feat: unify installation model catalog

This commit is contained in:
Codex
2026-09-02 18:45:33 +02:00
parent ae053961a3
commit 7b7927bfe5
169 changed files with 3696 additions and 4572 deletions
+29 -67
View File
@@ -35,7 +35,7 @@ export interface CanonicalDiagnostics {
}
interface WorkspaceMetadata {
schema_version: 3;
schema_version: 4;
id: string;
name: string;
description?: string;
@@ -51,31 +51,12 @@ interface WorkspaceDwh {
supported_transports: DwhTransport[];
}
interface WorkspaceBase<TVectorStore> {
interface WorkspaceBase {
workspace: WorkspaceMetadata;
dwh: WorkspaceDwh;
semantic_index: {
vector_store: TVectorStore;
embedding: {
provider: "ollama_internal";
model: "qwen3-embedding:0.6b";
dimensions: 1024;
};
};
llm_policy: {
default?: `${string}/${string}`;
allowed: `${string}/${string}`[];
};
diagnostics?: Pick<CanonicalDiagnostics, "dwh_rest">;
}
interface QdrantVectorStore {
engine: "qdrant";
collection: string;
dimensions: 1024;
distance: "cosine";
}
export interface EvidencePolicy {
max_chunk_chars: number;
retain_published_generations: number;
@@ -120,12 +101,12 @@ export interface WorkspaceEvidence {
policy: EvidencePolicy;
}
export interface WorkspaceV3 extends WorkspaceBase<QdrantVectorStore> {
export interface WorkspaceV4 extends WorkspaceBase {
evidence?: WorkspaceEvidence;
}
export type CanonicalWorkspace = WorkspaceV3;
export type WorkspaceDescriptor = WorkspaceV3;
export type CanonicalWorkspace = WorkspaceV4;
export type WorkspaceDescriptor = WorkspaceV4;
const workspaceId = z.string().regex(/^[a-z][a-z0-9-]{2,62}$/, {
message: "workspace id must match ^[a-z][a-z0-9-]{2,62}$",
@@ -135,9 +116,6 @@ const identifier = z.string().regex(/^[A-Za-z_][A-Za-z0-9_]*$/, {
});
const port = z.number().int().min(1).max(65_535);
const timeoutMs = z.number().int().positive();
const modelReference = z.string().regex(/^[^/\s]+\/[^/\s]+$/, {
message: "model must use provider/model syntax",
});
function isOriginRelativeDiagnosticPath(value: string): boolean {
return /^\/(?!\/)[^\\\u0000-\u001F\u007F?#]*$/.test(value) && !/%5c/i.test(value);
@@ -166,21 +144,6 @@ const dwhSchema = z.object({
timeout_ms: timeoutMs.optional(),
supported_transports: z.array(z.enum(DWH_TRANSPORTS)).min(1),
}).strict();
const internalEmbeddingSchema = z.object({
provider: z.literal("ollama_internal"),
model: z.literal("qwen3-embedding:0.6b"),
dimensions: z.literal(1024),
}).strict();
const qdrantVectorStoreSchema = z.object({
engine: z.literal("qdrant"),
collection: workspaceId,
dimensions: z.literal(1024),
distance: z.literal("cosine"),
}).strict();
const llmPolicySchema = z.object({
default: modelReference.optional(),
allowed: z.array(modelReference).min(1),
}).strict();
const positiveSafeInteger = z.number().int().safe().positive();
const nonnegativeSafeInteger = z.number().int().safe().nonnegative();
@@ -366,7 +329,6 @@ function unique<T>(values: readonly T[], context: z.RefinementCtx, path: Propert
function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
unique(workspace.dwh.supported_transports, context, ["dwh", "supported_transports"]);
unique(workspace.llm_policy.allowed, context, ["llm_policy", "allowed"]);
if (workspace.evidence?.source.type === "filesystem") {
const expected = `${workspace.workspace.id}/evidence`;
@@ -379,20 +341,6 @@ function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
}
}
if (workspace.semantic_index.vector_store.dimensions !== workspace.semantic_index.embedding.dimensions) {
context.addIssue({
code: "custom",
path: ["semantic_index", "embedding", "dimensions"],
message: "embedding dimensions must match vector store dimensions",
});
}
if (workspace.llm_policy.default && !workspace.llm_policy.allowed.includes(workspace.llm_policy.default)) {
context.addIssue({
code: "custom",
path: ["llm_policy", "default"],
message: "LLM default must be included in the allowlist",
});
}
if (workspace.diagnostics?.dwh_rest && !workspace.dwh.supported_transports.includes("rest_api")) {
context.addIssue({
code: "custom",
@@ -402,23 +350,18 @@ function workspaceInvariants(workspace: any, context: z.RefinementCtx): void {
}
}
const WorkspaceV3Schema = z.object({
const WorkspaceV4Schema = z.object({
dwh: dwhSchema,
llm_policy: llmPolicySchema,
evidence: workspaceEvidenceSchema.optional(),
diagnostics: z.object({
dwh_rest: dwhRestDiagnostic.optional(),
}).strict().optional(),
workspace: z.object({
schema_version: z.literal(3), id: workspaceId, name: z.string().trim().min(1),
schema_version: z.literal(4), id: workspaceId, name: z.string().trim().min(1),
description: z.string().trim().min(1).optional(), language: z.enum(["en", "it"]),
}).strict(),
semantic_index: z.object({
vector_store: qdrantVectorStoreSchema,
embedding: internalEmbeddingSchema,
}).strict(),
}).strict().superRefine(workspaceInvariants);
const WorkspaceDescriptorSchema = WorkspaceV3Schema;
const WorkspaceDescriptorSchema = WorkspaceV4Schema;
export function parseWorkspaceYaml(source: string): WorkspaceDescriptor {
const documents = parseAllDocuments(source, { uniqueKeys: true });
@@ -431,6 +374,25 @@ export function parseWorkspaceYaml(source: string): WorkspaceDescriptor {
return validateWorkspaceDescriptor(document.toJSON());
}
/** Deterministically removes the two installation-owned v3 blocks without altering workspace data. */
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");
const document = documents[0];
if (document.errors.length > 0 || document.warnings.length > 0) {
throw new Error("Invalid workspace YAML");
}
const value = document.toJSON() as Record<string, unknown>;
const metadata = value.workspace as Record<string, unknown> | undefined;
if (!metadata || metadata.schema_version !== 3) {
throw new Error("Workspace migration requires schema version 3");
}
metadata.schema_version = 4;
delete value.semantic_index;
delete value.llm_policy;
return serializeWorkspaceYaml(validateWorkspaceDescriptor(value));
}
export function validateWorkspaceDescriptor(workspace: unknown): WorkspaceDescriptor {
return WorkspaceDescriptorSchema.parse(workspace) as WorkspaceDescriptor;
}
@@ -439,11 +401,11 @@ export function isCanonicalWorkspace(workspace: unknown): workspace is Canonical
return WorkspaceDescriptorSchema.safeParse(workspace).success;
}
export function isOperationalWorkspace(workspace: unknown): workspace is WorkspaceV3 {
export function isOperationalWorkspace(workspace: unknown): workspace is WorkspaceV4 {
return WorkspaceDescriptorSchema.safeParse(workspace).success;
}
export function validateOperationalWorkspace(workspace: unknown): WorkspaceV3 {
export function validateOperationalWorkspace(workspace: unknown): WorkspaceV4 {
return validateWorkspaceDescriptor(workspace);
}