inspect-ai 0.3.65__py3-none-any.whl → 0.3.67__py3-none-any.whl

inspect_ai/_display/core/config.py

@@ -35,6 +35,10 @@ def task_config(
             value = [str(v) for v in value]
             config_print.append(f"{name}: {','.join(value)}")
         elif name not in ["limit", "model"]:
+            if isinstance(value, list):
+                value = ",".join([str(v) for v in value])
+            if isinstance(value, str):
+                value = value.replace("[", "\\[")
             config_print.append(f"{name}: {value}")
     values = ", ".join(config_print)
     if values:

inspect_ai/_display/textual/app.py

@@ -1,13 +1,21 @@
 import asyncio
 import contextlib
 from asyncio import CancelledError
-from typing import Any, AsyncIterator, ClassVar, Coroutine, Generic, Iterator, cast
+from typing import (
+    Any,
+    AsyncIterator,
+    ClassVar,
+    Coroutine,
+    Generic,
+    Iterator,
+    cast,
+)
 
 import rich
 from rich.console import Console
+from rich.text import Text
 from textual.app import App, ComposeResult
 from textual.binding import Binding, BindingType
-from textual.content import Content
 from textual.css.query import NoMatches
 from textual.events import Print
 from textual.widget import Widget
@@ -308,9 +316,9 @@ class TaskScreenApp(App[TR]):
 
         def set_unread(unread: int | None) -> None:
             if unread is not None:
-                console_tab.label = Content.from_rich_text(f"Console ({unread}")
+                console_tab.label = Text(f"Console ({unread}")
             else:
-                console_tab.label = Content.from_rich_text("Console")
+                console_tab.label = Text("Console")
 
         self.watch(console_view, "unread", set_unread)
 
@@ -377,7 +385,7 @@ class TaskScreenApp(App[TR]):
         def set_title(self, title: str) -> None:
             tabs = self.app.query_one(TabbedContent)
             tab = tabs.get_tab(self.tab_id)
-            tab.label = Content.from_rich_text(title)
+            tab.label = Text(title)
 
         def activate(self) -> None:
             # show the tab

inspect_ai/_display/textual/widgets/footer.py

@@ -26,8 +26,8 @@ class AppFooter(Widget):
     right: reactive[RenderableType] = reactive("")
 
     def compose(self) -> ComposeResult:
-        yield Static(id="footer-left")
-        yield Static(id="footer-right")
+        yield Static(id="footer-left", markup=False)
+        yield Static(id="footer-right", markup=False)
 
     def watch_left(self, new_left: RenderableType) -> None:
         footer_left = cast(Static, self.query_one("#footer-left"))

inspect_ai/_display/textual/widgets/sandbox.py

@@ -38,6 +38,6 @@ class SandboxView(Vertical):
         with Horizontal():
             yield Static("", classes="indent" if self.sandbox_name else "no_indent")
             with Vertical():
-                yield Static(self.connection.command)
+                yield Static(self.connection.command, markup=False)
                 if self.connection.ports:
                     yield PortMappingsView(self.connection.ports)

inspect_ai/_display/textual/widgets/task_detail.py

@@ -233,20 +233,22 @@ class TaskMetrics(Widget):
         for metric in self.metrics:
             # Add the value static but keep it around
             # for future updates
-            self.value_widgets[metric.name] = Static(self._metric_value(metric.value))
+            self.value_widgets[metric.name] = Static(
+                self._metric_value(metric.value), markup=False
+            )
 
-            grid.mount(Static(metric.name))
+            grid.mount(Static(metric.name, markup=False))
             grid.mount(self.value_widgets[metric.name])
 
     def _title(self) -> Widget:
         if self.scorer is None:
             return Static("")
         elif self.reducer is None:
-            return Static(self.scorer)
+            return Static(self.scorer, markup=False)
         else:
             return Horizontal(
-                Static(self.scorer, classes="scorer"),
-                Static(f"({self.reducer})", classes="reducer"),
+                Static(self.scorer, classes="scorer", markup=False),
+                Static(f"({self.reducer})", classes="reducer", markup=False),
             )
 
     def _metric_value(self, val: float) -> str:

