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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported 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.

packages/apps/redis/Chart.yaml (1)

19-25: Add app.kubernetes.io/version label in your templates

I ran a search for .Chart.AppVersion and app.kubernetes.io/version under packages/apps/redis/** and found no matches—so the new appVersion in Chart.yaml isn’t being injected into any rendered resources. To fix this:

• Update your chart’s templates (under packages/apps/redis/templates/)—for example in your Deployment or StatefulSet YAML—to include the label, e.g.:

metadata:
  labels:
    app.kubernetes.io/version: {{ .Chart.AppVersion }}

This ensures the appVersion value from Chart.yaml propagates into your Kubernetes objects.

packages/apps/vm-instance/README.md (3)

88-88: Fix heading typo: “UO Series” → “O Series”.

Section title should match the “O Series” introduced above.

Apply:

-### UO Series Characteristics
+### O Series Characteristics

---

123-123: Typo: “emaulation” → “emulation”.

User-facing docs: correct misspelling.

Apply:

-  from the vCPUs in order to reduce emaulation related impact on the
+  from the vCPUs in order to reduce emulation related impact on the

---

165-165: Typo: “emaulation” → “emulation”.

Same misspelling appears again in the RT series section.

Apply:

-  from the vCPUs in order to reduce emaulation related impact on the
+  from the vCPUs in order to reduce emulation related impact on the

packages/apps/rabbitmq/values.schema.json (1)

94-126: Ack: Duplicate singular vhost removed.

Removing the duplicate aligns schema and README. Thanks for cleaning this up.

packages/apps/kafka/values.yaml (1)

40-41: Consistent per-replica resource phrasing — looks good

Clarifies CPU/Memory as “available to each replica,” aligning with the repo-wide standardization.

For consistency within this file, consider adding similar per-field lines for ZooKeeper (resources.cpu/resources.memory) as done for Kafka. Not required, but keeps sections uniform.

packages/apps/http-cache/values.yaml (1)

31-32: Docs clarify per-replica resources — approved

The CPU/Memory descriptions now clearly indicate per-replica scope.

Optional: mirror these explicit per-field lines for nginx.resources (cpu/memory) to match the HAProxy section’s detail.

packages/apps/vm-disk/Chart.yaml (1)

19-25: Quote appVersion values in all Chart.yaml files for consistency

To follow the recommended convention (and avoid YAML parsing quirks), wrap the version strings in quotes. The following charts currently have unquoted appVersion fields:

• packages/apps/vm-instance/Chart.yaml (line 26)
• packages/apps/virtual-machine/Chart.yaml (line 26)
• packages/apps/vm-disk/Chart.yaml (line 25)
• packages/apps/kubernetes/Chart.yaml (line 25)
• packages/apps/ferretdb/Chart.yaml (line 25)

Apply this diff to each:

-packages/apps/vm-instance/Chart.yaml
-appVersion: 0.11.0
+packages/apps/vm-instance/Chart.yaml
+appVersion: "0.11.0"

-packages/apps/virtual-machine/Chart.yaml
-appVersion: 0.12.0
+packages/apps/virtual-machine/Chart.yaml
+appVersion: "0.12.0"

-packages/apps/vm-disk/Chart.yaml
-appVersion: 0.4.0
+packages/apps/vm-disk/Chart.yaml
+appVersion: "0.4.0"

-packages/apps/kubernetes/Chart.yaml
-appVersion: 1.32.6
+packages/apps/kubernetes/Chart.yaml
+appVersion: "1.32.6"

-packages/apps/ferretdb/Chart.yaml
-appVersion: 2.4.0
+packages/apps/ferretdb/Chart.yaml
+appVersion: "2.4.0"

Please ensure this quoting convention is applied consistently across all Helm charts in this PR.

packages/apps/redis/README.md (1)

20-21: Nit: end sentences with periods for consistency in the table

Other descriptions in the same table end with a period. Consider aligning for polish.

