feat: introduce new logic improvements and structure for synthetics #45
Conversation
WalkthroughAdds a config_map-driven, per-config workflow for Datadog Synthetics: per-config synthetics_paths, parameters, locations, and tags; merges globals/context tags/per-config overrides per test; iterates per-test for module creation; restructures outputs to maps keyed by config entries; adds runtime validation; updates docs and Terraform version/provider. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant U as User
participant T as Terraform
participant YC as YAML Loader
participant M as Merge Logic
participant DP as Datadog Provider
participant O as Outputs
rect rgba(230,240,255,0.5)
note over U,T: Run terraform plan/apply with `config_map` (and optional top-level vars)
U->>T: terraform apply
end
rect rgba(240,255,230,0.5)
T->>T: Build local.configs (merge top-level with config_map)
T->>YC: Load synthetics_paths per config
YC-->>T: map_configs per config key
T->>T: Build test_keys_map (config_key,test_key)
end
rect rgba(255,245,230,0.5)
T->>T: Validate: error if no tests across configs
end
rect rgba(235,255,255,0.5)
T->>M: Merge [globals + context_tags? + per-config tags + YAML test map]
M-->>T: per-test merged definitions
end
rect rgba(255,235,245,0.5)
T->>DP: Create/Update Synthetics per merged test (for_each)
DP-->>T: returns test IDs, monitor IDs, names
end
rect rgba(245,245,245,0.8)
T->>O: Aggregate outputs keyed by config keys
O-->>U: structured maps: names, ids, monitor_ids, name→id
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~75 minutes Suggested labels
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (2)
src/CHANGELOG.md (1)
22-27: Fix typo in heading
config_paramters→config_parametersfor consistency with the variable name and to avoid confusion.-### `config_paramters` now map of strings +### `config_parameters` now map of stringsREADME.yaml (1)
104-108: Spelling & grammar touch-ups
expecs→expects- Datadog provider name should be capitalised consistently.
- the Datadog Terraform provider and the Datadog API expecs tags to be passed in + the Datadog Terraform provider and the Datadog API expects tags to be passed in
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
README.yaml(4 hunks)src/CHANGELOG.md(1 hunks)src/context.tf(1 hunks)src/main.tf(2 hunks)src/outputs.tf(1 hunks)src/variables.tf(2 hunks)src/versions.tf(1 hunks)
🧰 Additional context used
🪛 LanguageTool
src/CHANGELOG.md
[style] ~38-~38: To form a complete sentence, be sure to include a subject.
Context: .../synthetics/tests/browser/{public_id}` can be directly used a map value (you still...
(MISSING_IT_THERE)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Summary
🔇 Additional comments (4)
src/context.tf (1)
267-269: Indentation tidy-up looks goodPure whitespace change that improves readability; no functional impact.
src/versions.tf (1)
13-16: Validate the newcloudposse/utilsprovider requirementAdding a required provider that is never configured or referenced will trigger an unnecessary download and can confuse consumers.
Please double-check that:
utilsfunctions/resources are actually used in this module (e.g.utils_*data sources).- The version constraint
>= 1.12.0matches the first version that contains the needed functionality.If the provider is not yet used, consider dropping the stanza (or follow up with the provider blocks that will use it).
src/outputs.tf (1)
17-20: Confirm correct output attribute onmodule.datadog_syntheticsIt looks like you’re iterating over
v.datadog_synthetic_tests, but thecloudposse/platform/datadog//modules/syntheticsmodule may export its tests under a different key (for examplesynthetic_testsorsyntics_tests). A typo here will cause your plan to fail.• Inspect the actual outputs of
module.datadog_synthetics(via the Terraform Registry docs, the module’s source, orterraform console)
• Update your loop to match the exact attribute name. For example, if the output issynthetic_tests:- for vv in v.datadog_synthetic_tests : vv.name => vv.id + for vv in v.synthetic_tests : vv.name => vv.idOr, if it’s
synthetics_tests:- for vv in v.datadog_synthetic_tests : vv.name => vv.id + for vv in v.synthetics_tests : vv.name => vv.idPlease verify the correct attribute name and update accordingly.
src/variables.tf (1)
55-59: Narrowingconfig_parameterstomap(string)– double-check call sitesChanging from
map(any)tomap(string)tightens type safety, but it will force callers to cast numbers/booleans to strings, breaking existing configs that interpolate raw values. Please verify all downstream modules and sample YAML still compile after the change.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
src/main.tf (1)
81-82: Merge order still flips precedence – per-config parameters lose
merge(a, b, c)lets later arguments win.
Keepingeach.value.config_parametersfirst means any overlapping key invar.config_parametersoverrides the per-config value, contrary to the documented behaviour flagged in the previous review.- parameters = merge(each.value.config_parameters, var.config_parameters, local.context_tags) + # per-config > global > context + parameters = merge(var.config_parameters, each.value.config_parameters, local.context_tags)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/main.tf(2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Summary
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
src/main.tf (1)
8-16: Fallback map still overrides user-provided_top_levelentry
merge()gives later arguments precedence, therefore the synthetic fallback that is supplied aftervar.config_mapwill clobber any caller-defined_top_levelkey—exactly the concern raised in an earlier review.
Please reverse the merge order (or gate the fallback behindcontains(keys(var.config_map), local.legacy_config_key)as suggested previously) so user intent wins.
🧹 Nitpick comments (1)
src/main.tf (1)
73-75: Pin module sources to immutable SHAs to satisfy CKV_TF_1 and ensure reproducibilityStatic analysis flags every module block because only a version is pinned. Supply the full registry source with
?ref=or convert to a Git source locked to a commit hash.-source = "cloudposse/config/yaml" -version = "1.0.2" +source = "cloudposse/config/yaml" +version = "1.0.2" +# recommend: +# source = "git::https://github.com/cloudposse/terraform-yaml-config.git?ref=<commit-sha>"Repeat for
cloudposse/config/yaml//modules/deepmergeandcloudposse/platform/datadog//modules/synthetics.Also applies to: 88-90, 103-106
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/main.tf(1 hunks)
🧰 Additional context used
🪛 Checkov (3.2.334)
src/main.tf
[MEDIUM] 72-84: Ensure Terraform module sources use a commit hash
(CKV_TF_1)
[MEDIUM] 86-100: Ensure Terraform module sources use a commit hash
(CKV_TF_1)
🪛 GitHub Actions: Branch
src/main.tf
[error] 80-80: Git diff detected changes in src/main.tf. The pipeline failed due to uncommitted changes.
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Summary
🔇 Additional comments (1)
src/main.tf (1)
1-123: Formatting / updated plan artefacts caused pipeline failureCI reports “Git diff detected changes in src/main.tf”. Run
terraform fmtand commit the result, or inspect whether autogeneratedterraform-docs/tfsecupdates were missed.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (2)
src/main.tf (2)
8-16: Fallback_top_levelentry still overrides user-supplied config
merge(var.config_map, …fallback…)gives the second argument higher precedence, so a caller-defined_top_levelentry will be silently clobbered by the empty fallback map – exactly the issue called out in a previous review.- configs = local.enabled ? merge(var.config_map, length(var.synthetics_paths) == 0 ? {} : { (local.legacy_config_key) = { + configs = local.enabled ? merge( + # only add the fallback when the caller did **not** define the key + contains(keys(var.config_map), local.legacy_config_key) || length(var.synthetics_paths) == 0 + ? {} + : { + (local.legacy_config_key) = { + synthetics_paths = var.synthetics_paths + config_parameters = {} + locations = [] + tags = {} + context_tags_enabled = null + } + }, + var.config_map, + ) : {}This preserves user intent and prevents hard-to-trace configuration loss.
