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
+34 -7
View File
@@ -53,7 +53,8 @@ interface WorkspaceDwh {
interface WorkspaceBase {
workspace: WorkspaceMetadata;
dwh: WorkspaceDwh;
/** Legacy connection block; current descriptors bind their database through PostgreSQL. */
dwh?: WorkspaceDwh;
diagnostics?: Pick<CanonicalDiagnostics, "dwh_rest">;
}
@@ -328,7 +329,9 @@ function unique<T>(values: readonly T[], context: z.RefinementCtx, path: Propert
}
function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
unique(workspace.dwh.supported_transports, context, ["dwh", "supported_transports"]);
if (workspace.dwh) {
unique(workspace.dwh.supported_transports, context, ["dwh", "supported_transports"]);
}
if (workspace.evidence?.source.type === "filesystem") {
const expected = `${workspace.workspace.id}/evidence`;
@@ -341,7 +344,8 @@ function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
}
}
if (workspace.diagnostics?.dwh_rest && !workspace.dwh.supported_transports.includes("rest_api")) {
if (workspace.diagnostics?.dwh_rest
&& !workspace.dwh?.supported_transports.includes("rest_api")) {
context.addIssue({
code: "custom",
path: ["diagnostics", "dwh_rest"],
@@ -351,7 +355,7 @@ function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
}
const WorkspaceV4Schema = z.object({
dwh: dwhSchema,
dwh: dwhSchema.optional(),
evidence: workspaceEvidenceSchema.optional(),
diagnostics: z.object({
dwh_rest: dwhRestDiagnostic.optional(),
@@ -363,7 +367,7 @@ const WorkspaceV4Schema = z.object({
}).strict().superRefine(workspaceInvariants);
const WorkspaceDescriptorSchema = WorkspaceV4Schema;
export function parseWorkspaceYaml(source: string): WorkspaceDescriptor {
function parseWorkspaceDocument(source: string): unknown {
const documents = parseAllDocuments(source, { uniqueKeys: true });
if (documents.length !== 1) throw new Error("Workspace YAML must contain exactly one document");
const document = documents[0];
@@ -371,10 +375,30 @@ export function parseWorkspaceYaml(source: string): WorkspaceDescriptor {
throw new Error(`Invalid workspace YAML: ${[...document.errors, ...document.warnings]
.map((error) => error.message).join("; ")}`);
}
return validateWorkspaceDescriptor(document.toJSON());
return document.toJSON();
}
/** Deterministically removes the two installation-owned v3 blocks without altering workspace data. */
export function parseWorkspaceYaml(source: string): WorkspaceDescriptor {
const value = parseWorkspaceDocument(source);
assertAuthoredWorkspaceIsDatabaseFree(value);
return validateWorkspaceDescriptor(value);
}
/** Parses an ephemeral, generated core runtime descriptor that may contain a Catalog binding. */
export function parseRuntimeWorkspaceYaml(source: string): WorkspaceDescriptor {
return validateWorkspaceDescriptor(parseWorkspaceDocument(source));
}
function assertAuthoredWorkspaceIsDatabaseFree(workspace: unknown): void {
if (workspace !== null && typeof workspace === "object"
&& ("dwh" in workspace || "diagnostics" in workspace)) {
throw new Error(
"Workspace YAML must not contain database configuration; use the PostgreSQL Metadata Catalog",
);
}
}
/** Build a database-free v4 descriptor; legacy database/configuration fields are not carried over. */
export function migrateWorkspaceV3Yaml(source: string): string {
const documents = parseAllDocuments(source, { uniqueKeys: true });
if (documents.length !== 1) throw new Error("Workspace YAML must contain exactly one document");
@@ -388,6 +412,8 @@ export function migrateWorkspaceV3Yaml(source: string): string {
throw new Error("Workspace migration requires schema version 3");
}
metadata.schema_version = 4;
delete value.dwh;
delete value.diagnostics;
delete value.semantic_index;
delete value.llm_policy;
return serializeWorkspaceYaml(validateWorkspaceDescriptor(value));
@@ -423,6 +449,7 @@ export function resolveDiagnosticUrl(baseUrl: string, path: string): URL {
export function serializeWorkspaceYaml(workspace: CanonicalWorkspace): string {
const canonical = validateOperationalWorkspace(workspace);
assertAuthoredWorkspaceIsDatabaseFree(canonical);
return stringify(canonical, { lineWidth: 0, sortMapEntries: true });
}