inspect-ai 0.3.105__py3-none-any.whl → 0.3.107__py3-none-any.whl

inspect_ai/_eval/context.py

@@ -1,4 +1,7 @@
+from anyio.abc import TaskGroup
+
 from inspect_ai._util.dotenv import init_dotenv
+from inspect_ai._util.eval_task_group import init_eval_task_group
 from inspect_ai._util.hooks import init_hooks
 from inspect_ai._util.logger import init_logger
 from inspect_ai.approval._apply import have_tool_approval, init_tool_approval
@@ -19,6 +22,7 @@ def init_eval_context(
     log_level: str | None,
     log_level_transcript: str | None,
     max_subprocesses: int | None = None,
+    task_group: TaskGroup | None = None,
 ) -> None:
     init_dotenv()
     init_logger(log_level, log_level_transcript)
@@ -27,6 +31,7 @@ def init_eval_context(
     init_hooks()
     init_active_samples()
     init_human_approval_manager()
+    init_eval_task_group(task_group)
 
 
 def init_task_context(

inspect_ai/_eval/eval.py

@@ -4,11 +4,15 @@ import sys
 from pathlib import Path
 from typing import Any, Literal, cast
 
+import anyio
+from anyio.abc import TaskGroup
+
 from inspect_ai._eval.task.task import resolve_model_roles
 from inspect_ai._util.notgiven import NOT_GIVEN, NotGiven
 from inspect_ai.agent._agent import Agent, is_agent
 from inspect_ai.agent._as_solver import as_solver
 from inspect_ai.log._model import model_roles_config_to_model_roles
+from inspect_ai.util._anyio import inner_exception
 
 if sys.version_info < (3, 11):
     from exceptiongroup import ExceptionGroup
@@ -359,6 +363,112 @@ async def eval_async(
     Returns:
         List of EvalLog (one for each task)
     """
+    result: list[EvalLog] | None = None
+
+    async def run(tg: TaskGroup) -> None:
+        try:
+            nonlocal result
+            result = await _eval_async_inner(
+                tg=tg,
+                tasks=tasks,
+                model=model,
+                model_base_url=model_base_url,
+                model_args=model_args,
+                model_roles=model_roles,
+                task_args=task_args,
+                sandbox=sandbox,
+                sandbox_cleanup=sandbox_cleanup,
+                solver=solver,
+                tags=tags,
+                metadata=metadata,
+                approval=approval,
+                log_level=log_level,
+                log_level_transcript=log_level_transcript,
+                log_dir=log_dir,
+                log_format=log_format,
+                limit=limit,
+                sample_id=sample_id,
+                epochs=epochs,
+                fail_on_error=fail_on_error,
+                retry_on_error=retry_on_error,
+                debug_errors=debug_errors,
+                message_limit=message_limit,
+                token_limit=token_limit,
+                time_limit=time_limit,
+                working_limit=working_limit,
+                max_samples=max_samples,
+                max_tasks=max_tasks,
+                max_subprocesses=max_subprocesses,
+                max_sandboxes=max_sandboxes,
+                log_samples=log_samples,
+                log_realtime=log_realtime,
+                log_images=log_images,
+                log_buffer=log_buffer,
+                log_shared=log_shared,
+                log_header_only=log_header_only,
+                score=score,
+                score_display=score_display,
+                **kwargs,
+            )
+        finally:
+            tg.cancel_scope.cancel()
+
+    try:
+        async with anyio.create_task_group() as tg:
+            tg.start_soon(run, tg)
+    except Exception as ex:
+        raise inner_exception(ex)
+    except anyio.get_cancelled_exc_class():
+        # Cancelled exceptions are expected and handled by _eval_async_inner
+        pass
+
+    assert result is not None, "Eval async did not return a result."
+
+    return result
+
+
+async def _eval_async_inner(
+    tg: TaskGroup,
+    tasks: Tasks,
+    model: str | Model | list[str] | list[Model] | None | NotGiven = NOT_GIVEN,
+    model_base_url: str | None = None,
+    model_args: dict[str, Any] | str = dict(),
+    model_roles: dict[str, str | Model] | None = None,
+    task_args: dict[str, Any] | str = dict(),
+    sandbox: SandboxEnvironmentType | None = None,
+    sandbox_cleanup: bool | None = None,
+    solver: Solver | SolverSpec | Agent | list[Solver] | None = None,
+    tags: list[str] | None = None,
+    metadata: dict[str, Any] | None = None,
+    approval: str | list[ApprovalPolicy] | ApprovalPolicyConfig | None = None,
+    log_level: str | None = None,
+    log_level_transcript: str | None = None,
+    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] | list[int] | list[str | int] | None = None,
+    epochs: int | Epochs | None = None,
+    fail_on_error: bool | float | None = None,
+    retry_on_error: int | None = None,
+    debug_errors: bool | None = None,
+    message_limit: int | None = None,
+    token_limit: int | None = None,
+    time_limit: int | None = None,
+    working_limit: int | None = None,
+    max_samples: int | None = None,
+    max_tasks: int | None = None,
+    max_subprocesses: int | None = None,
+    max_sandboxes: int | None = None,
+    log_samples: bool | None = None,
+    log_realtime: bool | None = None,
+    log_images: bool | None = None,
+    log_buffer: int | None = None,
+    log_shared: bool | int | None = None,
+    log_header_only: bool | None = None,
+    score: bool = True,
+    score_display: bool | None = None,
+    **kwargs: Unpack[GenerateConfigArgs],
+) -> list[EvalLog]:
     # only a single call to eval_async can be active at a time, this used
     # to be due to running tasks switching to the task's directory, however
     # that feature no longer exists so we may be able to revisit this
@@ -387,6 +497,7 @@ async def eval_async(
             max_subprocesses=max_subprocesses,
             log_level=log_level,
             log_level_transcript=log_level_transcript,
+            task_group=tg,
             **kwargs,
         )
 
