fix: resolve migration issue for oidv_issuer schema modal#1610
Merged
Conversation
Signed-off-by: pranalidhanavade <pranali.dhanavade@ayanworks.com>
📝 WalkthroughWalkthroughThis PR reverts a previous migration and introduces a replacement migration that adds ChangesDatabase Constraint Tightening
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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. Review rate limit: 0/1 reviews remaining, refill in 60 minutes.Comment |
|
sagarkhole4
approved these changes
May 4, 2026
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In
`@libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql`:
- Around line 2-6: The migration currently adds oidc_issuer.orgId and
immediately creates a FK, but it never backfills orgId from the existing
orgAgentId mapping so pre-existing issuers stay NULL; change the migration to
(1) add "orgId" as nullable on oidc_issuer (keep "isPrimary" as is), (2) run an
UPDATE that sets oidc_issuer.orgId = org_agents.orgId by joining
oidc_issuer.orgAgentId = org_agents.id (use the table names oidc_issuer and
org_agents and the columns orgAgentId and orgId), (3) if schema requires
non-null, ALTER COLUMN to NOT NULL afterwards, and only then add the FOREIGN KEY
constraint "oidc_issuer_orgId_fkey" referencing organisation(id) with the same
ON DELETE/ON UPDATE behavior.
- Around line 1-6: Restore the deleted April migration 20260427080006 exactly as
it was in commit f95dcd3 so history remains immutable: re-add the original SQL
that modified both oidc_issuer and the oid4vc_credentials /
issued_oid4vc_credentials foreign keys (the exact ALTER TABLE and ADD CONSTRAINT
statements previously present) and do not modify its checksum; then keep the
current May migration (20260504110536) only as an additive follow-up that
includes exclusively the new changes (e.g., adding isPrimary and orgId on
oidc_issuer and its FK), ensuring the April migration file contents and names
match f95dcd3 precisely and the May migration only appends new ALTERs.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 70300b48-0df0-4027-a7c3-434980bb7184
📒 Files selected for processing (3)
libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sqllibs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sqllibs/prisma-service/prisma/schema.prisma
💤 Files with no reviewable changes (1)
- libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sql
Comment on lines
+1
to
+6
| -- AlterTable | ||
| ALTER TABLE "oidc_issuer" ADD COLUMN "isPrimary" BOOLEAN NOT NULL DEFAULT false, | ||
| ADD COLUMN "orgId" UUID; | ||
|
|
||
| -- AddForeignKey | ||
| ALTER TABLE "oidc_issuer" ADD CONSTRAINT "oidc_issuer_orgId_fkey" FOREIGN KEY ("orgId") REFERENCES "organisation"("id") ON DELETE SET NULL ON UPDATE CASCADE; |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
base="$(git merge-base HEAD origin/main 2>/dev/null || true)"
if [ -n "$base" ]; then
git diff --unified=40 "$base" -- \
libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sql \
libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql
else
fd '20260427080006_added_org_id_and_is_primary_in_oidc_issuer|20260504110536_add_orgid_and_isprimary_in_oidc_issuer' \
libs/prisma-service/prisma/migrations \
-x sh -c 'echo "=== $1 ==="; sed -n "1,160p" "$1"' sh {}
fiRepository: credebl/platform
Length of output: 305
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Find and read the migration files from the directories
echo "=== April Migration (20260427080006) ==="
cat "libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sql" 2>/dev/null || echo "File not found"
echo ""
echo "=== May Migration (20260504110536) ==="
cat "libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql" 2>/dev/null || echo "File not found"
# Check git diff for changes to the April migration
echo ""
echo "=== Git diff for April migration (if base exists) ==="
base="$(git merge-base HEAD origin/main 2>/dev/null || true)"
if [ -n "$base" ]; then
git diff "$base" -- libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sql || echo "No differences found"
else
echo "Could not determine merge base"
fiRepository: credebl/platform
Length of output: 546
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== All migration directories ==="
ls -la libs/prisma-service/prisma/migrations/ | grep "202604\|202605"
echo ""
echo "=== Files in migration directories ==="
find libs/prisma-service/prisma/migrations/ -name "*202604*" -o -name "*202605*" | sort
echo ""
echo "=== Git status for migration files ==="
git status --short -- libs/prisma-service/prisma/migrations/ | head -20
echo ""
echo "=== Recent migration-related commits ==="
git log --oneline -20 -- libs/prisma-service/prisma/migrations/ 2>/dev/null || echo "No recent commits found"Repository: credebl/platform
Length of output: 450
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== Git log for April migration (all history) ==="
git log --full-history --oneline -- libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/ 2>/dev/null | head -20
echo ""
echo "=== Git log for April migration with status ==="
git log --full-history -p --follow -- libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/ 2>/dev/null | head -100
echo ""
echo "=== Show recent migration fix commit ==="
git show c73ff1d --stat 2>/dev/null || echo "Commit not found"
echo ""
echo "=== Files changed in that commit ==="
git diff-tree --no-commit-id --name-only -r c73ff1d 2>/dev/null | grep -i migration || echo "No migration files in that commit"Repository: credebl/platform
Length of output: 50372
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== Check if April migration appears in git show for c73ff1d ==="
git show c73ff1d | grep -i "20260427080006" || echo "April migration not mentioned in commit"
echo ""
echo "=== Files added/deleted/modified in migrations folder ==="
git show --name-status c73ff1d -- libs/prisma-service/prisma/migrations/ 2>/dev/null | head -50 || echo "No migration changes found"
echo ""
echo "=== Check git log --full-history for April migration ==="
git log --full-history --all --oneline -- 'libs/prisma-service/prisma/migrations/*20260427080006*' 2>/dev/null || echo "No history found"
echo ""
echo "=== List all commits that touched migrations ==="
git log --oneline --all -- libs/prisma-service/prisma/migrations/ 2>/dev/null | head -10Repository: credebl/platform
Length of output: 5304
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== Show April migration in f95dcd3 ==="
git show f95dcd3:libs/prisma-service/prisma/migrations/20260427080006_added_org_id_and_is_primary_in_oidc_issuer/migration.sql 2>/dev/null || echo "Not found in that commit"
echo ""
echo "=== Check if April migration was deleted in c73ff1d ==="
git show c73ff1d --raw -- libs/prisma-service/prisma/migrations/ 2>/dev/null | grep "20260427080006" || echo "April migration not in c73ff1d"
echo ""
echo "=== Show May migration in c73ff1d ==="
git show c73ff1d:libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql 2>/dev/null || echo "Not found"
echo ""
echo "=== Show commit message of c73ff1d ==="
git show --format=fuller c73ff1d | head -20Repository: credebl/platform
Length of output: 2172
Restore the April migration and keep it immutable.
The April migration (20260427080006) was created in commit f95dcd3 with essential schema changes to both oidc_issuer and oid4vc_credentials tables. The "fix: resolve migration issue" commit deleted it entirely and created a May migration containing only a subset of those changes. This creates two critical issues:
- Migration checksum drift: Any environment that already applied the April migration will fail to reconcile with the current migration history.
- Incomplete schema changes: The May migration omits the
oid4vc_credentialsandissued_oid4vc_credentialsforeign key updates from the original April migration.
Restore the April migration exactly as it existed in f95dcd3 and ship only this May migration as an additive follow-up if needed.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In
`@libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql`
around lines 1 - 6, Restore the deleted April migration 20260427080006 exactly
as it was in commit f95dcd3 so history remains immutable: re-add the original
SQL that modified both oidc_issuer and the oid4vc_credentials /
issued_oid4vc_credentials foreign keys (the exact ALTER TABLE and ADD CONSTRAINT
statements previously present) and do not modify its checksum; then keep the
current May migration (20260504110536) only as an additive follow-up that
includes exclusively the new changes (e.g., adding isPrimary and orgId on
oidc_issuer and its FK), ensuring the April migration file contents and names
match f95dcd3 precisely and the May migration only appends new ALTERs.
Comment on lines
+2
to
+6
| ALTER TABLE "oidc_issuer" ADD COLUMN "isPrimary" BOOLEAN NOT NULL DEFAULT false, | ||
| ADD COLUMN "orgId" UUID; | ||
|
|
||
| -- AddForeignKey | ||
| ALTER TABLE "oidc_issuer" ADD CONSTRAINT "oidc_issuer_orgId_fkey" FOREIGN KEY ("orgId") REFERENCES "organisation"("id") ON DELETE SET NULL ON UPDATE CASCADE; |
There was a problem hiding this comment.
Backfill oidc_issuer.orgId from the existing orgAgentId mapping.
Line 595 in libs/prisma-service/prisma/schema.prisma already makes orgAgentId mandatory, and org_agents.orgId is the current org link. Without a data update here, every pre-existing issuer keeps orgId = NULL, so the new direct organisation relation misses historical rows.
Suggested migration patch
-- AlterTable
ALTER TABLE "oidc_issuer" ADD COLUMN "isPrimary" BOOLEAN NOT NULL DEFAULT false,
ADD COLUMN "orgId" UUID;
+UPDATE "oidc_issuer" AS oi
+SET "orgId" = oa."orgId"
+FROM "org_agents" AS oa
+WHERE oa."id" = oi."orgAgentId"
+ AND oi."orgId" IS NULL;
+
-- AddForeignKey
ALTER TABLE "oidc_issuer" ADD CONSTRAINT "oidc_issuer_orgId_fkey" FOREIGN KEY ("orgId") REFERENCES "organisation"("id") ON DELETE SET NULL ON UPDATE CASCADE;📝 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.
Suggested change
| ALTER TABLE "oidc_issuer" ADD COLUMN "isPrimary" BOOLEAN NOT NULL DEFAULT false, | |
| ADD COLUMN "orgId" UUID; | |
| -- AddForeignKey | |
| ALTER TABLE "oidc_issuer" ADD CONSTRAINT "oidc_issuer_orgId_fkey" FOREIGN KEY ("orgId") REFERENCES "organisation"("id") ON DELETE SET NULL ON UPDATE CASCADE; | |
| ALTER TABLE "oidc_issuer" ADD COLUMN "isPrimary" BOOLEAN NOT NULL DEFAULT false, | |
| ADD COLUMN "orgId" UUID; | |
| UPDATE "oidc_issuer" AS oi | |
| SET "orgId" = oa."orgId" | |
| FROM "org_agents" AS oa | |
| WHERE oa."id" = oi."orgAgentId" | |
| AND oi."orgId" IS NULL; | |
| -- AddForeignKey | |
| ALTER TABLE "oidc_issuer" ADD CONSTRAINT "oidc_issuer_orgId_fkey" FOREIGN KEY ("orgId") REFERENCES "organisation"("id") ON DELETE SET NULL ON UPDATE CASCADE; |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In
`@libs/prisma-service/prisma/migrations/20260504110536_add_orgid_and_isprimary_in_oidc_issuer/migration.sql`
around lines 2 - 6, The migration currently adds oidc_issuer.orgId and
immediately creates a FK, but it never backfills orgId from the existing
orgAgentId mapping so pre-existing issuers stay NULL; change the migration to
(1) add "orgId" as nullable on oidc_issuer (keep "isPrimary" as is), (2) run an
UPDATE that sets oidc_issuer.orgId = org_agents.orgId by joining
oidc_issuer.orgAgentId = org_agents.id (use the table names oidc_issuer and
org_agents and the columns orgAgentId and orgId), (3) if schema requires
non-null, ALTER COLUMN to NOT NULL afterwards, and only then add the FOREIGN KEY
constraint "oidc_issuer_orgId_fkey" referencing organisation(id) with the same
ON DELETE/ON UPDATE behavior.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Summary by CodeRabbit
Refactor