feat: complete catalog-driven preprocessing
Publish documentation / publish (push) Successful in 2m12s

This commit is contained in:
Codex
2026-09-06 17:49:35 +02:00
parent 8707ae1d46
commit cffa60772e
141 changed files with 5898 additions and 3015 deletions
+17 -5
View File
@@ -41,7 +41,10 @@ function directRendered(): Record<string, unknown> {
vector: {
engine: "qdrant",
base_url: "http://qdrant:6333",
collection: "psd-clinical",
collections: {
reference: "psd-clinical-reference",
memory: "psd-clinical-memory",
},
dimensions: 1024,
distance: "cosine",
collection_lifecycle: "require_existing",
@@ -103,10 +106,10 @@ function restRendered(): Record<string, unknown> {
}
const directCanonical =
`{"schemaVersion":2,"dwh":{` +
`{"schemaVersion":3,"dwh":{` +
`"engine":"postgres","database":"postgres","schema":"datawarehouse",` +
`"transport":"postgres_direct","host":"dwh.internal","port":5432,"user":"thoth_reader"},` +
`"vector":{"collection":"psd-clinical","dimensions":1024,"distance":"cosine"},` +
`"vector":{"collections":{"reference":"psd-clinical-reference","memory":"psd-clinical-memory"},"dimensions":1024,"distance":"cosine"},` +
`"embedding":{"id":"ollama/qwen3-embedding:0.6b","model":"qwen3-embedding:0.6b","dimensions":1024},` +
`"roots":{"artifacts":"/data/sessions/psd-clinical/artifacts",` +
`"indexes":"/data/sessions/psd-clinical/indexes"}}`;
@@ -128,7 +131,7 @@ test("canonical effective config excludes secrets, evidence, session storage, an
expect(json).not.toContain("sources");
expect(json).not.toContain("collection_lifecycle");
expect(json).not.toContain("base_url"); // vector/embedding service URLs are not identity
expect(json).not.toContain("memory");
expect(json).not.toContain('"memory":"/data');
expect(json).not.toContain('"sessions"');
});
@@ -190,7 +193,16 @@ test("DWH-affecting changes alter the effective config identity", () => {
const changedDatabase = { ...base, database: { ...(base.database as object), database: "analytics" } };
expect(effectiveConfigIdentity("psd-clinical", changedDatabase)).not.toBe(identityBefore);
const changedCollection = { ...base, resources: { ...base.resources, vector: { ...(base.resources as Record<string, any>).vector, collection: "other" } } };
const changedCollection = {
...base,
resources: {
...base.resources,
vector: {
...(base.resources as Record<string, any>).vector,
collections: { reference: "other-reference", memory: "other-memory" },
},
},
};
expect(effectiveConfigIdentity("psd-clinical", changedCollection)).not.toBe(identityBefore);
const changedEmbeddingIdentity = { ...base, resources: { ...base.resources, embeddings: { ...(base.resources as Record<string, any>).embeddings, model: "other-embedding" } } };