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
+2 -131
View File
@@ -19,11 +19,6 @@ const validYaml = `workspace:
id: psd-clinical
name: Policlinico San Donato
language: it
dwh:
engine: postgres
database: postgres
schema: datawarehouse
supported_transports: [postgres_direct]
`;
function withFilesystemEvidence(source: string, id = "psd-clinical"): string {
@@ -34,119 +29,12 @@ function withFilesystemEvidence(source: string, id = "psd-clinical"): string {
`);
}
function withDwhRestTransport(source: string): string {
return source.replace(
"supported_transports: [postgres_direct]",
"supported_transports: [postgres_direct, rest_api]",
);
}
function withDwhRestDiagnostic(source: string): string {
return withDwhRestTransport(source).concat(`diagnostics:
dwh_rest:
method: GET
path: /health
auth: none
response:
database: database
schema: schema
`);
}
function withEmbeddingDiagnostic(source: string): string {
return source.concat(`diagnostics:
embedding:
method: GET
path: /models
auth: none
response:
model: model
dimensions: dimensions
`);
}
function withDwhRestAndEmbeddingDiagnostics(source: string): string {
return withDwhRestTransport(source).concat(`diagnostics:
dwh_rest:
method: GET
path: /health
auth: none
response:
database: database
schema: schema
embedding:
method: GET
path: /models
auth: none
response:
model: model
dimensions: dimensions
`);
}
function withVectorRestTransport(source: string): string {
return source.replace(
"supported_transports: [pgvector_direct]",
"supported_transports: [pgvector_direct, rest_api]",
);
}
function withVectorMetadataDiagnostic(source: string): string {
return withVectorRestTransport(source).concat(`diagnostics:
vector_rest:
metadata:
method: GET
path: /metadata
auth: none
response:
collection: collection
dimensions: dimensions
distance: distance
`);
}
function withReversibleVectorProbe(source: string): string {
return withVectorRestTransport(source).concat(`diagnostics:
vector_rest:
metadata:
method: GET
path: /metadata
auth: none
response:
collection: collection
dimensions: dimensions
distance: distance
reversible_probe:
method: POST
path: /probe
auth: bearer
response:
operation: operation
`);
}
function legacyV1Yaml(source = validYaml): string {
return source
.replace(" engine: qdrant\n", " engine: pgvector\n database: postgres\n schema: vectors\n")
.replace(" collection: psd-clinical\n", " collection: psd_clinical\n")
.replace(" dimensions: 1024", " dimensions: 768")
.replace(" provider: ollama_internal", " provider: ollama_compatible")
.replace(" model: qwen3-embedding:0.6b", " model: nomic-embed-text-v2-moe")
.replace(" dimensions: 1024", " dimensions: 768")
.replace("distance: cosine\n", "distance: cosine\n supported_transports: [pgvector_direct]\n")
.replace("schema_version: 4", "schema_version: 1");
return source.replace("schema_version: 4", "schema_version: 1");
}
function legacyV2Yaml(source = validYaml): string {
return source
.replace(" engine: qdrant\n", " engine: pgvector\n database: postgres\n schema: vectors\n")
.replace(" collection: psd-clinical\n", " collection: psd_clinical\n")
.replace(" dimensions: 1024", " dimensions: 768")
.replace(" provider: ollama_internal", " provider: ollama_compatible")
.replace(" model: qwen3-embedding:0.6b", " model: nomic-embed-text-v2-moe")
.replace(" dimensions: 1024", " dimensions: 768")
.replace("distance: cosine\n", "distance: cosine\n supported_transports: [pgvector_direct]\n")
.replace("schema_version: 4", "schema_version: 2");
return source.replace("schema_version: 4", "schema_version: 2");
}
const runFile = promisify(execFile);
@@ -605,23 +493,6 @@ test("keeps content-only historical descriptor revisions distinguishable by comm
expect(oldPinned.workspace).toEqual(newPinned.workspace);
});
test.each([
["adds", validYaml, withDwhRestDiagnostic(validYaml)],
["removes", withDwhRestDiagnostic(validYaml), validYaml],
])("pulls a curator change that %s a diagnostics branch without API rewrite", async (_operation, baseSource, remoteSource) => {
const remote = await fixture(baseSource);
const registry = new WorkspaceRegistry(config(join(remote.root, "registry"), remote.remote));
await registry.bootstrap();
const initial = await registry.read("psd-clinical");
writeFileSync(join(remote.source, "psd-clinical", "workspace.yaml"), remoteSource);
await git(remote.source, ["add", "psd-clinical/workspace.yaml"]);
await git(remote.source, ["commit", "-m", `Registry ${_operation} diagnostic branch`]);
await git(remote.source, ["push", "origin", "main"]);
await registry.pull();
const updated = await registry.read("psd-clinical");
expect(updated.revision.commit).not.toBe(initial.revision.commit);
});
test.each([
["v1", legacyV1Yaml()],
["v2", legacyV2Yaml()],