Repository navigation
Conversation
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) 查重: 不重复。镜像内按 "Gemini functionResponse image cost / summary notes / rawGoogleParts" 检索 open+closed issue 与 PR,无同症状同机制条目。作者已核对的 #2022(image recovery channel)与 #3412(opaque media accounting)均为 closed、相邻但不同机制——本 PR 修的是「Gemini tool-response parts 里的图片既不进成本/计数,折叠时也不进摘要占位」这一独立缺口。 开始按 PR Review 规范审核(方向 → 回归 → 代码 → 测试有效性),结论稍后在本线程给出。 |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Review of #6147 — "fix: include Gemini tool-response images in budgets and summary notes" (Closes #6146) Dup screen (from my first reply): 不重复 — no same-symptom/same-mechanism issue or PR exists; the cited #2022/#3412 are adjacent-but-different-mechanism (recovery-index lane and custom-shape counting lane, vs. this one's accounting/notes lane). ① Direction — correct layer, root cause. The kernel codec ( ② Regression audit (existing behaviors on the touched paths):
③ Code quality — clean 4-file diff (+130/-5), generator idiom matches repo style, no dead code, comments accurate. One flagged asymmetry (non-blocking, needs your/owner's call):
Behavior changes (disclosed per policy) — old → new:
Consequence: screenshot-heavy sessions' payload estimates rise → folding may trigger slightly earlier than before. This is the intended correction of the up-to-~15× undercount vs actual screenshot cost (pixel-billing rationale per #488), not drift. ④ Tests — real teeth, verified live. I checked out the Rebase & CI status (live-checked). PR base Auto-merge gate (§7.4): strong candidate — pure 标签: bug · gemini · scope/kernel · p2(缺陷;Gemini 原生线客户端;上下文管理/折叠决策域;能用但有明显问题——无数据丢失无缓存泄露,不升 p1) 结构化八问(中文,供人工评审)
判定:可合(建议先 rebase 到当前 master; |
… tool media (ranxianglei#6146) Review supplement to PR ranxianglei#6147: ranxianglei#3617 gate discipline requires both directions of a gate. The image/* mime filter on the Gemini note path had only its positive case pinned. Adds a nested application/pdf case asserting it is billed and counted but earns no recovery note — the note carries a decompress({imageRef}) recovery ref, and the restore channel indexes nested google media for image/* mimes only (src/image-restore.ts), so a note there would promise a restore it cannot deliver. Billing stays mime-agnostic. Also drops a stray double blank line in tests/preflight-google-summary.test.ts.
|
Confirmed the Fixed this in Validation: 70 related tests, all 5 |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Round 2 — reviewing your One attribution note first: The
Local verification at CI (mirror-cached view of your pushed head): 30 checks — 0 failed / 0 pending / 0 cancelled. All test shards (ubuntu 22/24 ×3, windows 22 ×5), static-gates (both OS/node), mysql-contract, test-import-graph, gates green; 14 skipped = the env-gated e2e lanes. One coverage gap to close before merge:
Your note on the live Codex four-phase gate: fine — this PR touches none of the request-pipeline paths ( 结构化八问(中文,供人工评审)
判定:可合(较上轮新增两个前置项:① rebase 到当前 master——本地已验证干净,建议推分支时做;② 建议 owner 加 |
|
Updated the branch with master The merged source tree is identical to the locally validated tree: 70 related tests and all 5 image-billing E2E tests passed, with no failures, skips or cancellations. Typecheck, the full build with dist checks, and @ranxianglei, could you add the |
|
Landed via batch PR #6439 (merged) — closing as superseded. |
… tool media (ranxianglei#6146) Review supplement to PR ranxianglei#6147: ranxianglei#3617 gate discipline requires both directions of a gate. The image/* mime filter on the Gemini note path had only its positive case pinned. Adds a nested application/pdf case asserting it is billed and counted but earns no recovery note — the note carries a decompress({imageRef}) recovery ref, and the restore channel indexes nested google media for image/* mimes only (src/image-restore.ts), so a note there would promise a restore it cannot deliver. Billing stays mime-agnostic. Also drops a stray double blank line in tests/preflight-google-summary.test.ts. (cherry picked from commit 5f3d479)
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Close-out confirmed — verified live before saying so:
To @Afloat16: your merge-commit update ( Review record complete (round 1: accounting/notes fix; round 2: |
[bot] 🏷 (ai: vllm-qwen/qwen3.8-27b) Re-dispatch check — nothing new to act on. Verified live just now:
No action taken this round; no open items. 判定:线程已完结,本轮仅复核状态,无新增工作。 |
Problem
Gemini screenshots in
functionResponse.partssurvive on the wire, but image cost/count walkers skip their enclosing result. They therefore contribute zero to fitting and per-image learning. Summary rendering also ignoresrawGoogleParts, losing descriptions and recovery references when results are folded.The recovery index additionally skipped an entire function response when its payload contained
$ref, even though that reference can name aninlineDataimage carried in the same response.Changes
image/*inline bytes even when the response references them with$ref. A reference without inline bytes still produces no indexed image or recovery note. Indexing leaves the wire response unchanged.5f3d479byci-check, covering non-image nested media: billed and counted, without a recovery note.Validation
The branch includes master
dc041dd1ab1a014efa352ba47a6f31fc47f55284through merge commitc24efc51d0b28c7fbe17067a713cbc27750f92bc. All three existing commits and their original authors remain intact. The merge's source tree07fcfc86014f6057d05c198cf1d38693c339f3c7is identical to the locally validated integration tree.npm run test:e2e:imagetests passed. Both test runs had 0 failures, skips or cancellations.npm run typecheck, the fullnpm run buildincluding dist checks, andgit diff --checkpassed.ci:fulllabel is still needed to execute the image-billing CI lane.Related work checked: #2022 and #3412. The recovery storage format is unchanged.
Closes #6146
Behavior changes (old → new)
$ref: actual nested image bytes remain indexed and recoverable; a dangling reference does not promise recovery.