inspect-ai 0.3.11__py3-none-any.whl → 0.13.3__py3-none-any.whl

inspect_ai/__init__.py

@@ -6,7 +6,7 @@ from inspect_ai._eval.eval import eval, eval_async, eval_retry, eval_retry_async
 from inspect_ai._eval.list import list_tasks
 from inspect_ai._eval.registry import task
 from inspect_ai._eval.score import score, score_async
-from inspect_ai._eval.types import Task, TaskInfo, Tasks
+from inspect_ai._eval.task import Task, TaskInfo, Tasks
 from inspect_ai._util.constants import PKG_NAME
 
 __version__ = importlib_version(PKG_NAME)

inspect_ai/_cli/list.py

@@ -11,7 +11,7 @@ from typing_extensions import Unpack
 from inspect_ai._cli.common import CommonOptions, common_options, resolve_common_options
 from inspect_ai._cli.util import parse_cli_args
 from inspect_ai._eval.list import list_tasks
-from inspect_ai._eval.types import TaskInfo
+from inspect_ai._eval.task import TaskInfo
 from inspect_ai.log import list_eval_logs
 
 

inspect_ai/_eval/eval.py

@@ -26,10 +26,10 @@ from inspect_ai.solver import Solver
 from inspect_ai.util._context import init_async_context
 
 from .loader import resolve_tasks
+from .task import Tasks, TaskSpec
 from .task.log import TaskLogger
 from .task.run import task_run
 from .task.util import task_file, task_run_dir
-from .types import Tasks, TaskSpec
 
 log = logging.getLogger(__name__)
 

inspect_ai/_eval/list.py

@@ -8,7 +8,7 @@ from typing import Any, Callable
 from inspect_ai._util.error import exception_message
 from inspect_ai._util.file import file
 
-from .types import TaskInfo
+from .task import TaskInfo
 
 logger = getLogger(__name__)
 

inspect_ai/_eval/loader.py

@@ -18,8 +18,8 @@ from inspect_ai.model import Model, ModelName
 
 from .list import task_files
 from .registry import task_create
+from .task import Task, TaskInfo, Tasks
 from .task.constants import TASK_FILE_ATTR, TASK_RUN_DIR_ATTR
-from .types import Task, TaskInfo, Tasks
 
 
 def resolve_tasks(

inspect_ai/_eval/registry.py

@@ -14,7 +14,7 @@ from inspect_ai._util.registry import (
 )
 from inspect_ai.model import ModelName
 
-from .types import Task
+from .task import Task
 
 MODEL_PARAM = "model"
 

inspect_ai/_eval/score.py

@@ -17,9 +17,9 @@ from inspect_ai.model import ModelName
 from inspect_ai.scorer import Metric, Score, Scorer, Target
 from inspect_ai.solver import TaskState
 
+from .task import Task
 from .task.results import eval_results
 from .task.util import task_run_dir
-from .types import Task
 
 
 def score(log: EvalLog, scorer: Scorer) -> EvalLog:

inspect_ai/_eval/task/__init__.py

@@ -0,0 +1,3 @@
+from .task import Task, TaskInfo, TaskSpec, Tasks  # noqa: I001, F401
+
+__all__ = ["Task", "TaskInfo", "TaskSpec", "Tasks"]

inspect_ai/_eval/task/run.py

@@ -23,6 +23,7 @@ from inspect_ai.log import (
     EvalConfig,
     EvalError,
     EvalLog,
+    EvalResults,
     EvalStats,
 )
 from inspect_ai.log._log import eval_error
@@ -34,7 +35,7 @@ from inspect_ai.model import (
 from inspect_ai.scorer import Score, Scorer, Target
 from inspect_ai.solver import Generate, Plan, Solver, TaskState
 
-from ..types import Task
+from ..task import Task
 from .generate import task_generate
 from .images import samples_with_base64_images, states_with_base64_images
 from .log import TaskLogger, collect_eval_data, log_output, log_plan
@@ -101,7 +102,9 @@ async def task_run(
         plan = (
             plan
             if isinstance(plan, Plan)
-            else Plan(plan) if plan is not None else task.plan
+            else Plan(plan)
+            if plan is not None
+            else task.plan
         )
         score = score and task.scorer is not None
         scorer: Scorer | None = task.scorer if (score and task.scorer) else None
@@ -132,7 +135,6 @@ async def task_run(
                     len(plan.steps) + (1 if plan.finish else 0) + (1)  # scorer
                 )
                 with td.progress(total=total_steps) as p:
-
                     # forward progress
                     def progress() -> None:
                         p.update(1)
@@ -195,6 +197,8 @@ async def task_run(
                         metrics=task.metrics,
                     )
                     logger.log_results(results)
+                else:
+                    results = EvalResults()
 
