feat(preprod): add commitcomparison model (#97292)

Adds a new `CommitComparison` model to track Git data for Emerge
customers migrating to Sentry.

See:
https://www.notion.so/sentry/Emerge-Git-User-Experience-2148b10e4b5d80829406c85e010bd083

Author: trevor-e

migrations_lockfile.txt

@@ -27,7 +27,7 @@ preprod: 0013_binary_uuid
 
 replays: 0006_add_bulk_delete_job
 
-sentry: 0963_scheduleddeletion_json_field
+sentry: 0964_add_commitcomparison_table
 
 social_auth: 0003_social_auth_json_field
 

src/sentry/migrations/0964_add_commitcomparison_table.py

@@ -0,0 +1,99 @@
+# Generated by Django 5.2.1 on 2025-08-06 20:24
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+import sentry.db.models.fields.bounded
+import sentry.db.models.fields.foreignkey
+from sentry.new_migrations.migrations import CheckedMigration
+
+
+class Migration(CheckedMigration):
+    # This flag is used to mark that a migration shouldn't be automatically run in production.
+    # This should only be used for operations where it's safe to run the migration after your
+    # code has deployed. So this should not be used for most operations that alter the schema
+    # of a table.
+    # Here are some things that make sense to mark as post deployment:
+    # - Large data migrations. Typically we want these to be run manually so that they can be
+    #   monitored and not block the deploy for a long period of time while they run.
+    # - Adding indexes to large tables. Since this can take a long time, we'd generally prefer to
+    #   run this outside deployments so that we don't block them. Note that while adding an index
+    #   is a schema change, it's completely safe to run the operation after the code has deployed.
+    # Once deployed, run these manually via: https://develop.sentry.dev/database-migrations/#migration-deployment
+
+    is_post_deployment = False
+
+    dependencies = [
+        ("sentry", "0963_scheduleddeletion_json_field"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="CommitComparison",
+            fields=[
+                (
+                    "id",
+                    sentry.db.models.fields.bounded.BoundedBigAutoField(
+                        primary_key=True, serialize=False
+                    ),
+                ),
+                ("date_updated", models.DateTimeField(auto_now=True)),
+                ("date_added", models.DateTimeField(auto_now_add=True)),
+                (
+                    "organization_id",
+                    sentry.db.models.fields.bounded.BoundedBigIntegerField(db_index=True),
+                ),
+                ("head_sha", models.CharField(max_length=64)),
+                ("base_sha", models.CharField(max_length=64, null=True)),
+                ("provider", models.CharField(max_length=64, null=True)),
+                ("head_repo_name", models.CharField(max_length=255)),
+                ("base_repo_name", models.CharField(max_length=255, null=True)),
+                ("head_ref", models.CharField(max_length=255, null=True)),
+                ("base_ref", models.CharField(max_length=255, null=True)),
+                ("pr_number", models.PositiveIntegerField(null=True)),
+                (
+                    "base_commit",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        related_name="base_commit_set",
+                        to="sentry.commit",
+                    ),
+                ),
+                (
+                    "head_commit",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        related_name="head_commit_set",
+                        to="sentry.commit",
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "sentry_commitcomparison",
+                "indexes": [
+                    models.Index(
+                        fields=["organization_id", "head_repo_name", "head_sha"],
+                        name="sentry_comm_organiz_d9bea9_idx",
+                    ),
+                    models.Index(
+                        fields=["organization_id", "head_repo_name", "base_sha"],
+                        name="sentry_comm_organiz_2c6634_idx",
+                    ),
+                ],
+                "constraints": [
+                    models.UniqueConstraint(
+                        condition=models.Q(("base_sha__isnull", False)),
+                        fields=("organization_id", "head_sha", "base_sha"),
+                        name="unique_commit_comparison",
+                    ),
+                    models.UniqueConstraint(
+                        condition=models.Q(("base_sha__isnull", True)),
+                        fields=("organization_id", "head_sha"),
+                        name="unique_single_commit",
+                    ),
+                ],
+            },
+        ),
+    ]

src/sentry/models/__init__.py

@@ -16,6 +16,7 @@
 from .broadcast import *  # NOQA
 from .commit import *  # NOQA
 from .commitauthor import *  # NOQA
+from .commitcomparison import *  # NOQA
 from .commitfilechange import *  # noqa
 from .counter import *  # NOQA
 from .dashboard import *  # NOQA

src/sentry/models/commitcomparison.py

@@ -0,0 +1,63 @@
+from django.db import models
+
+from sentry.backup.scopes import RelocationScope
+from sentry.db.models.base import DefaultFieldsModel, region_silo_model
+from sentry.db.models.fields.bounded import BoundedBigIntegerField
+from sentry.db.models.fields.foreignkey import FlexibleForeignKey
+
+
+@region_silo_model
+class CommitComparison(DefaultFieldsModel):
+    """
+    Captures Git information provided by our users and links with our richer data models.
+    Can represent a single commit (main branch) or a comparison between commits (PR branch).
+    See https://www.notion.so/sentry/Emerge-Git-User-Experience-2148b10e4b5d80829406c85e010bd083
+    """
+
+    __relocation_scope__ = RelocationScope.Excluded
+
+    organization_id = BoundedBigIntegerField(db_index=True)
+
+    # Core commit information
+    head_sha = models.CharField(max_length=64)
+    base_sha = models.CharField(max_length=64, null=True)  # merge-base
+
+    # Repository information
+    provider = models.CharField(max_length=64, null=True)
+    head_repo_name = models.CharField(max_length=255)  # "owner/repo"
+    base_repo_name = models.CharField(max_length=255, null=True)  # for forks
+
+    # Branch/ref information
+    head_ref = models.CharField(max_length=255, null=True)  # "feature/xyz"
+    base_ref = models.CharField(max_length=255, null=True)  # "main"
+
+    # Pull request information
+    pr_number = models.PositiveIntegerField(null=True)
+
+    # Sentry data, can be hydrated separately
+    head_commit = FlexibleForeignKey(
+        "sentry.Commit", null=True, on_delete=models.SET_NULL, related_name="head_commit_set"
+    )
+    base_commit = FlexibleForeignKey(
+        "sentry.Commit", null=True, on_delete=models.SET_NULL, related_name="base_commit_set"
+    )
+
+    class Meta:
+        app_label = "sentry"
+        db_table = "sentry_commitcomparison"
+        indexes = [
+            models.Index(fields=["organization_id", "head_repo_name", "head_sha"]),
+            models.Index(fields=["organization_id", "head_repo_name", "base_sha"]),
+        ]
+        constraints = [
+            models.UniqueConstraint(
+                fields=["organization_id", "head_sha", "base_sha"],
+                condition=models.Q(base_sha__isnull=False),
+                name="unique_commit_comparison",
+            ),
+            models.UniqueConstraint(
+                fields=["organization_id", "head_sha"],
+                condition=models.Q(base_sha__isnull=True),
+                name="unique_single_commit",
+            ),
+        ]