95-97:coalesce()will crash when both inputs arenull
coalesce(local.configs[…].context_tags_enabled, var.context_tags_enabled)throws an evaluation error if both values are unset (the default). Wrap intry()or add a safe fallback:- coalesce(local.configs[each.value.config_key].context_tags_enabled, var.context_tags_enabled) ? local.context_tags : {}, + coalesce( + local.configs[each.value.config_key].context_tags_enabled, + var.context_tags_enabled, + false, # safe default + ) ? local.context_tags : {},
🧹 Nitpick comments (1)
src/main.tf (1)
72-84: Pin registry modules to a specific commit to satisfy CKV_TF_1Checkov flags both module blocks for not using a commit hash. Consider pinning via the
refattribute to an exact commit or tag to ensure reproducible builds and reduce supply-chain risk.Also applies to: 86-100
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
src/main.tf(1 hunks)src/versions.tf(1 hunks)
✅ Files skipped from review due to trivial changes (1)
- src/versions.tf
🧰 Additional context used
🪛 Checkov (3.2.334)
src/main.tf
[MEDIUM] 72-84: Ensure Terraform module sources use a commit hash
(CKV_TF_1)
[MEDIUM] 86-100: Ensure Terraform module sources use a commit hash
(CKV_TF_1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Summary
|
Bats is finding a magical Cloud Posse requires all providers to use registry format introduced in Terraform 0.13, for example
aws = {
source = "hashicorp/aws"
version = ">= 3.0"
}
Please add constraints for these providers:
- null
--------------------------------- |
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (3)
src/main.tf (3)
8-16: Fallback_top_levelentry can still clobber caller-supplied config
merge(var.config_map, …fallback…)gives the fallback higher precedence, so if a caller already defines_top_level, their values are silently replaced by the empty stub.
This is the exact issue flagged in the previous review and is still unresolved.- configs = local.enabled ? merge(var.config_map, length(var.synthetics_paths) == 0 ? {} : { (local.legacy_config_key) = { + configs = local.enabled ? merge( + # inject fallback only when the caller did **not** define the key + contains(keys(var.config_map), local.legacy_config_key) || length(var.synthetics_paths) == 0 + ? {} + : { + (local.legacy_config_key) = { + synthetics_paths = var.synthetics_paths + config_parameters = {} + locations = [] + tags = {} + context_tags_enabled = null + } + }, + var.config_map, + ) : {}Failing to flip the precedence will keep erasing legitimate user input and lead to puzzling plans.
81-82: Parameter-precedence is still inverted;context_tagsoverwrite per-config values
merge()is last-arg wins. With the current order
merge(each.value.config_parameters, var.config_parameters, local.context_tags)
every collision is won bylocal.context_tags, then by global parameters, leaving per-config settings with the lowest priority—opposite to the documented intent.- parameters = merge(each.value.config_parameters, var.config_parameters, local.context_tags) + # precedence: context < global < per-config + parameters = merge( + local.context_tags, + var.config_parameters, + each.value.config_parameters, + )This keeps behaviour predictable and in line with the README.
95-97:coalesce()may throw when both inputs are null
coalesce(local.configs[…].context_tags_enabled, var.context_tags_enabled)will panic if both sides arenull(the default). Plans will fail unless the user explicitly sets one of them.Guard with a safe default or
try():- coalesce(local.configs[each.value.config_key].context_tags_enabled, var.context_tags_enabled) ? local.context_tags : {}, + coalesce( + local.configs[each.value.config_key].context_tags_enabled, + var.context_tags_enabled, + false, # safe default + ) + ? local.context_tags + : {},Preventing unexpected runtime errors is worth the small verbosity.
🧹 Nitpick comments (1)
src/main.tf (1)
112-116: Location list may contain duplicated private location IDs
distinct(compact(concat(local.configs[each.key].locations, var.locations, [local.datadog_synthetics_private_location_id])))removes duplicates, but if the caller already included the private location in either list and provided it in a different capitalisation, thedistinct()on raw strings will consider them different.
Consider normalising to lower-case beforedistinct()to avoid accidental duplication of the same location ID.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/main.tf(2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Summary
|
/terratest |
|
There are no real tests for this component. So we set terratest statuses to successful execution without running any tests |
|
@goruha can you please check why the |
|
@RoseSecurity it's not "magical" provider |
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
|
💥 This pull request now has conflicts. Could you fix it @RoseSecurity? 🙏 |
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
There was a problem hiding this comment.
Actionable comments posted: 3
♻️ Duplicate comments (10)
README.yaml (7)
51-67: Fix typo and call out string-only parameters (map(string))
- “they keys” → “the keys”.
- Add note: config_parameters is map(string); quote/convert non-strings.
config_map: # The top-level key must be unique within the component configuration. this-test: config_parameters: this_test_param: "this-test-value" + # Note: config_parameters is a map(string). Quote all values or coerce to strings. synthetics_paths: # Paths relative to the component directory (where `main.tf` is located) - catalog/synthetics/this-test.yaml - # If re-using the same test with different parameters, ensure they keys + # If re-using the same test with different parameters, ensure the keys # are distinct. One way to do this is to parameterize the key along with # the test parameters and fill them in using Atmos' Go template support, # https://atmos.tools/core-concepts/stacks/imports/#go-templates-in-imports
118-127: Fix typo and clarify tags format guidance
- “expecs” → “expects”.
- Explicitly tell users to omit list-based tags in YAML and use component inputs.
### Special note about tags Cloud Posse modules expect tags to be passed in as a map of strings, but - the Datadog Terraform provider and the Datadog API expecs tags to be passed in + the Datadog Terraform provider and the Datadog API expects tags to be passed in as a list of strings. Unfortunately, we do not have a good way to support both formats at the same time. We have chosen to support the map of strings, to be consistent with other Cloud Posse modules, which - means that tags passed in via the API schema will be ignored. If you want - to specify tags in the YAML files, you need to specify them as maps of strings. + means that tags passed in via the API schema will be ignored. If you want + to specify tags in YAML, omit the list-based `tags` field entirely and provide tags + via the component inputs (map of strings). Having both will cause Terraform to fail.
206-209: Update examples link to this repo’s pathPoint to this repository’s examples under src/catalog/synthetics/examples.
- These configuration examples are defined in the YAML files in the [catalog/synthetics/examples](https://github.com/cloudposse/terraform-aws-components/tree/main/modules/datadog-synthetics/catalog/synthetics/examples) folder. + These configuration examples are defined in the YAML files in the [catalog/synthetics/examples](https://github.com/cloudposse-terraform-components/aws-datadog-synthetics/tree/main/src/catalog/synthetics/examples) folder.
261-269: Align env var names with headers (DD_*), and mention both keys- # Be sure you have already set `public_id` and `DATADOG_APP_KEY` as described above + # Be sure you have already set `public_id`, `DD_API_KEY`, and `DD_APP_KEY` as described above
342-344: Avoid backticks; quote the Terraform address literally- atmos terraform import datadog-synthetics `module.datadog_synthetics["long key name"].datadog_synthetics_test.default["other long key name"]` ${public_id} -s=<stack-name> + atmos terraform import datadog-synthetics 'module.datadog_synthetics["long key name"].datadog_synthetics_test.default["other long key name"]' "${public_id}" -s=<stack-name>
211-216: Variable name typo: usesynthetics_pathsFix reference to match the variable name used elsewhere.
- Then use the `synthetic_paths` variable to point the component to the synthetic test configuration files. + Then use the `synthetics_paths` variable to point the component to the synthetic test configuration files.
236-239: Replace hex-like example keys to avoid Gitleaks/CI failuresUse placeholders; add a warning comment.
- export DD_API_KEY="1234567890abcdef1234567890abcdef" - export DD_APP_KEY="1234567890abcdef1234567890abcdef12345678" + export DD_API_KEY="<YOUR_DD_API_KEY>" + export DD_APP_KEY="<YOUR_DD_APP_KEY>" + # Do not commit real keys. These are placeholders for local use only.src/main.tf (3)
8-16: Fallback_top_levelcan overwrite user-provided entryMerging the fallback after var.config_map will clobber a user-defined
_top_level. Inject only when missing.- configs = local.enabled ? merge(var.config_map, length(var.synthetics_paths) == 0 ? {} : { (local.legacy_config_key) = { + configs = local.enabled ? merge( + contains(keys(var.config_map), local.legacy_config_key) || length(var.synthetics_paths) == 0 + ? {} + : { (local.legacy_config_key) = { synthetics_paths = var.synthetics_paths # We do not need to include the top-level parameters here because they are always included, # but we do need to include the attributes to ensure they are always present, even when var.config_map is empty. config_parameters = {} locations = [] tags = {} context_tags_enabled = null - } }) : {} + } }, + var.config_map, + ) : {}
81-82: Parameter precedence inverted (context should be lowest, per-config highest)Per-config must override globals; context tags should not overwrite either.