@@ -934,10 +1045,11 @@ def eval_init(
     max_subprocesses: int | None = None,
     log_level: str | None = None,
     log_level_transcript: str | None = None,
+    task_group: TaskGroup | None = None,
     **kwargs: Unpack[GenerateConfigArgs],
 ) -> list[Model]:
     # init eval context
-    init_eval_context(log_level, log_level_transcript, max_subprocesses)
+    init_eval_context(log_level, log_level_transcript, max_subprocesses, task_group)
 
     # resolve model and task args
     model_args = resolve_args(model_args)

inspect_ai/_eval/run.py

@@ -522,15 +522,16 @@ async def startup_sandbox_environments(
 
     # return shutdown method
     async def shutdown() -> None:
-        for cleanup_jobs in cleanups:
-            try:
-                cleanup_fn, config, task_run_dir = cleanup_jobs
-                with chdir(task_run_dir):
-                    await cleanup_fn("shutdown", config, cleanup)
-            except BaseException as ex:
-                log.warning(
-                    f"Error occurred shutting down sandbox environments: {exception_message(ex)}"
-                )
+        with anyio.CancelScope(shield=True):
+            for cleanup_jobs in cleanups:
+                try:
+                    cleanup_fn, config, task_run_dir = cleanup_jobs
+                    with chdir(task_run_dir):
+                        await cleanup_fn("shutdown", config, cleanup)
+                except BaseException as ex:
+                    log.warning(
+                        f"Error occurred shutting down sandbox environments: {exception_message(ex)}"
+                    )
 
     return shutdown
 

inspect_ai/_util/eval_task_group.py

@@ -0,0 +1,15 @@
+from anyio.abc import TaskGroup
+
+_eval_task_group: TaskGroup | None = None
+
+
+def init_eval_task_group(tg: TaskGroup | None) -> None:
+    global _eval_task_group
+    _eval_task_group = tg
+
+
+def eval_task_group() -> TaskGroup:
+    global _eval_task_group
+    if _eval_task_group is None:
+        raise RuntimeError("Task group has not been initialized")
+    return _eval_task_group

