inspect-ai 0.3.50__tar.gz → 0.3.52__tar.gz

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/.pre-commit-config.yaml

@@ -5,7 +5,7 @@ default_language_version:
   python: python3.11
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.8.2
+  rev: v0.8.3
   hooks:
     # Run the linter.
     - id: ruff

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## v0.3.52 (13 December 2024)
+
+- Eval: `--sample-id` option for evaluating specific sample id(s).
+- Bedrock: Detect and report HTTP rate limit errors.
+- Azure AI: Add `emulate_tools` model arg to force tool emulation (emulation is enabled by default for Llama models).
+- Basic Agent: Add `max_tool_output` parameter to override default max tool output from generate config.
+- Inspect View: Correct display of sample ID for single sample tasks.
+- Trace: Show custom tool views in `--trace` mode.
+- Bugfix: Support for dynamic metric names in realtime scoring display.
+
+## v0.3.51 (13 December 2024)
+
+- Bugfix: Task display fails to load when no scorers are defined for a task.
+
 ## v0.3.50 (12 December 2024)
 
 - Tools: Improved typing/schema support (unions, optional params, enums).

{inspect_ai-0.3.50/src/inspect_ai.egg-info → inspect_ai-0.3.52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: inspect_ai
-Version: 0.3.50
+Version: 0.3.52
 Summary: Framework for large language model evaluations
 Author: UK AI Safety Institute
 License: MIT License
@@ -68,7 +68,7 @@ Requires-Dist: pytest-asyncio; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: pytest-dotenv; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: ruff==0.8.2; extra == "dev"
+Requires-Dist: ruff==0.8.3; extra == "dev"
 Requires-Dist: textual-dev>=0.86.2; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-aiofiles; extra == "dev"

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/docs/models.qmd

@@ -187,6 +187,16 @@ $ export AZUREAI_BASE_URL=https://your-url-at.azure.com
 $ inspect eval --model azureai/llama-2-70b-chat-wnsnw
 ```
 
+#### Tool Emulation
+
+When using the `azureai` model provider, tool calling support can be 'emulated' for models that Azure AI has not yet implemented tool calling for. This occurs by default for Llama models. For other models, use the `emulate_tools` model arg to force tool emulation:
+
+```bash
+inspect eval ctf.py -M emulate_tools=true
+```
+
+You can also use this option to disable tool emulation for Llama models with `emulate_tools=false`.
+
 ### AWS Bedrock {#aws-bedrock}
 
 [AWS Bedrock](https://aws.amazon.com/bedrock/) provides hosting of models from Anthropic as well as a wide variety of other open models. Note that all models on AWS Bedrock require that you [request model access](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html) before using them in a deployment (in some cases access is granted immediately, in other cases it could one or more days).

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/docs/workflow.qmd

@@ -170,6 +170,10 @@ There are several other command line options you can pass to eval. Here are some
 # limit to 10 samples
 $ inspect eval theory.py --limit 10
 
+# limit to specific sample id(s)
+$ inspect eval theory.py --sample-id 10
+$ insepct eval theory.py --sample_id 9,10
+
 # limit tokens
 $ inspect eval theory.py --max-tokens 128
 

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/pyproject.toml

@@ -129,7 +129,7 @@ dev = [
     "pytest-cov",
     "pytest-dotenv",
     "pytest-xdist",
-    "ruff==0.8.2", # match version specified in .pre-commit-config.yaml
+    "ruff==0.8.3", # match version specified in .pre-commit-config.yaml
     "textual-dev>=0.86.2",
     "types-PyYAML",
     "types-aiofiles",

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_cli/eval.py

@@ -12,7 +12,7 @@ from inspect_ai._util.constants import (
     DEFAULT_MAX_RETRIES,
 )
 from inspect_ai._util.file import filesystem
-from inspect_ai._util.samples import parse_samples_limit
+from inspect_ai._util.samples import parse_sample_id, parse_samples_limit
 from inspect_ai.log._file import log_file_info
 from inspect_ai.model import GenerateConfigArgs
 from inspect_ai.scorer._reducer import create_reducers
@@ -144,6 +144,12 @@ def eval_options(func: Callable[..., Any]) -> Callable[..., click.Context]:
         help="Limit samples to evaluate e.g. 10 or 10-20",
         envvar="INSPECT_EVAL_LIMIT",
     )
+    @click.option(
+        "--sample-id",
+        type=str,
+        help="Evaluate specific sample(s) (comma separated list of ids)",
+        envvar="INSPECT_EVAL_SAMPLE_ID",
+    )
     @click.option(
         "--epochs",
         type=int,
@@ -391,6 +397,7 @@ def eval_command(
     epochs: int | None,
     epochs_reducer: str | None,
     limit: str | None,
+    sample_id: str | None,
     max_retries: int | None,
     timeout: int | None,
     max_connections: int | None,
@@ -458,6 +465,7 @@ def eval_command(
         epochs=epochs,
         epochs_reducer=epochs_reducer,
         limit=limit,
+        sample_id=sample_id,
         message_limit=message_limit,
         token_limit=token_limit,
         time_limit=time_limit,
@@ -543,6 +551,7 @@ def eval_set_command(
     epochs: int | None,
     epochs_reducer: str | None,
     limit: str | None,
+    sample_id: str | None,
     max_retries: int | None,
     timeout: int | None,
     max_connections: int | None,
@@ -612,6 +621,7 @@ def eval_set_command(
         epochs=epochs,
         epochs_reducer=epochs_reducer,
         limit=limit,
+        sample_id=sample_id,
         message_limit=message_limit,
         token_limit=token_limit,
         time_limit=time_limit,
@@ -662,6 +672,7 @@ def eval_exec(
     epochs: int | None,
     epochs_reducer: str | None,
     limit: str | None,
+    sample_id: str | None,
     message_limit: int | None,
     token_limit: int | None,
     time_limit: int | None,
@@ -699,8 +710,9 @@ def eval_exec(
         else None
     )
 
-    # resolve range
+    # resolve range and sample id
     eval_limit = parse_samples_limit(limit)
+    eval_sample_id = parse_sample_id(sample_id)
 
     # resolve fail_on_error
     if no_fail_on_error is True:
@@ -734,6 +746,7 @@ def eval_exec(
             log_dir=log_dir,
             log_format=log_format,
             limit=eval_limit,
+            sample_id=eval_sample_id,
             epochs=eval_epochs,
             fail_on_error=fail_on_error,
             debug_errors=debug_errors,

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_display/core/config.py

@@ -24,6 +24,10 @@ def task_config(
             config_print.append(
                 f"{name}: {','.join([approver['name'] for approver in value['approvers']])}"
             )
+        elif name == "sample_id":
+            value = value if isinstance(value, list) else [value]
+            value = [str(v) for v in value]
+            config_print.append(f"{name}: {','.join(value)}")
         elif name not in ["limit", "model"]:
             config_print.append(f"{name}: {value}")
     values = ", ".join(config_print)

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_display/core/panel.py

@@ -112,7 +112,7 @@ def tasks_title(completed: int, total: int) -> str:
 def task_title(profile: TaskProfile, show_model: bool) -> str:
     eval_epochs = profile.eval_config.epochs or 1
     epochs = f" x {profile.eval_config.epochs}" if eval_epochs > 1 else ""
-    samples = f"{profile.samples//eval_epochs:,}{epochs} sample{'s' if profile.samples > 1 else ''}"
+    samples = f"{profile.samples//eval_epochs:,}{epochs} sample{'s' if profile.samples != 1 else ''}"
     title = f"{registry_unqualified_name(profile.name)} ({samples})"
     if show_model:
         title = f"{title}: {profile.model}"

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_display/textual/widgets/task_detail.py

@@ -63,6 +63,9 @@ class TaskDetail(Widget):
     def update_metrics(self, metrics: list[TaskDisplayMetric]) -> None:
         # Group by reducer then scorer within reducers
         self.metrics = metrics
+
+        # clear the existing computed reducers
+        self.by_reducer = {}
         for metric in metrics:
             reducer_group = (
                 self.by_reducer[metric.reducer]
@@ -85,6 +88,10 @@ class TaskDetail(Widget):
         if not self.grid.is_attached:
             return
 
+        # don't refresh the grid if there are no scores
+        if len(self.by_reducer) == 0:
+            return
+
         # Compute the row and column count
         row_count = len(self.by_reducer)
         col_count = len(next(iter(self.by_reducer.values())))
@@ -113,6 +120,7 @@ class TaskDetail(Widget):
         for remove in to_remove:
             task_metric = self.existing_metrics[remove]
             task_metric.remove()
+            del self.existing_metrics[remove]
 
         # add or update widgets with metrics
         for reducer, scorers in self.by_reducer.items():
@@ -183,24 +191,49 @@ class TaskMetrics(Widget):
         self.grid: Grid = Grid()
         self.value_widgets: dict[str, Static] = {}
 
+    def grid_id(self) -> str:
+        return f"{self.id}-grid"
+
     def compose(self) -> ComposeResult:
-        # Just yield a single DataTable widget
+        # Yield the title and base grid
         yield Center(self._title())
-        with Grid():
-            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)
-                )
-
-                yield Static(metric.name)
-                yield self.value_widgets[metric.name]
+        yield Grid(id=self.grid_id())
 
     def update(self, metrics: list[TaskMetric]) -> None:
+        self.metrics = metrics
+
+        # We assume that generally the initial metric names will
+        # always match future updates (so we can just update values in line)
+        # but if an unrecognized metric appears on the scene, just
+        # recompute the whole grid
+        need_recompute = False
         for metric in metrics:
-            widget = self.value_widgets[metric.name]
-            widget.update(content=f"{metric.value:,.3f}")
+            widget = self.value_widgets.get(metric.name)
+            if widget:
+                # Just update the values themselves
+                widget.update(content=f"{metric.value:,.3f}")
+            else:
+                # Don't have a widget for this, recompute the whole grid
+                need_recompute = True
+                break
+
+        if need_recompute:
+            self.recompute_grid()
+
+    def on_mount(self) -> None:
+        self.recompute_grid()
+
+    def recompute_grid(self) -> None:
+        grid = self.query_one(f"#{self.grid_id()}")
+
+        grid.remove_children()
+        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))
+
+            grid.mount(Static(metric.name))
+            grid.mount(self.value_widgets[metric.name])
 
     def _title(self) -> Widget:
         if self.scorer is None:

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_display/textual/widgets/transcript.py

@@ -10,10 +10,10 @@ from textual.widget import Widget
 from textual.widgets import Static
 
 from inspect_ai._util.content import ContentText
-from inspect_ai._util.format import format_function_call
 from inspect_ai._util.rich import lines_display
 from inspect_ai._util.transcript import (
     set_transcript_markdown_options,
+    transcript_function,
     transcript_markdown,
     transcript_separator,
 )
@@ -36,6 +36,7 @@ from inspect_ai.log._transcript import (
 from inspect_ai.model._chat_message import ChatMessage, ChatMessageUser
 from inspect_ai.model._render import messages_preceding_assistant
 from inspect_ai.tool._tool import ToolResult
+from inspect_ai.tool._tool_transcript import transcript_tool_call
 
 
 class TranscriptView(ScrollableContainer):
@@ -195,16 +196,7 @@ def render_tool_event(event: ToolEvent) -> list[EventDisplay]:
             display.extend(render_event(e) or [])
 
     # render the call
-    content: list[RenderableType] = []
-    if event.view:
-        if event.view.title:
-            content.append(Text.from_markup(f"[bold]{event.view.title}[/bold]\n"))
-        if event.view.format == "markdown":
-            content.append(transcript_markdown(event.view.content))
-        else:
-            content.append(event.view.content)
-    else:
-        content.append(render_function_call(event.function, event.arguments))
+    content = transcript_tool_call(event)
 
     # render the output
     if isinstance(event.result, list):
@@ -266,7 +258,7 @@ def render_subtask_event(event: SubtaskEvent) -> list[EventDisplay]:
         for e in event.events:
             display.extend(render_event(e) or [])
 
-    content: list[RenderableType] = [render_function_call(event.name, event.input)]
+    content: list[RenderableType] = [transcript_function(event.name, event.input)]
     if event.result:
         content.append(Text())
         if isinstance(event.result, str | int | float | bool | None):
@@ -309,11 +301,6 @@ def render_error_event(event: ErrorEvent) -> EventDisplay:
     return EventDisplay("error", event.error.traceback.strip())
 
 
-def render_function_call(function: str, arguments: dict[str, Any]) -> RenderableType:
-    call = format_function_call(function, arguments)
-    return transcript_markdown("```python\n" + call + "\n```\n")
-
-
 def render_as_json(json: Any) -> RenderableType:
     return transcript_markdown(
         "```json\n"

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_eval/eval.py

@@ -61,6 +61,7 @@ def eval(
     log_dir: str | None = None,
     log_format: Literal["eval", "json"] | None = None,
     limit: int | tuple[int, int] | None = None,
+    sample_id: str | int | list[str | int] | None = None,
     epochs: int | Epochs | None = None,
     fail_on_error: bool | float | None = None,
     debug_errors: bool | None = None,
@@ -110,6 +111,7 @@ def eval(
            to "eval", the native high-performance format).
         limit (int | tuple[int, int] | None): Limit evaluated samples
            (defaults to all samples).
+        sample_id (str | int | list[str | int] | None): Evaluate specific sample(s) from the dataset.
         epochs (int | Epochs | None): Epochs to repeat samples for and optional score
            reducer function(s) used to combine sample scores (defaults to "mean")
         fail_on_error (bool | float | None): `True` to fail on first sample error
@@ -163,6 +165,7 @@ def eval(
             log_dir=log_dir,
             log_format=log_format,
             limit=limit,
+            sample_id=sample_id,
             epochs=epochs,
             fail_on_error=fail_on_error,
             debug_errors=debug_errors,
@@ -198,6 +201,7 @@ async def eval_async(
     log_dir: str | None = None,
     log_format: Literal["eval", "json"] | None = None,
     limit: int | tuple[int, int] | None = None,
+    sample_id: str | int | list[str | int] | None = None,
     epochs: int | Epochs | None = None,
     fail_on_error: bool | float | None = None,
     debug_errors: bool | None = None,
@@ -245,8 +249,9 @@ async def eval_async(
             (defaults to file log in ./logs directory).
         log_format (Literal["eval", "json"] | None): Format for writing log files (defaults
            to "eval", the native high-performance format).
-        limit (int | tuple[int, int] | None): Limit evaluated samples
+        limit (str | int | list[str | int] | None): Limit evaluated samples
             (defaults to all samples).
+        sample_id (str | list[str] | None): Evaluate specific sample(s) from the dataset.
         epochs (int | Epochs | None): Epochs to repeat samples for and optional score
             reducer function(s) used to combine sample scores (defaults to "mean")
         fail_on_error (bool | float | None): `True` to fail on first sample error
@@ -335,6 +340,10 @@ async def eval_async(
         # resolve solver
         solver = chain(solver) if isinstance(solver, list) else solver
 
+        # ensure consistency of limit and sample_id
+        if sample_id is not None and limit is not None:
+            raise ValueError("You cannot specify both sample_id and limit.")
+
         # resolve epochs
         if isinstance(epochs, int):
             epochs = Epochs(epochs)
@@ -345,6 +354,7 @@ async def eval_async(
         epochs_reducer = epochs.reducer if epochs else None
         eval_config = EvalConfig(
             limit=limit,
+            sample_id=sample_id,
             epochs=epochs.epochs if epochs else None,
             epochs_reducer=reducer_log_names(epochs_reducer)
             if epochs_reducer
@@ -642,6 +652,7 @@ async def eval_retry_async(
         task_args = eval_log.eval.task_args
         tags = eval_log.eval.tags
         limit = eval_log.eval.config.limit
+        sample_id = eval_log.eval.config.sample_id
         epochs = (
             Epochs(eval_log.eval.config.epochs, eval_log.eval.config.epochs_reducer)
             if eval_log.eval.config.epochs
@@ -699,6 +710,7 @@ async def eval_retry_async(
                 log_dir=log_dir,
                 log_format=log_format,
                 limit=limit,
+                sample_id=sample_id,
                 epochs=epochs,
                 fail_on_error=fail_on_error,
                 debug_errors=debug_errors,

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_eval/evalset.py

@@ -65,6 +65,7 @@ def eval_set(
     log_level_transcript: str | None = None,
     log_format: Literal["eval", "json"] | None = None,
     limit: int | tuple[int, int] | None = None,
+    sample_id: str | int | list[str | int] | None = None,
     epochs: int | Epochs | None = None,
     fail_on_error: bool | float | None = None,
     debug_errors: bool | None = None,
@@ -125,6 +126,7 @@ def eval_set(
           log files (defaults to "eval", the native high-performance format).
         limit (int | tuple[int, int] | None): Limit evaluated samples
            (defaults to all samples).
