evals-lab 0.14.0 → 0.15.0
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/CHANGELOG.md +44 -0
- package/lab/VERSION +1 -1
- package/lab/demo/manifest.json +2 -2
- package/lab/demo/pipelines/demo-1.json +14 -11
- package/lab/demo/pipelines/demo-2.json +14 -11
- package/lab/demo/pipelines/documents.json +3 -4
- package/lab/demo/pipelines/sentiment.json +1 -1
- package/lab/demo/pipelines/weather-alerts.json +1 -1
- package/lab/demo/pipelines/wordings.json +1 -1
- package/lab/evals-core.mjs +243 -164
- package/lab/kinds/list.mjs +327 -223
- package/lab/server.py +130 -28
- package/lab/web/dist/assets/gallery-Cy8oycht.js +5 -0
- package/lab/web/dist/assets/gallery-eVJoaK-6.css +1 -0
- package/lab/web/dist/assets/main-B-LGmhPu.css +1 -0
- package/lab/web/dist/assets/main-wqNvXpWp.js +15 -0
- package/lab/web/dist/assets/tokens-CWVzmtid.css +1 -0
- package/lab/web/dist/assets/tokens-mCS6IZGh.js +64 -0
- package/lab/web/dist/gallery.html +4 -4
- package/lab/web/dist/index.html +4 -4
- package/package.json +1 -1
- package/lab/web/dist/assets/gallery-B_-TH0F-.css +0 -1
- package/lab/web/dist/assets/gallery-qrf0ZGXK.js +0 -5
- package/lab/web/dist/assets/main-D6xARg2A.js +0 -16
- package/lab/web/dist/assets/main-xVU6J7Gi.css +0 -1
- package/lab/web/dist/assets/tokens-C8dqXDHN.js +0 -62
- package/lab/web/dist/assets/tokens-tQ7zTPkd.css +0 -1
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,50 @@ Newest first. Read a release's **Upgrade notes** before installing it: an
|
|
|
5
5
|
upgrade can rewrite what the lab keeps in your data directory, and an older
|
|
6
6
|
version cannot always read it back.
|
|
7
7
|
|
|
8
|
+
## 0.15.0
|
|
9
|
+
|
|
10
|
+
### Upgrade notes
|
|
11
|
+
|
|
12
|
+
- **Copy your data directory before upgrading** (see "User data" in the
|
|
13
|
+
README). A pipeline 0.15.0 saves is pipeline version 19 and a filter set is
|
|
14
|
+
version 4, neither of which 0.14.x can read. To go back, reinstall 0.14.0
|
|
15
|
+
and restore the copy.
|
|
16
|
+
- A job's Pre-format and Post-format filters become one Filters list, in run
|
|
17
|
+
order around its Response Format, and each filter becomes one of seven
|
|
18
|
+
verbs. Every reply reads as it did, except a filter that was linked where
|
|
19
|
+
it never ran: it now runs where it sits.
|
|
20
|
+
|
|
21
|
+
### Added
|
|
22
|
+
|
|
23
|
+
- Filters are seven verbs, in one Filters table with the Response Format as
|
|
24
|
+
a row.
|
|
25
|
+
- A typed prompt edited between runs becomes its next version, not a new
|
|
26
|
+
prompt.
|
|
27
|
+
- Results show a spinner on the row a run is processing, and (Not run) on
|
|
28
|
+
rows a stopped run never reached.
|
|
29
|
+
- Enter in a picker's search picks the top match.
|
|
30
|
+
|
|
31
|
+
### Changed
|
|
32
|
+
|
|
33
|
+
- A picker ends in Cancel and a viewer in Close.
|
|
34
|
+
- Escape closes the innermost dialog or menu, and focus returns to what
|
|
35
|
+
opened it.
|
|
36
|
+
- Enter presses the main button in more dialogs.
|
|
37
|
+
- Links are amber.
|
|
38
|
+
- Keyboard and screen readers: focus rings are no longer clipped, menus
|
|
39
|
+
move with the arrow keys, and Results' run tabs are a proper tab list.
|
|
40
|
+
- When another tab saved first, the conflict bar keeps that copy by default,
|
|
41
|
+
with one button to override it.
|
|
42
|
+
- A dynamic Source's Status is its newest fetch's, and its button says Get
|
|
43
|
+
response.
|
|
44
|
+
- The Sources toolbar stays on one row on a phone, and a tile's quota says
|
|
45
|
+
what it measures.
|
|
46
|
+
|
|
47
|
+
### Fixed
|
|
48
|
+
|
|
49
|
+
- Add source adds one Source, not two.
|
|
50
|
+
- A focus trap skips disabled buttons.
|
|
51
|
+
|
|
8
52
|
## 0.14.0
|
|
9
53
|
|
|
10
54
|
### Upgrade notes
|
package/lab/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.
|
|
1
|
+
0.15.0 (2026.10.14-867)
|
package/lab/demo/manifest.json
CHANGED
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
"version": 1,
|
|
4
4
|
"id": "demo",
|
|
5
5
|
"name": "Demo",
|
|
6
|
-
"packVersion": "2026.10.14.
|
|
6
|
+
"packVersion": "2026.10.14.3",
|
|
7
7
|
"requires": {
|
|
8
|
-
"lab": ">=
|
|
8
|
+
"lab": ">=19",
|
|
9
9
|
"plugins": []
|
|
10
10
|
},
|
|
11
11
|
"description": "Six demos, each a dataset with a starter pipeline: two sets of public-domain images, short texts to classify, one question in four wordings, a dynamic Source's snapshot, and PDFs to check and sort."
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"version":
|
|
2
|
+
"version": 19,
|
|
3
3
|
"id": "demo-1",
|
|
4
4
|
"name": "Demo: images pipeline",
|
|
5
5
|
"jobs": [
|
|
@@ -32,18 +32,17 @@
|
|
|
32
32
|
},
|
|
33
33
|
{
|
|
34
34
|
"type": "filters",
|
|
35
|
-
"stage": "items",
|
|
36
35
|
"filterSets": [
|
|
37
36
|
{
|
|
38
37
|
"id": "filters-j1",
|
|
39
38
|
"set": null,
|
|
40
39
|
"pin": null,
|
|
41
40
|
"own": {
|
|
42
|
-
"version":
|
|
41
|
+
"version": 4,
|
|
43
42
|
"filters": [
|
|
44
43
|
{
|
|
45
44
|
"id": "tidy",
|
|
46
|
-
"type": "
|
|
45
|
+
"type": "trim",
|
|
47
46
|
"match": {},
|
|
48
47
|
"options": {
|
|
49
48
|
"ignoreFailures": false,
|
|
@@ -51,12 +50,12 @@
|
|
|
51
50
|
},
|
|
52
51
|
"tests": [],
|
|
53
52
|
"op": {
|
|
54
|
-
"
|
|
53
|
+
"bullets": true
|
|
55
54
|
}
|
|
56
55
|
},
|
|
57
56
|
{
|
|
58
57
|
"id": "already there",
|
|
59
|
-
"type": "
|
|
58
|
+
"type": "remove",
|
|
60
59
|
"match": {
|
|
61
60
|
"duplicate": true
|
|
62
61
|
},
|
|
@@ -64,7 +63,10 @@
|
|
|
64
63
|
"ignoreFailures": false,
|
|
65
64
|
"repeat": 1
|
|
66
65
|
},
|
|
67
|
-
"tests": []
|
|
66
|
+
"tests": [],
|
|
67
|
+
"op": {
|
|
68
|
+
"kind": "items"
|
|
69
|
+
}
|
|
68
70
|
},
|
|
69
71
|
{
|
|
70
72
|
"id": "keep first",
|
|
@@ -76,12 +78,13 @@
|
|
|
76
78
|
},
|
|
77
79
|
"tests": [],
|
|
78
80
|
"op": {
|
|
79
|
-
"n": 12
|
|
81
|
+
"n": 12,
|
|
82
|
+
"unit": "items"
|
|
80
83
|
}
|
|
81
84
|
},
|
|
82
85
|
{
|
|
83
86
|
"id": "case",
|
|
84
|
-
"type": "
|
|
87
|
+
"type": "change-case",
|
|
85
88
|
"match": {},
|
|
86
89
|
"options": {
|
|
87
90
|
"ignoreFailures": false,
|
|
@@ -89,14 +92,14 @@
|
|
|
89
92
|
},
|
|
90
93
|
"tests": [],
|
|
91
94
|
"op": {
|
|
92
|
-
"kind": "case",
|
|
93
95
|
"mode": "LOWER"
|
|
94
96
|
}
|
|
95
97
|
}
|
|
96
98
|
]
|
|
97
99
|
}
|
|
98
100
|
