tuieval 0.2.0.dev33__py3-none-any.whl → 0.2.0.dev34__py3-none-any.whl

tuieval/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.0.dev33'
-__version_tuple__ = version_tuple = (0, 2, 0, 'dev33')
+__version__ = version = '0.2.0.dev34'
+__version_tuple__ = version_tuple = (0, 2, 0, 'dev34')
 
 __commit_id__ = commit_id = None

tuieval/tui.py

@@ -10,9 +10,10 @@ Run screen:    live reasoning and answer, per-test ✓/✗, TTFT and tokens/s, p
                k skips the current model, c cancels everything, f pauses auto-scroll.
                r shows results at any time (also mid-run); n starts a new run when it ends.
                Enter on a Recent results row shows that answer in full.
-Results:       ctrl+r reloads (it also reloads when a run's pack finishes). Per question compares
-               each model's tokens and seconds on the same question. Enter on a Failures row or a
-               Per question cell shows the answer: grading and checks, reasoning, answer, question.
+Results:       opens on Per question, which compares each model's tokens and seconds on the same
+               question. ctrl+r reloads (it also reloads when a run's pack finishes). Enter on a
+               Failures row or a Per question cell shows the answer: grading and checks, reasoning,
+               answer, question.
 Answer detail: [ and ] step to the previous/next answer; esc/q close.
 Anywhere:      esc/q go back (q quits only on Setup), ctrl+q quits, w lists this session's runs and
                tunes. Leaving a live run or tune keeps it going; the header shows its progress.
@@ -315,8 +316,8 @@ with the model's reasoning and answer as they stream, then recent results with t
   v  with several models at a time: stream the next one (k skips the one streaming)""",
     "ResultsScreen": """[b]Results[/b]
 
-Start with [b]Production readiness[/b]: one verdict per model and use case, and what's missing when
-it's INCONCLUSIVE. The other tabs are the evidence:
+Opens on [b]Per question[/b]. [b]Production readiness[/b] gives one verdict per model and use case,
+and what's missing when it's INCONCLUSIVE. The other tabs are the evidence:
   Scorecard              accuracy, critical failures and truncation per model and pack
   Speed & tokens         time and tokens per answer (★ = nothing beats it on both accuracy and time)
   Per question           every question, model by model
@@ -2324,7 +2325,7 @@ class ResultsScreen(Screen):
             yield Static(id="results-info")
             if self.smoke_dir:
                 yield Button("Show this Smoke run's results", id="toggle-smoke")
-        with TabbedContent():
+        with TabbedContent(initial="tab-per-question"):
             with TabPane("Production readiness"):
                 yield Static(id="readiness-short")
                 yield Static(self.READINESS_HELP, id="readiness-help")

{tuieval-0.2.0.dev33.dist-info → tuieval-0.2.0.dev34.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tuieval
-Version: 0.2.0.dev33
+Version: 0.2.0.dev34
 Summary: Evaluate local and frontier LLMs on your own questions: accuracy, speed, tokens and PASS/FAIL verdicts, in the terminal.
 Project-URL: Homepage, https://github.com/ashe-wb/tuieval
 Project-URL: Issues, https://github.com/ashe-wb/tuieval/issues

{tuieval-0.2.0.dev33.dist-info → tuieval-0.2.0.dev34.dist-info}/RECORD

@@ -1,6 +1,6 @@
 tuieval/__init__.py,sha256=myVXVX7htbwezW6k3x_FuKgn1RSZ2WcTaDEMByGn6Wg,312
 tuieval/__main__.py,sha256=E6Gls0DNz8GQK2K-kOUIx8cYhgANW_CH54VKrfCfs14,52
-tuieval/_version.py,sha256=k3gviRBoabIwHghgU4oKC7KWfTdp0ZY3l8hIEvwhtyw,535
+tuieval/_version.py,sha256=3QorieDWyZTxv0MUxA9ST5YYuP9gGglKSd1FqdHAeoo,535
 tuieval/builtin.toml,sha256=Kxw22RZCJhURUyu5Wz8tj5Y1nM85A8hFVRbA4ocoPUg,4293
 tuieval/cli.py,sha256=7joEA07W2we-kcg4VXxfCSXazj7dWBCKlQlSXpXQfTc,4390
 tuieval/client.py,sha256=Vui7ucVv_GiKObGoVS_EWSZFUKPou9PWmutqMTrahXk,9313
@@ -16,7 +16,7 @@ tuieval/remove.py,sha256=Vwh43nm9lVb9U9aN-h6CMYbkTwdR3UWfZObwweF72n0,5157
 tuieval/run_evals.py,sha256=ZGx4XcZ15qD3vIg15xCfdX4SxTDHXBp_GYoiGexchdw,43668
 tuieval/scaffold.py,sha256=YBOqniJpf_GtKKAFF3_OHxxMGbmTWdFjcClGcOnrrKE,12130
 tuieval/selftest.py,sha256=nExkrOidgymlmvkxImEBfrQG5iTUN5WuRMIKtqusCCs,9835
-tuieval/tui.py,sha256=thjGLDQCZ5YkFmtZ-xB3914ez7I5S2wePwZlFbcqggg,159589
+tuieval/tui.py,sha256=U-8GTkKqmzUqCpzCEZ6G2lhx_KE7VM9RcVRTG1stDjc,159670
 tuieval/tune.py,sha256=jXwYuSjfdqbLCE3WonP2xaUHwk_FnhI67twB1BaHggI,38992
 tuieval/verdict.py,sha256=Muo1a05mCv781MlEJsXwDsGaKbRi0JS4Lv8HdvK_Aco,19054
 tuieval/watch_proxy.py,sha256=z916NRhEur04a9RnLm6ZpIEY1SnnUGPiHYbmlD9ktQ0,11035
@@ -45,8 +45,8 @@ tuieval/templates/packs/tool_call/pack.toml,sha256=n4bx0lGJHSmW41uVqhfIXJ2BWZpmT
 tuieval/templates/packs/tool_call/system.txt,sha256=mKxu-lB-0YjLHXdgeFJa8x2C180OvcNz5cHv2N5Bg3U,254
 tuieval/templates/packs/tool_call/tests.yaml,sha256=Nv7c4syrzJ9cU8EBKSK_1ZSFx9V02aCjW4-2TBCPT7s,1859
 tuieval/templates/packs/tool_call/tools.yaml,sha256=HgxCkh0On2VwbHSsjAGM8tNCK7ZtKLGrs7lMCn3Fprs,1048
-tuieval-0.2.0.dev33.dist-info/METADATA,sha256=L2qAnllTr4S8SGHETuWG2e0PuC9dIQ0IFiVZGUdKJY0,13189
-tuieval-0.2.0.dev33.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-tuieval-0.2.0.dev33.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
-tuieval-0.2.0.dev33.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
-tuieval-0.2.0.dev33.dist-info/RECORD,,
+tuieval-0.2.0.dev34.dist-info/METADATA,sha256=CYqXAib2FyXNiK3IyJaDOd_aLoRqRvHsTGdF0RSQaMI,13189
+tuieval-0.2.0.dev34.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+tuieval-0.2.0.dev34.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
+tuieval-0.2.0.dev34.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
+tuieval-0.2.0.dev34.dist-info/RECORD,,