Refactor new_block_ids handling for robustness by hlin99 · Pull Request #2536 · LMCache/LMCache

hlin99 · 2026-02-04T07:45:09Z

What this PR does / why we need it:

Flatten nested lists in new_block_ids (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists.
Improve robustness and readability of the code.
Behavior is unchanged for existing valid inputs; no logic is affected.

Special notes for your reviewers:

If applicable:

[ x ] this PR contains user facing changes - docs added
[ x ] this PR contains unit tests

- Flatten nested lists in `new_block_ids` (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists. - Improve robustness and readability of the code. - Behavior is unchanged for existing valid inputs; no logic is affected. Signed-off-by: Tony Lin <tony.lin@intel.com>

gemini-code-assist · 2026-02-04T07:45:23Z

Summary of Changes

Hello @hlin99, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refactors the update function in vllm_v1_adapter.py to improve its handling of the new_block_ids parameter. The core change involves adding logic to automatically flatten nested list structures within new_block_ids, such as [[1,2],[3,4]] or [1,[2,3]], into a single-level list. This modification aims to make the function more resilient to diverse input formats without altering its current functionality for already valid inputs, thereby increasing the overall robustness and readability of the code.

Highlights

Robust new_block_ids Handling: Implemented logic to flatten nested lists within the new_block_ids parameter when it is a list, enhancing the function's robustness to varied input structures.
Preservation of Existing Behavior: The change ensures that the behavior for existing valid single-level list inputs remains unchanged, maintaining backward compatibility.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

lmcache/integration/vllm/vllm_v1_adapter.py
- Modified the update function to include a flattening mechanism for the new_block_ids parameter when it is a list.
- Added a list comprehension to detect and flatten nested lists, ensuring new_block_ids is always a single-level list for further processing.

Activity

No specific activity (comments, reviews, progress updates) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request refactors the handling of new_block_ids to robustly flatten nested lists. The implementation is correct, but can be simplified. My review includes a suggestion to remove a redundant conditional check, which makes the code more concise and readable without affecting its behavior.

Signed-off-by: Tony Lin <tony.lin@intel.com>

maobaolong

@sammshen This is a good direction, WDYT?

sammshen

LGTM

hlin99 · 2026-02-21T02:08:21Z

hi @maobaolong could you help merge this PR？many thanks for you guys to spend time reviewing

maobaolong · 2026-02-21T02:11:21Z

@hlin99 I pressed the enable auto-merge button, just wait the ci all getting green. Thanks for your contribution!

hlin99 · 2026-02-23T13:58:21Z

@hlin99 I pressed the enable auto-merge button, just wait the ci all getting green. Thanks for your contribution!

hi @maobaolong not sure why the auto-merge did not work as expected even though the CI got passed. i rebased to the latest, could you help trigger the merge again? thx!

hlin99 · 2026-02-27T00:44:03Z

hi @maobaolong @sammshen could you help manually merge this PR if no more comment? auto-merge seems does not work...... thanks.

* Refactor new_block_ids handling for robustness - Flatten nested lists in `new_block_ids` (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists. - Improve robustness and readability of the code. - Behavior is unchanged for existing valid inputs; no logic is affected. Signed-off-by: Tony Lin <tony.lin@intel.com> * small change to address gemini's comments Signed-off-by: Tony Lin <tony.lin@intel.com> --------- Signed-off-by: Tony Lin <tony.lin@intel.com>

* Refactor new_block_ids handling for robustness - Flatten nested lists in `new_block_ids` (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists. - Improve robustness and readability of the code. - Behavior is unchanged for existing valid inputs; no logic is affected. Signed-off-by: Tony Lin <tony.lin@intel.com> * small change to address gemini's comments Signed-off-by: Tony Lin <tony.lin@intel.com> --------- Signed-off-by: Tony Lin <tony.lin@intel.com> Signed-off-by: shaoxiawjc <wjc2800@163.com>

