Skip to content

Conversation

@Koufan-De-King
Copy link
Contributor

No description provided.

@stephane-segning
Copy link
Contributor

@codex please review

Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

@Koufan-De-King Koufan-De-King self-assigned this Oct 20, 2025
@stephane-segning
Copy link
Contributor

@codex please review

Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines 9 to +13
type: choice
options:
- dev
- prod
pull_request: null

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Provide environment input when triggering deploy on pull requests

Adding the pull_request event causes this workflow to run without inputs.environment, yet later steps still rely on that input for environment naming and for terraform init -var-file=${{ inputs.environment }}.tfvars. On a pull request run, this expression evaluates to an empty string, so Terraform is invoked with a non-existent .tfvars file and the job fails before planning. Either supply a default environment for PR runs or skip these steps when the workflow wasn’t dispatched with an explicit input.

Useful? React with 👍 / 👎.

Comment on lines +56 to +60
OPENID_CLIENT_SECRET = var.keycloak_client_secret
OPENID_SESSION_SECRET = random_string.social_session_secret.result

# USE_REDIS = "true"
REDIS_URI = var.redis_uri

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Populate Kubernetes secret using stringData instead of data

The kubernetes_secret uses the data attribute with raw strings, including values such as REDIS_URI = var.redis_uri that contain characters like ://. The Kubernetes provider expects data values to be base64 encoded, so applying this module will fail with an “illegal base64 data” error and the secret is never created. Use the string_data attribute or wrap each value in base64encode(...) before assigning to data.

Useful? React with 👍 / 👎.

Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines 9 to +13
type: choice
options:
- dev
- prod
pull_request: null

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Provide environment input when triggering deploy on pull requests

Adding the pull_request event causes this workflow to run without inputs.environment, yet later steps still rely on that input for environment naming and for terraform init -var-file=${{ inputs.environment }}.tfvars. On a pull request run, this expression evaluates to an empty string, so Terraform is invoked with a non-existent .tfvars file and the job fails before planning. Either supply a default environment for PR runs or skip these steps when the workflow wasn’t dispatched with an explicit input.

Useful? React with 👍 / 👎.

Comment on lines +56 to +60
OPENID_CLIENT_SECRET = var.keycloak_client_secret
OPENID_SESSION_SECRET = random_string.social_session_secret.result

# USE_REDIS = "true"
REDIS_URI = var.redis_uri

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Populate Kubernetes secret using stringData instead of data

The kubernetes_secret uses the data attribute with raw strings, including values such as REDIS_URI = var.redis_uri that contain characters like ://. The Kubernetes provider expects data values to be base64 encoded, so applying this module will fail with an “illegal base64 data” error and the secret is never created. Use the string_data attribute or wrap each value in base64encode(...) before assigning to data.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants