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.
@@ -450,7 +450,7 @@ checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5"
450
450
 
451
451
  [[package]]
452
452
  name = "stillwright"
453
- version = "0.2.2"
453
+ version = "0.3.1"
454
454
  dependencies = [
455
455
  "chrono",
456
456
  "clap",
@@ -1,6 +1,6 @@
1
1
  [package]
2
2
  name = "stillwright"
3
- version = "0.2.2"
3
+ version = "0.3.1"
4
4
  edition = "2021"
5
5
  rust-version = "1.89"
6
6
  description = "State keeper (sw) for the Stillwright agent skills: goals, runs, inbox, dated notes, hash-pinned tools"
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: stillwright
3
- Version: 0.2.2
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
- Three small tasks (code, writing, research), each done by a fresh Claude Sonnet agent with and
93
- without the Stillwright skills, graded by scripts and a read-only judge. Both sides finished
94
- every task. The plain side made one false claim; Stillwright made none and left a plan and a
95
- log every time. It cost about the same in dollars and more wall time. Three tasks is a small
96
- sample and is stated as such; raw runs, grading script and judge report:
97
- [docs/evals.md](docs/evals.md) and the
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: 67 black-box tests drive the binary on Linux, macOS and Windows in
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
- Three small tasks (code, writing, research), each done by a fresh Claude Sonnet agent with and
76
- without the Stillwright skills, graded by scripts and a read-only judge. Both sides finished
77
- every task. The plain side made one false claim; Stillwright made none and left a plan and a
78
- log every time. It cost about the same in dollars and more wall time. Three tasks is a small
79
- sample and is stated as such; raw runs, grading script and judge report:
80
- [docs/evals.md](docs/evals.md) and the
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: 67 black-box tests drive the binary on Linux, macOS and Windows in
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`