tuieval 0.2.0.dev70__py3-none-any.whl → 0.2.0.dev72__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.dev70'
-__version_tuple__ = version_tuple = (0, 2, 0, 'dev70')
+__version__ = version = '0.2.0.dev72'
+__version_tuple__ = version_tuple = (0, 2, 0, 'dev72')
 
 __commit_id__ = commit_id = None

tuieval/run_evals.py

@@ -11,6 +11,7 @@
     tuieval run --only my-model --packs my-pack,other-pack
     tuieval run --tags moe --packs my-pack        # models tagged "moe"
     tuieval run --packs my-pack --tests a,b       # only these tests of a pack (or --tests my-pack:a,other:b)
+    tuieval run --only my-model --packs my-pack --tests a --retest   # ask a question again
     tuieval run --preset nightly                  # a selection saved in the TUI (presets.toml)
     tuieval run --tier smoke --only my-model      # 3 tests per pack, 1 repeat: check paths and flags
     tuieval run --tier smoke --only openrouter:qwen/qwen3-32b   # any OpenRouter model, no models.toml edit
@@ -742,7 +743,8 @@ def main(argv=None):
     p.add_argument("--packs", help="comma-separated packs (default: all)")
     p.add_argument("--tests", help="comma-separated test ids to run instead of the tier's sample: id with one "
                                    "pack in --packs, else pack:id (and --packs defaults to those packs)")
-    p.add_argument("--force", action="store_true", help="rerun packs (or the --tests) that already have current results")
+    p.add_argument("--retest", "--force", action="store_true", dest="force",
+                   help="ask again even if already answered: the packs, or just the --tests (earlier answers go to history/)")
     p.add_argument("--repeat", type=int, help="times each question is asked, any tier (default: 1 for smoke and "
                                                   "screen, the pack's certification count for certify)")
     p.add_argument("--tier", choices=engine.TIERS, default="screen",

tuieval/tui.py

@@ -385,6 +385,9 @@ HELP = {
 [b]Models at a time[/b]: how many of the ticked models run side by side (blank: this machine's
 parallel_models in models.toml, default 1). Answers note the models they ran alongside.
 
+[b]Retest[/b]: ask the ticked questions again even if they're already answered (only the tests
+picked with e, if any). Without it, answered questions are skipped. Replaced answers go to history/.
+
 [b]Keys[/b]
   s  start (with a run going: add to it, or queue it)   r  results
   a  add a model (a GGUF, a model id, openrouter:<id>)  m  scan model folders for new GGUFs
@@ -646,7 +649,7 @@ class SetupScreen(Screen):
             yield Input("", id="repeat", type="integer", max_length=2, placeholder="1")
             yield Label("Models at a time")
             yield Input("", id="parallel", type="integer", max_length=1, placeholder="1")
-            yield Checkbox("Rerun existing results", id="force")
+            yield Checkbox("Retest (ask again, even if already answered)", id="force")
         yield Static(id="estimate")
         with Horizontal(id="buttons"):
             yield Button("Start  [s]", id="start", variant="success")
@@ -958,7 +961,7 @@ class SetupScreen(Screen):
         if not run:
             text += "\n[yellow]Nothing selected can run (see skipping).[/yellow]"
         elif rerun:
-            text += "\n[yellow]Everything selected has results; Start runs it again.[/yellow]"
+            text += "\n[yellow]Everything selected has results; Start retests it.[/yellow]"
         resumed = [j for j in run if "done earlier" in j.note]
         if resumed:
             text += f"   [yellow]{len(resumed)} pack(s) continue from earlier results[/yellow]"

{tuieval-0.2.0.dev70.dist-info → tuieval-0.2.0.dev72.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tuieval
-Version: 0.2.0.dev70
+Version: 0.2.0.dev72
 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.dev70.dist-info → tuieval-0.2.0.dev72.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=QOWJeoQKxfTmTuGLJAd_kCYTn77Y6YRZnI-F8SiBGe4,535
+tuieval/_version.py,sha256=5bSTQoJyfnoC1UimCugL5jEW1WKsn9kwuboOZkyp3xk,535
 tuieval/builtin.toml,sha256=Kxw22RZCJhURUyu5Wz8tj5Y1nM85A8hFVRbA4ocoPUg,4293
 tuieval/cli.py,sha256=JGtN4J6d4cr9G7OfBxDiNtxvVEew9MgUhJBlYKYPhJ4,4687
 tuieval/client.py,sha256=kpsyLEZKfxCsvIGBHBbBy83TpI97CvnGCDq-4AbJS4Y,9986
@@ -15,10 +15,10 @@ tuieval/packs.py,sha256=tiLmxsrX_M5EUMuR4Yvb7pLBLEI15wamHSjflD6wjoY,11299
 tuieval/profiles.py,sha256=soeLxjdB-l-OxSY8jZ4yjwfdSnsBV-QICcwKxRJS7nQ,3663
 tuieval/pta.py,sha256=i5oPj-Pz3N9u7bzzuZwsQvMGdxWdAncww2nR15K6PHY,12108
 tuieval/remove.py,sha256=Vwh43nm9lVb9U9aN-h6CMYbkTwdR3UWfZObwweF72n0,5157
-tuieval/run_evals.py,sha256=1zNkCdFt744cqpebqiyj-sZrbOI22c6IYBcXk9koz20,46538
+tuieval/run_evals.py,sha256=WVrGU418Fv4oP5ddKNd5k2_0QjNz4ZEiJHQhKrNDR4w,46712
 tuieval/scaffold.py,sha256=YBOqniJpf_GtKKAFF3_OHxxMGbmTWdFjcClGcOnrrKE,12130
 tuieval/selftest.py,sha256=nExkrOidgymlmvkxImEBfrQG5iTUN5WuRMIKtqusCCs,9835
-tuieval/tui.py,sha256=CkK7e3aJ3kli--u0cJrpaQKEoGAucs3grg3xt6x5v2c,166041
+tuieval/tui.py,sha256=q-ufpI9YdYPJhrmomDOZJME8sBw1u94_P3t4VMzEIpo,166257
 tuieval/tune.py,sha256=azxxthgJeag8JyoQUgaRxq6oI1XvEgzb9vkszjJZH7w,39645
 tuieval/verdict.py,sha256=VB-0LTxR9y8bJHT9RicxtE9K7cUHBdCu40hOCrsbmA4,19150
 tuieval/watch_proxy.py,sha256=bnDO1i6n6yUs1hODoUWcMppJMGPavoQqs6aNYrIxpT8,11416
@@ -47,8 +47,8 @@ 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.dev70.dist-info/METADATA,sha256=ch13-8H_mRWS0lk2qo4vcY55Vu8P1dxdVWiLCOb-KrY,14215
-tuieval-0.2.0.dev70.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-tuieval-0.2.0.dev70.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
-tuieval-0.2.0.dev70.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
-tuieval-0.2.0.dev70.dist-info/RECORD,,
+tuieval-0.2.0.dev72.dist-info/METADATA,sha256=MbPZAuXA-J7aRQAolpHk2QRyyt97Y3Sua4RjKuER1bM,14215
+tuieval-0.2.0.dev72.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+tuieval-0.2.0.dev72.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
+tuieval-0.2.0.dev72.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
+tuieval-0.2.0.dev72.dist-info/RECORD,,