feat: unify installation model catalog
This commit is contained in:
Codex
@@ -1,63 +1,5 @@
|
||||
import {
|
||||
closeSync, constants, fstatSync, lstatSync, openSync, readFileSync,
|
||||
type Stats,
|
||||
} from "node:fs";
|
||||
import { parseAllDocuments } from "yaml";
|
||||
import { z } from "zod";
|
||||
import {
|
||||
loadSecretBundle,
|
||||
METADATA_GENERATION_SECRET_KEYS,
|
||||
} from "../config/secret-bundle.js";
|
||||
|
||||
const MAX_INSTALLATION_BYTES = 1024 * 1024;
|
||||
const RUNTIME_INSTALLATION_FILE = "/run/thothii-installation/thothii-installation.yaml";
|
||||
const modelId = z.string().regex(/^[a-z][a-z0-9._-]{0,63}$/);
|
||||
const apiKeyEnvironment = z.enum(METADATA_GENERATION_SECRET_KEYS);
|
||||
const endpointSchema = z.object({
|
||||
baseUrl: z.string().min(1).max(2048).refine((value) => {
|
||||
try {
|
||||
const url = new URL(value);
|
||||
return (url.protocol === "http:" || url.protocol === "https:")
|
||||
&& url.username === "" && url.password === "" && url.search === "" && url.hash === "";
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}),
|
||||
apiVersion: z.string().regex(/^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$/).optional(),
|
||||
}).strict();
|
||||
const configuredModelSchema = z.object({
|
||||
id: modelId,
|
||||
label: z.string().min(1).max(128).refine((value) => value.trim() === value && !/\p{Cc}/u.test(value)),
|
||||
litellm: z.object({
|
||||
provider: z.string().regex(/^[A-Za-z0-9][A-Za-z0-9._-]{0,63}$/),
|
||||
model: z.string().regex(/^[A-Za-z0-9][A-Za-z0-9._:/-]{0,255}$/),
|
||||
disableThinking: z.literal(true).optional(),
|
||||
endpoint: endpointSchema.optional(),
|
||||
}).strict(),
|
||||
apiKeyEnv: apiKeyEnvironment.optional(),
|
||||
}).strict().superRefine((value, context) => {
|
||||
if (value.apiKeyEnv === undefined && value.litellm.endpoint === undefined) {
|
||||
context.addIssue({
|
||||
code: z.ZodIssueCode.custom,
|
||||
path: ["apiKeyEnv"],
|
||||
message: "keyless models require an explicit endpoint",
|
||||
});
|
||||
}
|
||||
if (value.litellm.disableThinking === true && value.litellm.endpoint === undefined) {
|
||||
context.addIssue({
|
||||
code: z.ZodIssueCode.custom,
|
||||
path: ["litellm", "disableThinking"],
|
||||
message: "thinking may be disabled only for an explicit endpoint",
|
||||
});
|
||||
}
|
||||
});
|
||||
const metadataGenerationSchema = z.object({
|
||||
default: modelId.optional(),
|
||||
models: z.array(configuredModelSchema).max(64).default([]),
|
||||
}).strict();
|
||||
const installationSchema = z.object({
|
||||
metadataGeneration: metadataGenerationSchema.optional(),
|
||||
}).passthrough();
|
||||
import { loadSecretBundle } from "../config/secret-bundle.js";
|
||||
import { loadRuntimeModelCatalog } from "../models/runtime-model-catalog.js";
|
||||
|
||||
export interface MetadataGenerationModelChoice {
|
||||
id: string;
|
||||
@@ -86,7 +28,6 @@ export class MetadataGenerationModelUnavailableError extends Error {
|
||||
}
|
||||
}
|
||||
|
||||
/** The complete interface callers need: safe discovery plus fail-closed runtime resolution. */
|
||||
export interface MetadataGenerationModels {
|
||||
catalog(): MetadataGenerationModelCatalog;
|
||||
resolve(selection: string): ResolvedMetadataGenerationModel;
|
||||
@@ -96,140 +37,78 @@ class RestartLoadedMetadataGenerationModels implements MetadataGenerationModels
|
||||
readonly #models: ReadonlyMap<string, ResolvedMetadataGenerationModel>;
|
||||
readonly #catalog: MetadataGenerationModelCatalog;
|
||||
|
||||
constructor(
|
||||
models: ReadonlyMap<string, ResolvedMetadataGenerationModel> = new Map(),
|
||||
defaultModel: string | null = null,
|
||||
choices: MetadataGenerationModelChoice[] = [],
|
||||
) {
|
||||
constructor(models: ReadonlyMap<string, ResolvedMetadataGenerationModel>, defaultModel: string | null) {
|
||||
this.#models = models;
|
||||
this.#catalog = {
|
||||
models: choices.map((choice) => ({ ...choice })),
|
||||
models: [...models.values()].map(({ id }) => ({ id, label: id })),
|
||||
default: defaultModel,
|
||||
};
|
||||
}
|
||||
|
||||
catalog(): MetadataGenerationModelCatalog {
|
||||
return {
|
||||
models: this.#catalog.models.map((choice) => ({ ...choice })),
|
||||
default: this.#catalog.default,
|
||||
};
|
||||
return { models: this.#catalog.models.map((choice) => ({ ...choice })), default: this.#catalog.default };
|
||||
}
|
||||
|
||||
resolve(selection: string): ResolvedMetadataGenerationModel {
|
||||
const model = typeof selection === "string" ? this.#models.get(selection) : undefined;
|
||||
const model = this.#models.get(selection);
|
||||
if (!model) throw new MetadataGenerationModelUnavailableError();
|
||||
return model;
|
||||
}
|
||||
}
|
||||
|
||||
function invalid(message = "metadata-generation configuration is invalid"): Error {
|
||||
function invalid(message = "metadata-generation runtime catalog is invalid"): Error {
|
||||
return new Error(message);
|
||||
}
|
||||
|
||||
function protectedInstallationStat(file: string, info: Stats): boolean {
|
||||
const mode = info.mode & 0o777;
|
||||
if (!info.isFile() || info.isSymbolicLink() || info.nlink !== 1
|
||||
|| info.size < 1 || info.size > MAX_INSTALLATION_BYTES) return false;
|
||||
if (file === RUNTIME_INSTALLATION_FILE && info.uid === 0 && mode === 0o444) return true;
|
||||
return info.uid === (process.getuid?.() ?? info.uid) && (mode === 0o400 || mode === 0o600);
|
||||
}
|
||||
|
||||
function readProtectedInstallation(file: string): string {
|
||||
let descriptor: number | undefined;
|
||||
try {
|
||||
const before = lstatSync(file);
|
||||
if (!protectedInstallationStat(file, before)) throw new Error("unavailable");
|
||||
descriptor = openSync(file, constants.O_RDONLY | constants.O_NOFOLLOW);
|
||||
const opened = fstatSync(descriptor);
|
||||
if (!protectedInstallationStat(file, opened)
|
||||
|| before.dev !== opened.dev || before.ino !== opened.ino) throw new Error("unavailable");
|
||||
const source = readFileSync(descriptor, "utf8");
|
||||
const after = fstatSync(descriptor);
|
||||
const current = lstatSync(file);
|
||||
if (!protectedInstallationStat(file, after) || !protectedInstallationStat(file, current)
|
||||
|| opened.dev !== after.dev || opened.ino !== after.ino
|
||||
|| opened.dev !== current.dev || opened.ino !== current.ino) throw new Error("unavailable");
|
||||
return source;
|
||||
} finally {
|
||||
if (descriptor !== undefined) try { closeSync(descriptor); } catch { /* sanitized below */ }
|
||||
}
|
||||
}
|
||||
|
||||
function readInstallation(file: string): unknown {
|
||||
try {
|
||||
const documents = parseAllDocuments(readProtectedInstallation(file), { uniqueKeys: true });
|
||||
if (documents.length !== 1) throw invalid("metadata-generation installation must contain one YAML document");
|
||||
const document = documents[0];
|
||||
if (document.errors.length > 0 || document.warnings.length > 0) {
|
||||
throw invalid("metadata-generation installation contains invalid YAML");
|
||||
}
|
||||
return document.toJSON();
|
||||
} catch (error) {
|
||||
if (error instanceof Error && error.message.startsWith("metadata-generation")) throw error;
|
||||
throw invalid("metadata-generation installation is unavailable");
|
||||
}
|
||||
}
|
||||
|
||||
export function loadMetadataGenerationModels(options: {
|
||||
installationFile?: string;
|
||||
catalogFile?: string;
|
||||
secretsFile?: string;
|
||||
}): MetadataGenerationModels {
|
||||
if (!options.installationFile) return new RestartLoadedMetadataGenerationModels();
|
||||
const installation = installationSchema.safeParse(readInstallation(options.installationFile));
|
||||
if (!installation.success) throw invalid();
|
||||
const configured = installation.data.metadataGeneration;
|
||||
if (!configured || configured.models.length === 0) {
|
||||
if (configured?.default !== undefined) throw invalid("metadata-generation default does not identify a configured model");
|
||||
return new RestartLoadedMetadataGenerationModels();
|
||||
}
|
||||
if (!configured.default) throw invalid("metadata-generation default is required when models are configured");
|
||||
const catalog = loadRuntimeModelCatalog(options.catalogFile);
|
||||
const configured = catalog.metadataModels();
|
||||
if (configured.length === 0) return new RestartLoadedMetadataGenerationModels(new Map(), null);
|
||||
|
||||
const seen = new Set<string>();
|
||||
for (const model of configured.models) {
|
||||
if (seen.has(model.id)) throw invalid(`metadata-generation model id "${model.id}" is duplicated`);
|
||||
seen.add(model.id);
|
||||
}
|
||||
if (!seen.has(configured.default)) {
|
||||
throw invalid(`metadata-generation default "${configured.default}" is not configured`);
|
||||
}
|
||||
const requiresSecrets = configured.models.some((model) => model.apiKeyEnv !== undefined);
|
||||
const requiresSecrets = configured.some((model) => model.authentication.mode === "secret_env");
|
||||
let secrets: ReadonlyMap<string, string> = new Map();
|
||||
if (requiresSecrets) {
|
||||
if (!options.secretsFile) throw invalid("metadata-generation keyed models require THT_SECRETS_FILE");
|
||||
try {
|
||||
secrets = loadSecretBundle(options.secretsFile);
|
||||
} catch {
|
||||
throw invalid("metadata-generation secrets are unavailable");
|
||||
}
|
||||
try { secrets = loadSecretBundle(options.secretsFile); }
|
||||
catch { throw invalid("metadata-generation secrets are unavailable"); }
|
||||
}
|
||||
|
||||
const models = new Map<string, ResolvedMetadataGenerationModel>();
|
||||
for (const configuredModel of configured.models) {
|
||||
const labels = new Map<string, string>();
|
||||
for (const configuredModel of configured) {
|
||||
const adapter = configuredModel.metadataAdapter;
|
||||
if (!adapter || configuredModel.authentication.mode === "pi_auth") throw invalid();
|
||||
const apiKeyEnv = configuredModel.authentication.apiKeyEnv;
|
||||
let apiKey: string | undefined;
|
||||
if (configuredModel.apiKeyEnv !== undefined) {
|
||||
apiKey = secrets.get(configuredModel.apiKeyEnv);
|
||||
if (!apiKey) {
|
||||
throw invalid(`metadata-generation model "${configuredModel.id}" secret "${configuredModel.apiKeyEnv}" is missing`);
|
||||
}
|
||||
if (configuredModel.authentication.mode === "secret_env") {
|
||||
if (!apiKeyEnv) throw invalid();
|
||||
apiKey = secrets.get(apiKeyEnv);
|
||||
if (!apiKey) throw invalid(`metadata-generation model "${configuredModel.id}" secret "${apiKeyEnv}" is missing`);
|
||||
if (apiKey.length > 16 * 1024 || /\s/u.test(apiKey)) {
|
||||
throw invalid(`metadata-generation model "${configuredModel.id}" secret "${configuredModel.apiKeyEnv}" is unusable`);
|
||||
throw invalid(`metadata-generation model "${configuredModel.id}" secret "${apiKeyEnv}" is unusable`);
|
||||
}
|
||||
}
|
||||
labels.set(configuredModel.id, configuredModel.label);
|
||||
models.set(configuredModel.id, Object.freeze({
