[chibchombiano26]

...

[github-actions]

❌ DCO Check Failed

Hi @chibchombiano26, your pull request has failed the Developer Certificate of Origin (DCO) check.

This repository supports remediation commits, so you can fix this without rewriting history — but you must follow the required message format.

---

🛠 Quick Fix: Add a remediation commit

Run this command:

git commit --allow-empty -s -m "DCO Remediation Commit for chibchombiano26 <2654397+chibchombiano26@users.noreply.github.com>

I, chibchombiano26 <2654397+chibchombiano26@users.noreply.github.com>, hereby add my Signed-off-by to this commit: c7c00c11225306b0a5df78eb9de091dbc3779fdc"
git push

---

🔧 Advanced: Sign off each commit directly

For the latest commit:

git commit --amend --signoff
git push --force-with-lease

For multiple commits:

git rebase --signoff origin/main
git push --force-with-lease

More info: DCO check report

[mergify]

Merge Protections

🟢 Merge protection satisfied — ready to merge.

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)(?:\(.+\))?(!)?:

[github-actions]

AI triage (advisory)

Checked commit c7c00c1122. The analysis read the diff only. It did not run code from this pull request.

Warning

The AI analysis did not finish. Only the deterministic checks are shown.

CI safety: not assessed.

_{The ai:* labels are advisory. They do not approve CI and they do not add tests:full. A new push runs this check again.}

[github-actions]

AI first review (advisory): blocker found

This review covers the full diff at 8fe112e33b. It read the code and did not run it.

The PR adds a chart verification VLM and per-model prompt overrides. The main risk is that _is_verified_chart — the sole function that decides whether extraction runs or is silently suppressed — has no regression test. The human reviewer must confirm that the new verification and prompt-override paths are covered by at least one test before merging.

_{A maintainer makes the merge decision. This review never approves the pull request.}

[github-actions]

blocker: No regression test for the verification gate or prompt-override path

_is_verified_chart is the only function that decides whether chart extraction runs after verification. A bug in its regex strip or JSON parse returns False, silently suppressing extraction for every chart in the document without any error or log at ERROR level (only return False). The prompt_overrides path in __call__ (line 266) is also untested.

Neither _is_verified_chart nor any code that exercises verification_engine or prompt_overrides appears in tests/test_chart_extraction_tabledata.py or any other test file. AGENTS.md requires a focused test for behavior changes.

A minimal test should call _is_verified_chart with at least: a plain JSON true response, a fenced ```json response, a false response, and an unparseable response. A second test should confirm that prompt_overrides replaces the default prompt in batch_inputs.

[github-actions]

AI first review (advisory): blocker found

This review covers the changes since 8fe112e33b at 67f191d370. It read the code and did not run it.

The new changes only add a chart description request (chart2summary) and a Markdown export to the API example, plus matching docs. They did not change the library code, and I found no new defect. The main risk is still that the library change in granite_vision.py has no test. This covers the _is_verified_chart gate that decides whether extraction runs, and the prompt_overrides path.

Earlier findings

• open (blocker): No regression test for the verification gate or prompt-override path

_{A maintainer makes the merge decision. This review never approves the pull request.}

[codecov]

Codecov Report

❌ Patch coverage is 26.78571% with 82 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...g/models/stages/chart_extraction/granite_vision.py	0.00%	38 Missing ⚠️
docling/utils/api_image_request.py	8.69%	21 Missing ⚠️
docling/cli/main.py	0.00%	9 Missing ⚠️
...erence_engines/vlm/api_openai_compatible_engine.py	0.00%	9 Missing ⚠️
docling/datamodel/chart_extraction_options.py	80.76%	2 Missing and 3 partials ⚠️

📢 Thoughts on this report? Let us know!