                 # collect eval data
                 collect_eval_data(stats, logger)
@@ -295,7 +299,6 @@ async def resolve_dataset(
     epochs: int,
     log_images: bool,
 ) -> tuple[Dataset, list[Sample], list[TaskState]]:
-
     # apply limit to dataset
     dataset_limit = (
         slice(0, len(dataset))

inspect_ai/_eval/task/util.py

@@ -7,7 +7,7 @@ from inspect_ai.dataset import Sample
 from inspect_ai.model import ChatMessage, ChatMessageUser
 from inspect_ai.solver import TaskState
 
-from ..types import Task
+from ..task import Task
 from .constants import TASK_FILE_ATTR, TASK_RUN_DIR_ATTR
 
 

inspect_ai/_view/www/App.mjs

@@ -20,6 +20,7 @@ import { WorkSpace } from "./src/workspace/WorkSpace.mjs";
 
 export function App() {
   const [selected, setSelected] = useState(-1);
+  const [pendingLog, setPendingLog] = useState(undefined);
   const [logs, setLogs] = useState({ log_dir: "", files: [] });
   const [logHeaders, setLogHeaders] = useState({});
   const [offcanvas, setOffcanvas] = useState(false);
@@ -126,24 +127,32 @@ export function App() {
   // Ensure that we have a selected index when there is are 
   // new logs
   useEffect(() => {
-    setSelected(0);
-  }, [logs])
+    if (logs && pendingLog) {
+      const index = logs.files.findIndex((val) => {
+        return pendingLog.endsWith(val.name);
+      });
+      if (index > -1) {
+        setSelected(index);    
+      }
+      setPendingLog(undefined);
+    }
+  }, [logs, pendingLog])
   
   // listen for updateState messages from vscode
   useEffect(() => {
-    const onMessage = (e) => {
+    const onMessage = async (e) => {
       switch (e.data.type || e.data.message) {
         case "updateState": {
           if (e.data.url) {
-
             const index = logs.files.findIndex((val) => {
-              return val.name.endsWith(e.data.url);
+              return e.data.url.endsWith(val.name);
             });
             if (index > -1) {
               // Select the correct index
               setSelected(index);    
             } else {
-              // TODO: Error
+              await loadLogs();
+              setPendingLog(e.data.url);
             }
           }
         }
@@ -153,7 +162,7 @@ export function App() {
     return () => {
       window.removeEventListener("message", onMessage);
     };
-  }, [setCurrentLog]);
+  }, [logs, setCurrentLog, setPendingLog]);
 
   useEffect(async () => {
     // See whether a specific task_file has been passed.
@@ -176,6 +185,9 @@ export function App() {
     // initial fetch of logs
     await load();
 
+    // Select the first log
+    setSelected(0);
+
     // poll every 1s for events
     setInterval(() => {
       api.client_events().then((events) => {

inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs

@@ -24,6 +24,7 @@ export const samplesDescriptor = (samples, epochs, context) => {
   const uniqScoreValues = [
     ...new Set(
       samples
+        .filter(sample => !!sample.score)
         .map((sample) => sample.score.value)
         .filter((value) => {
           return value !== null;

inspect_ai/_view/www/src/samples/SamplesTab.mjs

@@ -92,7 +92,7 @@ export const SamplesTab = (props) => {
   // Focus the sample list
   useEffect(() => {
     const listEl = sampleListRef.current;
-    if (listEl) {
+    if (listEl && listEl.base) {
       listEl.base.focus();
     }
   }, [items]);

inspect_ai/solver/__init__.py

@@ -6,7 +6,8 @@ from ._prompt import (
     prompt_template,
     system_message,
 )
-from ._solver import Generate, Solver, TaskState, generate, solver
+from ._solver import Generate, Solver, generate, solver
+from ._task_state import TaskState
 from ._tool.tool import Tool, tool
 from ._tool.use_tools import use_tools
 from ._tool.web_search import web_search

inspect_ai/solver/_critique.py

@@ -5,7 +5,8 @@ from inspect_ai.model import (
 )
 from inspect_ai.util import resource
 
-from ._solver import Generate, Solver, TaskState, solver
+from ._solver import Generate, Solver, solver
+from ._task_state import TaskState
 
 
 @solver

inspect_ai/solver/_multiple_choice.py

@@ -4,7 +4,8 @@ from random import Random
 
 from inspect_ai.util import resource
 
-from ._solver import Generate, Solver, TaskState, solver
+from ._solver import Generate, Solver, solver
+from ._task_state import TaskState
 
 logger = logging.getLogger(__name__)
 

inspect_ai/solver/_plan.py

@@ -11,7 +11,8 @@ from inspect_ai._util.registry import (
     registry_tag,
 )
 
-from ._solver import Solver, TaskState
+from ._solver import Solver
+from ._task_state import TaskState
 
 
 class Plan:

inspect_ai/solver/_prompt.py

@@ -3,7 +3,8 @@ from typing import Any
 from inspect_ai.model import ChatMessageSystem
 from inspect_ai.util import resource
 
-from ._solver import Generate, Solver, TaskState, solver
+from ._solver import Generate, Solver, solver
+from ._task_state import TaskState
 from ._util import append_system_message
 
 

inspect_ai/solver/_solver.py

@@ -18,110 +18,9 @@ from inspect_ai._util.registry import (
     registry_name,
     registry_tag,
 )
-from inspect_ai.model import (
-    ChatMessage,
-    ChatMessageUser,
-    GenerateConfigArgs,
-    ModelName,
-    ModelOutput,
-    ToolChoice,
-)
-
-from ._tool.tool import Tool
-
+from inspect_ai.model import GenerateConfigArgs
 
-class TaskState:
-    def __init__(
-        self,
-        model: ModelName,
-        sample_id: int | str,
-        epoch: int,
-        input: str | list[ChatMessage],
-        choices: list[str] | None,
-        messages: list[ChatMessage],
-        tools: list[Tool] = [],
-        tool_choice: ToolChoice | None = None,
-        output: ModelOutput | None = None,
-        completed: bool = False,
-        metadata: dict[str, Any] = {},
-    ) -> None:
-        self._model = model
-
-        self.sample_id = sample_id
-        """Unique id for sample."""
-
-        self.epoch = epoch
-        """Epoch number for sample."""
-
-        self._input = input
-
-        self.choices = choices
-        """Sample choices."""
-
-        self.messages = messages
-        """Chat conversation history for sample."""
-
-        self.tools = tools
-        """Tools available to the model."""
-
-        self.tool_choice = tool_choice
-        """Tool choice directive."""
-
-        self.output = output if output else ModelOutput(model=str(model), choices=[])
-        """Model output."""
-
-        self.completed = completed
-        """Flag to indicate that the solver loop should terminate."""
-
-        self.metadata = metadata
-        """Additional task state metadata."""
-
-    @property
-    def model(self) -> ModelName:
-        """Name of model being evaluated."""
-        return self._model
-
-    @property
-    def input(self) -> str | list[ChatMessage]:
-        """Sample input."""
-        return self._input
-
-    @property
-    def input_text(self) -> str:
-        """Sample input as text."""
-        if isinstance(self._input, str):
-            return self._input
-        else:
-            input = next(
-                (message.text for message in self._input if message.role == "user"),
-                None,
-            )
-            if input:
-                return input
-            else:
-                raise ValueError(
-                    "input_text requested from TaskState but none available"
-                )
-
-    @property
-    def user_prompt(self) -> ChatMessageUser:
-        """User prompt for this state.
-
-        Tasks are very general and can have may types of inputs.
-        However, in many cases solvers assume they can interact with
-        the state as a "chat" in a predictable fashion (e.g. prompt
-        engineering solvers). This property enables easy read and
-        write access to the user chat prompt. Raises an
-        exception if there is no user prompt
-
-        Returns:
-           First user `ChatMessage` in the task state.
-        """
-        prompt = next((m for m in self.messages if m.role == "user"), None)
-        if prompt:
-            return prompt
-        else:
-            raise ValueError("user_prompt requested from TaskState but none available")
+from ._task_state import TaskState
 
 
 @runtime_checkable

inspect_ai/solver/_task_state.py

@@ -0,0 +1,145 @@
+from typing import Any
+
+from inspect_ai.model import (
+    ChatMessage,
+    ChatMessageUser,
+    ModelName,
+    ModelOutput,
+    ToolChoice,
+)
+
+from ._tool.tool import Tool
+
+
+class TaskState:
+    """
+    The `TaskState` represents the internal state of the `Task` being run for a single `Sample`.
+
+    It's a mutable object that is updated by each solver during a sample's
+    evaluation. It allows us to maintain things like the message history between
+    the running `Task` and the model, the tools available to the model, the
+    final output of the model and whether or not it's completed yet.
+    """
+
+    def __init__(
+        self,
+        model: ModelName,
+        sample_id: int | str,
+        epoch: int,
+        input: str | list[ChatMessage],
+        choices: list[str] | None,
+        messages: list[ChatMessage],
+        tools: list[Tool] = [],
+        tool_choice: ToolChoice | None = None,
+        output: ModelOutput | None = None,
+        completed: bool = False,
+        metadata: dict[str, Any] = {},
+    ) -> None:
+        self._model = model
+        """Model name used for this task."""
+
+        self.sample_id = sample_id
+        """Unique id for sample."""
+
+        self.epoch = epoch
+        """Epoch number for sample."""
+
+        self._input = input
+        """
+        The original input from the `Sample` for this `TaskState`.
+
+        Should be treated as immutable and not changed during the run, so that
+        it can be referenced or checked wherever needed. Access through `input`
+        or `input_text` only
+        """
+
+        self.choices = choices
+        """
+        List of choices for the sample, specifically used by the `multiple_choice` scorer.
+
+        For example, if the sample was a multiple choice question like "What is
+        the capital of France? A) Paris B) London C) Berlin", we would store the
+        possible answers here.
+        """
+
+        self.messages = messages
+        """
+        Chat conversation history for sample.
+
+        This will generally get appended to every time a `generate` call is made
+        to the model. Useful for both debug and for solvers/scorers to assess
+        model performance or choose the next step.
+        """
+
+        self.tools = tools
+        """Tools available to the model."""
+
+        self.tool_choice = tool_choice
+        """Tool choice directive."""
+
+        self.output = output if output else ModelOutput(model=str(model), choices=[])
+        """
+        The 'final' model output once we've completed all solving.
+
+        For simple evals this may just be the last `message` from the
+        conversation history, but more complex solvers may generate this in
+        different ways depending on what solvers are used..
+        """
+
+        self.completed = completed
+        """Flag to indicate that the solver loop should terminate."""
+
+        self.metadata = metadata
+        """Additional task state metadata."""
+
+    @property
+    def model(self) -> ModelName:
+        """Name of model being evaluated."""
+        return self._model
+
+    @property
+    def input(self) -> str | list[ChatMessage]:
+        """Input from the `Sample`, should be considered immutable."""
+        return self._input
+
+    @property
+    def input_text(self) -> str:
+        """
+        Convenience function for accessing the initial input from the `Sample` as a string.
+
+        If the `input` is a `list[ChatMessage]`, this will return the text from
+        the first chat message
+        """
+        if isinstance(self._input, str):
+            return self._input
+        else:
+            input = next(
+                (message.text for message in self._input if message.role == "user"),
+                None,
+            )
+            if input:
+                return input
+            else:
+                raise ValueError(
+                    "input_text requested from TaskState but none available"
+                )
+
+    @property
+    def user_prompt(self) -> ChatMessageUser:
+        """User prompt for this state.
+
+        Tasks are very general and can have may types of inputs.
+        However, in many cases solvers assume they can interact with
+        the state as a "chat" in a predictable fashion (e.g. prompt
+        engineering solvers). This property enables easy read and
+        write access to the user chat prompt. Raises an
+        exception if there is no user prompt
+
+        Returns:
+           First user `ChatMessage` in the task state.
+        """
+        prompt = next((m for m in self.messages if m.role == "user"), None)
+        if prompt:
+            return prompt
+        else:
+            raise ValueError("user_prompt requested from TaskState but none available")

inspect_ai/solver/_tool/use_tools.py

@@ -3,7 +3,8 @@ from inspect_ai.model import (
     ToolChoice,
 )
 
-from .._solver import Generate, Solver, TaskState, solver
+from .._solver import Generate, Solver, solver
+from .._task_state import TaskState
 from .._util import append_system_message
 from .tool import Tool
 from .tool_def import tool_defs

