sensez 0.1.10 → 0.1.12
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 +28 -3
- package/package.json +5 -5
package/README.md
CHANGED
|
@@ -18,12 +18,11 @@ and the `spine` to do it fast.
|
|
|
18
18
|
|
|
19
19
|
Supported language profiles currently include Python, JavaScript, TypeScript, and Rust (for dogfooding primarily).
|
|
20
20
|
|
|
21
|
+
Docs: https://popov95s.github.io/sensez/latest/
|
|
22
|
+
|
|
21
23
|
## Quick Start
|
|
22
24
|
### Python
|
|
23
25
|
```Bash
|
|
24
|
-
# Run a one-off scan with uv
|
|
25
|
-
uvx --from sensez sensez noze .
|
|
26
|
-
|
|
27
26
|
# Add as a project dev dependency; run it with `uv run sensez ...`
|
|
28
27
|
uv add --dev sensez
|
|
29
28
|
uv run sensez init
|
|
@@ -31,6 +30,9 @@ uv run sensez init
|
|
|
31
30
|
# Install as a global CLI so `sensez ...` works directly
|
|
32
31
|
uv tool install sensez
|
|
33
32
|
sensez init
|
|
33
|
+
|
|
34
|
+
# or run a one-off scan with uv
|
|
35
|
+
uvx sensez noze .
|
|
34
36
|
```
|
|
35
37
|
|
|
36
38
|
### JS/TS
|
|
@@ -77,6 +79,25 @@ repo intelligence signals, including dead code (`5.75s`).
|
|
|
77
79
|
|
|
78
80
|
`sensez` tries to lower dead code noise and allows for configuration of what gets reported. It also includes a few more Python and TS/JS opinionated smells, apart from overall structural consistency metrics.
|
|
79
81
|
|
|
82
|
+
## Agent Impact
|
|
83
|
+
|
|
84
|
+
We gave the same coding agent 70 real-world Python tasks from SWE-PolyBench and
|
|
85
|
+
SWE-bench Verified, plus 21 synthetic tasks designed to trigger specific
|
|
86
|
+
maintainability traps. Both variants received SOLID/DRY principles. The Sensez
|
|
87
|
+
variant additionally used the `noze_sniff` MCP tool in a mandatory feedback loop
|
|
88
|
+
before declaring each task complete.
|
|
89
|
+
|
|
90
|
+
| | New quality issues | Clone tokens | New clones | Lines written | Tokens used |
|
|
91
|
+
|---|---|---|---|---|---|
|
|
92
|
+
| Without Sensez | 14 | 1,251 | 129 | 2,080 | 1.23M |
|
|
93
|
+
| With Sensez | 2 | 126 | 0 | 682 | 1.34M |
|
|
94
|
+
| **Reduction** | **86%** | **90%** | **100%** | **67%** | **+8.7% overhead** |
|
|
95
|
+
|
|
96
|
+
Sensez agents produced structurally cleaner code with 67% fewer lines.
|
|
97
|
+
|
|
98
|
+
Benchmarks used: SWE-PolyBench_500, SWE-bench Verified, and synthetic pillar tests.
|
|
99
|
+
Full methodology and per-benchmark results in [`evals/`](evals/).
|
|
100
|
+
|
|
80
101
|
## The Problem
|
|
81
102
|
|
|
82
103
|
Coding agents drift. Not due to bad intentions, but because their loop is leaky.
|
|
@@ -243,3 +264,7 @@ action = "warning"
|
|
|
243
264
|
|
|
244
265
|
Sensez does not send telemetry or source code anywhere. Local metrics stay under
|
|
245
266
|
`.sensez/local-metrics/`.
|
|
267
|
+
|
|
268
|
+
---
|
|
269
|
+
|
|
270
|
+
Disclaimer: [DISCLAIMER.md](DISCLAIMER.md)
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "sensez",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.12",
|
|
4
4
|
"description": "Sensez CLI launcher for structural maintainability checks",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"readme": "README.md",
|
|
@@ -18,10 +18,10 @@
|
|
|
18
18
|
"README.md"
|
|
19
19
|
],
|
|
20
20
|
"optionalDependencies": {
|
|
21
|
-
"sensez-darwin-arm64": "0.1.
|
|
22
|
-
"sensez-darwin-x64": "0.1.
|
|
23
|
-
"sensez-linux-arm64-gnu": "0.1.
|
|
24
|
-
"sensez-linux-x64-gnu": "0.1.
|
|
21
|
+
"sensez-darwin-arm64": "0.1.12",
|
|
22
|
+
"sensez-darwin-x64": "0.1.12",
|
|
23
|
+
"sensez-linux-arm64-gnu": "0.1.12",
|
|
24
|
+
"sensez-linux-x64-gnu": "0.1.12"
|
|
25
25
|
},
|
|
26
26
|
"publishConfig": {
|
|
27
27
|
"provenance": true
|