Apply this minimal tweak:

-| `resources.cpu`    | CPU available to each replica                                                                                                             | `*quantity` | `null`  |
-| `resources.memory` | Memory (RAM) available to each replica                                                                                                    | `*quantity` | `null`  |
+| `resources.cpu`    | CPU available to each replica.                                                                                                            | `*quantity` | `null`  |
+| `resources.memory` | Memory (RAM) available to each replica.                                                                                                   | `*quantity` | `null`  |

packages/apps/rabbitmq/values.yaml (1)

27-35: Redact example passwords to placeholders for consistency

These examples still show hard-coded example passwords. Switching to placeholders aligns with the PR goal to avoid real-looking secrets in docs and examples.

Apply this diff to the examples:

-##     password: strongpassword
+##     password: <your-password-1>
-##   user2:
-##     password: hackme
+##   user2:
+##     password: <your-password-2>
-##   user3:
-##     password: testtest
+##   user3:
+##     password: <your-password-3>

packages/apps/ferretdb/values.schema.json (1)

47-56: Add minimal length validation for access/secret keys

To prevent empty strings from passing schema validation (especially when UIs prefill defaults), add minLength to these fields.

Apply this diff:

         "s3AccessKey": {
           "description": "Access key for S3, used for authentication",
-          "type": "string",
-          "default": "\u003cyour-access-key\u003e"
+          "type": "string",
+          "minLength": 1,
+          "default": "\u003cyour-access-key\u003e"
         },
         "s3SecretKey": {
           "description": "Secret key for S3, used for authentication",
-          "type": "string",
-          "default": "\u003cyour-secret-key\u003e"
+          "type": "string",
+          "minLength": 1,
+          "default": "\u003cyour-secret-key\u003e"
         },

packages/apps/virtual-machine/values.yaml (1)

58-60: Avoid duplicated links after inlining them in the description.

Line 58 now contains the links; lines 59–60 repeat them, making the block redundant.

Apply this diff to remove the duplicate bullets:

 ## @param cloudInit {string} Cloud-init user data config. See cloud-init documentation for more details: [format](https://cloudinit.readthedocs.io/en/latest/explanation/format.html), [examples](https://cloudinit.readthedocs.io/en/latest/reference/examples.html).
-## - https://cloudinit.readthedocs.io/en/latest/explanation/format.html
-## - https://cloudinit.readthedocs.io/en/latest/reference/examples.html

packages/apps/virtual-machine/README.md (2)

44-44: Tighten wording: make the sentence standalone and polished.

Use “Whether …” instead of a lowercase “if …” for better style in the table:

-| `running`                 | if the virtual machine should be running                                                                                                                                                                                                  | `bool`      | `true`       |
+| `running`                 | Whether the virtual machine should be running                                                                                                                                                                                             | `bool`      | `true`       |

---

57-57: Grammar nit: complete the sentence in the SSH keys description.

“Can be a single key…” is a fragment; adding “It” makes it a complete sentence.

-| `sshKeys`                 | List of SSH public keys for authentication. Can be a single key or a list of keys.                                                                                                                                                        | `[]string`  | `[]`         |
+| `sshKeys`                 | List of SSH public keys for authentication. It can be a single key or a list of keys.                                                                                                                                                     | `[]string`  | `[]`         |

packages/apps/kafka/README.md (1)

44-45: Nit: Use canonical “ZooKeeper” capitalization for brand consistency.

Elsewhere it’s often written “ZooKeeper.” Consider updating “Zookeeper” to “ZooKeeper” across the doc for consistency.

-| `zookeeper.resources.cpu`    | CPU available to each replica
-| `zookeeper.resources.memory` | Memory (RAM) available to each replica
+| `zookeeper.resources.cpu`    | CPU available to each replica
+| `zookeeper.resources.memory` | Memory (RAM) available to each replica

packages/apps/rabbitmq/values.schema.json (1)

94-126: Confirm and document removal of the singular vhost property (potential breaking change).

AI summary notes the top-level singular vhost was removed as a duplicate. If users previously set vhost, this is a breaking schema change. Ensure:

• Chart release notes/changelog include a migration note (use vhosts[<name>] instead).
• Template logic doesn’t reference the removed key.
• Version bump is appropriate per your chart versioning policy (Helm SemVer typically reserves MAJOR for breaking changes).

