Closed
Conversation
|
Claude finished @BenWu's task in 1m 11s —— View job Code Review
Overall this is a clean and straightforward PoC. The approach (fire-and-forget publish to GCP Pub/Sub within the existing event emitter) is reasonable, and the gRPC retry handling is a good callout. A few issues to address, some before shipping to prod: Issues1.
{
name: 'GCP_EVENT_PROJECT',
value: 'pocket-snowplow-shim-dev', // never changes for prod!
},Unlike 2. Unguarded
const gcp_credentials = config.gcp.serviceAccountKey
? JSON.parse(config.gcp.serviceAccountKey) // throws if malformed JSON
: undefined;If 3. Config defaults silently fall through to dev values in prod
projectId: process.env.GCP_EVENT_PROJECT || 'pocket-snowplow-shim-dev',
topicName: process.env.GCP_EVENT_TOPIC || 'snowplow-events-dev',If either env var is accidentally unset in prod, events will silently publish to the dev GCP project/topic with no error. Since these are set explicitly via the infra config, the fallback values aren't needed in practice — but if you want to keep them, consider naming them to make the dev intent clear (or at minimum document that they're dev-only defaults). Minor4. 5. 6. PubSub/topic initialized at module level — This works fine, but it does make unit testing harder (you can't easily mock the client per test). Not a blocker for a PoC, but worth noting if you add tests later. Moving initialization into the class (or injecting the What looks good
|
Plan Result (corpus-scheduler-lambda-cdk-production)
Change Result (Click me) # aws_lambda_function.corpus-scheduler-sqs-lambda_F2ECDF9F will be updated in-place
~ resource "aws_lambda_function" "corpus-scheduler-sqs-lambda_F2ECDF9F" {
id = "CorpusSchedulerLambda-Prod-SQS-Function"
~ qualified_arn = "arn:aws:lambda:us-east-1:996905175585:function:CorpusSchedulerLambda-Prod-SQS-Function:290" -> (known after apply)
~ qualified_invoke_arn = "arn:aws:apigateway:us-east-1:lambda:path/2015-03-31/functions/arn:aws:lambda:us-east-1:996905175585:function:CorpusSchedulerLambda-Prod-SQS-Function:290/invocations" -> (known after apply)
tags = {
"app_code" = "content"
"component_code" = "content-corpusschedulerlambda"
"env_code" = "prod"
"environment" = "Prod"
"service" = "CorpusSchedulerLambda"
}
~ version = "290" -> (known after apply)
# (20 unchanged attributes hidden)
~ environment {
~ variables = {
~ "GIT_SHA" = (sensitive value)
# (7 unchanged elements hidden)
}
}
# (4 unchanged blocks hidden)
}
Plan: 0 to add, 1 to change, 0 to destroy.
|
Plan Result (prospect-translation-lambda-cdk-production)
Change Result (Click me) # aws_lambda_function.translation-lambda_translation-sqs-lambda_B9BDF6BA will be updated in-place
~ resource "aws_lambda_function" "translation-lambda_translation-sqs-lambda_B9BDF6BA" {
id = "ProspectAPI-Prod-Sqs-Translation-Function"
tags = {
"app_code" = "content"
"component_code" = "content-prospectapi"
"env_code" = "prod"
"environment" = "Prod"
"service" = "ProspectAPI-Sqs-Translation"
}
# (22 unchanged attributes hidden)
~ environment {
~ variables = {
~ "GIT_SHA" = (sensitive value)
# (5 unchanged elements hidden)
}
}
# (4 unchanged blocks hidden)
}
Plan: 0 to add, 1 to change, 0 to destroy.
|
Plan Result (section-manager-lambda-cdk-production)
Change Result (Click me) # aws_lambda_function.section-manager-sqs-lambda_D7365DAE will be updated in-place
~ resource "aws_lambda_function" "section-manager-sqs-lambda_D7365DAE" {
id = "SectionManagerLambda-Prod-SQS-Function"
~ qualified_arn = "arn:aws:lambda:us-east-1:996905175585:function:SectionManagerLambda-Prod-SQS-Function:86" -> (known after apply)
~ qualified_invoke_arn = "arn:aws:apigateway:us-east-1:lambda:path/2015-03-31/functions/arn:aws:lambda:us-east-1:996905175585:function:SectionManagerLambda-Prod-SQS-Function:86/invocations" -> (known after apply)
tags = {
"app_code" = "content"
"component_code" = "content-sectionmanagerlambda"
"env_code" = "prod"
"environment" = "Prod"
"service" = "SectionManagerLambda"
}
~ version = "86" -> (known after apply)
# (20 unchanged attributes hidden)
~ environment {
~ variables = {
- "GIT_SHA" = "829a2457a67a8e774bc9e284cd4b7a490c879f84" -> null
# (5 unchanged elements hidden)
}
}
# (4 unchanged blocks hidden)
}
Plan: 0 to add, 1 to change, 0 to destroy.
|
Plan Result (curated-corpus-api-cdk-production)
|
Plan Result (prospect-api-cdk-production)
Change Result (Click me) # data.aws_iam_policy_document.application_ecs_service_ecs-iam_data-ecs-task-role-policy_090CC3AD will be read during apply
# (depends on a resource or a module with changes pending)
<= data "aws_iam_policy_document" "application_ecs_service_ecs-iam_data-ecs-task-role-policy_090CC3AD" {
+ id = (known after apply)
+ json = (known after apply)
+ minified_json = (known after apply)
+ version = "2012-10-17"
+ statement {
+ actions = [
+ "dynamodb:BatchGet*",
+ "dynamodb:DescribeTable",
+ "dynamodb:Get*",
+ "dynamodb:Query",
+ "dynamodb:Scan",
+ "dynamodb:UpdateItem",
]
+ effect = "Allow"
+ resources = [
+ "arn:aws:dynamodb:us-east-1:996905175585:table/PROAPI-Prod-Prospects",
+ "arn:aws:dynamodb:us-east-1:996905175585:table/PROAPI-Prod-Prospects/*",
]
}
+ statement {
+ actions = [
+ "s3:*",
]
+ effect = "Allow"
+ resources = [
+ "arn:aws:s3:::pocket-prospectapi-prod-images",
+ "arn:aws:s3:::pocket-prospectapi-prod-images/*",
]
}
+ statement {
+ actions = [
+ "logs:CreateLogGroup",
+ "logs:CreateLogStream",
+ "logs:DescribeLogGroups",
+ "logs:DescribeLogStreams",
+ "logs:PutLogEvents",
]
+ effect = "Allow"
+ resources = [
+ "*",
]
}
}
# aws_dynamodb_table.dynamodb_prospects_dynamodb_table_9854E41E will be updated in-place
~ resource "aws_dynamodb_table" "dynamodb_prospects_dynamodb_table_9854E41E" {
id = "PROAPI-Prod-Prospects"
name = "PROAPI-Prod-Prospects"
tags = {
"app_code" = "content"
"component_code" = "content-prospectapi"
"env_code" = "prod"
"environment" = "Prod"
"service" = "ProspectAPI"
}
# (9 unchanged attributes hidden)
- global_secondary_index {
- hash_key = "scheduledSurfaceGuid" -> null
- name = "scheduledSurfaceGuid-prospectType" -> null
- non_key_attributes = [] -> null
- projection_type = "ALL" -> null
- range_key = "prospectType" -> null
- read_capacity = 0 -> null
- write_capacity = 0 -> null
}
+ global_secondary_index {
+ hash_key = "scheduledSurfaceGuid"
+ name = "scheduledSurfaceGuid-prospectType"
+ non_key_attributes = []
+ projection_type = "ALL"
+ range_key = "prospectType"
+ read_capacity = 5
+ write_capacity = 5
}
# (5 unchanged blocks hidden)
}
# aws_iam_policy.application_ecs_service_ecs-iam_ecs-task-role-policy_6FC89FB6 will be updated in-place
~ resource "aws_iam_policy" "application_ecs_service_ecs-iam_ecs-task-role-policy_6FC89FB6" {
id = "arn:aws:iam::996905175585:policy/ProspectAPI-Prod-TaskRolePolicy"
name = "ProspectAPI-Prod-TaskRolePolicy"
~ policy = jsonencode(
{
- Statement = [
- {
- Action = [
- "dynamodb:UpdateItem",
- "dynamodb:Scan",
- "dynamodb:Query",
- "dynamodb:Get*",
- "dynamodb:DescribeTable",
- "dynamodb:BatchGet*",
]
- Effect = "Allow"
- Resource = [
- "arn:aws:dynamodb:us-east-1:996905175585:table/PROAPI-Prod-Prospects/*",
- "arn:aws:dynamodb:us-east-1:996905175585:table/PROAPI-Prod-Prospects",
]
},
- {
- Action = "s3:*"
- Effect = "Allow"
- Resource = [
- "arn:aws:s3:::pocket-prospectapi-prod-images/*",
- "arn:aws:s3:::pocket-prospectapi-prod-images",
]
},
- {
- Action = [
- "logs:PutLogEvents",
- "logs:DescribeLogStreams",
- "logs:DescribeLogGroups",
- "logs:CreateLogStream",
- "logs:CreateLogGroup",
]
- Effect = "Allow"
- Resource = "*"
},
]
- Version = "2012-10-17"
}
) -> (known after apply)
tags = {
"app_code" = "content"
"component_code" = "content-prospectapi"
"env_code" = "prod"
"environment" = "Prod"
"service" = "ProspectAPI"
}
# (5 unchanged attributes hidden)
}
Plan: 0 to add, 2 to change, 0 to destroy. |
mmiermans
reviewed
Mar 17, 2026
Contributor
mmiermans
left a comment
mmiermans
left a comment
There was a problem hiding this comment.
I'm curious to understand the different approaches we could take. Let meet live to discuss.
| "@aws-sdk/client-s3": "3.529.1", | ||
| "@aws-sdk/lib-storage": "3.529.1", | ||
| "@devoxa/prisma-relay-cursor-connection": "3.1.0", | ||
| "@google-cloud/pubsub": "^5.3.0", |
Contributor
There was a problem hiding this comment.
What are the pros/cons of using pub/sub directly versus using @mozilla/glean with a mozlog configuration? I created an experimental PR using Glean in this repo a year ago.
Collaborator
Author
|
No longer needed. I'll add details in https://mozilla-hub.atlassian.net/browse/DENG-10803 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Goal
This adds an additional call in the event emitter in the curated_corpus_api to send events to a pubsub topic in gcp for further transformations and loading into bigquery (that's set up in https://github.com/mozilla-services/data-sandbox-terraform/pull/121/changes). The code so far is a simple proof of concept to validate this approach. This does work locally when triggering an event via graphql
I'd love feedback/perspectives on:
Implementation Decisions
Deployment steps
References
JIRA ticket: