util-genai: ToolInvocation._apply_finish never calls the completion hook, so tool arguments/results bypass redaction hooks

[bytesrabbit]

Version: opentelemetry-util-genai 1.1b0 (_tool_invocation.py:120).

What happens. InferenceInvocation._apply_finish and WorkflowInvocation._apply_finish
call _call_completion_hook(...) before ending the span, so a CompletionHook registered through
the opentelemetry_genai_completion_hook entry point (the documented way to add redaction or
upload) sees inference and workflow content. ToolInvocation._apply_finish writes
gen_ai.tool.call.arguments and gen_ai.tool.call.result and ends the span without calling the
hook, so tool content bypasses every hook, including redaction.

Reproduce. Register a hook that records every call; run handler.tool("t") with
arguments={"token": "sk-..."}; the hook is never called and the attribute reaches the exporter.

Suggested fix. Call _call_completion_hook from ToolInvocation._apply_finish with the
arguments and result as inputs/outputs (or add a dedicated hook method for tools), consistently
with the other invocation types.

[akshat-lakhera]

Hey @bytesrabbit can pick this up.

I'll patch ToolInvocation._apply_finish to route the tool arguments and results through _call_completion_hook before the span ends, bringing it in line with the other invocation types. I'll also wire up a unit test to ensure redaction hooks properly intercept dummy tokens.

Will have a PR up for this shortly.