ref(crons): Reorganize incident creation / issue occurrence logic

[ShashankFC]

Test 8

Summary by CodeRabbit

Release Notes

• New Features
  • Implemented automatic incident creation and detection for monitor failures, respecting configurable failure thresholds.
  • Enhanced incident context with human-readable failure reason summaries, environment details, and tracking of last successful check-in times to aid in incident diagnosis and resolution.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

---

Replicated from ai-code-review-evaluation/sentry-coderabbit#8

[ShashankFC]

@cubic-dev-ai review this pull request

[cubic-dev-ai]

@cubic-dev-ai review this pull request

@ShashankFC I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

3 issues found across 4 files

Prompt for AI agents (all issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name="src/sentry/monitors/logic/incident_occurrence.py">

<violation number="1" location="src/sentry/monitors/logic/incident_occurrence.py:132">
P3: Typo in docstring: "humam readible" should be "human readable".</violation>

<violation number="2" location="src/sentry/monitors/logic/incident_occurrence.py:168">
P1: Bug: Returns the original `monitor_environment.monitor.config` instead of the locally modified `config` copy. The `schedule_type` display transformation on line 167 is silently discarded.</violation>
</file>

<file name="src/sentry/monitors/logic/incidents.py">

<violation number="1" location="src/sentry/monitors/logic/incidents.py:52">
P1: Missing check that enough check-ins exist to meet the failure threshold. If fewer check-ins exist than `failure_issue_threshold` (e.g., a newly created monitor), an incident will be created prematurely because the code only verifies that none of the returned check-ins are OK, not that there are *enough* failures to meet the threshold.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

P1: Bug: Returns the original monitor_environment.monitor.config instead of the locally modified config copy. The schedule_type display transformation on line 167 is silently discarded.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At src/sentry/monitors/logic/incident_occurrence.py, line 168:

<comment>Bug: Returns the original `monitor_environment.monitor.config` instead of the locally modified `config` copy. The `schedule_type` display transformation on line 167 is silently discarded.</comment>

<file context>
@@ -0,0 +1,171 @@
+        "id": str(monitor_environment.monitor.guid),
+        "slug": str(monitor_environment.monitor.slug),
+        "name": monitor_environment.monitor.name,
+        "config": monitor_environment.monitor.config,
+        "status": monitor_environment.get_status_display(),
+        "type": monitor_environment.monitor.get_type_display(),
</file context>

[cubic-dev-ai]

P1: Missing check that enough check-ins exist to meet the failure threshold. If fewer check-ins exist than failure_issue_threshold (e.g., a newly created monitor), an incident will be created prematurely because the code only verifies that none of the returned check-ins are OK, not that there are enough failures to meet the threshold.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At src/sentry/monitors/logic/incidents.py, line 52:

<comment>Missing check that enough check-ins exist to meet the failure threshold. If fewer check-ins exist than `failure_issue_threshold` (e.g., a newly created monitor), an incident will be created prematurely because the code only verifies that none of the returned check-ins are OK, not that there are *enough* failures to meet the threshold.</comment>

<file context>
@@ -0,0 +1,104 @@
+
+            # If we have any successful check-ins within the threshold of
+            # commits we have NOT reached an incident state
+            if any([checkin["status"] == CheckInStatus.OK for checkin in previous_checkins]):
+                return False
+
</file context>

[cubic-dev-ai]

P3: Typo in docstring: "humam readible" should be "human readable".

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At src/sentry/monitors/logic/incident_occurrence.py, line 132:

<comment>Typo in docstring: "humam readible" should be "human readable".</comment>

<file context>
@@ -0,0 +1,171 @@
+
+def get_failure_reason(failed_checkins: Sequence[SimpleCheckIn]):
+    """
+    Builds a humam readible string from a list of failed check-ins.
+
+    "3 missed check-ins detected"
</file context>