[Content Understanding] Update to_llm_input page markers and filter telemetry warnings

[chienyuanchang]

Description

Updates the azure-ai-contentunderstanding to_llm_input() helper to align its rendered output with the upcoming service page-marker format and to remove non-user-facing telemetry from RAI warning output.

Changes made:

• Updated SDK-injected document page markers from <!-- page N --> to <!-- InputPageNumber: N -->.
• Added duplicate-marker defense: if service markdown already contains <!-- InputPageNumber:, to_llm_input() does not inject additional page markers.
• Filtered service-emitted internal telemetry warnings whose message starts with LLMStats: from the rendered rai_warnings front matter.
• Preserved LLMStats: text when it appears in the document markdown body; only structured warnings are filtered.
• Updated unit tests and sample tests for the new marker format and warning-filter behavior.
• Updated CHANGELOG.md.

Relevant issues / context:

• Agent Framework feedback that prompted the LLMStats: filtering: Python: Adopt azure-ai-contentunderstanding to_llm_input in CU context provider microsoft/agent-framework#5796

This PR is not based on regenerated SDK code from a new API spec.

All SDK Contribution checklist:

• The pull request does not introduce [breaking changes]
  • No public API signatures are changed. This only changes rendered text produced by the preview to_llm_input() helper.
• CHANGELOG is updated for new features, bug fixes or other significant changes.
• I have read the contribution guidelines.

General Guidelines and Best Practices

• Title of the pull request is clear and informative.
• There are a small number of commits, each of which have an informative message.

Testing Guidelines

• Pull request includes test coverage for the included changes.

Testing performed:

cd sdk/contentunderstanding/azure-ai-contentunderstanding

.venv/bin/python -m pytest tests/test_to_llm_input.py -q
# 84 passed

AZURE_TEST_RUN_LIVE=true .venv/bin/python -m pytest tests/samples/test_sample_to_llm_input.py::TestSampleToLlmInput::test_to_llm_input_multi_page_content_range -q -s
# 1 passed

[Copilot]

Pull request overview

This PR updates the azure-ai-contentunderstanding to_llm_input() helper output format to align with an upcoming service page-marker convention and to suppress non-user-facing telemetry warnings from the rendered rai_warnings YAML front matter.

Changes:

• Switched SDK-injected page markers from <!-- page N --> to <!-- InputPageNumber: N -->, and avoided injecting markers when the service markdown already includes InputPageNumber markers.
• Filtered service warning messages that begin with LLMStats: (after leading whitespace) from the rendered rai_warnings block.
• Updated unit tests and sample tests to validate the new marker format and warning filtering, and bumped package version/changelog.

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
sdk/contentunderstanding/azure-ai-contentunderstanding/tests/test_to_llm_input.py	Updates assertions for the new InputPageNumber marker format and adds coverage for LLMStats: warning filtering and duplicate-marker defense.
sdk/contentunderstanding/azure-ai-contentunderstanding/tests/samples/test_sample_to_llm_input.py	Updates sample test expectations to the new page marker format.
sdk/contentunderstanding/azure-ai-contentunderstanding/tests/samples/test_sample_to_llm_input_async.py	Updates async sample test expectations to the new page marker format.
sdk/contentunderstanding/azure-ai-contentunderstanding/README.md	Adds 1.2.0b2 to the SDK-to-service-version compatibility table.
sdk/contentunderstanding/azure-ai-contentunderstanding/CHANGELOG.md	Adds an unreleased 1.2.0b2 entry documenting the marker change and telemetry-warning filtering.
sdk/contentunderstanding/azure-ai-contentunderstanding/azure/ai/contentunderstanding/_version.py	Bumps the package version to 1.2.0b2.
sdk/contentunderstanding/azure-ai-contentunderstanding/azure/ai/contentunderstanding/_helpers.py	Implements InputPageNumber marker injection + duplicate-marker bypass, and filters LLMStats: entries from rendered RAI warnings.