI:0 failed / 7 pending(22574103f4 运行中),mergeable_state=behind(落后 master,非阻塞)。 八问(PR #7092 全量,含 ccfee8a + 2257410):
判定:可合。方向正确(根因 = 计量器量错量;按 wire prompt 键 = #7013 的更彻底方案,无新配置面),无回归,测试有牙(双向钉死 #3617),diff 干净。建议 owner 合并后关闭 #7016(被本 PR 完全吸收)与 #6860(机制被取代)。 |
…the whole body (#7013) estimateRawBodyBreakdown now also reports the wire-format's prompt mass (messages/tools/system per protocol), and the window-fit gates (egress fuse, preflight doom tiers, side-request guard) use it instead of the whole-body total. A non-prompt upload field (e.g. DSH's dsh_session_log, telemetry that rides the wire but consumes no window) no longer dooms a fitting prompt. - preflight: estimateRawBodyBreakdown gains a promptKeys param and a `prompt` field on RawBodyBreakdown; PROMPT_BODY_KEYS maps each wire protocol to its prompt top-level keys. - server: measuredOutbound now requires protocol and returns the prompt mass; the two preflight doom tiers use outboundBreakdown.prompt. - relay: the egress fuse call passes prepared.protocol. - side-request: the guard estimates the prompt mass, not the whole body. - 413 messages reworded body→prompt, noting the other bucket is excluded. Consumers kept as whole-body total (not window-fit): - handle.ts rawInputTokens (#1082 GC rebuild-cost signal). - threads-lane synthetic prompt-only shapes. Tests: raw-body-walk-depth (prompt mass per protocol + a giant non-prompt field excluded), side-request-isolation (guard uses prompt mass), issue4079 egress fuse (both-ways: giant upload + small prompt forwards; over-window prompt still dooms), issue4185 (doom wording updated). Closes #7013 (cherry picked from commit ff258d0)
… dominating other (#6844) #6844's 88%-other body took a manual body dump to attribute: which host-attached field carries the non-prompt mass. estimateRawBodyBreakdown now tracks per-top-level-field token counts inside the other bucket (otherTop, descending) and measuredBreakdownClause names the dominating field in the 413 reason. No meter semantics change: total, the four buckets and prompt are byte-identical to before; otherTop is pure diagnostics. Ported from sx4im/billion-context PR #6860's otherTop diagnostic, which is independent of that PR's hardcoded-field exemption (superseded by the prompt-mass metering in bccd147).
… 413 (#7090) The 413 clause names the top-level field dominating the non-prompt `other` bucket, but only in tokens. DSH's dsh_session_log upload is capped in BYTES (8 MiB), and 8 MiB of session log is routinely truncated or backlogged — so bytes localize the truncation better than a token estimate. Additive: RawBodyBreakdown.otherTop entries gain a `bytes` field (UTF-8 byte length of the field's string content, sum of leaves — an approximation of the field's JSON size, excluding syntax overhead). The clause now reads `top field: dsh_session_log ~1,755,712 tokens ≈7,275,441 B`. No change to total/prompt/estimateRawBodyTokens; the bytes are diagnostic-only and are never priced against the window budget. Field data motivating this (from an independent repro on DSH 0.2.2-rc.3 + bili 0.1.215, anthropic lane): wireChars=9947234 with dsh_session_log alone at 7,275,441 chars (94% of the wire) — the real prompt (messages+system+tools) was ~736K tokens, under the 1,048,576 window, so the session should have forwarded but 413'd on the whole-body meter.