inspect_ai/_display/textual/widgets/tasks.py

@@ -128,8 +128,8 @@ class TasksView(Container):
             progress_view.update_count_width(self.sample_count_width)
 
     def compose(self) -> ComposeResult:
-        yield Static(id="tasks-config")
-        yield Static(id="tasks-targets")
+        yield Static(id="tasks-config", markup=False)
+        yield Static(id="tasks-targets", markup=False)
         yield ScrollableContainer(id="tasks-progress")
 
     def watch_config(self, new_config: RenderableType) -> None:
@@ -191,8 +191,8 @@ class TaskProgressView(Widget):
         self.model_name_width = model_name_width
 
         self.progress_bar = ProgressBar(total=task.profile.steps, show_eta=False)
-        self.count_display = Static()
-        self.metrics_display = Static(id="task-metrics")
+        self.count_display = Static(markup=False)
+        self.metrics_display = Static(id="task-metrics", markup=False)
         self.task_progress = TaskProgress(self.progress_bar)
 
         self.toggle = Toggle()
@@ -211,10 +211,12 @@ class TaskProgressView(Widget):
         yield (self.toggle if self.display_metrics else Static())
         yield TaskStatusIcon()
         yield Static(
-            progress_description(self.t.profile, self.description_width, pad=True)
+            progress_description(self.t.profile, self.description_width, pad=True),
+            markup=False,
         )
         yield Static(
-            progress_model_name(self.t.profile.model, self.model_name_width, pad=True)
+            progress_model_name(self.t.profile.model, self.model_name_width, pad=True),
+            markup=False,
         )
         yield self.progress_bar
         yield self.count_display

inspect_ai/_display/textual/widgets/transcript.py

@@ -117,7 +117,7 @@ class TranscriptView(ScrollableContainer):
                         )
                         if isinstance(d.content, Markdown):
                             set_transcript_markdown_options(d.content)
-                        widgets.append(Static(d.content))
+                        widgets.append(Static(d.content, markup=False))
                         widgets.append(Static(Text(" ")))
         return widgets
 

inspect_ai/_eval/task/run.py

@@ -551,9 +551,11 @@ async def task_run_sample(
     # helper to handle exceptions (will throw if we've exceeded the limit)
     def handle_error(ex: BaseException) -> tuple[EvalError, BaseException | None]:
         err = sample_error(ex)
-        py_logger.warning(
-            f"Sample error (id: {sample.id}, epoch: {state.epoch}): {exception_message(ex)})"
-        )
+        # if we aren't raising the error then print a warning
+        if err[1] is None:
+            py_logger.warning(
+                f"Sample error (id: {sample.id}, epoch: {state.epoch}): {exception_message(ex)})"
+            )
         transcript()._event(ErrorEvent(error=err[0]))
         return err
 

inspect_ai/_eval/task/task.py

@@ -331,7 +331,15 @@ def resolve_epochs(epochs: int | Epochs | None) -> Epochs | None:
 
 
 def resolve_dataset(dataset: Dataset | Sequence[Sample] | None) -> Dataset:
-    dataset = dataset or [Sample(input="prompt")]
+    # this is a convenience for tests that don't want to define a dummy sample
+    if dataset is None:
+        dataset = [Sample(input="prompt")]
+
+    # raise error if the dataset is empty
+    if len(dataset) == 0:
+        raise ValueError("The specified dataset is empty (has no samples)")
+
+    # resolve sequence to dataset if necessary
     return dataset if isinstance(dataset, Dataset) else MemoryDataset(list(dataset))
 
 

inspect_ai/_util/format.py

@@ -1,4 +1,5 @@
 import pprint
+from string import Formatter
 from textwrap import indent
 from typing import Any
 
@@ -33,3 +34,60 @@ def format_progress_time(time: float, pad_hours: bool = True) -> str:
     hours, minutes = divmod(minutes, 60)
     hours_fmt = f"{hours:2.0f}" if pad_hours else f"{hours:.0f}"
     return f"{hours_fmt}:{minutes:02.0f}:{seconds:02.0f}"
+
+
+def format_template(
+    template: str,
+    params: dict[str, Any],
+    skip_unknown: bool = True,
+) -> str:
+    """Format a template string, optionally preserving unknown placeholders.
+
+    Args:
+        template: A string containing {placeholders} to be formatted
+        params: Dictionary of parameters to substitute into the template
+        skip_unknown: If True, preserve unknown placeholders; if False, raise KeyError
+
+    Returns:
+        The formatted string with parameters substituted
+
+    Examples:
+        >>> format_template("Hello {name}!", {"name": "World"})
+        'Hello World!'
+        >>> format_template("Hello {name}!", {}, skip_unknown=True)
+        'Hello {name}!'
+    """
+
+    class SafeFormatter(Formatter):
+        def get_field(self, field_name: str, args: Any, kwargs: Any) -> Any:
+            try:
+                # Handle array indexing and nested attributes
+                first, rest = (
+                    field_name.split(".", 1)
+                    if "." in field_name
+                    else (field_name, None)
+                )
+                first = first.split("[")[0]  # Remove any array indexing for the check
+
+                if first not in params and skip_unknown:
+                    return "{" + field_name + "}", field_name
+
+                obj = params.get(first)
+                if obj is None and skip_unknown:
+                    return "{" + field_name + "}", field_name
+
+                return super().get_field(field_name, args, kwargs)
+            except (AttributeError, KeyError, IndexError) as e:
+                if skip_unknown:
+                    return "{" + field_name + "}", field_name
+                raise KeyError(f"Failed to format field '{field_name}'") from e
+
+        def format_field(self, value: Any, format_spec: str) -> Any:
+            try:
+                return super().format_field(value, format_spec)
+            except (ValueError, TypeError):
+                if skip_unknown:
+                    return "{" + str(value) + ":" + format_spec + "}"
+                raise
+
+    return SafeFormatter().format(template, **params)

inspect_ai/_view/www/dist/assets/index.css

@@ -16346,22 +16346,24 @@ ul.jsondiffpatch-textdiff {
 ._noTop_14odp_27 {
   margin-top: 0;
 }
-._body_5y0hl_1 {
+._flatBody_gk2ju_1 {
   color: var(--bs-danger);
   display: grid;
-  grid-template-columns: 1fr;
-  align-content: align;
-  justify-items: center;
+  grid-template-columns: max-content max-content;
+  column-gap: 0.2em;
+  margin-top: 0.4rem;
 }
 
-._iconSmall_5y0hl_9 {
+._iconSmall_gk2ju_9 {
   font-size: var(--inspect-font-size-small);
   line-height: var(--inspect-font-size-small);
   height: var(--inspect-font-size-small);
 }
 
-._message_5y0hl_15 {
-  width: 300px;
+._lineBase_gk2ju_15 {
+  font-size: var(--inspect-font-size-base);
+  line-height: var(--inspect-font-size-base);
+  height: var(--inspect-font-size-base);
 }
 ._target_yamz4_1 {
   padding-left: 0;
@@ -19222,6 +19224,23 @@ span.ap-marker-container:hover span.ap-marker {
 .message-band-btn.warning {
   color: var(--bs-warning-text-emphasis);
 }
+._body_5y0hl_1 {
+  color: var(--bs-danger);
+  display: grid;
+  grid-template-columns: 1fr;
+  align-content: align;
+  justify-items: center;
+}
+
+._iconSmall_5y0hl_9 {
+  font-size: var(--inspect-font-size-small);
+  line-height: var(--inspect-font-size-small);
+  height: var(--inspect-font-size-small);
+}
+
+._message_5y0hl_15 {
+  width: 300px;
+}
 ._grid_1kcta_1 {
   display: grid;
   padding-top: 1em;
@@ -19585,16 +19604,17 @@ span.ap-marker-container:hover span.ap-marker {
   padding: 0 0.2em;
   justify-content: center;
 }
-._statusPanel_1fzh4_1 {
+._statusPanel_66f9o_1 {
   padding: 1em;
   margin-top: 0.5em;
   text-transform: uppercase;
   font-size: var(--inspect-font-size-smaller);
   display: grid;
   grid-template-columns: auto auto;
+  justify-content: end;
 }
 
-._statusIcon_1fzh4_10 {
+._statusIcon_66f9o_11 {
   font-size: var(--inspect-font-size-large);
   margin-right: 0.3em;
   margin-top: -0.1em;