tuieval 0.2.0.dev32__tar.gz → 0.2.0.dev34__tar.gz

{tuieval-0.2.0.dev32 → tuieval-0.2.0.dev34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tuieval
-Version: 0.2.0.dev32
+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
@@ -26,8 +26,6 @@ Description-Content-Type: text/markdown
 
 <p align="center"><img src="https://raw.githubusercontent.com/ashe-wb/tuieval/main/docs/images/brand/readme-header.png" alt="tuieval" width="100%"></p>
 
-**Find out which model you can trust with your work, on your own questions, in the terminal.**
-
 Run the same eval packs against local models (llama.cpp GGUFs, LM Studio, Ollama, vLLM; tiny, dense or MoE) and against any frontier model on OpenRouter, side by side.
 
 tuieval measures **accuracy, speed and token use** together, and gives a **PASS / FAIL / INCONCLUSIVE** verdict per use case. Grading is automatic; there's no LLM judge.

{tuieval-0.2.0.dev32 → tuieval-0.2.0.dev34}/README.md

@@ -1,7 +1,5 @@
 <p align="center"><img src="https://raw.githubusercontent.com/ashe-wb/tuieval/main/docs/images/brand/readme-header.png" alt="tuieval" width="100%"></p>
 
-**Find out which model you can trust with your work, on your own questions, in the terminal.**
-
 Run the same eval packs against local models (llama.cpp GGUFs, LM Studio, Ollama, vLLM; tiny, dense or MoE) and against any frontier model on OpenRouter, side by side.
 
 tuieval measures **accuracy, speed and token use** together, and gives a **PASS / FAIL / INCONCLUSIVE** verdict per use case. Grading is automatic; there's no LLM judge.

{tuieval-0.2.0.dev32 → tuieval-0.2.0.dev34}/src/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.dev32'
-__version_tuple__ = version_tuple = (0, 2, 0, 'dev32')
+__version__ = version = '0.2.0.dev34'
+__version_tuple__ = version_tuple = (0, 2, 0, 'dev34')
 
 __commit_id__ = commit_id = None

{tuieval-0.2.0.dev32 → tuieval-0.2.0.dev34}/src/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.dev32 → tuieval-0.2.0.dev34}/tests/test_tuieval.py

@@ -733,6 +733,25 @@ class FirstRun(unittest.TestCase):
                              env=dict(os.environ, TUIEVAL_HOME=self.ws, TUIEVAL_DETECT_PORTS=""), timeout=60).stdout.strip()
         self.assertEqual(out, "['first'] ['my-model'] smoke False")   # tuning shows once something has run
 
+    def test_results_open_on_per_question(self):
+        tuieval(self.ws, "add", "my-model", "--server", "local")
+        code = textwrap.dedent("""
+            import asyncio
+            from tuieval.tui import EvalsApp
+            from textual.widgets import TabbedContent
+            async def go():
+                app = EvalsApp({})
+                async with app.run_test(size=(140, 40)) as pilot:
+                    await pilot.pause()
+                    await pilot.press("r")
+                    await pilot.pause()
+                    print(type(app.screen).__name__, app.screen.query_one(TabbedContent).active)
+            asyncio.run(go())
+        """)
+        out = subprocess.run([sys.executable, "-c", code], capture_output=True, text=True,
+                             env=dict(os.environ, TUIEVAL_HOME=self.ws, TUIEVAL_DETECT_PORTS=""), timeout=60).stdout.strip()
+        self.assertEqual(out, "ResultsScreen tab-per-question")
+
     def test_doctor(self):
         tuieval(self.ws, "add", "mock", "--server", "local", "--label", "wanted")
         p = tuieval(self.ws, "doctor", check=False, ports=self.port)