simplicio-cli 0.2.0__tar.gz → 0.2.2__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.
Files changed (21) hide show
  1. {simplicio_cli-0.2.0/simplicio_cli.egg-info → simplicio_cli-0.2.2}/PKG-INFO +25 -8
  2. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/README.md +23 -6
  3. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/pyproject.toml +2 -2
  4. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2/simplicio_cli.egg-info}/PKG-INFO +25 -8
  5. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/LICENSE +0 -0
  6. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/setup.cfg +0 -0
  7. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/__init__.py +0 -0
  8. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/bench.py +0 -0
  9. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/cache.py +0 -0
  10. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/cli.py +0 -0
  11. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/pipeline.py +0 -0
  12. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/precedent.py +0 -0
  13. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/prompt.py +0 -0
  14. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/providers.py +0 -0
  15. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/skill_router.py +0 -0
  16. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio/templates/simplicio_prompt.md +0 -0
  17. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio_cli.egg-info/SOURCES.txt +0 -0
  18. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio_cli.egg-info/dependency_links.txt +0 -0
  19. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio_cli.egg-info/entry_points.txt +0 -0
  20. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio_cli.egg-info/requires.txt +0 -0
  21. {simplicio_cli-0.2.0 → simplicio_cli-0.2.2}/simplicio_cli.egg-info/top_level.txt +0 -0
@@ -1,7 +1,7 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: simplicio-cli
3
- Version: 0.2.0
4
- Summary: Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +54 pts on a 156-check benchmark vs raw prompting.
3
+ Version: 0.2.2
4
+ Summary: Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +55 pts on a 156-check benchmark, 21% faster, ~same tokens.
5
5
  Author-email: Wesley Simplicio <wesleybob4@gmail.com>
6
6
  License: MIT
7
7
  Project-URL: Homepage, https://github.com/wesleysimplicio/simplicio-cli
@@ -41,6 +41,8 @@ Dynamic: license-file
41
41
  [![Python](https://img.shields.io/pypi/pyversions/simplicio-cli.svg)](https://pypi.org/project/simplicio-cli/)
42
42
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
43
43
 
44
+ [![simplicio-cli pipeline hero: one-line task to verified code change](https://raw.githubusercontent.com/wesleysimplicio/simplicio-cli/master/output/imagegen/simplicio-cli-readme-hero-web.png)](output/imagegen/simplicio-cli-readme-hero.png)
45
+
44
46
  > *"hide the Delete button for non-admins"* → diff + test + applied + verified.
45
47
  > Works with **OpenRouter, OpenAI, Anthropic, GLM, DeepSeek, Ollama** — one env var.
46
48
 
@@ -56,18 +58,33 @@ Same model. Same task. Only the prompt changes. **Measured, reproducible, determ
56
58
 
57
59
  | Model | Without simplicio | With simplicio | Gain |
58
60
  |---|---|---|---|
59
- | **Llama 3.1 8B Instruct** | 34% | **98%** | **+64 pts** |
60
- | **Gemma 3 12B IT** | 38% | **94%** | **+56 pts** |
61
- | **Qwen 2.5 7B Instruct** | 38% | **80%** | **+42 pts** |
62
- | **Average across 3 models · 10 cases · 156 checks** | **37%** | **91%** | **+54 pts (+145%)** |
61
+ | **Gemma 3 12B IT** | 34% | **92%** | **+58 pts** |
62
+ | **Llama 3.1 8B Instruct** | 36% | **90%** | **+54 pts** |
63
+ | **Qwen 2.5 7B Instruct** | 34% | **88%** | **+54 pts** |
64
+ | **Average across 3 models · 10 cases · 156 checks** | **35%** | **90%** | **+55 pts (+156%)** |
63
65
 
64
66
  ### Output-quality signals (rate across all 30 runs)
65
67
 
66
68
  | Signal | Raw prompt | With simplicio |
67
69
  |---|---|---|
68
70
  | **DIFF block present** | 0% | **100%** |
69
- | Target file mentioned | 3% | **96%** |
70
- | TEST block present | 86% | **93%** |
71
+ | Target file mentioned | 0% | **96%** |
72
+ | TEST block present | 80% | **96%** |
73
+
74
+ ### Cost — tokens & wall-clock (measured, not estimated)
75
+
76
+ Same provider, same models, same cases. Token counts pulled from the API
77
+ `usage` field; latency from `time.perf_counter()` around each call.
78
+
79
+ | Side | Tokens / run | Wall-clock / run | Total tokens (30 runs) | Total time |
80
+ |---|---|---|---|---|
81
+ | Raw prompt | 759 | 12.4s | 22,774 | 6m 13s |
82
+ | With simplicio | **770** | **9.9s** | **23,127** | **4m 58s** |
83
+ | Δ | **+1%** | **−21%** | +353 | **−75s** |
84
+
85
+ simplicio wraps the objective in a 6-layer contract — more input tokens up
86
+ front, fewer completion tokens because the model stops guessing. Net effect
87
+ across 30 runs: roughly the same token bill, **21% faster, 90% pass-rate**.
71
88
 
72
89
  > A 7B-parameter open model wrapped in simplicio's 6-layer contract outperforms
73
90
  > the same model with raw prompting **by 42 to 64 points**. Without changing the
@@ -6,6 +6,8 @@
6
6
  [![Python](https://img.shields.io/pypi/pyversions/simplicio-cli.svg)](https://pypi.org/project/simplicio-cli/)
7
7
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
8
8
 
9
+ [![simplicio-cli pipeline hero: one-line task to verified code change](https://raw.githubusercontent.com/wesleysimplicio/simplicio-cli/master/output/imagegen/simplicio-cli-readme-hero-web.png)](output/imagegen/simplicio-cli-readme-hero.png)
10
+
9
11
  > *"hide the Delete button for non-admins"* → diff + test + applied + verified.
10
12
  > Works with **OpenRouter, OpenAI, Anthropic, GLM, DeepSeek, Ollama** — one env var.
11
13
 
@@ -21,18 +23,33 @@ Same model. Same task. Only the prompt changes. **Measured, reproducible, determ
21
23
 
22
24
  | Model | Without simplicio | With simplicio | Gain |
23
25
  |---|---|---|---|
24
- | **Llama 3.1 8B Instruct** | 34% | **98%** | **+64 pts** |
25
- | **Gemma 3 12B IT** | 38% | **94%** | **+56 pts** |
26
- | **Qwen 2.5 7B Instruct** | 38% | **80%** | **+42 pts** |
27
- | **Average across 3 models · 10 cases · 156 checks** | **37%** | **91%** | **+54 pts (+145%)** |
26
+ | **Gemma 3 12B IT** | 34% | **92%** | **+58 pts** |
27
+ | **Llama 3.1 8B Instruct** | 36% | **90%** | **+54 pts** |
28
+ | **Qwen 2.5 7B Instruct** | 34% | **88%** | **+54 pts** |
29
+ | **Average across 3 models · 10 cases · 156 checks** | **35%** | **90%** | **+55 pts (+156%)** |
28
30
 
29
31
  ### Output-quality signals (rate across all 30 runs)
30
32
 
31
33
  | Signal | Raw prompt | With simplicio |
32
34
  |---|---|---|
33
35
  | **DIFF block present** | 0% | **100%** |
34
- | Target file mentioned | 3% | **96%** |
35
- | TEST block present | 86% | **93%** |
36
+ | Target file mentioned | 0% | **96%** |
37
+ | TEST block present | 80% | **96%** |
38
+
39
+ ### Cost — tokens & wall-clock (measured, not estimated)
40
+
41
+ Same provider, same models, same cases. Token counts pulled from the API
42
+ `usage` field; latency from `time.perf_counter()` around each call.
43
+
44
+ | Side | Tokens / run | Wall-clock / run | Total tokens (30 runs) | Total time |
45
+ |---|---|---|---|---|
46
+ | Raw prompt | 759 | 12.4s | 22,774 | 6m 13s |
47
+ | With simplicio | **770** | **9.9s** | **23,127** | **4m 58s** |
48
+ | Δ | **+1%** | **−21%** | +353 | **−75s** |
49
+
50
+ simplicio wraps the objective in a 6-layer contract — more input tokens up
51
+ front, fewer completion tokens because the model stops guessing. Net effect
52
+ across 30 runs: roughly the same token bill, **21% faster, 90% pass-rate**.
36
53
 