inspect_ai/agent/_react.py

@@ -82,9 +82,8 @@ def react(
           the submit tool within the message. Alternatively, an async function
           to call to determine whether the loop should continue and what message
           to play back. Note that this function is called on _every_ iteration of
-          the loop. If you return a `str` with a custom message it will be
-          sent to the model as a user message only in the case that no tool
-          calls were made.
+          the loop so if you only want to send a message back when the model fails
+          to call tools you need to code that behavior explicitly.
        truncation: Truncate the conversation history in the event of a context
           window overflow. Defaults to "disabled" which does no truncation. Pass
           "auto" to use `trim_messages()` to reduce the context size. Pass a
@@ -246,13 +245,12 @@ def react(
                                 )
                             )
                     elif isinstance(do_continue, str):
-                        # if there were no tool calls we need to send back the user message
-                        if not state.output.message.tool_calls:
-                            state.messages.append(
-                                ChatMessageUser(
-                                    content=do_continue.format(submit=submit_tool.name)
-                                )
+                        # send back the user message
+                        state.messages.append(
+                            ChatMessageUser(
+                                content=do_continue.format(submit=submit_tool.name)
                             )
+                        )
                     else:  # do_continue is False
                         break
 
@@ -328,11 +326,14 @@ def react_no_submit(
                 if on_continue:
                     do_continue = await _call_on_continue(on_continue, state)
                     if do_continue is True:
-                        do_continue = DEFAULT_CONTINUE_PROMOT_NO_SUBMIT
-                    if do_continue:
-                        # send back user message if there are no tool calls
                         if not state.output.message.tool_calls:
-                            state.messages.append(ChatMessageUser(content=do_continue))
+                            state.messages.append(
+                                ChatMessageUser(
+                                    content=DEFAULT_CONTINUE_PROMOT_NO_SUBMIT
+                                )
+                            )
+                    elif isinstance(do_continue, str):
+                        state.messages.append(ChatMessageUser(content=do_continue))
                     else:
                         break
                 elif not state.output.message.tool_calls:
@@ -471,12 +472,34 @@ def _remove_submit_tool(
 
         # remove submit tool from assistant messages
         if isinstance(message, ChatMessageAssistant) and message.tool_calls:
-            tools_calls = [
+            new_tools_calls = [
                 tool_call
                 for tool_call in message.tool_calls
                 if tool_call.function != submit_name
             ]
-            message = message.model_copy(update=dict(tool_calls=tools_calls))
+
+            # If a submit tool call was removed, we need to update the message
+            if len(new_tools_calls) < len(message.tool_calls):
+                message = message.model_copy(
+                    update=dict(
+                        tool_calls=new_tools_calls,
+                        # Some models (OpenAI) don't like to see the reasoning
+                        # content item that led to the submit tool call, so we
+                        # have to remove it too.
+                        content=(
+                            [
+                                content
+                                for content in message.content
+                                if (
+                                    isinstance(content, str)
+                                    or content.type != "reasoning"
+                                )
+                            ]
+                            if isinstance(message.content, list)
+                            else message.content
+                        ),
+                    )
+                )
 
         # always append message
         filtered.append(message)

inspect_ai/model/_providers/_openai_web_search.py

@@ -14,7 +14,7 @@ def maybe_web_search_tool(model_name: str, tool: ToolInfo) -> WebSearchToolParam
             tool.name == "web_search"
             and tool.options
             and "openai" in tool.options
-            and model_name in COMPATIBLE_MODELS
+            and any(model_name.startswith(model) for model in COMPATIBLE_MODELS)
         )
         else None
     )

inspect_ai/model/_providers/groq.py

@@ -156,6 +156,11 @@ class GroqAPI(ModelAPI):
                     "completion_time": completion.usage.completion_time,
                     "total_time": completion.usage.total_time,
                 }
+            if completion.choices[0].message.executed_tools:
+                metadata["executed_tools"] = [
+                    tool.model_dump()
+                    for tool in completion.choices[0].message.executed_tools
+                ]
 
