Introduce reset metrics api by maobaolong · Pull Request #2602 · LMCache/LMCache

maobaolong · 2026-02-14T06:29:42Z

What this PR does / why we need it:

This PR introduce a way to reset Prometheus metrics. It introduces dedicated methods within the PrometheusLogger to clear and re-register counters and histograms, and exposes this functionality through a new API endpoint. This allows for easier management and debugging of metric data, particularly in environments where metrics need to be reset periodically or on demand.

Special notes for your reviewers:

If applicable:

this PR contains user facing changes - docs added
this PR contains unit tests

gemini-code-assist · 2026-02-14T06:29:56Z

Summary of Changes

Hello @maobaolong, 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 enhances the observability capabilities of LMCache by implementing a mechanism to reset Prometheus metrics. It introduces dedicated methods within the PrometheusLogger to clear and re-register counters and histograms, and exposes this functionality through a new API endpoint. This allows for easier management and debugging of metric data, particularly in environments where metrics need to be reset periodically or on demand.

Highlights

Prometheus Metric Reset Functionality: Introduced reset_counters and reset_histograms methods within the PrometheusLogger class, allowing for the programmatic clearing and re-initialization of all registered Prometheus Counter and Histogram metrics.
Metric Creation Refactoring: Refactored the PrometheusLogger's __init__ method to use new helper methods, _create_counter and _create_histogram, for registering all metrics. This change centralizes metric creation and enables tracking for subsequent resetting.
New API Endpoint for Metrics Reset: Added a new POST endpoint /metrics/reset to the internal API server, which triggers the reset_observability_metrics function to clear all Prometheus metrics.
New Metrics and Histogram Bucket Adjustments: Added a new counter for num_unsuccessful_retrieve_requests and new histograms for fs_connector_get_time, nitrofs_connector_read_time, and instrumented_connector_get_time. Existing histogram bucket definitions were also refined for better granularity.

🧠 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/observability.py
- Added _create_counter and _create_histogram methods to PrometheusLogger for standardized metric registration.
- Modified PrometheusLogger.__init__ to utilize the new _create_counter and _create_histogram methods for all Prometheus metrics.
- Implemented reset_counters and reset_histograms methods in PrometheusLogger to clear and re-initialize metrics.
- Introduced a new global function reset_observability_metrics to orchestrate the resetting of all Prometheus metrics.
- Updated type hints to include Sequence for more flexible iterable types.
- Adjusted bucket definitions for several histograms and introduced short_profiling_buckets and long_profiling_buckets.
- Added counter_num_unsuccessful_retrieve_requests and new histogram metrics for connector timings.
lmcache/v1/internal_api_server/common/metrics_api.py
- Imported the reset_observability_metrics function.
- Added a new POST endpoint /metrics/reset to allow external triggers for resetting Prometheus metrics.

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 introduces functionality to reset Prometheus metrics via a new API endpoint, /metrics/reset, and refactors metric creation. However, the new /metrics/reset endpoint lacks authentication or authorization, posing a critical security risk by allowing unauthorized users to clear monitoring data, which could lead to a denial of service. Additionally, two critical bugs causing NameError exceptions were identified, along with a suggestion to remove an unused parameter for improved code quality.

Squash merge branch 'reset_metrics' into 'remote-backend-0120' * Add thread safe annotation * fix * Reset histogram type metrics * Support reset metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com>

maobaolong · 2026-02-15T08:14:39Z

.

sammshen

LGTM!

maobaolong · 2026-02-16T08:17:53Z

@chunxiaozheng Would you like to take a look at this PR? Thanks.

chunxiaozheng

lgtm

Support reset metrics (merge request !31) Squash merge branch 'reset_metrics' into 'remote-backend-0120' * Add thread safe annotation * fix * Reset histogram type metrics * Support reset metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com> Signed-off-by: DongDongJu <commisori28@gmail.com>

Support reset metrics (merge request !31) Squash merge branch 'reset_metrics' into 'remote-backend-0120' * Add thread safe annotation * fix * Reset histogram type metrics * Support reset metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com>

Support reset metrics (merge request !31) Squash merge branch 'reset_metrics' into 'remote-backend-0120' * Add thread safe annotation * fix * Reset histogram type metrics * Support reset metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com> Signed-off-by: shaoxiawjc <wjc2800@163.com>

gemini-code-assist Bot reviewed Feb 14, 2026

View reviewed changes

Comment thread lmcache/observability.py Outdated

Comment thread lmcache/v1/internal_api_server/common/metrics_api.py

maobaolong force-pushed the reset_metrics_gh branch 3 times, most recently from 75f545f to e7c84f6 Compare February 14, 2026 07:17

Support reset metrics (merge request !31)

20dde61

Squash merge branch 'reset_metrics' into 'remote-backend-0120' * Add thread safe annotation * fix * Reset histogram type metrics * Support reset metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com>

maobaolong force-pushed the reset_metrics_gh branch from 43438f2 to 20dde61 Compare February 14, 2026 07:30

LMCache deleted a comment from gemini-code-assist Bot Feb 14, 2026

maobaolong changed the title ~~Reset metrics gh~~ Introduce reset metrics api Feb 14, 2026

maobaolong closed this Feb 15, 2026

maobaolong reopened this Feb 15, 2026

sammshen approved these changes Feb 16, 2026

View reviewed changes

maobaolong added the full Run comprehensive tests on this PR label Feb 16, 2026

maobaolong enabled auto-merge (squash) February 16, 2026 10:19

chunxiaozheng approved these changes Feb 18, 2026

View reviewed changes

maobaolong merged commit 6aaeaa4 into LMCache:dev Feb 18, 2026
49 of 50 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Introduce reset metrics api#2602

Introduce reset metrics api#2602
maobaolong merged 1 commit intoLMCache:devfrom
maobaolong:reset_metrics_gh

maobaolong commented Feb 14, 2026 •

edited

Loading

Uh oh!

gemini-code-assist Bot commented Feb 14, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

Uh oh!

maobaolong commented Feb 15, 2026 •

edited

Loading

Uh oh!

sammshen left a comment

Uh oh!

maobaolong commented Feb 16, 2026

Uh oh!

chunxiaozheng left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

maobaolong commented Feb 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gemini-code-assist Bot commented Feb 14, 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!

Uh oh!

maobaolong commented Feb 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sammshen left a comment

Choose a reason for hiding this comment

Uh oh!

maobaolong commented Feb 16, 2026

Uh oh!

chunxiaozheng left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

maobaolong commented Feb 14, 2026 •

edited

Loading

maobaolong commented Feb 15, 2026 •

edited

Loading