@lmzhen/dsh-evolution-replay 0.32.3 → 0.32.5
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/README.md +12 -11
- package/package.json +5 -5
package/README.md
CHANGED
|
@@ -1,18 +1,19 @@
|
|
|
1
1
|
# @lmzhen/dsh-evolution-replay
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
compares plan outcomes and provides the `evolutionReplay` service behind `evolution
|
|
5
|
-
replay`.
|
|
3
|
+
> 计划回放/排行(高级)。
|
|
6
4
|
|
|
7
|
-
##
|
|
5
|
+
## 你会看到
|
|
8
6
|
|
|
9
|
-
|
|
10
|
-
- **Prompt prefix / KV cache:** independent of request-prefix construction — it does not alter the assembled prompt or tool list; family rules: `packages/README.md` §"Model-visible prompt prefix and the KV cache".
|
|
11
|
-
- **Mount it?** yes — the `evolution-replay` row, carried by the `evolution-host`, `evolution-all` and one-click `evolution-preset` bundles.
|
|
7
|
+
`/evolution replay`。
|
|
12
8
|
|
|
13
|
-
##
|
|
9
|
+
## 什么时候会用到
|
|
14
10
|
|
|
15
|
-
|
|
16
|
-
- **The activity-sidecar verdict is per read, and an unanswered read is its own state.** When `apply()` meets bytes this build cannot read as the current format, every `compare()` result carries `sourceCorrupt: true` and its report states the leaderboard is NOT the recorded history (an empty list does not mean nothing happened); a later successful read clears the qualification (a repaired sidecar plus an io reload (HMR / plugin restart)), while the corruption stays observable through the one warn `apply()` emits at mark time. A read that **THREW** (the io failed, or no state could be produced at all) is neither verdict: `compare()` then carries `sourceReadFailure: <message>` and its report says the read FAILED — never "nothing was recorded". Any ANSWERED read (clean or corrupt) retires that failure, so both qualifications describe the current read rather than latching.
|
|
11
|
+
你想比较历史计划效果时。
|
|
17
12
|
|
|
18
|
-
|
|
13
|
+
## 默认 / 前提
|
|
14
|
+
|
|
15
|
+
只在有审查/计划数据时才有内容。
|
|
16
|
+
|
|
17
|
+
## 边界
|
|
18
|
+
|
|
19
|
+
默认 inject 复盘不产生回放数据。
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@lmzhen/dsh-evolution-replay",
|
|
3
3
|
"description": "Replay/A-B evaluation primitives for evolution plans (community build)",
|
|
4
|
-
"version": "0.32.
|
|
4
|
+
"version": "0.32.5",
|
|
5
5
|
"publishConfig": {
|
|
6
6
|
"access": "public"
|
|
7
7
|
},
|
|
@@ -27,15 +27,15 @@
|
|
|
27
27
|
"license": "MIT",
|
|
28
28
|
"dependencies": {
|
|
29
29
|
"@deepseek-ai/schemastery": "^3.18.5",
|
|
30
|
-
"@lmzhen/dsh-evolution-activity": "^0.32.
|
|
31
|
-
"@lmzhen/dsh-evolution-core": "^0.32.
|
|
30
|
+
"@lmzhen/dsh-evolution-activity": "^0.32.5",
|
|
31
|
+
"@lmzhen/dsh-evolution-core": "^0.32.5"
|
|
32
32
|
},
|
|
33
33
|
"peerDependencies": {
|
|
34
34
|
"@deepseek-ai/cordis": "^4.0.5"
|
|
35
35
|
},
|
|
36
36
|
"devDependencies": {
|
|
37
|
-
"@lmzhen/dsh-evolution-activity": "^0.32.
|
|
38
|
-
"@lmzhen/dsh-evolution-core": "^0.32.
|
|
37
|
+
"@lmzhen/dsh-evolution-activity": "^0.32.5",
|
|
38
|
+
"@lmzhen/dsh-evolution-core": "^0.32.5"
|
|
39
39
|
},
|
|
40
40
|
"engines": {
|
|
41
41
|
"dsh": ">=0.2.1-rc.2 <0.2.2-0"
|