GPT Review — Vector Search Reliability Hardening Design + Prompt rev1
GPT Review — Vector Search Reliability Hardening Design + Prompt rev1
Date: 2026-05-11 Reviewer: GPT-5.5 Thinking / Incomex Hội đồng AI Reviewed:
knowledge/dev/laws/dieu44-trien-khai/design/p3d-vector-search-reliability-hardening-design.mdknowledge/dev/laws/dieu44-trien-khai/prompts/p3d-vector-search-reliability-hardening-implementation-prompt.mdknowledge/dev/laws/dieu44-trien-khai/reports/p3d-vector-search-reliability-hardening-design-report.md
Verdict
Design direction approved. Implementation prompt rev1 requires production-safety patch before dispatch.
The overall vision is correct: search/vector reliability must be hardened once, broadly enough to support both current KB search and future IU vector search. However, rev1 mixes several production-risk operations and must be tightened before execution.
Accepted
- Compose/build durability must be solved;
docker cphotfix is not enough. - Canary/regression suite is required.
- Recency tie-break is acceptable if tiny and only applied after path/title boost.
- Audit warning noise must be addressed so
sync_statusis meaningful. - Unified search contract for legacy KB + future IU vector is required.
- IU vector remains deferred; only compatibility contract/shape is prepared.
Required corrections
-
Do not allow PG update for
test_empty.md.tmplin this pack. Audit cleanup should be code-level classification/exclusion, not row mutation. No DB writes. -
Compose/build change must be guarded. Add
build:only after confirming Dockerfile and compose behavior. Back up compose. Rebuild onlyagent-data. Do not touch Qdrant. -
Force-recreate must be limited. Only
agent-datamay be recreated. Do not recreate the full stack. -
Canary parser must be inspected/adapted to actual MCP/API response. The template parser may be wrong. Agent must first capture actual response shape.
-
Recency tie-break must not depend on metadata fields that may be absent. If
updated_at/created_atis not in Qdrant payload, record warning and skip recency rather than inventing data or changing payloads. -
Audit cleanup must not change data/vector state. It may change health/audit classification code to exclude empty/folder/short/non-vectorizable docs, but no auto-heal/reindex/delete/upsert.
-
Unified IU contract should be documented and code-shaped minimally. Add optional
collection_name/source parameter only if low-risk; no IU collection, no IU payload, no new Qdrant index. -
Durability proof must include recreate test and canary after recreate. Search boost must survive
docker compose up -d --force-recreate agent-data.
Required next action
GPT will patch the implementation prompt to rev2 directly. Opus should not write another micro-review unless rev2 introduces a substantive issue.
Status
hardening_design=APPROVED
implementation_prompt_rev1=NOT_APPROVED_FOR_DISPATCH
required_next=GPT_PATCH_REV2_THEN_AGENT_DISPATCH
pack1_status=PAUSED