- parameters = merge(each.value.config_parameters, var.config_parameters, local.context_tags) + # precedence: context < global < per-config + parameters = merge( + local.context_tags, + var.config_parameters, + each.value.config_parameters, + )
95-97: coalesce() can error when both inputs are nullAdd a safe fallback to avoid plan-time crash.
- { tags = merge( - coalesce(local.configs[each.value.config_key].context_tags_enabled, var.context_tags_enabled) ? local.context_tags : {}, - local.configs[each.value.config_key].tags) }, + { tags = merge( + coalesce( + local.configs[each.value.config_key].context_tags_enabled, + var.context_tags_enabled, + false + ) + ? local.context_tags + : {}, + local.configs[each.value.config_key].tags + ) },
🧹 Nitpick comments (1)
src/main.tf (1)
44-59: Add provider constraint fornullto fix CINull resource is used; CI complains about missing provider constraints. Add to src/versions.tf.
Proposed src/versions.tf snippet:
terraform { required_version = ">= 1.5.0" required_providers { null = { source = "hashicorp/null" version = "~> 3.2" } # existing providers... } }Please add and re-run CI to confirm the failure is resolved.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
README.yaml(4 hunks)src/main.tf(2 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
src/{main,variables,outputs,providers,versions,context}.tf
📄 CodeRabbit inference engine (AGENTS.md)
Keep the Terraform component as the single source of truth in src/ with files: main.tf, variables.tf, outputs.tf, providers.tf, versions.tf, and context.tf
Files:
src/main.tf
src/**/*.tf
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.tf: Use 2-space indentation for Terraform files
In Terraform, prefer lower_snake_case for variables and locals; keep resource/data names descriptive and aligned with Cloud Posse null-label patterns
Do not commit formatting or lint violations; ensureterraform fmt -recursivehas been applied
Comply with TFLint rules configured in .tflint.hcl
Files:
src/main.tf
README.yaml
📄 CodeRabbit inference engine (AGENTS.md)
Treat README.yaml as the source for generated documentation
Files:
README.yaml
**/*.{yaml,yml,md}
📄 CodeRabbit inference engine (AGENTS.md)
Use 2-space indentation for YAML and Markdown files
Files:
README.yaml
🪛 Gitleaks (8.28.0)
README.yaml
[high] 237-237: Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
(generic-api-key)
[high] 238-238: Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
(generic-api-key)
🔇 Additional comments (1)
src/main.tf (1)
112-116: Only include private location when enabledIn src/main.tf (lines 112–116), wrap the private location ID in a conditional:
locations = distinct(compact(concat( local.configs[each.key].locations, var.locations, - [local.datadog_synthetics_private_location_id] + var.private_location_test_enabled ? [local.datadog_synthetics_private_location_id] : [] )))Verify that var.private_location_test_enabled (or a per-config equivalent) is wired correctly in your configs.
| Next, download the test definition (in JSON), convert it to YAML, and save it to a file. We use the `yq` command from | ||
| [mikefarah](https://github.com/mikefarah/yq) to do the conversion. You can install it with `brew install yq` on a Mac, | ||
| or you the version pre-installed in Geodesic. (Note that there are several other similar tools with the same name, | ||
| so be sure you are using the one from `mikefarah` by reviewing the output of `yq --version`.) | ||
There was a problem hiding this comment.
Grammar fix
“or you the version pre-installed” → “or use the version pre-installed”.
- or you the version pre-installed in Geodesic. (Note that there are several other similar tools with the same name,
+ or use the version pre-installed in Geodesic. (Note that there are several other similar tools with the same name,📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| Next, download the test definition (in JSON), convert it to YAML, and save it to a file. We use the `yq` command from | |
| [mikefarah](https://github.com/mikefarah/yq) to do the conversion. You can install it with `brew install yq` on a Mac, | |
| or you the version pre-installed in Geodesic. (Note that there are several other similar tools with the same name, | |
| so be sure you are using the one from `mikefarah` by reviewing the output of `yq --version`.) | |
| Next, download the test definition (in JSON), convert it to YAML, and save it to a file. We use the `yq` command from | |
| [mikefarah](https://github.com/mikefarah/yq) to do the conversion. You can install it with `brew install yq` on a Mac, | |
| or use the version pre-installed in Geodesic. (Note that there are several other similar tools with the same name, | |
| so be sure you are using the one from `mikefarah` by reviewing the output of `yq --version`.) |
🤖 Prompt for AI Agents
In README.yaml around lines 250 to 254, fix the grammatical error in the
sentence that reads "or you the version pre-installed in Geodesic." by changing
it to "or use the version pre-installed in Geodesic." so the instruction reads
correctly while leaving the rest of the paragraph unchanged.
| "Check that the `synthetic_paths` list matches at least one valid YAML file.\n\n %s\n\n" | ||
| ]), join("\n ", [for k, v in module.datadog_synthetics_yaml_config : k if length(v.map_configs) == 0]), | ||
| join("\n ", concat(["<config_map key>: [<synthetics_paths>]", "--------------------------------------"], | ||
| [for k, v in module.datadog_synthetics_yaml_config : format("%s: [\"%s\"]", k, join("\", \"", local.configs[k].synthetics_paths)) if length(v.map_configs) == 0]) | ||
| )) |
There was a problem hiding this comment.
Message typo: use synthetics_paths in precondition error
Align with variable name.
- "Check that the `synthetic_paths` list matches at least one valid YAML file.\n\n %s\n\n"
+ "Check that the `synthetics_paths` list matches at least one valid YAML file.\n\n %s\n\n"📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "Check that the `synthetic_paths` list matches at least one valid YAML file.\n\n %s\n\n" | |
| ]), join("\n ", [for k, v in module.datadog_synthetics_yaml_config : k if length(v.map_configs) == 0]), | |
| join("\n ", concat(["<config_map key>: [<synthetics_paths>]", "--------------------------------------"], | |
| [for k, v in module.datadog_synthetics_yaml_config : format("%s: [\"%s\"]", k, join("\", \"", local.configs[k].synthetics_paths)) if length(v.map_configs) == 0]) | |
| )) | |
| "Check that the `synthetics_paths` list matches at least one valid YAML file.\n\n %s\n\n" | |
| ]), join("\n ", [for k, v in module.datadog_synthetics_yaml_config : k if length(v.map_configs) == 0]), | |
| join("\n ", concat(["<config_map key>: [<synthetics_paths>]", "--------------------------------------"], | |
| [for k, v in module.datadog_synthetics_yaml_config : format("%s: [\"%s\"]", k, join("\", \"", local.configs[k].synthetics_paths)) if length(v.map_configs) == 0]) | |
| )) |
🤖 Prompt for AI Agents
In src/main.tf around lines 52 to 56, the precondition error message uses the
wrong variable name "synthetic_paths" — change that string to "synthetics_paths"
so it matches the actual variable/local name used elsewhere; update any
formatted output that referenced the incorrect name to use "synthetics_paths"
consistently and ensure the join/format lines still interpolate
local.configs[k].synthetics_paths correctly.
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
|
Heads up! This pull request looks stale. It will be closed soon, if there are no new commits. ⏳ |
mergify
bot
added
stale
what
Note
This improvement was first introduced by Nuru, but they never made it back to the community component. Feel free to adopt or disregard
config_mapadded, old configuration movedThe
config_mapargument of thedatadog_synthetics_testresource is now the primary wayto configure a test. The old collection of top-level arguments is still supported,
but it is now deprecated. The top level arguments are still applied to all tests, but
now you can deploy the same test multiple times with different parameters.
Note that if an entry in
config_map.synthetics_pathsspecifies multiple test files, or if the test fileitself contains multiple tests, they will all get the same configuration. If you want
to deploy tests with different configurations, you will need to use multiple files and
configure them individually.
Outputs are now maps
Corresponding to the change in the
config_mapargument, the outputs of the moduleare all maps, with keys corresponding to the keys in the
config_mapargument.The outputs relating to the top-level arguments are included in the maps
under the key
_top_level.config_paramtersnow map of stringsThe
config_parametersargument of thedatadog_synthetics_testresource is now a map of stringsinstead of a
map(any). The values have to be converted to strings anyway to be interpolatedinto the test configuration, and it resolves some type conversion issues in Terraform to
use fully-specified types.
usage
Summary by CodeRabbit
New Features
Refactor
Documentation
Chores