dsh-fast-mode 1.5.5 → 1.5.6

package/BENCHMARK.md

@@ -1394,3 +1394,11 @@ node bin/experiment.mjs stop                          # end it; later sessions g
 - Experiment E's minimal reproduction: `--gears safe,turbo`, then two concurrent waves of eight sessions on one prompt, and a per-session `ΣstepMs` median grouped by `gear`. The raw rows are in `~/.dsh/fast-mode-metrics.jsonl` (present on this machine); grouping by `sid` recomputes the table without re-running a model.
 - The 0.8.0 raw log is [`docs/bench-raw-2026-10-24.jsonl.gz`](docs/bench-raw-2026-10-24.jsonl.gz) (committed with the repo); under the stated conventions it reproduces every number in Experiments E and F.
 - For multi-repo tasks, do not treat the whole-history ratio table from `dsh-fast-mode-report` as a conclusion; group by task first, then compare medians inside a group.
+
+## 发布前复核块 REL16（2026-10-26，默认 vs `off`，5 家族 × 1 对 = 10 个单元）
+
+- **目的**：发版前用当时的默认（与 1.5.1 行为相同）对 `off` 再做一块同块对照，只回答两件事——隐藏测试有没有退化、总量方向有没有反过来。
+- **质量：两臂 10/10 全绿，逐任务通过数完全相同**（`shellops` 14/14、`ledger` 22/22、`codebase` 18/18、`stategraph` 10/10、`migrate` 14/14），无 leak、无超时、无 `steps=0`。
+- **速度**：墙钟合计 **0.967×**（1543.5 s → 1493.3 s），逐格中位 **0.999×**、3/5 格更快，步数 0.66×。逐格：`ledger` 0.78×、`shellops` 0.98×、`migrate` 1.00×、`stategraph` 1.31×、`codebase` 1.79×。
+- **读法**：单对、n=5，噪声带比 26–28% 的总口径宽，**不用这块替换总量结论**；它只用于回答「发版这一步有没有把质量或方向弄坏」。质量答案是没坏；速度方向在这一块落进噪声（0.97×）。
+- 原始结果 `bench/results/suite-REL16.jsonl`；`python3 bench/report.py --files bench/results/suite-REL16.jsonl --baseline off` 可复算。

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 1.5.6
+
+- **发版前复核块 REL16**：默认对 `off` 再跑 5 家族 × 1 对（10 个单元），两臂 **10/10 全绿、逐任务通过数完全相同**、无 leak；墙钟合计 **0.967×**、逐格中位 0.999×、3/5 格更快。单对 n=5 只作复核，不替换 26–28% 的总口径；原始数据 `bench/results/suite-REL16.jsonl`，分析与读法见 `BENCHMARK.md`、`README.md`。
+
 ## 1.5.5
 
 - **市场预检修复（续）**：peer 范围再改成 `>=3.18.5-rc.1 <4.0.0-0 || >=4.0.0-rc.1 <5.0.0-0`。预检规则要求范围里显式出现 `||` 与预发布段，单段范围即使写了 `-rc.1` 也判 error。行为无变化。

package/README.en.md

@@ -50,6 +50,8 @@ No model switch, no `reasoningEffort` rewrite, no request-field injection (`serv
 
 **Screen W10 + replication W11 (2026-10-26, 23 valid units combined): `workspaceMap` only half delivered, stays off by default.** 1.5.2 adds one knob, off by default: before the first action the harness hands the model a one-shot inventory of the working tree (depth 2, ≤60 entries, dependency and build directories skipped) so it does not have to spend a step listing files itself. Both blocks compare it with `def15` inside the same block: across 23 valid units **wall 0.927×, output 0.896×, steps 1.099×**, per-cell median 0.791×, 13/23 faster, zero gate reds. Half of the mechanism is confirmed: output really is 10 % lower (0.90× and 0.89× in the two blocks). But steps rise 10 % and the tail gets worse — p90 559 s versus 369 s and max 714 s versus 510 s, with the same reverse cells in both blocks (`stategraph` at 1.4×–1.77× in each). **Because a long task must not get slower, it is not promoted**: the 1.5.2 default behaves exactly like 1.5.1, and the knob ships with its numbers. The same round accounted for the remaining headroom: repeated verification is only 6 % of wall, tool results have a 1.2 kB median, rewriting an already written file is 0.8 % — so **0.67× is not reachable inside the "do not touch `reasoningEffort`, add no request fields" constraints**. See "复现块 W11" and "0.67× 在现有约束下的可达性" in [BENCHMARK.md](BENCHMARK.md).
 