* Refactor new_block_ids handling for robustness - Flatten nested lists in `new_block_ids` (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists. - Improve robustness and readability of the code. - Behavior is unchanged for existing valid inputs; no logic is affected. Signed-off-by: Tony Lin <tony.lin@intel.com> * small change to address gemini's comments Signed-off-by: Tony Lin <tony.lin@intel.com> --------- Signed-off-by: Tony Lin <tony.lin@intel.com> Signed-off-by: Aaron Wu <aaron.wu@dell.com>

* Refactor new_block_ids handling for robustness - Flatten nested lists in `new_block_ids` (e.g., [[1,2],[3,4]] or mixed [1,[2,3]]) while preserving single-level lists. - Improve robustness and readability of the code. - Behavior is unchanged for existing valid inputs; no logic is affected. Signed-off-by: Tony Lin <tony.lin@intel.com> * small change to address gemini's comments Signed-off-by: Tony Lin <tony.lin@intel.com> --------- Signed-off-by: Tony Lin <tony.lin@intel.com>

gemini-code-assist Bot reviewed Feb 4, 2026

View reviewed changes

Comment thread lmcache/integration/vllm/vllm_v1_adapter.py Outdated

small change to address gemini's comments

366348a

Signed-off-by: Tony Lin <tony.lin@intel.com>

maobaolong approved these changes Feb 15, 2026

View reviewed changes

sammshen approved these changes Feb 16, 2026

View reviewed changes

hlin99 added 2 commits February 16, 2026 14:18

Merge branch 'dev' into block_id_refactor

b66fad8

Merge branch 'dev' into block_id_refactor

cd57551

maobaolong enabled auto-merge (squash) February 21, 2026 02:10

Merge branch 'dev' into block_id_refactor

7934c36

hlin99 added 3 commits February 24, 2026 15:10

Merge branch 'dev' into block_id_refactor

82e5e6d

Merge branch 'dev' into block_id_refactor

c1345b0

Merge branch 'dev' into block_id_refactor

96efc20

hlin99 added 4 commits February 27, 2026 16:29

Merge branch 'dev' into block_id_refactor

161ed24

Merge branch 'dev' into block_id_refactor

4f1f88d

Merge branch 'dev' into block_id_refactor

e16907c

Merge branch 'dev' into block_id_refactor

16b0f5c

sammshen added the full Run comprehensive tests on this PR label Mar 2, 2026

hlin99 added 4 commits March 2, 2026 13:49

Merge branch 'dev' into block_id_refactor

0c22b36

Merge branch 'dev' into block_id_refactor

e956f3c

Merge branch 'dev' into block_id_refactor

df4f97c

Merge branch 'dev' into block_id_refactor

08789a9

maobaolong merged commit ed738ca into LMCache:dev Mar 3, 2026
24 checks passed

hlin99 deleted the block_id_refactor branch March 5, 2026 06:46

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Refactor new_block_ids handling for robustness#2536

Refactor new_block_ids handling for robustness#2536
maobaolong merged 16 commits intoLMCache:devfrom
hlin99:block_id_refactor

hlin99 commented Feb 4, 2026

Uh oh!

gemini-code-assist Bot commented Feb 4, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

maobaolong left a comment

Uh oh!

sammshen left a comment

Uh oh!

hlin99 commented Feb 21, 2026

Uh oh!

maobaolong commented Feb 21, 2026

Uh oh!

hlin99 commented Feb 23, 2026

Uh oh!

hlin99 commented Feb 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

hlin99 commented Feb 4, 2026

Uh oh!

gemini-code-assist Bot commented Feb 4, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

maobaolong left a comment

Choose a reason for hiding this comment

Uh oh!

sammshen left a comment

Choose a reason for hiding this comment

Uh oh!

hlin99 commented Feb 21, 2026

Uh oh!

maobaolong commented Feb 21, 2026

Uh oh!

hlin99 commented Feb 23, 2026

Uh oh!

hlin99 commented Feb 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants