tuieval 0.2.0.dev89__tar.gz → 0.2.0.dev90__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.
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/CHANGELOG.md +1 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/PKG-INFO +1 -1
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/_version.py +2 -2
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/tui.py +2 -3
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/.gitignore +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/LICENSE +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/README.md +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/RELEASING.md +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/README.md +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/favicon.ico +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/readme-header.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/social-preview.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-1024.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-128.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-16.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-16.svg +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-256.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-32.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-48.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-512.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-64.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon-animated.svg +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/brand/tuieval-icon.svg +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/tui-answer-reasoning.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/tui-run-reasoning.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/images/tui-setup.png +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/models.md +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/docs/writing-packs.md +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/pyproject.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/__init__.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/__main__.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/builtin.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/cli.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/client.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/compare.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/doctor.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/engine.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/export.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/__init__.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/answer.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/code.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/rag.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/reply.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/graders/tool_call.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/logs.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/machines.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/onboard.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/packs.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/profiles.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/pta.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/remove.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/run_evals.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/scaffold.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/selftest.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/models.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/answer/pack.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/answer/system.txt +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/answer/tests.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/code/pack.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/code/system.txt +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/code/tests.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/rag/pack.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/rag/system.txt +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/rag/tests.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/reply/pack.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/reply/system.txt +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/reply/tests.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/pack.toml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/system.txt +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/tests.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/tools.yaml +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/tune.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/verdict.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/watch_proxy.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/workspace.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/yamlout.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/tests/mock_server.py +0 -0
- {tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/tests/test_tuieval.py +0 -0
|
@@ -2,6 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
## Unreleased
|
|
4
4
|
|
|
5
|
+
- Results, Per question: the side-by-side summary shows any number of models (it stopped at 8).
|
|
5
6
|
- `max_tokens` in pack.toml sets one pack's output budget; changing it reruns only that pack. Models whose context or endpoint can't fit it are skipped for that pack.
|
|
6
7
|
- The run screen's queue keeps the running model in view, unless you scroll it yourself (scrolling back to it follows again).
|
|
7
8
|
- Start while a run is going skips models and packs already running or queued (it says which); picking only those adds nothing. Retest and picked questions still go through.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: tuieval
|
|
3
|
-
Version: 0.2.0.
|
|
3
|
+
Version: 0.2.0.dev90
|
|
4
4
|
Summary: Evaluate local and frontier LLMs on your own questions: accuracy, speed, tokens and PASS/FAIL verdicts, in the terminal.
|
|
5
5
|
Project-URL: Homepage, https://github.com/ashe-wb/tuieval
|
|
6
6
|
Project-URL: Issues, https://github.com/ashe-wb/tuieval/issues
|
|
@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
|
|
|
18
18
|
commit_id: str | None
|
|
19
19
|
__commit_id__: str | None
|
|
20
20
|
|
|
21
|
-
__version__ = version = '0.2.0.
|
|
22
|
-
__version_tuple__ = version_tuple = (0, 2, 0, '
|
|
21
|
+
__version__ = version = '0.2.0.dev90'
|
|
22
|
+
__version_tuple__ = version_tuple = (0, 2, 0, 'dev90')
|
|
23
23
|
|
|
24
24
|
__commit_id__ = commit_id = None
|
|
@@ -2983,10 +2983,9 @@ class ResultsScreen(Screen):
|
|
|
2983
2983
|
table.clear(columns=True)
|
|
2984
2984
|
title = self.query_one("#pq-compare-title", Static)
|
|
2985
2985
|
shared = [t for t in tests if all(m in t["cells"] for m in models)]
|
|
2986
|
-
if len(models) < 2
|
|
2986
|
+
if len(models) < 2:
|
|
2987
2987
|
table.display = False
|
|
2988
|
-
title.update("
|
|
2989
|
-
if len(models) > 8 else "")
|
|
2988
|
+
title.update("")
|
|
2990
2989
|
return
|
|
2991
2990
|
table.display = True
|
|
2992
2991
|
if not shared:
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/system.txt
RENAMED
|
File without changes
|
{tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/tests.yaml
RENAMED
|
File without changes
|
{tuieval-0.2.0.dev89 → tuieval-0.2.0.dev90}/src/tuieval/templates/packs/tool_call/tools.yaml
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|