Context
You are an independent expert assessing an OpenSearch 3.5.0 k-NN derived_source migration failure. Read the problem carefully, form your own conclusions, and answer the 6 questions below. Do not defer to the asker's hypotheses — challenge them if they seem wrong.
## Context
A backend service (CodeAlive) maintains an OpenSearch 3.5.0 index of source-code "artifacts" — one document per file/chunk in customer repositories. Each artifact has a 768-dim HNSW embedding for semantic search plus scalar fields (path, content, kind, etc.). Total ~2.9M docs, 82 GB, 4 primary shards x 1 replica, routing_partition_size=2, _routing.required=true.
A new release wants to add two denormalized scalar fields to every existing document:
- file_type (int enum) — derived in C# from path/content
- ext (string) — file extension
These two fields are not currently indexed. After migration runs, future writes will set them; they're being backfilled across all existing docs.
## Index settings (verified)when to use it
Community prompt sourced from the open-source GitHub repo CodeAlive-AI/ai-driven-development (MIT). A "Context" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
codingcommunitydeveloper
source
CodeAlive-AI/ai-driven-development · MIT
more in Coding
Coding✓ tested
Senior code review (strict mode)
senior staff engineer running a merciless but fair review
Coding✓ tested
Debug by hypothesis, not by guessing
debugging partner who forms theories before touching code
Coding✓ tested
Generate tests from described behavior
test engineer who writes tests that would actually catch regressions