homelab-codex-ws/services/kb-query/app/startup.py

"""Startup invariant -- module 5 phase 4 (kb/phases/kb-m5-faza4.md, §2 decision 2,
"twardy inwariant"): the configured `EMBED_MODEL` must already be the model behind the active
embeddings in both `document_chunk` and `document_summary`, or kb-query refuses to start
(crash-loop, visible via container restarts in monitoring -- deliberately loud, never a silent
mismatch). There is no per-request model choice today, so this is the only place drift could
sneak in (someone changes `EMBED_MODEL` without a re-index).

`document_summary.model` is the LLM that WROTE the summary (`claude-haiku-4-5` / `gemma3:12b`
-- see `services/kb-postgres/init/004_summaries.sql`), not the embedder; the column that
records which model embedded the summary text is `embedding_model`. The plan's SQL sketch for
this check named `model` for both tables -- checking `document_summary.model` against
`EMBED_MODEL` would never match (summaries are never written by `bge-m3`) and the service would
refuse to start unconditionally. Checked live against kb-postgres@PIHA on 2026-07-22 before
writing this: `document_summary.model` holds `{claude-haiku-4-5, gemma3:12b}`,
`document_summary.embedding_model` holds `{bge-m3}` -- `embedding_model` is the correct column.
"""
from __future__ import annotations

import asyncpg


class ModelInvariantError(RuntimeError):
    """The configured EMBED_MODEL is absent from document_chunk/document_summary embeddings."""


async def validate_embed_model(conn: asyncpg.Connection, embed_model: str) -> None:
    chunk_rows = await conn.fetch(
        "SELECT DISTINCT model FROM document_chunk "
        "WHERE excluded_reason IS NULL AND embedding IS NOT NULL"
    )
    chunk_models = {r["model"] for r in chunk_rows}
    if embed_model not in chunk_models:
        raise ModelInvariantError(
            f"EMBED_MODEL={embed_model!r} not found among document_chunk.model "
            f"of active embeddings ({sorted(chunk_models) or 'none'})"
        )

    summary_rows = await conn.fetch(
        "SELECT DISTINCT embedding_model FROM document_summary WHERE embedding IS NOT NULL"
    )
    summary_embed_models = {r["embedding_model"] for r in summary_rows}
    if embed_model not in summary_embed_models:
        raise ModelInvariantError(
            f"EMBED_MODEL={embed_model!r} not found among document_summary.embedding_model "
            f"of active embeddings ({sorted(summary_embed_models) or 'none'})"
        )