             # extract output
             choices = self._chat_choices_from_response(completion, tools)

inspect_ai/model/_providers/perplexity.py

@@ -49,7 +49,33 @@ class PerplexityAPI(OpenAICompatibleAPI):
         tool_choice: "ToolChoice",
         config: GenerateConfig,
     ) -> tuple[ModelOutput | Exception, "ModelCall"]:
-        result = await super().generate(input, tools, tool_choice, config)
+        search_options: dict[str, Any] | None = None
+        for tool in tools:
+            if (
+                tool.name == "web_search"
+                and tool.options
+                and "perplexity" in tool.options
+            ):
+                maybe_opts = tool.options["perplexity"]
+                if maybe_opts is not None:
+                    if maybe_opts is True:
+                        search_options = {}
+                    elif isinstance(maybe_opts, dict):
+                        search_options = maybe_opts
+                    else:
+                        raise TypeError(
+                            f"Expected a dictionary or True for perplexity_options, got {type(maybe_opts)}"
+                        )
+            else:
+                raise ValueError(
+                    "Perplexity does not support tools other than web_search with perplexity options"
+                )
+
+        if search_options:
+            extra_body = {**(config.extra_body or {}), **search_options}
+            config = config.merge(GenerateConfig(extra_body=extra_body))
+
+        result = await super().generate(input, [], tool_choice, config)
         output, call = cast(tuple[ModelOutput, "ModelCall"], result)
 
         if self._response:

inspect_ai/model/_providers/providers.py

@@ -16,7 +16,7 @@ from .._registry import modelapi
 def groq() -> type[ModelAPI]:
     FEATURE = "Groq API"
     PACKAGE = "groq"
-    MIN_VERSION = "0.16.0"
+    MIN_VERSION = "0.28.0"
 
     # verify we have the package
     try:

inspect_ai/tool/_tools/_web_search/_web_search.py

@@ -18,7 +18,7 @@ from ._tavily import TavilyOptions, tavily_search_provider
 from ._web_search_provider import SearchProvider
 
 Provider: TypeAlias = Literal[
-    "gemini", "openai", "anthropic", "tavily", "google", "exa"
+    "gemini", "openai", "anthropic", "perplexity", "tavily", "google", "exa"
 ]
 valid_providers = set(get_args(Provider))
 
@@ -35,6 +35,7 @@ class Providers(TypedDict, total=False):
     openai: dict[str, Any] | Literal[True]
     anthropic: dict[str, Any] | Literal[True]
     gemini: dict[str, Any] | Literal[True]
+    perplexity: dict[str, Any] | Literal[True]
     tavily: dict[str, Any] | Literal[True]
     google: dict[str, Any] | Literal[True]
     exa: dict[str, Any] | Literal[True]
@@ -44,6 +45,7 @@ class _NormalizedProviders(TypedDict, total=False):
     openai: dict[str, Any]
     anthropic: dict[str, Any]
     gemini: dict[str, Any]
+    perplexity: dict[str, Any]
     tavily: dict[str, Any]
     google: dict[str, Any]
     exa: dict[str, Any]
@@ -67,7 +69,7 @@ def web_search(
     Web searches are executed using a provider. Providers are split
     into two categories:
 
-    - Internal providers: "openai", "anthropic" - these use the model's built-in
+    - Internal providers: "openai", "anthropic", "gemini", "perplexity" - these use the model's built-in
       search capability and do not require separate API keys. These work only for
       their respective model provider (e.g. the "openai" search provider
       works only for `openai/*` models).
@@ -84,7 +86,7 @@ def web_search(
 
     Args:
       providers: Configuration for the search providers to use. Currently supported
-        providers are "openai", "anthropic", "tavily", "google", and "exa". The
+        providers are "openai", "anthropic", "perplexity", "tavily", "google", and "exa". The
         `providers` parameter supports several formats based on either a `str`
         specifying a provider or a `dict` whose keys are the provider names and
         whose values are the provider-specific options. A single value or a list
@@ -121,6 +123,9 @@ def web_search(
         - anthropic: Supports Anthropic's web search parameters.
           See https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/web-search-tool#tool-definition
 
+        - perplexity: Supports Perplexity's web search parameters.
+          See https://docs.perplexity.ai/api-reference/chat-completions-post
+
         - tavily: Supports options like `max_results`, `search_depth`, etc.
           See https://docs.tavily.com/documentation/api-reference/endpoint/search
 

{inspect_ai-0.3.105.dist-info → inspect_ai-0.3.107.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: inspect_ai
-Version: 0.3.105
+Version: 0.3.107
 Summary: Framework for large language model evaluations
 Author: UK AI Security Institute
 License: MIT License

{inspect_ai-0.3.105.dist-info → inspect_ai-0.3.107.dist-info}/RECORD

@@ -46,13 +46,13 @@ inspect_ai/_display/textual/widgets/toggle.py,sha256=ToYs-S4n90yuxWcAW2OTg6AbRf0
 inspect_ai/_display/textual/widgets/transcript.py,sha256=fmCJwe1EZ7bjeB6DXakQ2l3aoytEW_wdGTCN1Hea5uw,12558
 inspect_ai/_display/textual/widgets/vscode.py,sha256=SAIPO8VOkT_CFIfnCP_XxKixojdYXxMNdYU3Z2mq5Ek,1298
 inspect_ai/_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-inspect_ai/_eval/context.py,sha256=mdYinWG2lcYkWLieT42suzUDyaQBVHosbaWTKA6Uu48,1407
-inspect_ai/_eval/eval.py,sha256=7Izm4s64OIn8dZ2oQQF4fX_jneCODAWJ9Kzd0NRBIPk,44168
+inspect_ai/_eval/context.py,sha256=vEOqPNG3eWdkspaLYEJJE59D_WxH_3ZPHc3tP0MjwHg,1584
+inspect_ai/_eval/eval.py,sha256=DlDpqMWpF3JIgJ9Xeb0QJ9E99Dm1VW48viNEUwj6Lis,48279
 inspect_ai/_eval/evalset.py,sha256=cGLAX6qnMMi-LTenLtu47wv0JJTjAvFLbE6zKfZbfTg,25112
 inspect_ai/_eval/list.py,sha256=VbZ-2EI6MqrXvCN7VTz21TQSoU5K5_Q0hqhxmj5A_m0,3744
 inspect_ai/_eval/loader.py,sha256=dafv4TlQDqdvzPyrQrBsNiCzhvqjwmcVQzweX-AL1os,24805
 inspect_ai/_eval/registry.py,sha256=IMyF_Ru11DrqjFe1yZJvghQcJSfssQ08wQqTt_F38Ag,5570
-inspect_ai/_eval/run.py,sha256=_BKbpGppIvfl_ZFzpq28U86f8IBB7QHYf11ScANdf6U,21509
+inspect_ai/_eval/run.py,sha256=Wlmc4pE5hUTyGRn2iYC1xLleyI2R8ffIoCPkITTVePc,21590
 inspect_ai/_eval/score.py,sha256=KodaNhMCE1KV8qS33zj7Q8I0LD080WRCb32tyg1956w,10443
 inspect_ai/_eval/task/__init__.py,sha256=6FvojMW3yo36L7xDacppCHDxt6A8_tzj_ftg5bQ6eNk,199
 inspect_ai/_eval/task/constants.py,sha256=_YGvlhJL7kC7_3OCbyjDabnJNX2kopH_kRxwODF9cKw,117
@@ -86,6 +86,7 @@ inspect_ai/_util/dotenv.py,sha256=9KsPrGFYUVsBGDTnmDuvtptkiOuoxztVaIRdID58EuA,34
 inspect_ai/_util/entrypoints.py,sha256=FnK32vIRvSFdH80l5H0o6oiJif837oeDrl5N10_P-xo,1260
 inspect_ai/_util/environ.py,sha256=COdX6sqJIq3ikNQD2gR2nMT7yk0qW8x4EjlJwHS9A_M,1428
 inspect_ai/_util/error.py,sha256=NIYCkOXGMUF1_zSHpeTBKzBb79_llQZvvf0TGYHO57Y,2333
+inspect_ai/_util/eval_task_group.py,sha256=NBnvF-VuPT-foZ4_7ITjJ61LNQ29F0cuaTIh-y-FbVo,380
 inspect_ai/_util/exception.py,sha256=coVT0bQy6sADWSvTUaVVDDKnb1XCzREfuVi9UOvx_S0,149
 inspect_ai/_util/file.py,sha256=OqSe8RXF9OBWm8Rzvnsnu854ZqQWl-6aFlUrbjIVHoA,13432
 inspect_ai/_util/format.py,sha256=4TQ1FE4-TDNlHcr0r6dfsjv84sV11C9ouTfi55W-yIs,3323
@@ -519,7 +520,7 @@ inspect_ai/agent/_as_solver.py,sha256=glOKzItIPsveWDGlk2igLfFDOix_NlEkAtyQ6YsWB2
 inspect_ai/agent/_as_tool.py,sha256=-NGZUFAEimvSpog0UmNtYDMlbbuKaWnIgwNnMd_fffM,4912
 inspect_ai/agent/_filter.py,sha256=qnT0HbT4edpDi0MwXY3Q3It2pzNRkTRXZDOqfCwMY6M,1234
 inspect_ai/agent/_handoff.py,sha256=fonoLtC9CxCt7Ya_EbhHU-1indqVpOaTJ2b8-9BoM_k,3848
-inspect_ai/agent/_react.py,sha256=n59jkPQG97lHlEPhurluOVhkpnbqjMeBKrFdtA7pKxE,19061
+inspect_ai/agent/_react.py,sha256=oFUy2w96d9nSYeLBoeqLv1GuBjAFh0glPaPJ8M8jOPE,20003
 inspect_ai/agent/_run.py,sha256=wXAE26-w0W1Brn5KTEQH5Esl_ZrwH37Po18yX-EZQsI,3171
 inspect_ai/agent/_types.py,sha256=UeXBI_p8VVgEeMqenJjFRfyAWqWBKugUvVS2eJoIIUw,4560
 inspect_ai/agent/_bridge/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -638,14 +639,14 @@ inspect_ai/model/_trim.py,sha256=y2bSok4y844spv7vdjUVGnxWG93WcslAsXyplWDoRqU,337
 inspect_ai/model/_providers/_anthropic_citations.py,sha256=8Wub6F8vvup0-e-BKV3wcrT4n1_7q9Rimv0xnMQAEZM,5767
 inspect_ai/model/_providers/_google_citations.py,sha256=KtqQdvUrWV1lGYfD7aLOIwUbIqZbVJDCoX-uCMHBZz8,3573
 inspect_ai/model/_providers/_openai_computer_use.py,sha256=vbKkYLhqNuX16zuWfg5MaGp9H8URrPcLhKQ1pDsZtPo,5943
-inspect_ai/model/_providers/_openai_web_search.py,sha256=tKxoRHc8gHIt8kgIdp6eM_Ak62inGRTxdUe1JNJV0b8,1195
+inspect_ai/model/_providers/_openai_web_search.py,sha256=8hTUNmt7nYCWMn1RjxevWdeZL7FyLi6T2AWKOciNz3w,1228
 inspect_ai/model/_providers/anthropic.py,sha256=Dzu_5nWH4Xx1XklARkjCP0jkIvt8Nf5SDmzgblPGsf4,42201
 inspect_ai/model/_providers/azureai.py,sha256=KzgPYtUMsqEZZTHWYWYLnnRd6wh4qqlqqZL2JwvraLs,16738
 inspect_ai/model/_providers/bedrock.py,sha256=G252v6gUXtT56M4JaLLY7tEw2AJVQFucjeFgv0okhgo,23999
 inspect_ai/model/_providers/cloudflare.py,sha256=9yHfA5qbKWjzOfOzCJ_u8CZsH_U7AolAWLxvLBXKrhM,2375
 inspect_ai/model/_providers/google.py,sha256=6omSismcBEFH_2lVhOhLF5A3ceMpuZiARxWD91n2R6E,35748
 inspect_ai/model/_providers/grok.py,sha256=iAPXmZMR7VWPq6EIwRsoUJr_TR6b5kTt-Fkba1pogGQ,1267
-inspect_ai/model/_providers/groq.py,sha256=q9o4sy0uUyLQbSThB-MMTmSc5AtKmb6GJfgHBpf5amM,12262
+inspect_ai/model/_providers/groq.py,sha256=uPzH8gmJhBOwgXWAdiqtCYlBi79E051wr6-bxUrMUwA,12503
 inspect_ai/model/_providers/hf.py,sha256=jyXi4qyq2hdsp1waB2ON5m8f9mpE2h1GFD7Tu_phCEo,19115
 inspect_ai/model/_providers/llama_cpp_python.py,sha256=qVGpR7qnuP3wbYfFqSTkSc63sYsNnK1XC5IV-Ac0Uu4,618
 inspect_ai/model/_providers/mistral.py,sha256=TNVrwS1gJ-ClxPvDnhGQBelLtEm6r4eF4t25H0pJwQw,18152
@@ -657,8 +658,8 @@ inspect_ai/model/_providers/openai_compatible.py,sha256=2dGx2pJSj6o0uJWKE3mimX47
 inspect_ai/model/_providers/openai_o1.py,sha256=ahdXt2TFtPTdDvSGVQw7EaVindfbFbY2pLZrrB45rFg,13305
 inspect_ai/model/_providers/openai_responses.py,sha256=eNDDCyIfBPCy_gTbpRDr5UicGR_8xkIq9TBTZT7wU7w,6685
 inspect_ai/model/_providers/openrouter.py,sha256=sm-XlzcevoZfoR4C00jCxlfeL2NlnPVpJJA1mFFgkgw,4990
-inspect_ai/model/_providers/perplexity.py,sha256=2KA5l_BJjQOOvgGIy4O2e0INHOq4dqHIBlTYdN_WRTQ,4880
-inspect_ai/model/_providers/providers.py,sha256=Wk4p69q8_yRmrnIgTZjPLejeGgriAiJkxRUf5mozd3k,6806
+inspect_ai/model/_providers/perplexity.py,sha256=LUvy4kk_v4--zA08yqgQtPj4COecXP7Jym8ThtUxOGw,5954
+inspect_ai/model/_providers/providers.py,sha256=w8QpVV0Hj_pQjOEC3W-bisJraSwe3QbovH8-sYBz2Cc,6806
 inspect_ai/model/_providers/sglang.py,sha256=vmIIFC-wyltCAvewvgMVRs4jfp9wFSfinTuNo9TQxM8,8750
 inspect_ai/model/_providers/together.py,sha256=EUNag5nraqo3GvzwKB1jukhZj-GACxsCGPrBC4VR2MU,9786
 inspect_ai/model/_providers/vertex.py,sha256=_8wsThFHIpuwJ5Bvmx8PsEYKqauUYZ1v8B3dn41CtFw,17328
@@ -745,7 +746,7 @@ inspect_ai/tool/_tools/_web_search/_base_http_provider.py,sha256=ww9SbvrXa5MNxwR
 inspect_ai/tool/_tools/_web_search/_exa.py,sha256=vH5aLLsWRYpTaSkk1jN6os3x-eE8uAqT_U5ToJaIoP8,2372
 inspect_ai/tool/_tools/_web_search/_google.py,sha256=CD1ckTpw4prwkancWz6_aTWwGZ4xwKfbDcqAPiSLNS4,7239
 inspect_ai/tool/_tools/_web_search/_tavily.py,sha256=4i9lqhWTgT_cD-cocDQjW-eJhRZZ6pjzlFfKYe1rfdg,3053
-inspect_ai/tool/_tools/_web_search/_web_search.py,sha256=12xJq8eA90JDLq3S4HMZ_2Umu29xHd15wcap0KoVeRo,11033
+inspect_ai/tool/_tools/_web_search/_web_search.py,sha256=qB6O-NAdt4FYFshf02r71nIOYETuSOdMpAUgEeHw4BE,11308
 inspect_ai/tool/_tools/_web_search/_web_search_provider.py,sha256=SvbQd7l2wqz5cAdNk9zrXX8NqOoWd-FEtF-6zyLA7MA,208
 inspect_ai/util/__init__.py,sha256=pYCxgPSDHdN9S2UtYhL8l_oUkiVFInQ_-waSFrD09x8,2281
 inspect_ai/util/_anyio.py,sha256=ImV_Q9oJ0XT0Fy6qa68OHpCzcUbfxptbHAjYWre-m2U,1541
@@ -783,9 +784,9 @@ inspect_ai/util/_sandbox/docker/internal.py,sha256=c8X8TLrBPOvsfnq5TkMlb_bzTALyc
 inspect_ai/util/_sandbox/docker/prereqs.py,sha256=0j6_OauBBnVlpBleADcZavIAAQZy4WewVjbRn9c0stg,3355
 inspect_ai/util/_sandbox/docker/service.py,sha256=hhHIWH1VDFLwehdGd19aUBD_VKfDO3GCPxpw1HSwVQk,2437
 inspect_ai/util/_sandbox/docker/util.py,sha256=EeInihCNXgUWxaqZ4dNOJd719kXL2_jr63QCoXn68vA,3154
-inspect_ai-0.3.105.dist-info/licenses/LICENSE,sha256=xZPCr8gTiFIerrA_DRpLAbw-UUftnLFsHxKeW-NTtq8,1081
-inspect_ai-0.3.105.dist-info/METADATA,sha256=RTZ7JYgPfnTt7hQOBIE6SWp9DI98mCKdzObp-MeIyYc,5467
-inspect_ai-0.3.105.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-inspect_ai-0.3.105.dist-info/entry_points.txt,sha256=WGGLmzTzDWLzYfiyovSY6oEKuf-gqzSDNOb5V-hk3fM,54
-inspect_ai-0.3.105.dist-info/top_level.txt,sha256=Tp3za30CHXJEKLk8xLe9qGsW4pBzJpEIOMHOHNCXiVo,11
-inspect_ai-0.3.105.dist-info/RECORD,,
+inspect_ai-0.3.107.dist-info/licenses/LICENSE,sha256=xZPCr8gTiFIerrA_DRpLAbw-UUftnLFsHxKeW-NTtq8,1081
+inspect_ai-0.3.107.dist-info/METADATA,sha256=UDm4EwaGEHfBNNwE6qudz_TpT9awiq0wByKkjQn_sFE,5467
+inspect_ai-0.3.107.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+inspect_ai-0.3.107.dist-info/entry_points.txt,sha256=WGGLmzTzDWLzYfiyovSY6oEKuf-gqzSDNOb5V-hk3fM,54
+inspect_ai-0.3.107.dist-info/top_level.txt,sha256=Tp3za30CHXJEKLk8xLe9qGsW4pBzJpEIOMHOHNCXiVo,11
+inspect_ai-0.3.107.dist-info/RECORD,,