Replays Self-Serve Bulk Delete System#16
Conversation
This validates both the [Working Draft](https://www.w3.org/TR/reporting-1/#concept-reports) and the [Editor's Draft](https://w3c.github.io/reporting/#concept-reports) formats. Fixes [ID-730 - Accept current and upcoming data model](https://linear.app/getsentry/issue/ID-730/accept-current-and-upcoming-data-model).
…o 'low' (#93927)" This reverts commit 8d04522. Co-authored-by: roaga <47861399+roaga@users.noreply.github.com>
Missed in the initial commit, leading to some relevant logs being unannotated.
We have had a few tasks get killed at 10% rollout.
Also add a test, so that this doesn't happen again
Fixes DE-129 and DE-156 --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
These transitions should be matching
…` (#93946) Use `project_id` on the replay record instead of the URL (where it does not always exist). --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: getsantry[bot] <66042841+getsantry[bot]@users.noreply.github.com>
Also fixed `replay.view_html` -> `replay.view-html` --------- Co-authored-by: Michelle Zhang <56095982+michellewzhang@users.noreply.github.com>
…948) gets `npx @typescript/native-preview` passing again
This adds mode for all things tracing. This encompasses transactions/metrics/spans. Taken from https://github.com/getsentry/sentry/blob/feeaf393deeca8b97675bff23039c6320270aab5/src/sentry/runner/commands/devserver.py#L370
The conditions associated with a DCG can change over time, and it's good if we can be completely confident that they're consistent within a given task execution.
This is unused and most regex experiments have required broader changes to ensure that regexes are evaluated in a specific order (ex: traceparent). Removing this for now to simplify the code and very slightly improve runtime performance.
From some testing (on feedback lists of all different lengths), this prompt seems to work better. It doesn't write overly long sentences and also does a better job at "summarizing" versus just mentioning a few specific topics and leaving out others.
Just remove a couple custom Flex* classes in favor of the Flex primitive
This has been killed a few times. Refs SENTRY-42M7
…n table (#93892) <!-- Describe your PR here. --> [ticket](https://linear.app/getsentry/issue/ID-156/grouping-info-remove-type-field-from-ui) The Type field in the Grouping Info section of the issue details page was redundant. This removes the Type row from all variant types while keeping the underlying data structure intact. before  after 
### Changes Related to this PR: getsentry/sentry#93810. This is part 1 of the change, which is pulling out the new component and just adding it to the repo. Also includes some simplification of the logic in the base component. Part 2 will be replacing tables in widgets. ### Before/After There is no UI change as the table is not being used yet. There is a new story page for the component.
…93943) to prevent this issue from becoming too noisy, add a noise config
Unfortunately, 'event_data' went from being the variable for current event context to being the complete parsed data from Redis, and we continued logging it per group. That's more data than we should be logging even arguably once, let alone per group.
Co-authored-by: Abdullah Khan <abdullahkhan@PG9Y57YDXQ.local>
Adds some simple analytics to our endpoint so we can begin building a dashboard in Amplitude.
Previously, explore supported multiple y axis per chart, so each visualize supported multiple y axis. That functionality has since been removed for simplicity so update the types here to match. Keep in mind that saved queries still store them as an array so when serializing/deserializing, we still need to treat it as an array.
We'll need the `useGetTraceItemAttributeKeys` hook in other places so refactoring it so that it can exported.
- getsentry/sentry#93894 removed usage - getsentry/sentry-options-automator#4243 removed the last override
When the max segment ID is null the process fails. We should exit early since if there aren't any segments to delete there's nothing to do.
|
bugbot run |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 7 potential issues.
Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.
| units: {}, | ||
| }, | ||
| }} | ||
| /> |
There was a problem hiding this comment.
Feature-flagged table renders no widget data
High Severity
When organization.features includes use-table-widget-visualization, tableResultComponent renders TableWidgetVisualization with hardcoded empty columns and empty tableData. This drops all real result.data and result.meta, so the table appears blank despite successful query results.
| const queryKey = useMemo( | ||
| () => ['use-trace-item-attribute-keys', queryOptions], | ||
| [queryOptions] | ||
| ); |
There was a problem hiding this comment.
Trace attribute cache key misses organization scope
Medium Severity
useTraceItemAttributeKeys builds queryKey from only queryOptions and omits the org identifier. Since queryFn fetches /organizations/{slug}/trace-items/attributes/, cached results can be reused across organizations with matching params, returning wrong attribute keys.
Additional Locations (1)
| def validate_age(self, value: int) -> int: | ||
| """Validate that age is present, but not timestamp.""" | ||
| if self.initial_data.get("timestamp"): | ||
| raise serializers.ValidationError("If age is present, timestamp must be absent") |
There was a problem hiding this comment.
Age/timestamp mutual exclusion bypasses zero values
Low Severity
BrowserReportSerializer checks mutual exclusivity with truthy tests on self.initial_data.get("age") and get("timestamp"). If either field is 0, validation treats it as absent, so reports containing both age and timestamp can pass incorrectly.
| # Check if we need to yield any error messages that occurred before this event | ||
| while error_idx < len(error_events) and error_events[error_idx][ | ||
| "timestamp" | ||
| ] < event.get("timestamp", 0): |
There was a problem hiding this comment.
Error timestamp type breaks replay summarization
High Severity
fetch_error_details stores data["timestamp"] as-is from nodestore, then gen_request_data compares it with replay event timestamps using <. Error event timestamps are commonly ISO strings, so mixed string/number comparison can raise at runtime and fail the summarize endpoint.
Additional Locations (1)
| message=data.get("message", ""), | ||
| ) | ||
| for event_id, data in zip(error_ids, events.values()) | ||
| if data is not None |
There was a problem hiding this comment.
Error details can attach to wrong IDs
Medium Severity
fetch_error_details pairs error_ids with events.values() via zip, but get_multi returns a mapping keyed by node id. This assumes value iteration order matches requested IDs, which is not guaranteed by mapping contract, so titles/messages can be associated with the wrong error_id.
| ) | ||
|
|
||
| error_ids = response[0].get("error_ids", []) if response else [] | ||
|
|
There was a problem hiding this comment.
Error context skipped when fields are filtered
Medium Severity
error_ids are read from process_raw_response(...) using client-provided field filters. If the request omits error_ids in field, response[0] won’t contain it, so fetch_error_details gets an empty list and error context is silently dropped.
| # Fields that do not overlap between specs | ||
| # We need to support both specs | ||
| age = serializers.IntegerField(required=False) | ||
| timestamp = serializers.IntegerField(required=False, min_value=0) |
There was a problem hiding this comment.
Reports accepted without any timestamp field
Low Severity
BrowserReportSerializer makes both age and timestamp optional, but there is no validation requiring at least one of them. Reports missing both fields now validate and are counted, even though they lack required temporal context.
20 participants
Test 5
Summary by CodeRabbit
Release Notes
New Features
Bug Fixes
Replicated from ai-code-review-evaluation/sentry-coderabbit#5
Note
Medium Risk
Touches multiple product areas (AI pipelines, replay summarization, dashboards rendering) and modifies request validation and async task deadlines; regressions could affect user-facing summaries, table rendering behind a flag, and background processing behavior.
Overview
Adds AI summarization surfaces: a new frontend
FeedbackSummarycomponent + hook calling/feedback-summary/, and tighter LLM prompting/format constraints for feedback summary generation.Enhances replay breadcrumb summarization by pulling
error_idsfor a replay, fetching event details from nodestore, and interleaving error messages with breadcrumb logs before sending to Seer (with a query param to disable error context).Introduces a new
TableWidgetVisualization(GridEditable-based) with default cell renderers, fixtures, stories, and tests, and gates dashboard table rendering behind theuse-table-widget-visualizationfeature flag.Operational/cleanup changes: improved merged PR bot issue formatting (truncate titles + include environment), adds strict serializer validation to the browser reporting collector, adds detector
ownersupport in workflow validators, sets taskworkerprocessing_deadline_durationon several control-plane tasks, tweaks replay deletion to handle nullmax_segment_id, changes default autofix tuning tooff, removes unused parameterization regex experiment/option, adds snubaequationspassthrough, updates replay analytics event names/zoom tracking, and updates devservices with newsnuba-metrics+ tracing mode consumers.Written by Cursor Bugbot for commit ea188e2. Configure here.