+**Pre-release re-check (REL16, 10 units)**: the then-current default was run against `off` once more, purely to ask whether shipping had damaged quality. Both arms came back **10/10 green with identical per-task pass counts** (14/14, 22/22, 18/18, 10/10, 14/14) and no leaks; wall summed to **0.967×**, per-cell median 0.999×, faster in 3/5 cells. That is one pair at n=5, a wider noise band than the pooled total, so it is reported as a re-check and does not replace the 26–28 % headline — see [BENCHMARK.md](BENCHMARK.md).
+
 **Faster configurations that failed the gate stay ablation arms only.** `fl10` (a step-10 finish reminder) is the fastest configuration measured, but it suppresses re-verification after the tests pass and once went red on a cell where both the baseline and the default were green, so it stays an ablation arm (those numbers came from a retracted batch and are kept only as a decision record). `openBatch` (one opening reminder to put independent calls in one block) beat the default 0.77× vs 0.93× in the W6 screen, but an independent W7 rerun brought it back to 0.91× and 1.136× head-to-head — **not replicated, so dropped**. `batchVerify` was 0.84× against the default inside W5 and is likewise not promoted. **The defaults therefore stay as they are**: no step-based finish line, `stepBudget: 0`, and all three mechanisms off. Per-cell data and gate results are in the `H2`/`H3` sections of BENCHMARK.
 
 **The retired default: `finishLineSteps: 10`.** On 7 families and 14 pairs it produced a median **1.86×**, 13/14 pairs faster (sign test **p = 0.002**), output **−52 %**, steps **−10.0**, hidden tests **14/14 green**. That line was genuinely fast, and the cost was real too: it fired at step 10 even on a long task that was still making progress. So 1.5.0 demotes it to an ablation arm (`fl10`), off by default.

package/README.md

@@ -50,6 +50,8 @@
 
 **复现块 W7（2026-10-26，17 个有效单元）**：默认臂 **0.73×** 墙钟 / 0.75× 输出 / 0.59× 步数（最长一格 36 步 → 17 步），与 1.5.1 的 0.72×、W5 的 0.73× 一致：三块合并 65 个有效单元 **0.74×**。同块的 `openBatch` 是 0.91×，对默认头对头 1.136×，W6 的 0.77× 没有复现，**淘汰**。这一块还有 7 行运行崩溃（会话启动阶段 `exit=1`、1 步、0 输出），3 个单元因此作废并点名；从这一块起判据要求 `exit == 0 && 步数 ≥ 1 && 输出 > 0 && 判分完成 && 未泄漏` 才计数，所以「全绿」一律指有效单元全绿（1.5.1 29/29、W5 19/19、W7 17/17）。详见 [BENCHMARK.md](BENCHMARK.md) 的「复现块 W7」。
 
+**发版前复核（REL16，10 个单元）**：用当时的默认再对 `off` 跑一块，只查「质量有没有被发版弄坏」。结果两臂 **10/10 全绿、逐任务通过数完全相同**（14/14、22/22、18/18、10/10、14/14），无 leak；墙钟合计 **0.967×**、逐格中位 0.999×、3/5 格更快。单对 n=5，噪声带比总量宽，所以这条只作复核，不替换 26–28% 的总口径，详见 [BENCHMARK.md](BENCHMARK.md)。
+
 **更快但没过门禁的配置只作消融臂。** `fl10`（第 10 步提醒收尾）是实测最快的配置，但它会压掉「测试通过后又改了代码」的必要复验，且出现过基线与默认都绿而它红的一格，所以只是消融臂（这些数字出自已撤回的批次，只保留决策记录）。`openBatch`（开局发一次「把独立调用并进同一块」）在 W6 筛查里以 0.77× 快过默认的 0.93×，但 W7 独立复测回到 0.91×、头对头 1.136×，**没有复现即淘汰**。`batchVerify`（改完一批文件再跑一次覆盖检查）在 W5 同块对照里记到 0.84×，但那一臂的提醒实际零下发，测到的不是机制本身，所以它算**未测**，默认保持关闭。**所以默认不变**：不按步数收尾、`stepBudget: 0`、上述机制全关。单元级数据与门禁逐条见 BENCHMARK 的 `H2`/`H3`。
 
 **已退役的默认：`finishLineSteps: 10`。** 1.4.4 用它跑出 7 家族 14 对中位 **1.86×**、13/14 更快（符号检验 **p = 0.002**）、输出 **−52 %**、步数 **−10.0**、隐藏测试 **14/14 全绿**。这条线的速度是真的，代价也是真的：它到第 10 步就要求停止扩大范围，对**仍在推进的长任务**同样开火。所以 1.5.0 把它降级为消融臂（`fl10`），默认关闭。

package/docs/REFERENCE.en.md

@@ -1,6 +1,6 @@
 # Reference: principles, configuration and limits
 
-This manual describes what **dsh-fast-mode 1.5.5** actually does (compared with 1.5.0 it adds two experimental knobs, `preferPatch` and `workspaceMap`, both off by default; with the default config behaviour is identical to 1.5.0), matching `index.js`, `src/` and `client.js` in the repository. It is not a brochure: where something can be measured it gets a number, and where it has not been measured it says so.
+This manual describes what **dsh-fast-mode 1.5.6** actually does (compared with 1.5.0 it adds two experimental knobs, `preferPatch` and `workspaceMap`, both off by default; with the default config behaviour is identical to 1.5.0), matching `index.js`, `src/` and `client.js` in the repository. It is not a brochure: where something can be measured it gets a number, and where it has not been measured it says so.
 
 **The one contract: fast mode never changes reasoning effort, the thinking budget, or the model.** The `agent/request` hook does exactly one thing — `await next()`, read the `reasoningEffort` the request already carries for measurement, then return it unchanged. Whatever effort the user picked (the per-session choice in the UI, or the effort pinned by the profile's agent-default-model) is the effort every request uses.
 

package/docs/REFERENCE.md

@@ -1,6 +1,6 @@
 # 参考手册：原理、配置与边界
 
-本手册描述 **dsh-fast-mode 1.5.5** 的实际行为（相对 1.5.0 多两个默认关闭的实验旋钮 `preferPatch` 与 `workspaceMap`，默认配置下行为与 1.5.0 完全一致），对应仓库里的 `index.js`、`src/` 与 `client.js`。它不是宣传页：凡是能测量的地方给出数字，凡是没测量的地方直接说没测量。
+本手册描述 **dsh-fast-mode 1.5.6** 的实际行为（相对 1.5.0 多两个默认关闭的实验旋钮 `preferPatch` 与 `workspaceMap`，默认配置下行为与 1.5.0 完全一致），对应仓库里的 `index.js`、`src/` 与 `client.js`。它不是宣传页：凡是能测量的地方给出数字，凡是没测量的地方直接说没测量。
 
 **唯一的契约：Fast 模式从不改变思考强度、thinking 预算或模型。** `agent/request` 钩子只做一件事——`await next()`，读一下请求携带的 `reasoningEffort` 记进测量，然后原样返回。用户选的是哪一档（会话里的 UI 选择，或者 profile 里 agent-default-model 固定下来的那一档），每个请求就用哪一档。
 

package/index.js

@@ -95,7 +95,7 @@ const TAG = '[fast-mode]'
  * Shipped identity of this build. Traced into the debug log so a stale install is
  * visible at a glance, and pinned by a test against `package.json`.
  */
-export const VERSION = '1.5.5'
+export const VERSION = '1.5.6'
 const GLOBAL_AGENT = '__global__'
 
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-fast-mode",
-  "version": "1.5.5",
+  "version": "1.5.6",
   "description": "DeepSeek Harness fast mode: same thinking effort, fewer round trips. An adaptive parallel tool fan-out, output discipline that never trims the answer, and a cancellable stall guard. Never changes reasoning effort, the model, or the request body. Provider-agnostic, one dependency (@deepseek-ai/schemastery).",
   "repository": {
     "type": "git",