chore:Add DD_DURABLE_CROSS_INVOCATION_TRACING_ENABLED explanation in README.md#833
chore:Add DD_DURABLE_CROSS_INVOCATION_TRACING_ENABLED explanation in README.md#833joeyzhao2018 wants to merge 1 commit into
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4cb4fdfdbd
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".
| | DD_CAPTURE_LAMBDA_PAYLOAD | [Captures incoming and outgoing AWS Lambda payloads][1] in the Datadog APM spans for Lambda invocations. | `false` | | ||
| | DD_CAPTURE_LAMBDA_PAYLOAD_MAX_DEPTH | Determines the level of detail captured from AWS Lambda payloads, which are then assigned as tags for the `aws.lambda` span. It specifies the nesting depth of the JSON payload structure to process. Once the specified maximum depth is reached, the tag's value is set to the stringified value of any nested elements beyond this level. <br> For example, given the input payload: <pre>{<br> "lv1" : {<br> "lv2": {<br> "lv3": "val"<br> }<br> }<br>}</pre> If the depth is set to `2`, the resulting tag's key is set to `function.request.lv1.lv2` and the value is `{\"lv3\": \"val\"}`. <br> If the depth is set to `0`, the resulting tag's key is set to `function.request` and value is `{\"lv1\":{\"lv2\":{\"lv3\": \"val\"}}}` | `10` | | ||
| | DD_EXCEPTION_REPLAY_ENABLED | When set to `true`, the Lambda will run with Error Tracking Exception Replay enabled, capturing local variables. | `false` | | ||
| | DD_DURABLE_CROSS_INVOCATION_TRACING_ENABLED | For AWS Durable functions, the tracer creates extra checkpoints named `_datadog_{N}` to propagate trace context across function invocations, keeping spans from multiple invocations in one intact trace for each durable execution. | `true` | |
There was a problem hiding this comment.
This row is added to the table of datadog-lambda-python environment variables, but a repo-wide search shows DD_DURABLE_CROSS_INVOCATION_TRACING_ENABLED only appears in this README entry, unlike the other variables that are wired through datadog_lambda/config.py; the durable checkpoint extraction path also runs unconditionally when DurableExecutionArn is present. Users who set this documented flag to false will have it ignored by this package, so please either implement/read the setting or avoid documenting it here until it is actually supported.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
I heard you, Codex. Yes we need to migrate this library to the dd-trace library. But for now that feature flag's feature is split between two repos unfortunately....
1 participant
What does this PR do?
Add DD_DURABLE_CROSS_INVOCATION_TRACING_ENABLED explanation in README.md
Types of Changes