{inspect_ai-0.3.11.dist-info → inspect_ai-0.13.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: inspect_ai
-Version: 0.3.11
+Version: 0.13.3
 Summary: Framework for large language model evaluations
 Author: UK AI Safety Institute
 License: MIT License

{inspect_ai-0.3.11.dist-info → inspect_ai-0.13.3.dist-info}/RECORD

@@ -1,10 +1,10 @@
-inspect_ai/__init__.py,sha256=eeAabo6ZQ6QvU3vVHOhJQK6h5sQsaqYqLNaoPIp_KIU,672
+inspect_ai/__init__.py,sha256=laGXMK1BIoOC_x2D31Cmbs_3c335exZL0FByjAqRO-I,671
 inspect_ai/__main__.py,sha256=oWX4YwDZDg3GS3-IG0yPGoSEOfSzWihELg7QmrUlxjM,67
 inspect_ai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 inspect_ai/_cli/common.py,sha256=CTEvRG2kAwsP7HxI5LjpdXh4RdVBwD0oMfD0Sn8Hl3A,1705
 inspect_ai/_cli/eval.py,sha256=LyW4Gc15Q_fBbvTXfJczhXyXAHi_MoImjrMkTLRRf9g,7886
 inspect_ai/_cli/info.py,sha256=K1SMxB8LiLONlwygU_BxcL1u2KJyYyFDpW4qkgMIcjE,1922
-inspect_ai/_cli/list.py,sha256=TZiIj-vP8rQ0qTueQniVYppFSIUSLb4asMQvOL01UQM,3736
+inspect_ai/_cli/list.py,sha256=IIkqT1HFqTaYPn3wNxHT656-wHwCHvGA57Rtol2Mc4Y,3735
 inspect_ai/_cli/main.py,sha256=PjIGgPVAky8eNBX5N_O2EX4TpgIdkmFY1uYtsgSCvkQ,1028
 inspect_ai/_cli/score.py,sha256=6FRjaqYWY1XHWFFwxZyQJW1cPnIhr7e3ZotTvSZyTgg,2859
 inspect_ai/_cli/util.py,sha256=nT3W7uUGzslNOUsK95lp6ZhPmTRfqb9i0aHJ3Bx_L2Q,576
@@ -13,19 +13,20 @@ inspect_ai/_display/__init__.py,sha256=PPuC3ydm-duhpdTShtMqVpFMr2BNndGmIIOy0A-Y-
 inspect_ai/_display/_display.py,sha256=Jd2LB49jMANpLFpgmRFeAa3pIm5MKvROp3bW1x-p2O4,1417
 inspect_ai/_display/logger.py,sha256=57_5ToLTozASQGdRNTIPt8vmAKF7u3pJnhoXbWY3oAs,2720
 inspect_ai/_display/rich.py,sha256=Qe357AMXqlPADmW0yZCLYcI1g_b1Gu7Sa5wTZFZbkYg,11708
-inspect_ai/_eval/eval.py,sha256=eGsAfuOLDZO0gmhpsgu0lyHZpLzbVfC_MV_2A63QyfM,17293
-inspect_ai/_eval/list.py,sha256=AyWokTJzmjjFx0AVNE4TK3NGH2SdzT9AcHPuKNjbTos,6049
-inspect_ai/_eval/loader.py,sha256=HBmXTXPdoVneIcjeBdfV7mgzB_91c9PdG_HNIGyRYFA,7881
-inspect_ai/_eval/registry.py,sha256=-JiFnGjbckYYS7jPOUGwhOrqnstLhT8cHHV2hTZXh3A,3999
-inspect_ai/_eval/score.py,sha256=g2ahIqUeLT9ilaiPqzNGcqcGpJ1fd7bLn7zQypRTrZg,4334
-inspect_ai/_eval/types.py,sha256=tqBrdnKEay9KQ3pcX07CW8REaQgEFSsbqWGFLmyNAV8,4073
+inspect_ai/_eval/eval.py,sha256=la4sfT6EYXtsTkJ2yMmF_b6Saz4q6vJYvhQ-26kpBlI,17292
+inspect_ai/_eval/list.py,sha256=YsPclTQKfiafUu27QEpCve6IjDAHtGA-fv-7_-tCctM,6048