I can draft a short migration note if helpful.

packages/apps/virtual-machine/values.schema.json (1)

6-6: Good: Adds direct links to Cloud-init docs. Minor style nit on capitalization.

Consider using consistent casing (“Cloud-init” vs “cloud-init”) within the sentence.

- "description": "Cloud-init user data config. See cloud-init documentation for more details: [format](https://cloudinit.readthedocs.io/en/latest/explanation/format.html), [examples](https://cloudinit.readthedocs.io/en/latest/reference/examples.html).",
+ "description": "Cloud-init user data config. See Cloud-init documentation for more details: [format](https://cloudinit.readthedocs.io/en/latest/explanation/format.html), [examples](https://cloudinit.readthedocs.io/en/latest/reference/examples.html).",

packages/apps/clickhouse/values.schema.json (1)

11-16: Good security hygiene: secrets redacted. Consider guarding against placeholder use when backups are enabled.

Nice job replacing defaults with placeholders. To prevent accidental deployments with <password>/<your-access-key>/<your-secret-key> when backup.enabled is true, add conditional schema validation to forbid placeholders.

Example JSON Schema snippet to add under the backup object (sibling to "properties"), enforcing real credentials when enabled:

"allOf": [
  {
    "if": { "properties": { "enabled": { "const": true } }, "required": ["enabled"] },
    "then": {
      "allOf": [
        { "properties": { "resticPassword": { "not": { "const": "<password>" } } }, "required": ["resticPassword"] },
        { "properties": { "s3AccessKey":    { "not": { "const": "<your-access-key>" } } }, "required": ["s3AccessKey"] },
        { "properties": { "s3SecretKey":    { "not": { "const": "<your-secret-key>" } } }, "required": ["s3SecretKey"] }
      ]
    }
  }
]

Also applies to: 42-43, 47-48, 62-63

packages/apps/kubernetes/values.schema.json (1)

332-346: Use "replica" (not "worker node") for control plane resource descriptions

Control plane components (apiServer, controllerManager, scheduler, konnectivity server) run as replicas/pods, not worker nodes. Using “worker node” here is misleading and inconsistent with other apps in this PR that use “each replica.”

Apply this diff to align wording:

--- a/packages/apps/kubernetes/values.schema.json
+++ b/packages/apps/kubernetes/values.schema.json
@@
-                  "description": "CPU available to each worker node",
+                  "description": "CPU available to each replica",
@@
-                  "description": "Memory (RAM) available to each worker node",
+                  "description": "Memory (RAM) available to each replica",
@@
-                  "description": "CPU available to each worker node",
+                  "description": "CPU available to each replica",
@@
-                  "description": "Memory (RAM) available to each worker node",
+                  "description": "Memory (RAM) available to each replica",
@@
-                      "description": "CPU available to each worker node",
+                      "description": "CPU available to each replica",
@@
-                      "description": "Memory (RAM) available to each worker node",
+                      "description": "Memory (RAM) available to each replica",
@@
-                  "description": "CPU available to each worker node",
+                  "description": "CPU available to each replica",
@@
-                  "description": "Memory (RAM) available to each worker node",
+                  "description": "Memory (RAM) available to each replica",

Also applies to: 393-407, 467-481, 535-549

packages/apps/kubernetes/README.md (1)

146-171: Replace “worker node” with “replica” for control plane resources

These fields describe resources per control-plane replica, not worker nodes. Align wording to “each replica” for consistency and accuracy.

-| `controlPlane.apiServer.resources.cpu`              | CPU available to each worker node                                                                                                         | `*quantity` | `null`   |
-| `controlPlane.apiServer.resources.memory`           | Memory (RAM) available to each worker node                                                                                                | `*quantity` | `null`   |
+| `controlPlane.apiServer.resources.cpu`              | CPU available to each replica                                                                                                             | `*quantity` | `null`   |
+| `controlPlane.apiServer.resources.memory`           | Memory (RAM) available to each replica                                                                                                    | `*quantity` | `null`   |
@@
-| `controlPlane.controllerManager.resources.cpu`      | CPU available to each worker node                                                                                                         | `*quantity` | `null`   |
-| `controlPlane.controllerManager.resources.memory`   | Memory (RAM) available to each worker node                                                                                                | `*quantity` | `null`   |
+| `controlPlane.controllerManager.resources.cpu`      | CPU available to each replica                                                                                                             | `*quantity` | `null`   |
+| `controlPlane.controllerManager.resources.memory`   | Memory (RAM) available to each replica                                                                                                    | `*quantity` | `null`   |
@@
-| `controlPlane.scheduler.resources.cpu`              | CPU available to each worker node                                                                                                         | `*quantity` | `null`   |
-| `controlPlane.scheduler.resources.memory`           | Memory (RAM) available to each worker node                                                                                                | `*quantity` | `null`   |
+| `controlPlane.scheduler.resources.cpu`              | CPU available to each replica                                                                                                             | `*quantity` | `null`   |
+| `controlPlane.scheduler.resources.memory`           | Memory (RAM) available to each replica                                                                                                    | `*quantity` | `null`   |
@@
-| `controlPlane.konnectivity.server.resources.cpu`    | CPU available to each worker node                                                                                                         | `*quantity` | `null`   |
-| `controlPlane.konnectivity.server.resources.memory` | Memory (RAM) available to each worker node                                                                                                | `*quantity` | `null`   |
+| `controlPlane.konnectivity.server.resources.cpu`    | CPU available to each replica                                                                                                             | `*quantity` | `null`   |
+| `controlPlane.konnectivity.server.resources.memory` | Memory (RAM) available to each replica                                                                                                    | `*quantity` | `null`   |

packages/apps/postgres/values.schema.json (1)

38-47: Mark secret-like fields as writeOnly for better UX and safety.

Consider hinting UIs and tooling that these are sensitive. Many JSON Schema consumers respect writeOnly and/or password formats.

Apply this minimal enhancement:

         "s3AccessKey": {
           "description": "Access key for S3, used for authentication",
           "type": "string",
+          "writeOnly": true,
           "default": "\u003cyour-access-key\u003e"
         },
         "s3SecretKey": {
           "description": "Secret key for S3, used for authentication",
           "type": "string",
+          "writeOnly": true,
           "default": "\u003cyour-secret-key\u003e"
         },

packages/apps/mysql/values.schema.json (1)

39-63: Hint UIs that these fields are sensitive (writeOnly).

Optional but useful: mark password/keys as writeOnly to avoid echoing them in UIs or generated docs.

Suggested tweak:

         "resticPassword": {
           "description": "Password for Restic backup encryption",
           "type": "string",
+          "writeOnly": true,
           "default": "\u003cpassword\u003e"
         },
         "s3AccessKey": {
           "description": "Access key for S3, used for authentication",
           "type": "string",
+          "writeOnly": true,
           "default": "\u003cyour-access-key\u003e"
         },
         "s3Bucket": {
           "description": "S3 bucket used for storing backups",
           "type": "string",
           "default": "s3.example.org/mysql-backups"
         },
         "s3Region": {
           "description": "AWS S3 region where backups are stored",
           "type": "string",
           "default": "us-east-1"
         },
         "s3SecretKey": {
           "description": "Secret key for S3, used for authentication",
           "type": "string",
+          "writeOnly": true,
           "default": "\u003cyour-secret-key\u003e"
         },

packages/apps/ferretdb/Chart.yaml (1)

25-25: Optional: quote appVersion for consistency with other charts.

Helm recommends quoting appVersion; several charts in this PR already do that. Not critical, just consistency.

Apply:

-appVersion: 2.4.0
+appVersion: "2.4.0"

packages/apps/mysql/values.yaml (1)

67-67: Use a bucket-name placeholder (slashes are invalid in S3 bucket names)

Current example looks like a URL/path. S3 bucket names cannot include slashes; suggest a neutral placeholder to avoid confusion.

-  s3Bucket: "s3.example.org/mysql-backups"
+  s3Bucket: "<your-bucket>"

packages/apps/clickhouse/values.yaml (1)

59-65: Good redaction of credentials; consider empty defaults to prevent accidental deployments with placeholders.

Placeholders are better than real secrets in git. As a minor improvement, you could use empty strings by default so charts fail early if users forget to set them.

Here’s an optional tweak:

-  s3Bucket: "s3.example.org/clickhouse-backups"
+  s3Bucket: "s3.example.org/clickhouse-backups"
   schedule: "0 2 * * *"
   cleanupStrategy: "--keep-last=3 --keep-daily=3 --keep-within-weekly=1m"
-  s3AccessKey: "<your-access-key>"
-  s3SecretKey: "<your-secret-key>"
-  resticPassword: "<password>"
+  s3AccessKey: ""
+  s3SecretKey: ""
+  resticPassword: ""

packages/apps/clickhouse/README.md (1)

66-73: Capitalize “ClickHouse” consistently.

Minor nit for brand/style consistency.

Apply:

-| `clickhouseKeeper`                 | Clickhouse Keeper configuration                                                                                                           | `*object`   | `{}`    |
-| `clickhouseKeeper.enabled`         | Deploy ClickHouse Keeper for cluster coordination                                                                                         | `*bool`     | `true`  |
-| `clickhouseKeeper.size`            | Persistent Volume Claim size, available for application data                                                                              | `*quantity` | `1Gi`   |
+| `clickhouseKeeper`                 | ClickHouse Keeper configuration                                                                                                           | `*object`   | `{}`    |
+| `clickhouseKeeper.enabled`         | Deploy ClickHouse Keeper for cluster coordination                                                                                         | `*bool`     | `true`  |
+| `clickhouseKeeper.size`            | Persistent Volume Claim size, available for application data                                                                              | `*quantity` | `1Gi`   |

packages/apps/mysql/README.md (6)

17-19: Fix typo in placeholder.

-kubectl edit mariadb <instnace>
+kubectl edit mariadb <instance>

---

39-41: Align S3 path with parameter table (“mysql-backups” vs “mariadb-backups”).

The parameter table uses mysql-backups, but the example uses mariadb-backups. Align to avoid confusion.

-restic -r s3:s3.example.org/mariadb-backups/database_name snapshots
+restic -r s3:s3.example.org/mysql-backups/database_name snapshots

---

46-47: Align restore example S3 path with parameter table.

-restic -r s3:s3.example.org/mariadb-backups/database_name restore latest --target /tmp/
+restic -r s3:s3.example.org/mysql-backups/database_name restore latest --target /tmp/

---

54-58: Fix minor grammar.

-  Until `mariadbbackup` is not used to bootstrap a node by mariadb-operator (this feature is not inmplemented yet), follow these manual steps to fix it:
+  Until `mariadbbackup` is used to bootstrap a node by mariadb-operator (this feature is not implemented yet), follow these manual steps to fix it:

Optional: consider modern terminology (“primary/replica”) throughout the doc for consistency with the earlier example.

---

63-66: Optional: prefer “primary/replica” terminology in examples.

Matches the earlier “primary” example and modernizes terminology.

-  mysqldump -h <slave> -P 3306 -u<user> -p<password> --column-statistics=0 <database> <table> ~/tmp/fix-table.sql
-  mysql -h <master> -P 3306 -u<user> -p<password> <database> < ~/tmp/fix-table.sql
+  mysqldump -h <replica> -P 3306 -u<user> -p<password> --column-statistics=0 <database> <table> ~/tmp/fix-table.sql
+  mysql -h <primary> -P 3306 -u<user> -p<password> <database> < ~/tmp/fix-table.sql

---

104-109: Credential placeholders LGTM; consider redacting example passwords below as well.

The table is cleaned up. As a follow-up, consider changing the users example passwords (hackme) later in the doc to placeholders for consistency.

I can submit a follow-up patch to replace example passwords with <password> and unify “primary/replica” terminology throughout. Want me to draft it?

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

💡 Knowledge Base configuration:

• MCP integration is disabled by default for public repositories
• Jira integration is disabled by default for public repositories
• Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.