}
|
|
99
|
-
]
|
|
101
|
+
],
|
|
102
|
+
"format": 0
|
|
100
103
|
}
|
|
101
104
|
]
|
|
102
105
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"version":
|
|
2
|
+
"version": 19,
|
|
3
3
|
"id": "demo-2",
|
|
4
4
|
"name": "Demo: images 2 pipeline",
|
|
5
5
|
"jobs": [
|
|
@@ -32,18 +32,17 @@
|
|
|
32
32
|
},
|
|
33
33
|
{
|
|
34
34
|
"type": "filters",
|
|
35
|
-
"stage": "items",
|
|
36
35
|
"filterSets": [
|
|
37
36
|
{
|
|
38
37
|
"id": "filters-j1",
|
|
39
38
|
"set": null,
|
|
40
39
|
"pin": null,
|
|
41
40
|
"own": {
|
|
42
|
-
"version":
|
|
41
|
+
"version": 4,
|
|
43
42
|
"filters": [
|
|
44
43
|
{
|
|
45
44
|
"id": "tidy",
|
|
46
|
-
"type": "
|
|
45
|
+
"type": "trim",
|
|
47
46
|
"match": {},
|
|
48
47
|
"options": {
|
|
49
48
|
"ignoreFailures": false,
|
|
@@ -51,12 +50,12 @@
|
|
|
51
50
|
},
|
|
52
51
|
"tests": [],
|
|
53
52
|
"op": {
|
|
54
|
-
"
|
|
53
|
+
"bullets": true
|
|
55
54
|
}
|
|
56
55
|
},
|
|
57
56
|
{
|
|
58
57
|
"id": "already there",
|
|
59
|
-
"type": "
|
|
58
|
+
"type": "remove",
|
|
60
59
|
"match": {
|
|
61
60
|
"duplicate": true
|
|
62
61
|
},
|
|
@@ -64,7 +63,10 @@
|
|
|
64
63
|
"ignoreFailures": false,
|
|
65
64
|
"repeat": 1
|
|
66
65
|
},
|
|
67
|
-
"tests": []
|
|
66
|
+
"tests": [],
|
|
67
|
+
"op": {
|
|
68
|
+
"kind": "items"
|
|
69
|
+
}
|
|
68
70
|
},
|
|
69
71
|
{
|
|
70
72
|
"id": "keep first",
|
|
@@ -76,12 +78,13 @@
|
|
|
76
78
|
},
|
|
77
79
|
"tests": [],
|
|
78
80
|
"op": {
|
|
79
|
-
"n": 12
|
|
81
|
+
"n": 12,
|
|
82
|
+
"unit": "items"
|
|
80
83
|
}
|
|
81
84
|
},
|
|
82
85
|
{
|
|
83
86
|
"id": "case",
|
|
84
|
-
"type": "
|
|
87
|
+
"type": "change-case",
|
|
85
88
|
"match": {},
|
|
86
89
|
"options": {
|
|
87
90
|
"ignoreFailures": false,
|
|
@@ -89,14 +92,14 @@
|
|
|
89
92
|
},
|
|
90
93
|
"tests": [],
|
|
91
94
|
"op": {
|
|
92
|
-
"kind": "case",
|
|
93
95
|
"mode": "LOWER"
|
|
94
96
|
}
|
|
95
97
|
}
|
|
96
98
|
]
|
|
97
99
|
}
|
|
98
100
|
}
|
|
99
|
-
]
|
|
101
|
+
],
|
|
102
|
+
"format": 0
|
|
100
103
|
}
|
|
101
104
|
]
|
|
102
105
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"version":
|
|
2
|
+
"version": 19,
|
|
3
3
|
"id": "documents",
|
|
4
4
|
"name": "Demo: documents pipeline",
|
|
5
5
|
"jobs": [
|
|
@@ -25,18 +25,17 @@
|
|
|
25
25
|
},
|
|
26
26
|
{
|
|
27
27
|
"type": "filters",
|
|
28
|
-
"stage": "items",
|
|
29
28
|
"filterSets": [
|
|
30
29
|
{
|
|
31
30
|
"id": "filters-j1",
|
|
32
31
|
"set": null,
|
|
33
32
|
"pin": null,
|
|
34
33
|
"own": {
|
|
35
|
-
"version":
|
|
34
|
+
"version": 4,
|
|
36
35
|
"filters": [
|
|
37
36
|
{
|
|
38
37
|
"id": "unfence",
|
|
39
|
-
"type": "
|
|
38
|
+
"type": "remove",
|
|
40
39
|
"match": {},
|
|
41
40
|
"options": {
|
|
42
41
|
"ignoreFailures": false,
|