…y lane (#7090) The 413 clause says 'non-prompt fields in the other bucket are excluded from the window budget', but the display buckets (messages/tools/system/other) were split on the openai/anthropic key names only. On the responses lane the main prompt content `input` (and on the google lane `contents` / `systemInstruction`) fell into the `other` catch-all — so the clause would label prompt mass as non-prompt, and an operator reading 'other ~1.1M (non-prompt, excluded)' would misread their own conversation as the culprit. The gate already priced `prompt` correctly (PROMPT_BODY_KEYS); this is the display-side half of the same fix. With promptKeys supplied, each prompt key now lands in its named display bucket (PROMPT_KEY_BUCKET: messages/contents/ input→messages, tools→tools, system/systemInstruction/instructions→system) and everything else in `other`. The invariants now hold on every lane: `prompt === messages + tools + system` and `prompt + other === total`. total / estimateRawBodyTokens / prompt are unchanged; only the diagnostic split moves. Model-facing: the 413 clause now shows the responses lane's `input` under 'messages ~N' (where it belongs) instead of 'other ~N (non-prompt, excluded)'. Field data (independent repro on DSH 0.2.2-rc.3 + bili 0.1.215, responses lane): a 4.7 MiB /v1/responses body whose top-level keys are model/input/ stream/prompt_cache_key/store/max_output_tokens/tools/reasoning/include — no dsh_session_log on this lane; `input` alone was 1,141,965 tokens and previously sat in `other`.
…Y_KEYS (#7013) Route the three gate call sites (measuredOutbound, measured doom tier, sideRequestGuard) through a promptMassForProtocol helper that falls back to whole-body pricing (breakdown.total) when the protocol has no keys entry, instead of silently pricing 0 (which would OPEN the gate). The Record<WireProtocol, ...> type enforces existence at compile time; a new enumeration test adds the runtime non-empty guard. No behavior change for the four current protocols.
…body bytes (#7106) The DSH client gate (bodyOverWindowDetail) estimated tokens from the whole outbound body (bytes/4, x1.14) with no notion of which bytes are prompt. On official DeepSeek lanes the body also carries dsh_session_log - a transport-only session-log contribution of up to 8 MiB - so a prompt well inside the declared window (e.g. 736K < 1,048,576) was refused locally with doom-gate-pricing-mismatch. When the body parses, the gate now prices only the protocol's prompt keys (anthropic messages/tools/system, openai messages/tools, google contents/systemInstruction/tools, responses input/instructions/tools) with the same CJK-aware counter the server uses, and keeps the #4111 two-tier math: calibrated tier = floor x 1.14, bare floor = provably-over tier. Inline media stays excluded (as it has since #4111); transport-only fields are dropped from the floor. Unparseable bodies keep the whole-body byte estimate, with the early bound raised from bytes/4 to bytes/3 so CJK-dense bodies are not missed. Refusal wording now says prompt mass is what counts. Tests: tests/issue7106-client-doom-gate-prompt-mass.test.ts (6 cases: transport-field-does-not-doom, genuinely-over prompt still dooms, CJK-aware pricing, google/openai shape sniffing, byte fallback, image exclusion). Regression: 179/180 across the gate suites; the one failure (#3578) is a pre-existing Windows temp-dir EPERM cleanup flake, reproduced on clean master. (cherry picked from commit 266b286)
… review) (cherry picked from commit 239a247)
- drop the dead imageTokens field from WirePromptMass (computed but never consumed; the text walk already excludes image keys, #4111) - remove the accidental UTF-8 BOM that landed on native-intercept.ts line 1 - fix the stale CJK test comment (400K/1.2MB -> 1.1M/3.3MB) and its mojibake - rename the image test to match what it asserts (image bytes excluded, not "added back") - restore the trailing newline and drop a doubled blank line in the test file (cherry picked from commit 97c7c30)
2257410 to
32eda3a
Compare
|
(ai: deepseek/deepseek-flash) Independent confirmation that this PR addresses what users hit on the released build, not just master — DSH
Two things worth knowing for the merge/release note:
If it helps, I can re-test the released build on the same two sessions (forked-child first turn, and the rewind case) once it's out. |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Thanks for the independent confirmation on the released build — this is exactly the data that validates the axis the PR picks. Your numbers line up with the fix. Forked-child first turn: whole outbound body ~1.84M tokens, but the prompt mass (messages+tools+system) is only ~240K — well under the 1,048,576 window. The ~1.6M Both release-note points verified against the code:
Two things that changed since my last review (for the record):
On shipping: the release is the owner's call (I can't cut releases). Your offer to re-test the released build on the forked-child + rewind sessions once it's out is exactly the right validation — the two sessions you named are the repro. Verdict unchanged: 可合. The data independently confirms the axis; the expanded client-side fix is correct and tested; CI green. |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) 交叉引用:本 PR 与后开的 PR #7275("name top-level keys when the egress window fuse fires",针对 #7273 的 DSH 413 报告)是同机制家族(egress fuse 定价 + 413 字段定位)的两个在途 PR——两者改 src/server/relay.ts 同一行 #7275 的审核已完成,结论:代码过审,但判为 duplicate of 本 PR(先到者保留),已打 本 PR 侧无需动作,继续正常 review 流程即可;#7275 在决策前保持 open 挂起、不合并。 |
|
(ai: openai/gpt-6) 补充来自 g-yixuan/dsh-sidenote#103 的独立复现与验证。核对到本 PR 已覆盖同一根因后,沿用现有修复,没有另开重复 PR。 验证对象:本 PR head 使用真实 DSH SessionStore、Session-log 插件和请求扩展注册器,构造长历史并提交压缩后的 surface replacement,然后原生 fork。父子 把模块实际生成的请求及正反对照送入真实 bili HTTP 代理,本地模拟上游记录收到的请求数和日志附件哈希:
所有成功转发的大日志请求都校验了附件 JSON 的 SHA-256,转发前后完全一致。子会话请求的原始总量仍估算为 1799184 token,而窗口判断使用的正文量为 149565 token;保留原始计数、单独计算 prompt 的设计有效。真正超窗的对照仍未触达模拟上游。 本地检查:
这些结果支持使用本 PR 作为 sidenote #103 的上游修复。相较于单独给快照加预算,按协议计算模型输入能解决误判,同时保留日志上传和真正超窗保护。这里未调用真实模型 API;HTTP 200 证明请求完整通过本地拦截并转发,不代表已验证模型回答、供应商缓存命中率或报告者的现场配置。 |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) 感谢这份独立复现——是目前对根因覆盖最完整的一份证据,且你核对到本 PR 已覆盖同一根因后没有另开重复 PR,处理得很干净。 CI 复核:本 head 6 场景 A/B 表与 PR 行为逐行吻合:
两个关键不变量你都验到了:
产物一致性:本地构建与固定测试包 边界限定采纳:HTTP 200 只证明请求完整通过本地拦截并转发,不代表模型回答 / 供应商缓存命中 / 报告者现场配置已验证——这个限定是对的,别读成 e2e 模型级验证。 结论不变:可合。两份独立数据(@zhang-ming-hui 的 released-build 413 + 你的 A/B 复现)从两个方向钉死同一根因与修法;CI 绿;wire fidelity 与真实超窗保护都保留。发版仍是 owner 的决策(我不能切 release);「用本 PR 作为 sidenote #103 的上游修复」方向成立,等 owner 拍板发版即可。 |
Root-cause fix for the egress-fuse-pricing batch (aggregation thread #7230; supersedes the doom-gate-pricing-mismatch batch #7090 — same root cause, overlapping members): the measured-body egress fuse, the preflight doom gates, the side-request guard, and the client-local doom gate all priced the whole outbound body against the model window, but the window budget only applies to prompt mass. DSH's documented model-hidden top-level field
dsh_session_log(up to 8 MiB, DeepSeek-adapter routes only) landed in theothercatch-all bucket → ordinary DSH sessions 413 permanently (watermark never advances → deadlock); forked/seeded subagent sessions 413 on the FIRST request (inherited log); and the 413 message misdirected the user to clean upmessages[](the smallest bucket).What this PR does
Server-side metering (cherry-picked from PR #7016 with
-x, authorship preserved)PROMPT_BODY_KEYS: Record<WireProtocol, ReadonlySet<string>>— per-wire prompt fields: openaimessages+tools, anthropicmessages+tools+system, googlecontents+systemInstruction+tools, responsesinput+instructions+tools.estimateRawBodyBreakdown(parsed, promptKeys?)gains apromptfield (single walk, no extra pass).measuredOutbound(prepared)now takes the wire protocol and returnstokens = breakdown.prompt; all three server gates price prompt mass (relay.ts egress fuse, server.ts preflight measured gates, side-request.ts guard).promptMassForProtocol(parsed, protocol)— fail-closed: a protocol with noPROMPT_BODY_KEYSentry prices the whole body (never 0).totalandestimateRawBodyTokensare unchanged — therawInputTokensmetadata ([Feature] Default state file cleanup strategy #1082) keeps its whole-body semantics.otherbucket to its top-level fields (ported from PR [PR] fix: exclude model-hidden DSH fields from the measured body (#6844) #6860'sotherTopdiagnostic):otherTop(descending) added toRawBodyBreakdown;measuredBreakdownClausenames the dominating field (top field: dsh_session_log ~1,634,970) with the(non-prompt, excluded from the window budget)suffix — the 413 no longer misdirects the user to clean upmessages[].Client-local doom gate (cherry-picked from PR #7119 with
-x, authorship preserved — ZzXxYy1234)src/agent/prompt-mass.ts):promptMassOfWireBody(raw)shape-detects the wire protocol (contents→google, input→responses, system→anthropic, messages→openai) and prices only the prompt fields with the same CJK-aware walker as the server.bodyOverWindowDetail(native-intercept.ts) uses it when the body is parseable; non-JSON/unrecognized keeps the byte fallback. The DSH's unattributed over-limit gate prices base64 images as text (bytes/4) — media-heavy requests are falsely rejected wi | dsh 无归属超限门把 base64 图片当文本计价(bytes/4)——媒体重的请求被假拒 422,上游本会正常接受 #4111 two-tier contract (calibrated floor×1.14 / bare floor) is unchanged; media stays uncounted.Why not PR #6860's approach
#6860's hardcoded
MODEL_HIDDEN_BODY_KEYSexclusion would shrinktotal/estimateRawBodyTokens, contradicting #7016's deliberate whole-body total semantics. #7013 explicitly asked for no hardcoded one-plugin field list: the fix is to price the window budget by what the window consumes, which automatically excludes ANY host-attached non-prompt field, known or unknown. Only theotherTopdiagnostic was ported.Behavior changes (old → new)
tests/issue4079-egress-window-fuse.test.ts).dsh_session_log) no longer dooms the client when the prompt fits; a genuinely over-window prompt still dooms. Pinned intests/issue7106-client-doom-gate-prompt-mass.test.ts.outbound body measures ~N tokens … the body ITSELF exceeds the window→outbound prompt measures ~N tokens … the prompt ITSELF exceeds the window(relay fuse, both preflight gates); the breakdown clause'sotherbucket now carries the(non-prompt, excluded from the window budget)suffix and, when non-empty, names the dominating field.otherTopinRawBodyBreakdown(additive; pinned intests/raw-body-walk-depth.test.ts).Tests
Targeted, local: 265/265 green across
tests/raw-body-walk-depth.test.ts,tests/issue4079-egress-window-fuse.test.ts,tests/issue4185-identified-fresh-forward.test.ts,tests/preflight-zero-fold-calibration.test.ts,tests/side-request-isolation.test.ts,tests/issue7106-client-doom-gate-prompt-mass.test.ts,tests/dsh-native.test.ts,tests/issue4894-direct-window-guard.test.ts,tests/native-intercept.test.ts. Typecheck clean. Full-suite verdict = remote CI on the pushed head.Relationship to existing PRs
-x): superseded by this PR — recommend closing after merge (agents cannot close PRs).otherTopdiagnostic is ported here — recommend closing after merge.-x, authorship preserved) — recommend closing after merge.Pending decision (NOT fixed by this PR)
dsh_session_logstill rides to the upstream verbatim after the metering fix. Decision: A (keep pass-through) / B (strip documented DSH model-hidden fields at egress) / C (DSH stops sending). This PR fixes the METER only; the forwarding surface needs an owner decision.Fixes #6844
Fixes #7013
Fixes #7099
Fixes #7106
Fixes #7189
Fixes #7088
Related (decision item, not fixed here): #7114