[RaphaelFakhri]

convert_html_to_docling_table extracts the ```html code block from the model reply, but then converts the full reply. HTML in the surrounding prose, such as a literal <table> or a quoted copy of the original table, is parsed as part of the result. The editor then replaces the table data with an empty table or with the original table.

This change converts the extracted code block, as convert_html_to_docling_document and convert_markdown_to_docling_document already do. When the reply has no code block, the full reply is still converted.

Resolves #61

Tests

• Add test_convert_html_to_docling_table_ignores_prose_mentioning_tags and test_convert_html_to_docling_table_ignores_tables_outside_code_block to tests/test_base_functions.py. Both fail on main and pass with the fix.
• pytest -m "not slow" tests: 166 passed, 3 skipped (base install).
• ruff check, ruff format --check and mypy docling_agent pass.

[github-actions]

✅ DCO Check Passed

Thanks @RaphaelFakhri, all your commits are properly signed off. 🎉

[mergify]

Merge Protections

🔴 1 of 2 protections blocking · waiting on 👀 reviews

	Protection	Waiting on
🔴	Require two reviewer for test updates	👀 reviews
🟢	Enforce conventional commit	—

🔴 Require two reviewer for test updates

Waiting for

• #approved-reviews-by >= 1

This rule is failing.

When test data is updated, we require two reviewers

• #approved-reviews-by >= 1

---

Show 1 satisfied protection

🟢 Enforce conventional commit

Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/

• title ~= ^(fix|feat|docs|style|refactor|perf|test|build|ci|chore|revert)(?:\(.+\))?(!)?: