You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 882ea4d
Browse filesBrowse the repository at this point in the historyBrowse files
This implementation follows the exact patterns established by Microsoft.Extensions.AI's OpenTelemetry instrumentation, ensuring consistency across the AI ecosystem and leveraging proven patterns for telemetry integration.
Copy file name to clipboardExpand all lines: docs/specs/004-python-function-calling-loop.md
+6Lines changed: 6 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -392,6 +392,11 @@ that manually replay messages own the equivalent rule: do not resend an approval
392
392
Changing arguments after security middleware has processed them fails closed with `MiddlewareFailure`.
393
393
- Argument-validation failures after middleware retain the established `Argument parsing failed` result contract.
394
394
Exceptions raised by middleware or the tool body retain the separate `Function failed` contract.
395
+
- Provider-hosted shell calls remain informational transcript content. Only a well-formed explicit `local_shell_call`
396
+
or a shell call marked with a local environment, paired with a configured local executor, can enter the local
397
+
function loop and its approval boundary. Stateless replay preserves provider shell call/output items in their
398
+
original shape and fails explicitly when that provider representation is unavailable or inconsistent. Locally
399
+
generated shell outputs are sent in both service-side and stateless continuation modes.
395
400
396
401
### Reasoning-bound calls
397
402
@@ -514,6 +519,7 @@ that manually replay messages own the equivalent rule: do not resend an approval
514
519
| Calls across response messages | Every actionable call is executed once. |`test_base_client_executes_function_calls_across_multiple_response_messages`|
515
520
| Parallel calls | Results retain the corresponding call ids and execution count. |`test_max_function_calls_limits_parallel_invocations`, `test_streaming_multiple_function_calls_parallel_execution`|
516
521
| Informational-only call | The call is returned but not executed or approved. |`test_informational_only_function_call_is_not_invoked`, `test_informational_only_function_call_does_not_request_approval`, `test_streaming_informational_only_function_call_is_not_invoked`|
522
+
| OpenAI hosted/local shell boundary | Hosted shell calls remain informational in streaming and non-streaming responses even when a local executor is configured; only valid explicit local-shell items or shell calls marked with a local environment can execute, local execution preserves its configured approval mode, stateless loops preserve the complete provider shell transcript or fail explicitly, and locally generated shell outputs are sent in every continuation mode. | `packages/openai/tests/openai/test_openai_chat_client.py::test_response_content_creation_with_shell_call_remains_hosted_with_local_tool`, `test_parse_chunk_from_openai_shell_call_done_remains_hosted`, `test_parse_chunk_from_openai_local_environment_shell_call_done_emits_command`, `test_mixed_shell_calls_only_invoke_explicit_local_shell_call`, `test_stateless_shell_transcript_without_provider_item_fails`, `test_prepare_messages_keeps_local_shell_output_under_storage`, `test_malformed_local_environment_shell_call_is_not_executable`, `test_response_content_creation_with_local_shell_call_maps_to_function_call`, `test_malformed_local_shell_call_is_not_executable`, `test_response_function_call_named_local_shell_is_informational`, `test_parse_chunk_function_call_named_local_shell_is_informational`, `test_local_shell_tool_requires_approval_before_function_loop_execution` |
517
523
| Declaration-only call | The call is surfaced as user input and is not executed; streaming arguments appear once while finalized request metadata remains available. |`test_declaration_only_tool`, `test_streaming_declaration_only_tool_preserves_metadata_without_duplicate_arguments`|
518
524
| Function invocation disabled | The client bypasses the invocation loop without losing invocation kwargs. |`test_function_invocation_config_enabled_false`, `test_function_invocation_config_enabled_false_preserves_invocation_kwargs`, `test_streaming_function_invocation_config_enabled_false`|
519
525
| Runtime tool changes | Added tools become available on the next iteration and retain approval behavior. |`test_add_tools_available_next_iteration`, `test_add_tools_with_approval_required_tool`|
Copy file name to clipboardExpand all lines: dotnet/samples/05-end-to-end/DevUIAspireIntegration/DevUIIntegration.AppHost/DevUIIntegration.AppHost.csproj
Copy file name to clipboardExpand all lines: dotnet/samples/05-end-to-end/DevUIAspireIntegration/DevUIIntegration.AppHost/Properties/launchSettings.json
0 commit comments