fix: Use deepcopy in doc2len to preserve images/videos for length calculation

[wlhgtc]

What does this PR do?

Using pop in _build_messages removes images from doc, causing length calculation to ignore image tokens.

Then the calculate_length logic will ignore the image length.

Add concise overview of what this PR aims to achieve or accomplish. Reference related GitHub issues and PRs that help with the review.

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: ……
• Format the PR title as [{modules}] {type}: {description} (This will be checked by the CI)
  • {modules} include fsdp, megatron, sglang, vllm, rollout, trainer, ci, training_utils, recipe, hardware, deployment, ray, worker, single_controller, misc, perf, model, algo, env, tool, ckpt, doc, data, cfg, reward
  • If this PR involves multiple modules, separate them with , like [megatron, fsdp, doc]
  • {type} is in feat, fix, refactor, chore, test
  • If this PR breaks any API (CLI arguments, config, function signature, etc.), add [BREAKING] to the beginning of the title.
  • Example: [BREAKING][fsdp, megatron] feat: dynamic batching

Test

For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluation results, etc.

API and Usage Example

Demonstrate how the API changes if any, and provide usage example(s) if possible.

# Add code snippet or script demonstrating how to use this

Design & Code Changes

Demonstrate the high-level design if this PR is complex, and list the specific changes.

Checklist Before Submitting

Important

Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review.

• Read the Contribute Guide.
• Apply pre-commit checks: pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always
• Add / Update the documentation.
• Add unit or end-to-end test(s) to the CI workflow to cover all the code. If not feasible, explain why: ……
• Once your PR is ready for CI, send a message in the ci-request channel in the verl Slack workspace. (If not accessible, please try the Feishu group (飞书群).)
• If your PR is related to the recipe submodule, please also update the reference to the submodule commit via git submodule update --remote or cd recipe && git pull origin main.

[wlhgtc]

@wuxibin89

[gemini-code-assist]

Code Review

This pull request fixes a bug in the doc2len function where image and video tokens were not being counted due to their data being prematurely removed from the sample dictionary. The fix involves changing dict.pop to dict.get in the _build_messages helper function. While this correctly resolves the issue in doc2len, it introduces a regression in the __getitem__ method, which relies on the previous behavior of pop. My review includes a critical comment detailing this regression and suggests an alternative approach to fix the original bug without this side effect.

[wlhgtc]

Code Review

This pull request fixes a bug in the doc2len function where image and video tokens were not being counted due to their data being prematurely removed from the sample dictionary. The fix involves changing dict.pop to dict.get in the _build_messages helper function. While this correctly resolves the issue in doc2len, it introduces a regression in the __getitem__ method, which relies on the previous behavior of pop. My review includes a critical comment detailing this regression and suggests an alternative approach to fix the original bug without this side effect.

Fix