❌ Autofix failed (check again to retry)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

❌ Autofix failed (check again to retry)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

supabase/migrations/20260713062139_route_enrichment_through_agent.sql (3)

13-16: 🩺 Stability & Availability | 🟠 Major | 🏗️ Heavy lift

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

git status --short
git ls-files supabase/migrations/20260713062139_route_enrichment_through_agent.sql
ast-grep outline supabase/migrations/20260713062139_route_enrichment_through_agent.sql --view expanded
sed -n '1,220p' supabase/migrations/20260713062139_route_enrichment_through_agent.sql

Repository: BigSimmo/Database

Length of output: 6782

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

nl -ba supabase/migrations/20260713062139_route_enrichment_through_agent.sql | sed -n '1,220p' | sed -n '1,180p'

Repository: BigSimmo/Database

Length of output: 195

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

awk '{printf "%4d  %s\n", NR, $0}' supabase/migrations/20260713062139_route_enrichment_through_agent.sql | sed -n '1,180p'

Repository: BigSimmo/Database

Length of output: 7688

---

Keep document/job lock order consistent to avoid deadlocks.

request_indexing_v3_enrichment locks the document row before touching indexing_v3_agent_jobs, while claim_indexing_v3_agent_jobs locks the job row first and only then updates the document row. If both run against the same document at the same time, Postgres can end up with a circular wait and abort one transaction.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@supabase/migrations/20260713062139_route_enrichment_through_agent.sql` around
lines 13 - 16, Update request_indexing_v3_enrichment so it acquires locks in the
same order as claim_indexing_v3_agent_jobs: lock the relevant
indexing_v3_agent_jobs row before locking or updating the public.documents row.
Preserve the existing document ownership, ID, and indexed-status checks while
eliminating the document-first lock order.

---

41-54: 🩺 Stability & Availability | 🟠 Major | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

printf '\n== target migration excerpt ==\n'
sed -n '1,140p' supabase/migrations/20260713062139_route_enrichment_through_agent.sql

printf '\n== claim function excerpt ==\n'
rg -n -A80 -B20 'claim_indexing_v3_agent_jobs' supabase/migrations

printf '\n== unique index / constraint references ==\n'
rg -n 'indexing_v3_agent_jobs_document_id_idx|UNIQUE INDEX .*indexing_v3_agent_jobs|create unique index .*indexing_v3_agent_jobs' supabase -S

printf '\n== any triggers or locks on documents / agent jobs ==\n'
rg -n 'FOR UPDATE|lock.*documents|indexing_v3_agent_jobs' supabase/migrations -S

Repository: BigSimmo/Database

Length of output: 50374

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

printf '\n== metadata key usage ==\n'
rg -n 'indexing_v3_agent_attempt_count|indexing_v3_agent_max_attempts' supabase -S

printf '\n== job row writes/reads around request/claim status ==\n'
rg -n 'attempt_count|max_attempts|enrichment_status|indexing_v3_agent_status' supabase/migrations/20260713062139_route_enrichment_through_agent.sql supabase/migrations/20260702190000_indexing_v3_agent_jobs_table.sql -n -S

Repository: BigSimmo/Database

Length of output: 12971

---

Avoid the concurrent insert race here

public.indexing_v3_agent_jobs.document_id is unique, and the FOR UPDATE on documents doesn’t protect this insert. A concurrent claim_indexing_v3_agent_jobs insert can still win and make this RPC fail with 23505 instead of returning enrichment_active; add ON CONFLICT (document_id) DO NOTHING and read back the existing row id.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@supabase/migrations/20260713062139_route_enrichment_through_agent.sql` around
lines 41 - 54, Update the v_job_id creation branch in the enrichment RPC to make
the indexing_v3_agent_jobs insert conflict-safe: add ON CONFLICT (document_id)
DO NOTHING, then read the existing row id when the insert does not create one.
Preserve the enrichment_active behavior by checking the resulting job’s status
and returning that error for an already-processing job instead of propagating a
23505 uniqueness failure.

---

56-66: 🗄️ Data Integrity & Integration | 🟡 Minor | ⚡ Quick win

Reset doesn't clear stale indexing_v3_agent_attempt_count/_max_attempts from document metadata.

claim_indexing_v3_agent_jobs writes indexing_v3_agent_attempt_count and indexing_v3_agent_max_attempts into documents.metadata (lines 143-144 below) whenever a job is claimed. This reset only strips _locked_by, _locked_at, _last_error, _next_run_at, so after a user-triggered reset the document metadata can still show a stale attempt count from the prior cycle even though the job row's attempt_count was reset to 0.

🛠️ Proposed fix

   update public.documents
   set metadata = (coalesce(metadata, '{}'::jsonb)
       - 'indexing_v3_agent_locked_by' - 'indexing_v3_agent_locked_at'
-      - 'indexing_v3_agent_last_error' - 'indexing_v3_agent_next_run_at')
+      - 'indexing_v3_agent_last_error' - 'indexing_v3_agent_next_run_at'
+      - 'indexing_v3_agent_attempt_count' - 'indexing_v3_agent_max_attempts')
       || jsonb_build_object(

📝 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.

  update public.documents
  set metadata = (coalesce(metadata, '{}'::jsonb)
      - 'indexing_v3_agent_locked_by' - 'indexing_v3_agent_locked_at'
      - 'indexing_v3_agent_last_error' - 'indexing_v3_agent_next_run_at'
      - 'indexing_v3_agent_attempt_count' - 'indexing_v3_agent_max_attempts')
      || jsonb_build_object(
        'enrichment_status', 'pending',
        'indexing_v3_agent_status', 'pending',
        'indexing_v3_agent_updated_at', now()
      ),
      updated_at = now()
  where id = p_document_id and owner_id = p_owner_id;

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@supabase/migrations/20260713062139_route_enrichment_through_agent.sql` around
lines 56 - 66, Update the metadata cleanup in the document reset statement to
also remove indexing_v3_agent_attempt_count and indexing_v3_agent_max_attempts,
alongside the existing lock, error, and scheduling fields. Keep the pending
status fields and updated_at assignment unchanged.

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes