Python: Recommend include_detailed_errors in the tool-failure warning only when it is disabled

[Shivam Sharma (ShivamSharma43)]

Motivation & Context

When a tool raises, _function_execution_error_result logs a warning ending in "Set include_detailed_errors=True for the full detail." It does that in both branches regardless of the configuration, so a caller who already set include_detailed_errors=True is told to turn on a setting that is on, which reads as if the configuration was ignored.

Description & Review Guide

• What are the major changes? _function_execution_error_result reads include_detailed_errors once and appends the recommendation to the warning only when it is disabled. The rest of the warning, the sensitive-data branch (which still adds Exception: %r only when sensitive data is enabled), and the model-bound result are unchanged.
• What is the impact of these changes? With include_detailed_errors=False (the default) the warning is identical to today. With it enabled, the warning reads "Function '' raised an exception; returning an error result to the model." with no recommendation. Only the log text changes; no function-calling loop behavior changes.
• What do you want reviewers to focus on? Nothing beyond the warning text.

Tests: the existing test_function_invocation_result_parser_failure (which already parametrizes include_detailed_errors, streaming and sensitive data) now also asserts the recommendation appears only when detailed errors are disabled, and the new test_function_execution_error_warning_recommends_detailed_errors_only_when_disabled covers a raising tool across the sensitive-data settings. The include_detailed_errors=True cases of both fail without the change.

Related Issue

Fixes #9439

No open PR references this issue.

AI Assistance

• No material AI assistance was used.
• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: implementation, tests and this PR description were drafted with Claude Code and reviewed before submitting.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR links to an agreed issue with no competing open PR, or the Related Issue section documents a trivial-change or repository-automation exception.
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

🤖 Generated with Claude Code

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.