Repository navigation
release v0.1.190 - #2581
release v0.1.190#2581
Conversation
📦 Built Package ArtifactBranch: Option A — Install this exact build (recommended)npm install -g billion-context@0.0.2813-pr.2581.ff9a63cThis exact version is immutable and reproducible. The rolling Option B — Download artifact
tar xzf billion-context-pr2581.tgz
npm install -g packageInstall instructions are refreshed on each push. |
📦 release v0.1.190 — 版本区间回归审计结论审计范围: 结构化八问1. 是什么问题:这是发布 PR,不是单点缺陷——聚合 v0.1.189 以来约 60 项独立修复/特性。本审做的是「上一版本以来的全部变更」回归审计。 2. 什么原因导致(本窗变更的性质):一整套机制级根因修复,各自锚定具体事故——dsh 持久态保护(#2419/#2446/#2447/#2481)、external-summary autoFold(#2326/#2484/#2494)、fold 位置身份(#2480/#2487)、网络/代理健壮性(#2484/#2491/#2493/#2496/#2502)、anthropic thinking 签名安全(#2501)、安装就绪门禁(#2471)、非 ASCII 头守卫(#2455)。 3. 影响范围与严重程度:无用户可见破坏。多数改动是双重 opt-in 或证据白名单门控(autoFold 需 4. 怎么修复的:机制层、治本不堵漏——kernel 新增加法钩子 5. 是否有回归问题:未发现回归。逐项过既有行为:
6. 是否破坏缓存:净正向。#2558 修图片在 usage 基线下的重复计费(解除 clamp 饥饿);#2499 恢复客户端自管 session 折叠后前缀写回 cache;#2326 first-sight 批量排空把前缀重付从 2.29×/tok 压到 0.032×/tok(~70×);pi-subagents #2546 修 delegate 通知掉出 cache。未引入任何缓存/重试/增量游标/去重键失效;fold-reconcile 的 reuse-by-id 反而增强了 fold 状态复用。 7. 是否改了设计方向:无架构转向。全部扩展现有机制(kernel 钩子、证据白名单、三级 config 级联、exit-matrix 契约账本); 8. 是否引入了新的配置:是,2 个可选字段挂在既有 重大行为变更清单(旧→新 + 原因,Deliverables 第 4 条)
次要观察(非阻塞,记录备查)
判定可合(mergeable)。 整窗无回归、无缓存破坏、无设计转向;高危域逐行核实,KDD#10 合规;新增配置默认关且文档齐备;CI 在 rebased head |
🔁 本 issue 已在本会话完成审计,结论见上方楼层(comment id 27328):release v0.1.190 版本区间回归审计可合(mergeable)——整窗无回归、无缓存破坏、无设计转向,KDD#10 合规,新增配置默认关且文档齐备,CI 在 rebased head |
|
双重配置是啥 ?是否可以修复? |
@Dog 指的是我在审计里说的 autoFold 双重 opt-in—— "externalSummary": {
"enabled": true, // ① 打开外部摘要链
"autoFold": true, // ② 该链的“主动增长折叠”子模式
"autoFoldTargetTokens": 40000
}①和②各管什么(不是重复开关):
为什么要“双重”: autoFold 不是独立功能,它复用链的零模型折叠引擎,链不开它就无从运行。所以依赖真实存在,这是有意设计且已写进文档(CONFIGURATION.md:1119 “it only takes effect while the chain itself is enabled”)。不是 bug、不是冗余;合并成一个开关反而会把「响应式溢出压缩」和「主动增长折叠」两种行为混为一谈,我不建议。 唯一真正的体验瑕疵(可修): 若只写了 修法(属 config 面,按项目规则由你拍板):
我的建议是走 (A)。本 release PR 已是 version-bump-only 且审计完成,不在这里夹带改动——如果你认可方向,我另起一个小 PR(引用本线程)实现 (A);或你倾向 (B)/维持现状,告诉我即可。 |
|
本pr改 改不完不能发布 |
autoFold/autoFoldTargetTokens are parsed only after the chain's enabled gate, so setting them without "enabled": true was dropped silently — the most likely misconfiguration of the double opt-in went unnoticed. Both parsers now log a one-time warning per distinct knob-set instead of no-oping invisibly. Diagnostic only: behavior is unchanged (a valid "enabled": true chain emits nothing; a broken/absent chain still resolves to enabled:false), and no config or env surface is added. CONFIGURATION.md (+zh) and CHANGELOG updated. Directed as a release blocker in PR #2581 (v0.1.190).
已在 release 分支修好并推送(commit 按八问:
判定:可合。合并即由 release.yml 发布 v0.1.190(我这边不执行 merge,需你手动合并 #2581 )。CI 若转红我会跟进。 可选后续(选项 B):若你更想彻底去掉第二个开关(让 |
Release review: v0.1.190 (
|
收到,谢谢这份独立全量审(四切片 + 本地实测 A/B + canary,很扎实)。结论一致:可合。 我那笔已在位且与你的 9 条正交:autoFold 双重开关警告修复 对这 9 条(你标 none blocking)我的建议:
要我现在就开这 5 个 issue 吗?还是你自己分诊 / 或挑其中几条先在本 PR 修掉?给个方向我就动手。 (合并仍需你手动:#2581 ) |
- nudge suppression: growthFoldingArmed() gates autoFoldEngaged so a degenerate growth config (sub-MIN window, target clamped to the window) no longer silently swallows every classic nudge; applies to all four prepare lanes, responses lane honors the codex intercept bar - calibration straddle: a growth-armed zero-progress preflight with estimate < limit <= calibrated now arms the auto-fold cooldown too (was: skip the arm, re-fire the trigger every turn with a guaranteed 400 forward) - #2496: a Request-object input whose body was disturbed by the failed send fails with the original error — no retry, no respawn, no direct degrade (new Request(target, input) would throw 'Body is unusable') - #1662: pi-marker re-entry at depth 1 now dispatchDepth.run(2) like the anchor jump, bounding marker-wrapper chain growth - #2443: opencode conditional-tool registration rejections surface and re-arm the retry cadence instead of latching toolDeltaReady early - dsh-native-client: onTheme gated on !cancelled Deferred MINORs tracked in #2602.
|
Follow-up on the review MINORs — all six actionable findings are fixed in this PR (0fbf761, on top of ddba1b9); the three deferred ones are now tracked in #2602. Fixed in this PR
Regression coverage
Deferred → #2602#3 ledger floor never decays / cap<1024 surrender (deliberate, test-pinned), #7 |
独立核对完成,内容与追踪都到位: 分支栈(顺序正确): diff 范围与你列的 6 条一一对应(12 files / +315 −16):
#2602 已建、OPEN、正确跟踪三条 defer(ledger floor 不衰减+cap<1024 surrender / CI( 结论:代码与追踪都齐了,等 CI 全绿即可由你手动合并(我这边不 merge):#2581 |
|
ci 失败了看看为啥 |
- nudge suppression: growthFoldingArmed() gates autoFoldEngaged so a degenerate growth config (sub-MIN window, target clamped to the window) no longer silently swallows every classic nudge; applies to all four prepare lanes, responses lane honors the codex intercept bar - calibration straddle: a growth-armed zero-progress preflight with estimate < limit <= calibrated now arms the auto-fold cooldown too (was: skip the arm, re-fire the trigger every turn with a guaranteed 400 forward) - #2496: a Request-object input whose body was disturbed by the failed send fails with the original error — no retry, no respawn, no direct degrade (new Request(target, input) would throw 'Body is unusable') - #1662: pi-marker re-entry at depth 1 now dispatchDepth.run(2) like the anchor jump, bounding marker-wrapper chain growth - #2443: opencode conditional-tool registration rejections surface and re-arm the retry cadence instead of latching toolDeltaReady early - dsh-native-client: onTheme gated on !cancelled Deferred MINORs tracked in #2602.
0fbf761 to
30e679e
Compare
|
Correction — fix #5 withdrawn, commit amended (new head The pi-marker depth-1 change listed in my previous comment broke CI:
Effective fix set in |
独立核对确认,
结论:修正到位,等 CI 全绿即可手动合并(我这边不 merge):#2581 |
Auto-fallback from the one-click release workflow: direct push to master was blocked by branch protection. Merging this PR publishes via the standard release.yml flow.
Changes since v0.1.189
ctx.imageTokens又被加一次 #2558): target the image reserve at its 10th arg after the [Bug][Codex Responses] fixed instruction/tool overhead exceeds 272k budget; preflight has zero compressible ranges #2391 rebasectx.imageTokens又被加一次 #2558)127.*这类星号写法:本机和局域网上游也被送进系统代理 #2502)dsh.bundle.patch.yml禁用自动压缩在 web profile 下静默失效 #1772/fix(dsh): profile 层 patch 其实可以关掉 web profile 的原生自动压缩(#1772 结论修正)+ 一个会静默清空整个 preset 的写法坑 #2474)dsh.bundle.patch.yml禁用自动压缩在 web profile 下静默失效 #1772 conclusion correction — profile-layer full-snapshot patch CAN switch off web-profile native auto-compaction (fix(dsh): profile 层 patch 其实可以关掉 web profile 的原生自动压缩(#1772 结论修正)+ 一个会静默清空整个 preset 的写法坑 #2474)dsh.bundle.patch.yml禁用自动压缩在 web profile 下静默失效 #1772/fix(dsh): profile 层 patch 其实可以关掉 web profile 的原生自动压缩(#1772 结论修正)+ 一个会静默清空整个 preset 的写法坑 #2474)