+        sample_id (str | int | list[str | int] | None): Evaluate specific sample(s) from the dataset.
         epochs (int | Epochs | None): Epochs to repeat samples for and optional score
            reducer function(s) used to combine sample scores (defaults to "mean")
         fail_on_error (bool | float | None): `True` to fail on first sample error
@@ -181,6 +183,7 @@ def eval_set(
             log_dir=log_dir,
             log_format=log_format,
             limit=limit,
+            sample_id=sample_id,
             epochs=epochs,
             fail_on_error=fail_on_error,
             debug_errors=debug_errors,

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_eval/task/log.py

@@ -83,7 +83,12 @@ class TaskLogger:
         # ensure that the dataset has sample ids and record them
         sample_ids = cast(
             list[int | str],
-            [sample.id for sample in slice_dataset(dataset, eval_config.limit)],
+            [
+                sample.id
+                for sample in slice_dataset(
+                    dataset, eval_config.limit, eval_config.sample_id
+                )
+            ],
         )
 
         # create eval spec

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_eval/task/run.py

@@ -162,6 +162,7 @@ async def task_run(options: TaskRunOptions) -> EvalLog:
             dataset=task.dataset,
             model_name=model_name,
             limit=config.limit,
+            sample_id=config.sample_id,
             epochs=epochs,
             log_images=log_images,
             message_limit=config.message_limit,
@@ -748,13 +749,14 @@ async def resolve_dataset(
     dataset: Dataset,
     model_name: ModelName,
     limit: int | tuple[int, int] | None,
+    sample_id: str | int | list[str | int] | None,
     epochs: int,
     log_images: bool,
     message_limit: int | None,
     token_limit: int | None,
 ) -> tuple[Dataset, list[Sample], list[TaskState]]:
-    # apply limit to dataset
-    dataset = slice_dataset(dataset, limit)
+    # slice dataset
+    dataset = slice_dataset(dataset, limit, sample_id)
 
     # apply epochs (deepcopy the samples so they remain independent)
     samples: list[Sample] = []

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_eval/task/util.py

@@ -39,10 +39,19 @@ def task_file(task: Task, relative: bool = False) -> str | None:
 def slice_dataset(
     dataset: Dataset,
     limit: int | tuple[int, int] | None,
+    sample_id: str | int | list[str | int] | None,
 ) -> Dataset:
-    dataset_limit = (
-        slice(0, len(dataset))
-        if limit is None
-        else (slice(*limit) if isinstance(limit, tuple) else slice(0, limit))
-    )
-    return dataset[dataset_limit]
+    def normalise(id: str | int | None) -> str:
+        return id if isinstance(id, str) else str(id).zfill(20)
+
+    if sample_id is not None:
+        sample_id = sample_id if isinstance(sample_id, list) else [sample_id]
+        sample_id = [normalise(id) for id in sample_id]
+        return dataset.filter(lambda sample: normalise(sample.id) in sample_id)
+    else:
+        dataset_limit = (
+            slice(0, len(dataset))
+            if limit is None
+            else (slice(*limit) if isinstance(limit, tuple) else slice(0, limit))
+        )
+        return dataset[dataset_limit]

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_util/logger.py

@@ -1,5 +1,6 @@
 import os
 from logging import (
+    DEBUG,
     INFO,
     WARNING,
     FileHandler,
@@ -129,7 +130,7 @@ def init_logger(
     # init logging handler on demand
     global _logHandler
     if not _logHandler:
-        _logHandler = LogHandler(min(HTTP, levelno), transcript_levelno)
+        _logHandler = LogHandler(min(DEBUG, levelno), transcript_levelno)
         getLogger().addHandler(_logHandler)
 
     # establish default capture level
@@ -139,6 +140,7 @@ def init_logger(
     getLogger().setLevel(capture_level)
     getLogger(PKG_NAME).setLevel(capture_level)
     getLogger("httpx").setLevel(capture_level)
+    getLogger("botocore").setLevel(DEBUG)
 
     # set the levelno on the global handler
     _logHandler.display_level = levelno
@@ -154,7 +156,13 @@ def notify_logger_record(record: LogRecord, write: bool) -> None:
     if write:
         transcript()._event(LoggerEvent(message=LoggingMessage.from_log_record(record)))
     global _rate_limit_count
-    if record.levelno <= INFO and "429" in record.getMessage():
+    if (record.levelno <= INFO and "429" in record.getMessage()) or (
+        record.levelno == DEBUG
+        # See https://boto3.amazonaws.com/v1/documentation/api/latest/guide/retries.html#validating-retry-attempts
