peaks-loop 4.2.4 → 4.2.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/CHANGELOG.md +83 -0
- package/dist/cli/commands/compact-harness-window-reports.js +1 -1
- package/dist/services/context/auto-compact-reader.d.ts +8 -5
- package/dist/services/context/auto-compact-reader.js +14 -6
- package/dist/services/context/harness-compact-threshold-config.d.ts +9 -8
- package/dist/services/context/harness-compact-threshold-config.js +9 -8
- package/dist/services/context/harness-compact-threshold-ensure.d.ts +4 -3
- package/dist/services/context/harness-compact-threshold-ensure.js +4 -3
- package/dist/services/context/harness-window-config.d.ts +34 -43
- package/dist/services/context/harness-window-config.js +26 -39
- package/dist/services/context/harness-window-opt-out.js +2 -0
- package/dist/services/context/harness-window-ownership.js +1 -1
- package/dist/services/ide/adapters/claude-code-adapter.d.ts +7 -7
- package/dist/services/ide/adapters/claude-code-adapter.js +13 -13
- package/package.json +6 -6
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
{
|
|
2
2
|
"metadata": {
|
|
3
3
|
"pluginRoot": ".",
|
|
4
|
-
"version": "4.2.
|
|
4
|
+
"version": "4.2.6"
|
|
5
5
|
},
|
|
6
6
|
"plugins": [
|
|
7
7
|
{
|
|
8
8
|
"name": "peaks-loop",
|
|
9
9
|
"description": "Loop Engineering CLI — workflow primitive / loop guards / evaluators / slice orchestration",
|
|
10
|
-
"version": "4.2.
|
|
10
|
+
"version": "4.2.6",
|
|
11
11
|
"author": {
|
|
12
12
|
"name": "SquabbyZ"
|
|
13
13
|
},
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,88 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 4.2.6 — 2026-11-22(默认压缩窗口 250K → 1M:交给 harness 按模型上下文钳制)
|
|
4
|
+
|
|
5
|
+
**版本级别**:**patch**(只改一个默认常量及其文档注释;无新能力,无 schema 变更,无门禁阈值放宽)。
|
|
6
|
+
|
|
7
|
+
**一句话:`workspace init` 的默认窗口从 `250000` 改成 `1000000`——这是 harness 接受的上限,会被 harness 钳制到模型的真实上下文,因此同一个默认对 1M 模型等于 800K 触发,对 200K 模型等于 160K。**
|
|
8
|
+
|
|
9
|
+
### 1. 为什么改
|
|
10
|
+
|
|
11
|
+
Claude Code 会把 `CLAUDE_CODE_AUTO_COMPACT_WINDOW` 钳制到模型自身的上下文。本机实测结果:
|
|
12
|
+
|
|
13
|
+
| 模型 | 配置窗口 | `effectiveWindow` | 80% 触发阈值 |
|
|
14
|
+
|---|---|---|---|
|
|
15
|
+
| 1M(默认) | 1,000,000 | 980,000 | **800,000** |
|
|
16
|
+
| 200K(`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`) | 1,000,000 | 180,000 | **160,000** |
|
|
17
|
+
|
|
18
|
+
也就是说 `window = 1,000,000` 对**任何**模型都表现为「真实容量的 80%」,而旧默认 `250,000` 把 1M 模型硬压在 25%、在 200,000 就触发压缩——远早于用户预期。1,000,000 正是 harness 文档波段(100,000..1,000,000)的上限,所以它才是最中性的默认值。
|
|
19
|
+
|
|
20
|
+
### 2. 改了什么
|
|
21
|
+
|
|
22
|
+
- `DEFAULT_HARNESS_COMPACT_WINDOW_TOKENS`:`250_000` → `1_000_000`(`src/services/context/harness-compact-threshold-config.ts`)。
|
|
23
|
+
- `DEFAULT_HARNESS_COMPACT_PERCENT` 保持 `80`。
|
|
24
|
+
- 常量文档注释写明钳制实测与上表数值。
|
|
25
|
+
|
|
26
|
+
### 3. 影响面
|
|
27
|
+
|
|
28
|
+
- 全新项目跑 `peaks workspace init`,`.claude/settings.local.json` 现在写入 `CLAUDE_CODE_AUTO_COMPACT_WINDOW=1000000` 与 `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=80`(各带 provenance 标记)。
|
|
29
|
+
- 已有项目不会被改写:init 只在槽位为空时填默认值。本仓库自己的 `.claude/settings.local.json` 已是 `1000000`,实测 init 后文件字节不变。
|
|
30
|
+
- 仍需固定窗口的项目照旧直接编辑该文件。
|
|
31
|
+
|
|
32
|
+
### 4. 验证
|
|
33
|
+
|
|
34
|
+
| 项 | 结果 |
|
|
35
|
+
|---|---|
|
|
36
|
+
| `tsc -p tsconfig.json --noEmit` | 0 |
|
|
37
|
+
| `node .husky/peaks-gate.mjs repo` | 0 |
|
|
38
|
+
| 单元测试(`tests/unit/` 全量) | 705 文件 / 7623 通过 / 0 失败 |
|
|
39
|
+
| 变异(6 模块) | 90.57%,`passed: true`(最低单模块 85.66%) |
|
|
40
|
+
| 全新 git 项目 `workspace init` | 写入 `CLAUDE_CODE_AUTO_COMPACT_WINDOW=1000000` 与 `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=80` |
|
|
41
|
+
| 本仓库现有 settings 上重跑 init | 文件字节不变 |
|
|
42
|
+
|
|
43
|
+
## 4.2.5 — 2026-11-22(修 4.2.4 的严重缺陷:探针会把项目窗口覆盖回 1M)
|
|
44
|
+
|
|
45
|
+
**版本级别**:**patch**(只修缺陷,无新能力,无 schema 变更,无门禁阈值放宽)。
|
|
46
|
+
|
|
47
|
+
**一句话:4.2.4 配好的 250K 窗口,会被一次普通的 `peaks code context-now` 悄悄改回 1M——因为"晚到 1M 救援"把观察值当成了配置。**
|
|
48
|
+
|
|
49
|
+
### 1. 缺陷是什么
|
|
50
|
+
|
|
51
|
+
4.2.4 发布当天的验收测试里发现:
|
|
52
|
+
|
|
53
|
+
```
|
|
54
|
+
干净环境 peaks workspace init → 文件 250000 ✅
|
|
55
|
+
同一项目,会话上下文已超过 250K,跑 context-now → 文件 1000000 ❌
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
**触发条件比预想的常见**:不是"环境变量不一致",而是**任何一个上下文已经超过配置窗口的会话**,在该项目里跑 peaks 命令都会触发。
|
|
59
|
+
|
|
60
|
+
机制:当探测到的上下文 token 数超过文件里配置的窗口、且文件是 peaks 自己写的,adapter 会把**计算比例用的分母**抬到 1,000,000(这是既有的"晚到 1M 救援",用来防止比例 > 1 的自锁)。旧代码把这个**观察值也持久化**进了项目文件,于是配置被观察覆盖。
|
|
61
|
+
|
|
62
|
+
### 2. 修法
|
|
63
|
+
|
|
64
|
+
**文件即配置,探针只是观察。**
|
|
65
|
+
|
|
66
|
+
- `syncHarnessWindowForProject` 传入 `onlyFillEmptySlot`
|
|
67
|
+
- 文件里已有窗口值时,同步以 `file-configures-window` 拒绝写入
|
|
68
|
+
- **救援继续抬比分母**(自锁仍然被打破、比例仍然诚实),只是不再落盘
|
|
69
|
+
- 空槽仍会被首次探针填入;人工设定的值仍不动;显式调用方仍可写
|
|
70
|
+
|
|
71
|
+
**行为变化(需要知道)**:要改项目的窗口,现在是**编辑那个文件**(或删掉该键),而不是靠跑命令。相关提示语已改成这么说。
|
|
72
|
+
|
|
73
|
+
### 3. 验证
|
|
74
|
+
|
|
75
|
+
| 项 | 结果 |
|
|
76
|
+
|---|---|
|
|
77
|
+
| 单元测试 | 705 文件 / 7623 通过 |
|
|
78
|
+
| `tsc --noEmit` | 0 |
|
|
79
|
+
| `peaks-gate repo` | 0 |
|
|
80
|
+
| 变异(6 模块) | **90.57%**,每个模块 ≥ 80% |
|
|
81
|
+
|
|
82
|
+
### 4. 另外发现的一个守卫盲区(未在本版修)
|
|
83
|
+
|
|
84
|
+
子 agent 测试时用非 git 临时目录,工具把根解析成了真实主目录,往 `~/.claude/settings.local.json` 写了两行(已清除并核实)。原因是那次 `USERPROFILE` 被改过,`homedir()` 指向临时目录,而根路径走的是另一条规则——**H1 主目录守卫没有触发**。正常 shell 下会拒绝,但这是一个真实盲区,记入遗留。
|
|
85
|
+
|
|
3
86
|
## 4.2.4 — 2026-11-22(下游项目装完即用早期自动压缩,配置只落项目级)
|
|
4
87
|
|
|
5
88
|
**版本级别**:**minor**(新增能力:项目级压缩阈值配置 + `harnessThreshold` 如实上报;无 schema 变更,无门禁阈值放宽)。
|
|
@@ -112,7 +112,7 @@ function buildHarnessWindowStateActions(state, percent) {
|
|
|
112
112
|
state?.tokens === null || state?.tokens === undefined
|
|
113
113
|
? 'No window is set yet. The next `peaks code context-now` probe materializes the window it computes its ratio against.'
|
|
114
114
|
: `peaks-loop computes its context ratio against ${state.tokens} tokens; the harness fires near the end of that window. ${state.peakWritten
|
|
115
|
-
? 'peaks-loop wrote this value
|
|
115
|
+
? 'peaks-loop wrote this value, and it is the project’s configuration: a context probe will not replace it (only an empty slot is filled), so a session that outgrows it is reported, not rewritten.'
|
|
116
116
|
: "This value is not peaks-loop's own write, so peaks-loop will not raise it — it is treated as your setting."}`,
|
|
117
117
|
describePercentHalf(percent),
|
|
118
118
|
'Rollback: `peaks compact harness-window --reset`.',
|
|
@@ -54,12 +54,15 @@ export declare function resolveHarnessRatioWindow(state: HarnessWindowReadResult
|
|
|
54
54
|
/**
|
|
55
55
|
* Materialize a window into the harness's own settings, so the number
|
|
56
56
|
* peaks-loop divides by and the number the harness compacts against are one
|
|
57
|
-
* value rather than two resolutions
|
|
57
|
+
* value rather than two resolutions.
|
|
58
58
|
*
|
|
59
|
-
*
|
|
60
|
-
*
|
|
61
|
-
*
|
|
62
|
-
*
|
|
59
|
+
* A PROBE MAY ONLY FILL AN EMPTY SLOT. The project's settings file is its
|
|
60
|
+
* configuration; the probe's window is an observation (it may be shaped by an
|
|
61
|
+
* ambient process env or by a transcript inherited from another session), so a
|
|
62
|
+
* value the file already carries is never replaced — see
|
|
63
|
+
* `syncHarnessWindow`'s `onlyFillEmptySlot` and the `file-configures-window`
|
|
64
|
+
* result. `tokens: null` (a percent-only probe carries no token window) is
|
|
65
|
+
* likewise a no-op: peaks-loop never invents a window it did not measure.
|
|
63
66
|
*
|
|
64
67
|
* Returns `null` when the active adapter declares no window knob at all.
|
|
65
68
|
*/
|
|
@@ -114,12 +114,15 @@ export function resolveHarnessRatioWindow(state) {
|
|
|
114
114
|
/**
|
|
115
115
|
* Materialize a window into the harness's own settings, so the number
|
|
116
116
|
* peaks-loop divides by and the number the harness compacts against are one
|
|
117
|
-
* value rather than two resolutions
|
|
117
|
+
* value rather than two resolutions.
|
|
118
118
|
*
|
|
119
|
-
*
|
|
120
|
-
*
|
|
121
|
-
*
|
|
122
|
-
*
|
|
119
|
+
* A PROBE MAY ONLY FILL AN EMPTY SLOT. The project's settings file is its
|
|
120
|
+
* configuration; the probe's window is an observation (it may be shaped by an
|
|
121
|
+
* ambient process env or by a transcript inherited from another session), so a
|
|
122
|
+
* value the file already carries is never replaced — see
|
|
123
|
+
* `syncHarnessWindow`'s `onlyFillEmptySlot` and the `file-configures-window`
|
|
124
|
+
* result. `tokens: null` (a percent-only probe carries no token window) is
|
|
125
|
+
* likewise a no-op: peaks-loop never invents a window it did not measure.
|
|
123
126
|
*
|
|
124
127
|
* Returns `null` when the active adapter declares no window knob at all.
|
|
125
128
|
*/
|
|
@@ -127,7 +130,12 @@ export function syncHarnessWindowForProject(input) {
|
|
|
127
130
|
const location = resolveHarnessWindowLocation(input);
|
|
128
131
|
if (location === null)
|
|
129
132
|
return null;
|
|
130
|
-
return syncHarnessWindow({
|
|
133
|
+
return syncHarnessWindow({
|
|
134
|
+
location,
|
|
135
|
+
tokens: input.tokens,
|
|
136
|
+
env: input.env ?? process.env,
|
|
137
|
+
onlyFillEmptySlot: true
|
|
138
|
+
});
|
|
131
139
|
}
|
|
132
140
|
/**
|
|
133
141
|
* Read env-var-based context percentage. Returns `null` when the env
|
|
@@ -34,17 +34,18 @@ import { type HarnessPercentOwnership } from './harness-percent-ownership.js';
|
|
|
34
34
|
/**
|
|
35
35
|
* The window peaks-loop configures when nobody has said otherwise.
|
|
36
36
|
*
|
|
37
|
-
*
|
|
38
|
-
*
|
|
39
|
-
*
|
|
40
|
-
*
|
|
41
|
-
*
|
|
42
|
-
*
|
|
37
|
+
* 1_000_000 is the harness's accepted MAXIMUM (band 100_000..1_000_000), and
|
|
38
|
+
* that is why it is the neutral default: the harness CLAMPS the window to the
|
|
39
|
+
* model's own context, so the maximum means "as much as this model holds".
|
|
40
|
+
* Measured 2026-11-22: a 1M model gets effectiveWindow 980_000 → threshold
|
|
41
|
+
* 800_000; a 200K model given the same window is clamped to 180_000 → 160_000.
|
|
42
|
+
* The old 250_000 default capped a 1M model at 25% and fired at 200_000. A
|
|
43
|
+
* fresh project gets THIS rather than an unset slot ("no early compaction").
|
|
43
44
|
*/
|
|
44
|
-
export declare const DEFAULT_HARNESS_COMPACT_WINDOW_TOKENS =
|
|
45
|
+
export declare const DEFAULT_HARNESS_COMPACT_WINDOW_TOKENS = 1000000;
|
|
45
46
|
/**
|
|
46
47
|
* The percent peaks-loop configures when nobody has said otherwise — 80% of
|
|
47
|
-
* the window above, i.e.
|
|
48
|
+
* the window above, i.e. an 800_000-token trigger on the 1_000_000 default.
|
|
48
49
|
*
|
|
49
50
|
* The single named default, exported here and nowhere else.
|
|
50
51
|
*/
|
|
@@ -39,17 +39,18 @@ import { HARNESS_PERCENT_WRITTEN_KEY, boundedRawNote, isHarnessPercentPeaksOwned
|
|
|
39
39
|
/**
|
|
40
40
|
* The window peaks-loop configures when nobody has said otherwise.
|
|
41
41
|
*
|
|
42
|
-
*
|
|
43
|
-
*
|
|
44
|
-
*
|
|
45
|
-
*
|
|
46
|
-
*
|
|
47
|
-
*
|
|
42
|
+
* 1_000_000 is the harness's accepted MAXIMUM (band 100_000..1_000_000), and
|
|
43
|
+
* that is why it is the neutral default: the harness CLAMPS the window to the
|
|
44
|
+
* model's own context, so the maximum means "as much as this model holds".
|
|
45
|
+
* Measured 2026-11-22: a 1M model gets effectiveWindow 980_000 → threshold
|
|
46
|
+
* 800_000; a 200K model given the same window is clamped to 180_000 → 160_000.
|
|
47
|
+
* The old 250_000 default capped a 1M model at 25% and fired at 200_000. A
|
|
48
|
+
* fresh project gets THIS rather than an unset slot ("no early compaction").
|
|
48
49
|
*/
|
|
49
|
-
export const DEFAULT_HARNESS_COMPACT_WINDOW_TOKENS =
|
|
50
|
+
export const DEFAULT_HARNESS_COMPACT_WINDOW_TOKENS = 1_000_000;
|
|
50
51
|
/**
|
|
51
52
|
* The percent peaks-loop configures when nobody has said otherwise — 80% of
|
|
52
|
-
* the window above, i.e.
|
|
53
|
+
* the window above, i.e. an 800_000-token trigger on the 1_000_000 default.
|
|
53
54
|
*
|
|
54
55
|
* The single named default, exported here and nowhere else.
|
|
55
56
|
*/
|
|
@@ -30,9 +30,10 @@ export interface HarnessCompactThresholdResult {
|
|
|
30
30
|
* resolves to the value already in the file when there is one and to the
|
|
31
31
|
* default only when the slot is empty. Init carries no new MEASUREMENT, so
|
|
32
32
|
* rewriting an existing value from it would be peaks-loop overruling its own
|
|
33
|
-
* probe with a policy constant —
|
|
34
|
-
*
|
|
35
|
-
*
|
|
33
|
+
* probe with a policy constant — an existing peaks-written value stands even
|
|
34
|
+
* when the current default differs, and this repository's own file is the
|
|
35
|
+
* shape that rule protects. An explicit argument (`number`), or `null` for
|
|
36
|
+
* "do not manage this one
|
|
36
37
|
* on this call", is passed through as given (the provenance and band gates
|
|
37
38
|
* still apply).
|
|
38
39
|
*
|
|
@@ -40,9 +40,10 @@ function resolveEnsured(arg, fileRaw, parse, fallback) {
|
|
|
40
40
|
* resolves to the value already in the file when there is one and to the
|
|
41
41
|
* default only when the slot is empty. Init carries no new MEASUREMENT, so
|
|
42
42
|
* rewriting an existing value from it would be peaks-loop overruling its own
|
|
43
|
-
* probe with a policy constant —
|
|
44
|
-
*
|
|
45
|
-
*
|
|
43
|
+
* probe with a policy constant — an existing peaks-written value stands even
|
|
44
|
+
* when the current default differs, and this repository's own file is the
|
|
45
|
+
* shape that rule protects. An explicit argument (`number`), or `null` for
|
|
46
|
+
* "do not manage this one
|
|
46
47
|
* on this call", is passed through as given (the provenance and band gates
|
|
47
48
|
* still apply).
|
|
48
49
|
*
|
|
@@ -1,27 +1,16 @@
|
|
|
1
1
|
/**
|
|
2
2
|
* Harness auto-compact window ownership
|
|
3
3
|
*
|
|
4
|
-
* The
|
|
5
|
-
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
*
|
|
9
|
-
* knows for the model, while peaks-loop divided by `resolveContextWindow()`
|
|
10
|
-
* (env → config → model-name heuristic → 200_000 default). A 1M-window model
|
|
11
|
-
* whose id the heuristic does not recognise made peaks-loop's "95%" land at
|
|
12
|
-
* 190K while the harness waited for ~967K — a 5× early trigger, and (before
|
|
13
|
-
* T3) a deadlock, because nothing could lower the ratio.
|
|
14
|
-
*
|
|
15
|
-
* This module owns the OTHER half: the harness itself accepts a window override
|
|
16
|
-
* (`IdeCompactProfile.autoCompactWindowEnvVar`, declared per adapter — no IDE
|
|
17
|
-
* names here), so peaks-loop writes the very number it computes the ratio
|
|
18
|
-
* against into the harness's own machine-local settings file. Reader and writer
|
|
19
|
-
* reference one artifact, not two resolutions that must "remember" to agree.
|
|
4
|
+
* The two sides must agree on ONE number. The harness accepts a window override
|
|
5
|
+
* (`IdeCompactProfile.autoCompactWindowEnvVar`, declared per adapter), so
|
|
6
|
+
* peaks-loop writes the very number it computes its ratio against into the
|
|
7
|
+
* harness's own machine-local settings file. Reader and writer reference one
|
|
8
|
+
* artifact, not two resolutions that must "remember" to agree.
|
|
20
9
|
*
|
|
21
10
|
* Vendor neutrality: this module knows about a JSON file with an `env` block
|
|
22
11
|
* and nothing else. The settings path and the env-var name are BOTH passed in
|
|
23
|
-
* by the caller,
|
|
24
|
-
*
|
|
12
|
+
* by the caller, from the IDE adapter's declarations: no IDE id, no `.claude`
|
|
13
|
+
* literal, no registry import.
|
|
25
14
|
*/
|
|
26
15
|
import { isLinkedSettingsFile } from '../ide/shared/safe-path.js';
|
|
27
16
|
export { isLinkedSettingsFile };
|
|
@@ -43,25 +32,13 @@ export declare const HARNESS_WINDOW_SYNC_OPTOUT_VALUE = "off";
|
|
|
43
32
|
* Provenance marker: the window value peaks-loop ITSELF last wrote, recorded
|
|
44
33
|
* in the same `env` block as the window key.
|
|
45
34
|
*
|
|
46
|
-
*
|
|
47
|
-
*
|
|
48
|
-
*
|
|
49
|
-
*
|
|
50
|
-
*
|
|
51
|
-
*
|
|
52
|
-
*
|
|
53
|
-
*
|
|
54
|
-
* The second rule needs the late 1M rescue to be able to overrule the key when
|
|
55
|
-
* the observed context proves the key too small. Applied to a value a HUMAN
|
|
56
|
-
* pinned, that same rescue would silently destroy an explicit setting — the
|
|
57
|
-
* user asks for an early compact, a long session outgrows the pin, and
|
|
58
|
-
* peaks-loop rewrites the file to 1M, permanently. Applied to peaks-loop's own
|
|
59
|
-
* earlier output it is simply self-correction.
|
|
60
|
-
*
|
|
61
|
-
* This marker is what tells the two apart: it records what peaks-loop wrote,
|
|
62
|
-
* so a mismatch means the human has taken the key over and the rescue must
|
|
63
|
-
* stand down. It travels in the same write as the value it describes, so the
|
|
64
|
-
* two can never disagree about which write they belong to.
|
|
35
|
+
* The window key is shared — the harness reads it, the user may hand-edit it,
|
|
36
|
+
* and peaks-loop writes it. This marker records what peaks-loop wrote, so a
|
|
37
|
+
* mismatch means the human has taken the key over and the late 1M rescue must
|
|
38
|
+
* stand down. Applied to a human's pin that rescue would silently destroy an
|
|
39
|
+
* explicit setting; applied to peaks-loop's own earlier output it is
|
|
40
|
+
* self-correction. It travels in the same write as the value, so the two can
|
|
41
|
+
* never disagree about which write they belong to.
|
|
65
42
|
*/
|
|
66
43
|
export declare const HARNESS_WINDOW_WRITTEN_KEY = "PEAKS_HARNESS_WINDOW_WRITTEN";
|
|
67
44
|
/**
|
|
@@ -179,6 +156,13 @@ export interface HarnessWindowSyncResult {
|
|
|
179
156
|
* without it a stale process env (or any
|
|
180
157
|
* re-resolution) silently reverts a human's
|
|
181
158
|
* hand-edited window and re-claims ownership.
|
|
159
|
+
* - `file-configures-window` — a PROBE-driven call (`onlyFillEmptySlot`)
|
|
160
|
+
* found the file already carrying a value it may
|
|
161
|
+
* not replace. The file is the project's
|
|
162
|
+
* configuration; a probe is an observation and
|
|
163
|
+
* may only FILL an empty slot. Nothing was
|
|
164
|
+
* written; `requestedTokens` vs `previousTokens`
|
|
165
|
+
* names the disagreement the caller must report.
|
|
182
166
|
* - `symlinked-settings` — the file, or the `.claude` directory holding it,
|
|
183
167
|
* is a symlink or junction, so a write would
|
|
184
168
|
* follow it into whatever it points at.
|
|
@@ -232,10 +216,10 @@ export interface HarnessWindowSyncResult {
|
|
|
232
216
|
*
|
|
233
217
|
* Reported because "the file already holds the number we wanted" has two very
|
|
234
218
|
* different meanings and only this flag tells them apart: peaks-loop's own
|
|
235
|
-
* earlier output, which
|
|
236
|
-
* value a human pinned, which it never will. Without it, `unchanged`
|
|
237
|
-
* "all good" for a key peaks-loop has permanently stopped managing —
|
|
238
|
-
* state a user upgrading from a pre-marker release is silently in.
|
|
219
|
+
* earlier output, which the ratio rescue may use to raise the DENOMINATOR,
|
|
220
|
+
* versus a value a human pinned, which it never will. Without it, `unchanged`
|
|
221
|
+
* reads as "all good" for a key peaks-loop has permanently stopped managing —
|
|
222
|
+
* the state a user upgrading from a pre-marker release is silently in.
|
|
239
223
|
*
|
|
240
224
|
* Always `true` for `action: 'written'`: the write that produced the result
|
|
241
225
|
* is what sets the marker.
|
|
@@ -272,8 +256,9 @@ export declare function readSettingsObject(settingsPath: string): SettingsFileSh
|
|
|
272
256
|
* Order: the process env FIRST (that is the value the RUNNING session
|
|
273
257
|
* captured at start-up, so it is what the harness is actually compacting
|
|
274
258
|
* against right now), then the settings file (what the next session will
|
|
275
|
-
* read). When the two disagree, the
|
|
276
|
-
*
|
|
259
|
+
* read). When the two disagree, the FILE is the configured value; a probe
|
|
260
|
+
* reports the disagreement rather than replacing it, and the process env
|
|
261
|
+
* cannot be changed from inside a running session.
|
|
277
262
|
*/
|
|
278
263
|
export declare function readHarnessWindow(input: {
|
|
279
264
|
readonly location: HarnessWindowLocation;
|
|
@@ -294,6 +279,12 @@ export declare function syncHarnessWindow(input: {
|
|
|
294
279
|
readonly location: HarnessWindowLocation;
|
|
295
280
|
readonly tokens: number | null;
|
|
296
281
|
readonly env?: NodeJS.ProcessEnv | undefined;
|
|
282
|
+
/**
|
|
283
|
+
* True for a PROBE-driven call: fill an empty slot, never replace a value the
|
|
284
|
+
* file already configures. The observed window is an observation, so it must
|
|
285
|
+
* not become the project's configuration. Omitted by explicit callers (init).
|
|
286
|
+
*/
|
|
287
|
+
readonly onlyFillEmptySlot?: boolean;
|
|
297
288
|
}): HarnessWindowSyncResult;
|
|
298
289
|
/**
|
|
299
290
|
* Rollback: remove the window key and record the opt-out so the next sync
|
|
@@ -1,27 +1,16 @@
|
|
|
1
1
|
/**
|
|
2
2
|
* Harness auto-compact window ownership
|
|
3
3
|
*
|
|
4
|
-
* The
|
|
5
|
-
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
*
|
|
9
|
-
* knows for the model, while peaks-loop divided by `resolveContextWindow()`
|
|
10
|
-
* (env → config → model-name heuristic → 200_000 default). A 1M-window model
|
|
11
|
-
* whose id the heuristic does not recognise made peaks-loop's "95%" land at
|
|
12
|
-
* 190K while the harness waited for ~967K — a 5× early trigger, and (before
|
|
13
|
-
* T3) a deadlock, because nothing could lower the ratio.
|
|
14
|
-
*
|
|
15
|
-
* This module owns the OTHER half: the harness itself accepts a window override
|
|
16
|
-
* (`IdeCompactProfile.autoCompactWindowEnvVar`, declared per adapter — no IDE
|
|
17
|
-
* names here), so peaks-loop writes the very number it computes the ratio
|
|
18
|
-
* against into the harness's own machine-local settings file. Reader and writer
|
|
19
|
-
* reference one artifact, not two resolutions that must "remember" to agree.
|
|
4
|
+
* The two sides must agree on ONE number. The harness accepts a window override
|
|
5
|
+
* (`IdeCompactProfile.autoCompactWindowEnvVar`, declared per adapter), so
|
|
6
|
+
* peaks-loop writes the very number it computes its ratio against into the
|
|
7
|
+
* harness's own machine-local settings file. Reader and writer reference one
|
|
8
|
+
* artifact, not two resolutions that must "remember" to agree.
|
|
20
9
|
*
|
|
21
10
|
* Vendor neutrality: this module knows about a JSON file with an `env` block
|
|
22
11
|
* and nothing else. The settings path and the env-var name are BOTH passed in
|
|
23
|
-
* by the caller,
|
|
24
|
-
*
|
|
12
|
+
* by the caller, from the IDE adapter's declarations: no IDE id, no `.claude`
|
|
13
|
+
* literal, no registry import.
|
|
25
14
|
*/
|
|
26
15
|
import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs';
|
|
27
16
|
import { dirname } from 'node:path';
|
|
@@ -52,25 +41,13 @@ export const HARNESS_WINDOW_SYNC_OPTOUT_VALUE = 'off';
|
|
|
52
41
|
* Provenance marker: the window value peaks-loop ITSELF last wrote, recorded
|
|
53
42
|
* in the same `env` block as the window key.
|
|
54
43
|
*
|
|
55
|
-
*
|
|
56
|
-
*
|
|
57
|
-
*
|
|
58
|
-
*
|
|
59
|
-
*
|
|
60
|
-
*
|
|
61
|
-
*
|
|
62
|
-
*
|
|
63
|
-
* The second rule needs the late 1M rescue to be able to overrule the key when
|
|
64
|
-
* the observed context proves the key too small. Applied to a value a HUMAN
|
|
65
|
-
* pinned, that same rescue would silently destroy an explicit setting — the
|
|
66
|
-
* user asks for an early compact, a long session outgrows the pin, and
|
|
67
|
-
* peaks-loop rewrites the file to 1M, permanently. Applied to peaks-loop's own
|
|
68
|
-
* earlier output it is simply self-correction.
