stillwright 0.2.1__tar.gz → 0.3.0__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-0.2.1 → stillwright-0.3.0}/Cargo.lock +1 -1
- {stillwright-0.2.1 → stillwright-0.3.0}/Cargo.toml +1 -1
- {stillwright-0.2.1 → stillwright-0.3.0}/PKG-INFO +23 -9
- {stillwright-0.2.1 → stillwright-0.3.0}/README.md +22 -8
- {stillwright-0.2.1 → stillwright-0.3.0}/press/README.md +1 -1
- {stillwright-0.2.1 → stillwright-0.3.0}/src/main.rs +1400 -74
- {stillwright-0.2.1 → stillwright-0.3.0}/LICENSE +0 -0
- {stillwright-0.2.1 → stillwright-0.3.0}/examples/quickstart-run/README.md +0 -0
- {stillwright-0.2.1 → stillwright-0.3.0}/pyproject.toml +0 -0
- {stillwright-0.2.1 → stillwright-0.3.0}/src/gate.rs +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: stillwright
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.0
|
|
4
4
|
Classifier: Environment :: Console
|
|
5
5
|
Classifier: Programming Language :: Rust
|
|
6
6
|
Classifier: Topic :: Software Development
|
|
@@ -78,18 +78,30 @@ refuses the stale receipt. The rewind keeps the state it replaced, so nothing is
|
|
|
78
78
|
and the agent's final message is at most five lines.
|
|
79
79
|
- **Goals, not prompts.** It keeps a goal queue, plans each goal into checkable steps, routes
|
|
80
80
|
steps to the cheapest model that a command can verify, and measures the dollars.
|
|
81
|
+
- **Hooks the plugin brings along.** In Claude Code the plugin ships three hooks: the gate
|
|
82
|
+
before every shell command (`sw gate`: ask or block before a destructive one), the brief
|
|
83
|
+
after every context compaction (`sw run brief`), and a Stop hook (`sw run stop`) that refuses
|
|
84
|
+
to end a turn, once, while the open run has a `$`-checked step with no certified receipt. The
|
|
85
|
+
model gets the step and the exact commands back instead of the user getting "done". A step
|
|
86
|
+
logged as failed, a card waiting on you, or the host already continuing because of the hook
|
|
87
|
+
lets the turn end; a plan edited after work started costs one nudge and is dated in the log;
|
|
88
|
+
a machine without `sw` is never blocked.
|
|
81
89
|
|
|
82
90
|
## Measured
|
|
83
91
|
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
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
|
|
90
102
|
[Hugging Face dataset](https://huggingface.co/datasets/Folvix/stillwright-evals).
|
|
91
103
|
|
|
92
|
-
The gate itself is tested:
|
|
104
|
+
The gate itself is tested: 252 black-box tests drive the binary on Linux, macOS and Windows in
|
|
93
105
|
CI, including the ways two independent reviews found to get past it before release.
|
|
94
106
|
|
|
95
107
|
## Install
|
|
@@ -113,7 +125,9 @@ Or the agent's own way:
|
|
|
113
125
|
| Hermes Agent | `git clone --depth 1 https://github.com/HamzaIlyas/stillwright /tmp/stillwright && mkdir -p ~/.hermes/skills/stillwright && cp -R /tmp/stillwright/skills/. ~/.hermes/skills/stillwright/` |
|
|
114
126
|
|
|
115
127
|
For a whole team: run `sw init` in the repository and commit the two files it writes
|
|
116
|
-
(`.claude/settings.json`, `.github/copilot/settings.json`).
|
|
128
|
+
(`.claude/settings.json`, `.github/copilot/settings.json`). It writes the same three hooks
|
|
129
|
+
the plugin ships, for hosts and setups that do not load plugin hooks; with the plugin
|
|
130
|
+
installed, a hook written by `sw init` runs a second time, which is harmless.
|
|
117
131
|
|
|
118
132
|
The skills need the `sw` binary (a single file, no runtime). Any of these installs it:
|
|
119
133
|
|
|
@@ -61,18 +61,30 @@ refuses the stale receipt. The rewind keeps the state it replaced, so nothing is
|
|
|
61
61
|
and the agent's final message is at most five lines.
|
|
62
62
|
- **Goals, not prompts.** It keeps a goal queue, plans each goal into checkable steps, routes
|
|
63
63
|
steps to the cheapest model that a command can verify, and measures the dollars.
|
|
64
|
+
- **Hooks the plugin brings along.** In Claude Code the plugin ships three hooks: the gate
|
|
65
|
+
before every shell command (`sw gate`: ask or block before a destructive one), the brief
|
|
66
|
+
after every context compaction (`sw run brief`), and a Stop hook (`sw run stop`) that refuses
|
|
67
|
+
to end a turn, once, while the open run has a `$`-checked step with no certified receipt. The
|
|
68
|
+
model gets the step and the exact commands back instead of the user getting "done". A step
|
|
69
|
+
logged as failed, a card waiting on you, or the host already continuing because of the hook
|
|
70
|
+
lets the turn end; a plan edited after work started costs one nudge and is dated in the log;
|
|
71
|
+
a machine without `sw` is never blocked.
|
|
64
72
|
|
|
65
73
|
## Measured
|
|
66
74
|
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
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
|
|
73
85
|
[Hugging Face dataset](https://huggingface.co/datasets/Folvix/stillwright-evals).
|
|
74
86
|
|
|
75
|
-
The gate itself is tested:
|
|
87
|
+
The gate itself is tested: 252 black-box tests drive the binary on Linux, macOS and Windows in
|
|
76
88
|
CI, including the ways two independent reviews found to get past it before release.
|
|
77
89
|
|
|
78
90
|
## Install
|
|
@@ -96,7 +108,9 @@ Or the agent's own way:
|
|
|
96
108
|
| Hermes Agent | `git clone --depth 1 https://github.com/HamzaIlyas/stillwright /tmp/stillwright && mkdir -p ~/.hermes/skills/stillwright && cp -R /tmp/stillwright/skills/. ~/.hermes/skills/stillwright/` |
|
|
97
109
|
|
|
98
110
|
For a whole team: run `sw init` in the repository and commit the two files it writes
|
|
99
|
-
(`.claude/settings.json`, `.github/copilot/settings.json`).
|
|
111
|
+
(`.claude/settings.json`, `.github/copilot/settings.json`). It writes the same three hooks
|
|
112
|
+
the plugin ships, for hosts and setups that do not load plugin hooks; with the plugin
|
|
113
|
+
installed, a hook written by `sw init` runs a second time, which is harmless.
|
|
100
114
|
|
|
101
115
|
The skills need the `sw` binary (a single file, no runtime). Any of these installs it:
|
|
102
116
|
|
|
@@ -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`
|