+        # for boto retry logic / log messages (this is tracking standard or adapative retries)
+        and "botocore.retries.standard" in record.name
+        and "Retry needed, retrying request after delay of:" in record.getMessage()
+    ):
         _rate_limit_count = _rate_limit_count + 1
 
 

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_util/samples.py

@@ -7,3 +7,10 @@ def parse_samples_limit(limit: str | None) -> int | tuple[int, int] | None:
             return (limit_split[0] - 1, limit_split[1])
     else:
         return None
+
+
+def parse_sample_id(sample_id: str | None) -> list[str] | None:
+    if sample_id is not None:
+        return [id.strip() for id in sample_id.split(",")]
+    else:
+        return None

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_util/transcript.py

@@ -1,4 +1,5 @@
 import html
+from typing import Any
 
 from rich.align import AlignMethod
 from rich.box import ROUNDED, Box
@@ -8,6 +9,8 @@ from rich.panel import Panel
 from rich.rule import Rule
 from rich.text import Text
 
+from .format import format_function_call
+
 
 def transcript_code_theme() -> str:
     return "github-dark"
@@ -81,6 +84,11 @@ def transcript_separator(title: str, color: str) -> RenderableType:
     return Rule(title=title, style=f"{color} bold", align="center", end="\n\n")
 
 
+def transcript_function(function: str, arguments: dict[str, Any]) -> RenderableType:
+    call = format_function_call(function, arguments)
+    return transcript_markdown("```python\n" + call + "\n```\n")
+
+
 LINE = Box(" ── \n" "    \n" "    \n" "    \n" "    \n" "    \n" "    \n" "    \n")
 
 DOTTED = Box(" ·· \n" "    \n" "    \n" "    \n" "    \n" "    \n" "    \n" "    \n")

{inspect_ai-0.3.50 → inspect_ai-0.3.52}/src/inspect_ai/_view/www/dist/assets/index.js

@@ -20225,7 +20225,7 @@ const metadataViewsForSample = (id, sample) => {
   }
   return sampleMetadatas;
 };
-const SampleSummary = ({ id, sample, style, sampleDescriptor }) => {
+const SampleSummary = ({ parent_id, sample, style, sampleDescriptor }) => {
   const input = (sampleDescriptor == null ? void 0 : sampleDescriptor.messageShape.normalized.input) > 0 ? Math.max(0.15, sampleDescriptor.messageShape.normalized.input) : 0;
   const target = (sampleDescriptor == null ? void 0 : sampleDescriptor.messageShape.normalized.target) > 0 ? Math.max(0.15, sampleDescriptor.messageShape.normalized.target) : 0;
   const answer = (sampleDescriptor == null ? void 0 : sampleDescriptor.messageShape.normalized.answer) > 0 ? Math.max(0.15, sampleDescriptor.messageShape.normalized.answer) : 0;
@@ -20246,7 +20246,7 @@ const SampleSummary = ({ id, sample, style, sampleDescriptor }) => {
   const columns = [];
   columns.push({
     label: "Id",
-    value: id,
+    value: sample.id,
     size: `${idSize}em`
   });
   columns.push({
@@ -20299,7 +20299,7 @@ const SampleSummary = ({ id, sample, style, sampleDescriptor }) => {
   });
   return m$1`
     <div
-      id=${`sample-heading-${id}`}
+      id=${`sample-heading-${parent_id}`}
       style=${{
     display: "grid",
     gridTemplateColumns: `${columns.map((col) => {
@@ -25449,22 +25449,35 @@ const createsSamplesDescriptor = (scorers, samples, epochs, selectedScore) => {
         if (!sample || !sample.scores) {
           return [];
         }
-        scorers.map((score2) => {
+        const scoreNames = scorers.map((score2) => {
           return score2.name;
         });
         const sampleScorer = sample.scores[scorer];
         const scoreVal = sampleScorer.value;
         if (typeof scoreVal === "object") {
           const names = Object.keys(scoreVal);
-          const scores = names.map((name) => {
-            return {
-              name,
-              rendered: () => {
-                return scoreDescriptor.render(scoreVal[name]);
+          if (names.find((name) => {
+            return scoreNames.includes(name);
+          })) {
+            const scores = names.map((name) => {
+              return {
+                name,
+                rendered: () => {
+                  return scoreDescriptor.render(scoreVal[name]);
+                }
+              };
+            });
+            return scores;
+          } else {
+            return [
+              {
+                name: scorer,
+                rendered: () => {
+                  return scoreDescriptor.render(scoreVal);
+                }
               }
-            };
-          });
-          return scores;
+            ];
+          }
         } else {
           return [
             {