|
|
69
|
-
*
|
|
70
|
-
* This marker is what tells the two apart: it records what peaks-loop wrote,
|
|
71
|
-
* so a mismatch means the human has taken the key over and the rescue must
|
|
72
|
-
* stand down. It travels in the same write as the value it describes, so the
|
|
73
|
-
* two can never disagree about which write they belong to.
|
|
44
|
+
* The window key is shared — the harness reads it, the user may hand-edit it,
|
|
45
|
+
* and peaks-loop writes it. This marker records what peaks-loop wrote, so a
|
|
46
|
+
* mismatch means the human has taken the key over and the late 1M rescue must
|
|
47
|
+
* stand down. Applied to a human's pin that rescue would silently destroy an
|
|
48
|
+
* explicit setting; applied to peaks-loop's own earlier output it is
|
|
49
|
+
* self-correction. It travels in the same write as the value, so the two can
|
|
50
|
+
* never disagree about which write they belong to.
|
|
74
51
|
*/
|
|
75
52
|
export const HARNESS_WINDOW_WRITTEN_KEY = 'PEAKS_HARNESS_WINDOW_WRITTEN';
|
|
76
53
|
/**
|
|
@@ -158,8 +135,9 @@ function envString(settings, key) {
|
|
|
158
135
|
* Order: the process env FIRST (that is the value the RUNNING session
|
|
159
136
|
* captured at start-up, so it is what the harness is actually compacting
|
|
160
137
|
* against right now), then the settings file (what the next session will
|
|
161
|
-
* read). When the two disagree, the
|
|
162
|
-
*
|
|
138
|
+
* read). When the two disagree, the FILE is the configured value; a probe
|
|
139
|
+
* reports the disagreement rather than replacing it, and the process env
|
|
140
|
+
* cannot be changed from inside a running session.
|
|
163
141
|
*/
|
|
164
142
|
export function readHarnessWindow(input) {
|
|
165
143
|
const settings = readSettingsObject(input.location.settingsPath);
|
|
@@ -289,6 +267,15 @@ export function syncHarnessWindow(input) {
|
|
|
289
267
|
if (!peakOwned) {
|
|
290
268
|
return { ...base, action: 'skipped', reason: 'not-peaks-owned', tokens: current.tokens };
|
|
291
269
|
}
|
|
270
|
+
// THE FILE WINS OVER A PROBE. `onlyFillEmptySlot` marks the calls a context
|
|
271
|
+
// probe makes: they may FILL an absent key (the write below) but never
|
|
272
|
+
// replace a value the file already configures — the file is the project's
|
|
273
|
+
// configuration and the probe is an observation. Placed AFTER the B1 guard
|
|
274
|
+
// so a human pin still reports `not-peaks-owned`; this reason is only for a
|
|
275
|
+
// peaks-owned value the probe would otherwise have replaced.
|
|
276
|
+
if (input.onlyFillEmptySlot === true && fileRaw !== undefined) {
|
|
277
|
+
return { ...base, action: 'skipped', reason: 'file-configures-window', tokens: current.tokens };
|
|
278
|
+
}
|
|
292
279
|
const settings = fileSettings ?? {};
|
|
293
280
|
const env = typeof settings.env === 'object' && settings.env !== null && !Array.isArray(settings.env)
|
|
294
281
|
? settings.env
|
|
@@ -192,6 +192,8 @@ function skippedHarnessWindowClause(result) {
|
|
|
192
192
|
return `Harness window not managed: ${result.settingsPath} is a symlink (or a Windows junction), or the directory holding it is, so writing would follow the link and overwrite the file it points at. Replace the link with a real file (or directory) and the window lands here.`;
|
|
193
193
|
case 'not-peaks-owned':
|
|
194
194
|
return `Harness window not managed: ${result.settingsPath} already carries a window that peaks-loop did not write, and peaks-loop never overwrites (or claims) a value it did not write.`;
|
|
195
|
+
case 'file-configures-window':
|
|
196
|
+
return `Harness window not managed: ${result.settingsPath} already configures a window, and the project file wins over a probe — peaks-loop only fills an empty slot. Change ${result.key} in that file (or remove it and let the next probe fill it) if you want a different window.`;
|
|
195
197
|
default:
|
|
196
198
|
return `Harness window not managed (${String(result.reason)}).`;
|
|
197
199
|
}
|
|
@@ -82,7 +82,7 @@ function isPlainWindowSpelling(raw) {
|
|
|
82
82
|
* as 1000000, and a value of `1e6` equals a marker of `1000000` only because the
|
|
83
83
|
* parser is lenient. Neither is evidence of ownership, so the pair is `human`
|
|
84
84
|
* and is KEPT. An UNPARSEABLE value beside a plain, valid marker still proves
|
|
85
|
-
* corruption of peaks-loop's own write (`500k` beside `
|
|
85
|
+
* corruption of peaks-loop's own write (`500k` beside `1000000`) and stays
|
|
86
86
|
* removable — that recovery is the feature.
|
|
87
87
|
*/
|
|
88
88
|
function isWindowRemovable(input) {
|
|
@@ -133,13 +133,13 @@ export declare function parseContextWindowOverride(raw: unknown): number | null;
|
|
|
133
133
|
*
|
|
134
134
|
* Why it sits BELOW the two explicit pins. Both are human declarations of
|
|
135
135
|
* intent, and a pin that loses to a value peaks-loop wrote earlier is a
|
|
136
|
-
* silently ignored setting
|
|
137
|
-
*
|
|
138
|
-
* instead
|
|
139
|
-
*
|
|
140
|
-
*
|
|
141
|
-
*
|
|
142
|
-
*
|
|
136
|
+
* silently ignored setting. A probe cannot rewrite a non-empty file (the
|
|
137
|
+
* probe sync fills an empty slot only), so the writer REPORTS the
|
|
138
|
+
* disagreement instead of overwriting the project's own configuration. The
|
|
139
|
+
* conflict is therefore visible rather than silent, and the remedy is a
|
|
140
|
+
* deliberate one: edit the key in the file (or remove it and let the next
|
|
141
|
+
* probe fill the slot), or change `context.windowTokens` so a new project
|
|
142
|
+
* starts from a different value.
|
|
143
143
|
*
|
|
144
144
|
* Why layer 3 is not simply authoritative (the ratchet). Reading back a value
|
|
145
145
|
* peaks-loop wrote makes peaks-loop trust its own earlier resolution, so a
|
|
@@ -116,13 +116,13 @@ export function parseContextWindowOverride(raw) {
|
|
|
116
116
|
*
|
|
117
117
|
* Why it sits BELOW the two explicit pins. Both are human declarations of
|
|
118
118
|
* intent, and a pin that loses to a value peaks-loop wrote earlier is a
|
|
119
|
-
* silently ignored setting
|
|
120
|
-
*
|
|
121
|
-
* instead
|
|
122
|
-
*
|
|
123
|
-
*
|
|
124
|
-
*
|
|
125
|
-
*
|
|
119
|
+
* silently ignored setting. A probe cannot rewrite a non-empty file (the
|
|
120
|
+
* probe sync fills an empty slot only), so the writer REPORTS the
|
|
121
|
+
* disagreement instead of overwriting the project's own configuration. The
|
|
122
|
+
* conflict is therefore visible rather than silent, and the remedy is a
|
|
123
|
+
* deliberate one: edit the key in the file (or remove it and let the next
|
|
124
|
+
* probe fill the slot), or change `context.windowTokens` so a new project
|
|
125
|
+
* starts from a different value.
|
|
126
126
|
*
|
|
127
127
|
* Why layer 3 is not simply authoritative (the ratchet). Reading back a value
|
|
128
128
|
* peaks-loop wrote makes peaks-loop trust its own earlier resolution, so a
|
|
@@ -309,12 +309,12 @@ function findLatestTranscriptUsage(filePath) {
|
|
|
309
309
|
* Overruling it would not be self-correction, it would be peaks-loop
|
|
310
310
|
* silently rewriting a setting the user chose (and persisting the rewrite).
|
|
311
311
|
*
|
|
312
|
-
*
|
|
313
|
-
*
|
|
314
|
-
*
|
|
315
|
-
*
|
|
316
|
-
*
|
|
317
|
-
*
|
|
312
|
+
* The resolution this function returns becomes `probe.capacityTokens`, so the
|
|
313
|
+
* rescue keeps the RATIO honest. It does NOT persist the bump: a probe may
|
|
314
|
+
* only fill an empty harness slot (`syncHarnessWindowForProject`), so a file
|
|
315
|
+
* that already configures a window keeps it, and every later probe re-derives
|
|
316
|
+
* the same correction from the same evidence — the correction is a property
|
|
317
|
+
* of the observation, not a rewrite of the project's configuration.
|
|
318
318
|
*/
|
|
319
319
|
function resolveContextWindowTokens(model, contextTokens, overrides = {}) {
|
|
320
320
|
const resolved = resolveContextWindow(model, overrides);
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "peaks-loop",
|
|
3
|
-
"version": "4.2.
|
|
3
|
+
"version": "4.2.6",
|
|
4
4
|
"description": "Loop Engineering CLI — workflow primitive / loop guards / evaluators / slice orchestration",
|
|
5
5
|
"author": "SquabbyZ",
|
|
6
6
|
"keywords": [
|
|
@@ -133,11 +133,11 @@
|
|
|
133
133
|
"picomatch": "4.0.7",
|
|
134
134
|
"yaml": "^2.9.1",
|
|
135
135
|
"zod": "^4.6.7",
|
|
136
|
-
"peaks-loop-internal-runtime": "0.0.
|
|
137
|
-
"peaks-loop-
|
|
138
|
-
"peaks-loop-shared
|
|
139
|
-
"peaks-loop-workspace-runtime": "0.0.
|
|
140
|
-
"peaks-loop-
|
|
136
|
+
"peaks-loop-internal-runtime": "0.0.73",
|
|
137
|
+
"peaks-loop-mut": "0.1.87",
|
|
138
|
+
"peaks-loop-shared": "0.0.122",
|
|
139
|
+
"peaks-loop-workspace-runtime": "0.0.7",
|
|
140
|
+
"peaks-loop-shared-channel": "0.0.90"
|
|
141
141
|
},
|
|
142
142
|
"devDependencies": {
|
|
143
143
|
"@changesets/cli": "2.31.1",
|