+inspect_ai/_eval/loader.py,sha256=wKvMDdaMnLbJ3opKtKD8a8qrpE-y2huvv9p4EnXKF3Q,7880
+inspect_ai/_eval/registry.py,sha256=vTDPgKnGOGohl-IKQ-I2adkpXaQBCKuhA_cx78f3qMI,3998
+inspect_ai/_eval/score.py,sha256=g4sHYxg9ICfOfrS6ZjfWurMtNo0THRSIemONHyUfYKQ,4333
+inspect_ai/_eval/task/__init__.py,sha256=KCAhe9afbgLqolxXw80QSWwUZvfXSoqtjL8pyj-WUOg,123
 inspect_ai/_eval/task/constants.py,sha256=quAKMw-4-3xKd1T_KwXCZvHYoKRXt1ZGuaHbBcWJwnA,72
 inspect_ai/_eval/task/generate.py,sha256=53UNk9ReB7jf0FBwUkH_3IqSKg-vr5biQ3hLKbKwUic,3925
 inspect_ai/_eval/task/images.py,sha256=4bLN66eF2322r42FoINzGXMh1PTRjP_eCceZ8_msPeQ,2135
 inspect_ai/_eval/task/log.py,sha256=G0tj9QAB6BFTrSyuBEf6CFAZ6NpkLZfIWQUs1ZCYGNo,5255
 inspect_ai/_eval/task/results.py,sha256=eLfU7Dz4mmTGeKosBz4Iog1poakHdLgHkq2bs4Vw50s,2602
-inspect_ai/_eval/task/run.py,sha256=3If6SKM0vu1DD6eTrLvKeW8OgrjK8vxYGgHDw6f6iZY,11682
-inspect_ai/_eval/task/util.py,sha256=JOJR8PJF6xuLi5YxS4ZLz6xHBXZsmKmnG1SKwZtr74s,1174
+inspect_ai/_eval/task/run.py,sha256=SDJz4KKxLdpOLT8yjQAwqbkaptSuCDLfZidPdkhgsWg,11786
+inspect_ai/_eval/task/task.py,sha256=tqBrdnKEay9KQ3pcX07CW8REaQgEFSsbqWGFLmyNAV8,4073
+inspect_ai/_eval/task/util.py,sha256=_HcCOdjypVqgvLWakBgKx0MjrEhSWoKu7SX85DfxpiA,1173
 inspect_ai/_util/_async.py,sha256=OuK_dnZrnGi1W2-72sbpObO4Knr5Q_cLxJL1kTY12t8,276
 inspect_ai/_util/appdirs.py,sha256=6OsSZ8JcN6Nkp739CxCXfJwx_g9TqTfo7iAKDhtw7SY,355
 inspect_ai/_util/constants.py,sha256=ky9MfU9zrIvRX1PrlIr89npFtleSPoHevbYt4_t57go,445
@@ -53,7 +54,7 @@ inspect_ai/_view/schema.py,sha256=SlBJ75EsCjEtSzcVMuP2yu2cI3ju1Z3amUWaWbqNZjM,14
 inspect_ai/_view/view.py,sha256=Gm2p5A8dvwFM2NWkz8GPF7pqSmcC4X1dtXxPvkw0Q_M,9624
 inspect_ai/_view/www/.gitignore,sha256=8amgmyJs-OmKQoYgDF2evVwokkcHrDMXlH-OzwarFns,13
 inspect_ai/_view/www/App.css,sha256=VZtFGBwW_JsKtiC4WY0lLT-mcOlGYdxRvqm1-KyeSyQ,13934
-inspect_ai/_view/www/App.mjs,sha256=OI9imy6AlyX-92yzqcUNLcXA3B_hHrhennY5K_C2pp4,7195
+inspect_ai/_view/www/App.mjs,sha256=yEyCPMSH-wu7YMeNRTaZbdaSW3pvYYR_dF7jO_lQHWM,7605
 inspect_ai/_view/www/favicon.svg,sha256=b9AHYZaO2zBzeKH6G4PwXZMGGW_UxY0omKHam-c9MAs,1508
 inspect_ai/_view/www/index.html,sha256=HEUzotuCnX5GClv4feeppOhNrPN6CxXqp4N_Nsyp7oo,2158
 inspect_ai/_view/www/log-schema.json,sha256=pGcQiJEUqdzfsxKDqc-eEfRHXaP_FAVbWpUahpWaf9g,38118
@@ -113,8 +114,8 @@ inspect_ai/_view/www/src/samples/SampleDialog.mjs,sha256=ygslG6f8QOzRAwvRiSsKrPW
 inspect_ai/_view/www/src/samples/SampleDisplay.mjs,sha256=KZZB2YZkoSPDKK5facTwrlUccc23xqfsXO_W67QXN-Q,6525
 inspect_ai/_view/www/src/samples/SampleList.mjs,sha256=05TDU3dZFF1AOXDdtnddSNS6Y0qJDFtexFiDy4GnO-M,6598
 inspect_ai/_view/www/src/samples/SampleScoreView.mjs,sha256=Pm3rAV-W2dJ56aFxaxWD7ooaVJMbbSsTPe113wfFOPM,2989
-inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs,sha256=F4T_zxGQgaMj9HTAu2mhR2zMH91hGlVJR8lBezluXbo,7712
-inspect_ai/_view/www/src/samples/SamplesTab.mjs,sha256=GDg4fdfDrDN4gungaFcWrKuWicWSJB1NnGIV64P3Ctc,8514
+inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs,sha256=itfKTMAds_Y7cLjFJqzs--j3x28dlSH_3oW1QhbZxeQ,7754
+inspect_ai/_view/www/src/samples/SamplesTab.mjs,sha256=XSONY82wL02cyz9jye5osaJyd1U55zMvYA4mRK89Spg,8529
 inspect_ai/_view/www/src/samples/SamplesTools.mjs,sha256=A9qHXdMmFAfhGP2ceMxbmyWJBhWVKbi3qfNM3gGPDR0,854
 inspect_ai/_view/www/src/samples/tools/EpochFilter.mjs,sha256=FMWN67tPNcWTtqd8qPbaFWtsBBzP9013ZhFCfGsajNQ,775
 inspect_ai/_view/www/src/samples/tools/SampleFilter.mjs,sha256=f1FZBuhuFB_HUD4HoEASoY1cY4GUHIa0ZK9cAV_Hz4w,4834
@@ -177,16 +178,17 @@ inspect_ai/scorer/_metrics/__init__.py,sha256=NF9j0SoDIsGaf3Nl6pzGQYuycAc3gE-1af
 inspect_ai/scorer/_metrics/accuracy.py,sha256=U8H0iwA3qzqxanaRfYhhMmOV915VR6fbYTHNHyYES6g,943
 inspect_ai/scorer/_metrics/mean.py,sha256=gUMPBiWwnki9mYsEGVvme78dJCHqGoFVAEA9k7JHJ2E,555
 inspect_ai/scorer/_metrics/std.py,sha256=uwJW4V2NVDUqeyyn0rlHwguH7Z4jocYO_y7loLbqcbM,1250
-inspect_ai/solver/__init__.py,sha256=L8F7CJcS0u1CTvHmOihhJZ8nDcchd2AZzkPipRWg-bk,671
-inspect_ai/solver/_critique.py,sha256=0IK-iYyt8tN1C8la6lv-1syfyIb1ZMgwghHtyYE4W00,3100
-inspect_ai/solver/_multiple_choice.py,sha256=sm-xo24zOdJr-rG0RGwdhIfNvp18_as55KvJw7tuuN4,6245
-inspect_ai/solver/_plan.py,sha256=0WSR7saiGaatFCq1dVfprzpfs0aaA68EHsTfLPaZbOo,5190
-inspect_ai/solver/_prompt.py,sha256=-qlLgZiDqYnNxSTBx2eSL8dnUxBX9i5aNsWknvNbH-A,2292
-inspect_ai/solver/_solver.py,sha256=j6FhwsBVpX2SyWTCBZbVwFJ-DWU833GOS4o9VilCx8U,8435
+inspect_ai/solver/__init__.py,sha256=MqNUCE2-zcICh79ZSzIKp7RdGR5auJ3OBAD0v17mQfw,695
+inspect_ai/solver/_critique.py,sha256=87gYcwyF3j44IGkrSTXGVmerX7HQzOyowAuIcy2JHIo,3124
+inspect_ai/solver/_multiple_choice.py,sha256=_qCNjeB5QiQgACBt621Xo65e5V9AU2natHD8DePrTXU,6269
+inspect_ai/solver/_plan.py,sha256=geJU5BMKs9iM5vAQnT68_aiZNXmQNQ0CpuKkNdxNdGQ,5214
+inspect_ai/solver/_prompt.py,sha256=eXby9F6OoQ5Ivq2lpQVMdsmEbpO6E8oo03gBl3zvn2o,2316
+inspect_ai/solver/_solver.py,sha256=hyfKFFYAuQXfR69l-OMG-w5BN569IQRn06FzahCYN24,5572
+inspect_ai/solver/_task_state.py,sha256=98e8vxxA94cJ14Ia2BkqoZU5uclvfMJqiw0ItCxOzH0,4700
 inspect_ai/solver/_util.py,sha256=pthrf-CzC6FnQYSUFLXTYM4wFEJptZrh5POTmV-Jtow,446
 inspect_ai/solver/_tool/tool.py,sha256=6qpx9Q4JoAa6_KvVm2ul-oXBtgA4z7FYCyz6c7fjJ5A,3839
 inspect_ai/solver/_tool/tool_def.py,sha256=PMEWdzMSSB1h1HWKQNv-O766KTz7hbXA37-o8qu-QLA,2434
-inspect_ai/solver/_tool/use_tools.py,sha256=SkbfspCbtnxDH_u9dDTKcgNAG4IJ9-eDCTQhsHlLRt0,1680
+inspect_ai/solver/_tool/use_tools.py,sha256=fqqLtvD5_hMGnGCNTwrok315MPr6CIftwa6wio5b04k,1705
 inspect_ai/solver/_tool/web_search.py,sha256=ubdrbzMQoQuaNU-Qqc8VOaxOakWoo9R2uh3kLQvTTHU,7439
 inspect_ai/util/__init__.py,sha256=jc4QOrjjCggUmtiXSNQPBdzZv79a6158Ams-a3FEASI,247
 inspect_ai/util/_context/__init__.py,sha256=1D1hDT-u7xgIoqrdXo4SkBbBs69Kq2wLx2lqtlksoQY,280
@@ -194,9 +196,9 @@ inspect_ai/util/_context/concurrency.py,sha256=v5G57onvFRf2lktkPoNJavOBkheqrAglD
 inspect_ai/util/_context/logger.py,sha256=SODT-AQT-UcFzcRbjsrD0XWawoAF1nIKvgZ5LGqJOEs,690
 inspect_ai/util/_context/resource.py,sha256=6CDOos4izeGWfFh8Jq3BvonrsuH69JMXLtyAr7aUskE,3148
 inspect_ai/util/_context/subprocess.py,sha256=Md_1_tShPxMBFUEzNIJCOT8JJaNLFxKsfw1GeDp3CrU,4734
-inspect_ai-0.3.11.dist-info/LICENSE,sha256=aYPffOl9TwBXDQ8g33Jh6AsBhobb3A76qNm7r2HZsps,1079
-inspect_ai-0.3.11.dist-info/METADATA,sha256=DTFG0Ma1UjCoqcfC06s1r8ZNcniVcxIYshcoaKnUhcE,4185
-inspect_ai-0.3.11.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-inspect_ai-0.3.11.dist-info/entry_points.txt,sha256=WGGLmzTzDWLzYfiyovSY6oEKuf-gqzSDNOb5V-hk3fM,54
-inspect_ai-0.3.11.dist-info/top_level.txt,sha256=Tp3za30CHXJEKLk8xLe9qGsW4pBzJpEIOMHOHNCXiVo,11
-inspect_ai-0.3.11.dist-info/RECORD,,
+inspect_ai-0.13.3.dist-info/LICENSE,sha256=aYPffOl9TwBXDQ8g33Jh6AsBhobb3A76qNm7r2HZsps,1079
+inspect_ai-0.13.3.dist-info/METADATA,sha256=pclK1FtHKH1NR932xWpnfeDZk04qD0hYigH2FJebvu0,4185
+inspect_ai-0.13.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+inspect_ai-0.13.3.dist-info/entry_points.txt,sha256=WGGLmzTzDWLzYfiyovSY6oEKuf-gqzSDNOb5V-hk3fM,54
+inspect_ai-0.13.3.dist-info/top_level.txt,sha256=Tp3za30CHXJEKLk8xLe9qGsW4pBzJpEIOMHOHNCXiVo,11
+inspect_ai-0.13.3.dist-info/RECORD,,