stillwright 0.2.2__tar.gz → 0.3.1__tar.gz
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.
- {stillwright-0.2.2 → stillwright-0.3.1}/Cargo.lock +1 -1
- {stillwright-0.2.2 → stillwright-0.3.1}/Cargo.toml +1 -1
- {stillwright-0.2.2 → stillwright-0.3.1}/PKG-INFO +12 -8
- {stillwright-0.2.2 → stillwright-0.3.1}/README.md +11 -7
- {stillwright-0.2.2 → stillwright-0.3.1}/press/README.md +1 -1
- {stillwright-0.2.2 → stillwright-0.3.1}/src/main.rs +1210 -71
- {stillwright-0.2.2 → stillwright-0.3.1}/LICENSE +0 -0
- {stillwright-0.2.2 → stillwright-0.3.1}/examples/quickstart-run/README.md +0 -0
- {stillwright-0.2.2 → stillwright-0.3.1}/pyproject.toml +0 -0
- {stillwright-0.2.2 → stillwright-0.3.1}/src/gate.rs +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: stillwright
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.1
|
|
4
4
|
Classifier: Environment :: Console
|
|
5
5
|
Classifier: Programming Language :: Rust
|
|
6
6
|
Classifier: Topic :: Software Development
|
|
@@ -89,15 +89,19 @@ refuses the stale receipt. The rewind keeps the state it replaced, so nothing is
|
|
|
89
89
|
|
|
90
90
|
## Measured
|
|
91
91
|
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
92
|
+
Four baseline pilots (120 scored runs, Claude Sonnet 5.5, plain Claude Code, hidden tests the
|
|
93
|
+
agent could not see): zero cheats; on one-symptom tickets the agent fixed the ticket, passed the
|
|
94
|
+
visible test and left a documented second defect in the same file in 5 of 30 runs, naming it in
|
|
95
|
+
2. The 0.2 skill measured against that baseline on the same ten tasks: 1.85x the cost per
|
|
96
|
+
verified pass (interval 1.74 to 2.08) and one pass fewer (24 against 25), because its receipt
|
|
97
|
+
certified the same visible test and the reviewer never ran. 0.3 is the answer to that
|
|
98
|
+
measurement: three sw calls per small task, a shorter skill, and a code step that `sw` will not
|
|
99
|
+
certify without a reviewer's verdict, logged after the check and naming every changed file. Its own
|
|
100
|
+
number comes from the same tasks and is published either way. Notes, data and every run's
|
|
101
|
+
verdict: [docs/evals.md](docs/evals.md) (the 2026-11 pilot notes are listed there) and the
|
|
98
102
|
[Hugging Face dataset](https://huggingface.co/datasets/Folvix/stillwright-evals).
|
|
99
103
|
|
|
100
|
-
The gate itself is tested:
|
|
104
|
+
The gate itself is tested: 252 black-box tests drive the binary on Linux, macOS and Windows in
|
|
101
105
|
CI, including the ways two independent reviews found to get past it before release.
|
|
102
106
|
|
|
103
107
|
## Install
|
|
@@ -72,15 +72,19 @@ refuses the stale receipt. The rewind keeps the state it replaced, so nothing is
|
|
|
72
72
|
|
|
73
73
|
## Measured
|
|
74
74
|
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
75
|
+
Four baseline pilots (120 scored runs, Claude Sonnet 5.5, plain Claude Code, hidden tests the
|
|
76
|
+
agent could not see): zero cheats; on one-symptom tickets the agent fixed the ticket, passed the
|
|
77
|
+
visible test and left a documented second defect in the same file in 5 of 30 runs, naming it in
|
|
78
|
+
2. The 0.2 skill measured against that baseline on the same ten tasks: 1.85x the cost per
|
|
79
|
+
verified pass (interval 1.74 to 2.08) and one pass fewer (24 against 25), because its receipt
|
|
80
|
+
certified the same visible test and the reviewer never ran. 0.3 is the answer to that
|
|
81
|
+
measurement: three sw calls per small task, a shorter skill, and a code step that `sw` will not
|
|
82
|
+
certify without a reviewer's verdict, logged after the check and naming every changed file. Its own
|
|
83
|
+
number comes from the same tasks and is published either way. Notes, data and every run's
|
|
84
|
+
verdict: [docs/evals.md](docs/evals.md) (the 2026-11 pilot notes are listed there) and the
|
|
81
85
|
[Hugging Face dataset](https://huggingface.co/datasets/Folvix/stillwright-evals).
|
|
82
86
|
|
|
83
|
-
The gate itself is tested:
|
|
87
|
+
The gate itself is tested: 252 black-box tests drive the binary on Linux, macOS and Windows in
|
|
84
88
|
CI, including the ways two independent reviews found to get past it before release.
|
|
85
89
|
|
|
86
90
|
## Install
|
|
@@ -21,7 +21,7 @@ five lines or fewer. State is plain files; the CLI is one Rust binary. MIT.
|
|
|
21
21
|
## Files
|
|
22
22
|
|
|
23
23
|
- `logo.svg`, `logo.png` (dark), `logo-light.svg`, `logo-light.png`
|
|
24
|
-
- `card.png`: 1280×640 social card
|
|
24
|
+
- `card.png`: 1280×640 social card, drawn by `make_card.py`; the bottom 140 px stay empty because link previews on X and elsewhere lay a title bar over them
|
|
25
25
|
- `demo-horizontal.mp4` (960×560, about 18 s), `demo-vertical.mp4` (720×1280, about 17 s), and
|
|
26
26
|
`../assets/demo.gif`
|
|
27
27
|
- Colours: ink `#12211a`, text `#e5ede7`, accent `#3cc38b`, muted `#93a39a`
|