37
54
  > A 7B-parameter open model wrapped in simplicio's 6-layer contract outperforms
38
55
  > the same model with raw prompting **by 42 to 64 points**. Without changing the
@@ -1,7 +1,7 @@
1
1
  [project]
2
2
  name = "simplicio-cli"
3
- version = "0.2.0"
4
- description = "Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +54 pts on a 156-check benchmark vs raw prompting."
3
+ version = "0.2.2"
4
+ description = "Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +55 pts on a 156-check benchmark, 21% faster, ~same tokens."
5
5
  readme = "README.md"
6
6
  license = { text = "MIT" }
7
7
  requires-python = ">=3.9"
@@ -1,7 +1,7 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: simplicio-cli
3
- Version: 0.2.0
4
- Summary: Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +54 pts on a 156-check benchmark vs raw prompting.
3
+ Version: 0.2.2
4
+ Summary: Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +55 pts on a 156-check benchmark, 21% faster, ~same tokens.
5
5
  Author-email: Wesley Simplicio <wesleybob4@gmail.com>
6
6
  License: MIT
7
7
  Project-URL: Homepage, https://github.com/wesleysimplicio/simplicio-cli
@@ -41,6 +41,8 @@ Dynamic: license-file
41
41
  [![Python](https://img.shields.io/pypi/pyversions/simplicio-cli.svg)](https://pypi.org/project/simplicio-cli/)
42
42
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
43
43
 
44
+ [![simplicio-cli pipeline hero: one-line task to verified code change](https://raw.githubusercontent.com/wesleysimplicio/simplicio-cli/master/output/imagegen/simplicio-cli-readme-hero-web.png)](output/imagegen/simplicio-cli-readme-hero.png)
45
+
44
46
  > *"hide the Delete button for non-admins"* → diff + test + applied + verified.
45
47
  > Works with **OpenRouter, OpenAI, Anthropic, GLM, DeepSeek, Ollama** — one env var.
46
48
 
@@ -56,18 +58,33 @@ Same model. Same task. Only the prompt changes. **Measured, reproducible, determ
56
58
 
57
59
  | Model | Without simplicio | With simplicio | Gain |
58
60
  |---|---|---|---|
59
- | **Llama 3.1 8B Instruct** | 34% | **98%** | **+64 pts** |
60
- | **Gemma 3 12B IT** | 38% | **94%** | **+56 pts** |
61
- | **Qwen 2.5 7B Instruct** | 38% | **80%** | **+42 pts** |
62
- | **Average across 3 models · 10 cases · 156 checks** | **37%** | **91%** | **+54 pts (+145%)** |
61
+ | **Gemma 3 12B IT** | 34% | **92%** | **+58 pts** |
62
+ | **Llama 3.1 8B Instruct** | 36% | **90%** | **+54 pts** |
63
+ | **Qwen 2.5 7B Instruct** | 34% | **88%** | **+54 pts** |
64
+ | **Average across 3 models · 10 cases · 156 checks** | **35%** | **90%** | **+55 pts (+156%)** |
63
65
 
64
66
  ### Output-quality signals (rate across all 30 runs)
65
67
 
66
68
  | Signal | Raw prompt | With simplicio |
67
69
  |---|---|---|
68
70
  | **DIFF block present** | 0% | **100%** |
69
- | Target file mentioned | 3% | **96%** |
70
- | TEST block present | 86% | **93%** |
71
+ | Target file mentioned | 0% | **96%** |
72
+ | TEST block present | 80% | **96%** |
73
+
74
+ ### Cost — tokens & wall-clock (measured, not estimated)
75
+
76
+ Same provider, same models, same cases. Token counts pulled from the API
77
+ `usage` field; latency from `time.perf_counter()` around each call.
78
+
79
+ | Side | Tokens / run | Wall-clock / run | Total tokens (30 runs) | Total time |
80
+ |---|---|---|---|---|
81
+ | Raw prompt | 759 | 12.4s | 22,774 | 6m 13s |
82
+ | With simplicio | **770** | **9.9s** | **23,127** | **4m 58s** |
83
+ | Δ | **+1%** | **−21%** | +353 | **−75s** |
84
+
85
+ simplicio wraps the objective in a 6-layer contract — more input tokens up
86
+ front, fewer completion tokens because the model stops guessing. Net effect
87
+ across 30 runs: roughly the same token bill, **21% faster, 90% pass-rate**.
71
88
 
72
89
  > A 7B-parameter open model wrapped in simplicio's 6-layer contract outperforms
73
90
  > the same model with raw prompting **by 42 to 64 points**. Without changing the
File without changes
File without changes