|
||||
id: configuredModel.id,
|
||||
provider: configuredModel.litellm.provider,
|
||||
model: configuredModel.litellm.model,
|
||||
...(configuredModel.litellm.disableThinking === true ? { disableThinking: true as const } : {}),
|
||||
...(configuredModel.litellm.endpoint === undefined
|
||||
? {}
|
||||
: { endpoint: Object.freeze({ ...configuredModel.litellm.endpoint }) }),
|
||||
...(configuredModel.apiKeyEnv === undefined
|
||||
? {}
|
||||
: { apiKeyEnv: configuredModel.apiKeyEnv, apiKey }),
|
||||
provider: adapter.litellmProvider,
|
||||
model: configuredModel.upstreamModel,
|
||||
...(configuredModel.metadataGeneration?.disableThinking === true
|
||||
? { disableThinking: true as const } : {}),
|
||||
...(configuredModel.endpoint ? { endpoint: Object.freeze({ ...configuredModel.endpoint }) } : {}),
|
||||
...(apiKeyEnv ? { apiKeyEnv, apiKey } : {}),
|
||||
}));
|
||||
}
|
||||
return new RestartLoadedMetadataGenerationModels(
|
||||
models,
|
||||
configured.default,
|
||||
configured.models.map(({ id, label }) => ({ id, label })),
|
||||
);
|
||||
const result = new RestartLoadedMetadataGenerationModels(models, catalog.defaultMetadataGeneration);
|
||||
const safe = result.catalog();
|
||||
return {
|
||||
catalog: () => ({
|
||||
default: safe.default,
|
||||
models: safe.models.map((choice) => ({ ...choice, label: labels.get(choice.id) ?? choice.id })),
|
||||
}),
|
||||
resolve: (selection) => result.resolve(selection),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -12,6 +12,7 @@ import * as sensitiveDataFlagMigration from "./migrations/006_sensitive_data_fla
|
||||
import * as sensitiveDataSuggestionRunsMigration from "./migrations/007_sensitive_data_suggestion_runs.js";
|
||||
import * as catalogLogicalRelationshipsMigration from "./migrations/008_catalog_logical_relationships.js";
|
||||
import * as aiTokenUsageMigration from "./migrations/009_ai_token_usage.js";
|
||||
import * as canonicalModelIdsMigration from "./migrations/010_canonical_model_ids.js";
|
||||
|
||||
const connectionString = process.env.THT_CATALOG_MIGRATOR_DATABASE_URL;
|
||||
const host = process.env.THT_CATALOG_DB_HOST;
|
||||
@@ -46,6 +47,7 @@ const provider: MigrationProvider = {
|
||||
"007_sensitive_data_suggestion_runs": sensitiveDataSuggestionRunsMigration,
|
||||
"008_catalog_logical_relationships": catalogLogicalRelationshipsMigration,
|
||||
"009_ai_token_usage": aiTokenUsageMigration,
|
||||
"010_canonical_model_ids": canonicalModelIdsMigration,
|
||||
};
|
||||
},
|
||||
};
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
import { sql, type Kysely } from "kysely";
|
||||
import type { CatalogDatabase } from "../repository.js";
|
||||
|
||||
const canonicalModelPattern = "^[a-z][a-z0-9._-]{0,63}/[A-Za-z0-9][A-Za-z0-9._:-]{0,255}$";
|
||||
const legacyModelPattern = "^[a-z][a-z0-9._-]{0,63}$";
|
||||
|
||||
export async function up(db: Kysely<CatalogDatabase>): Promise<void> {
|
||||
await sql.raw(`alter table description_generation_runs
|
||||
drop constraint description_generation_runs_model_id_check,
|
||||
add constraint description_generation_runs_model_id_check
|
||||
check (model_id ~ '${canonicalModelPattern}')`).execute(db);
|
||||
await sql.raw(`alter table sensitive_data_suggestion_runs
|
||||
drop constraint sensitive_data_suggestion_runs_model_id_check,
|
||||
add constraint sensitive_data_suggestion_runs_model_id_check
|
||||
check (model_id ~ '${canonicalModelPattern}')`).execute(db);
|
||||
}
|
||||
|
||||
export async function down(db: Kysely<CatalogDatabase>): Promise<void> {
|
||||
await sql.raw(`alter table sensitive_data_suggestion_runs
|
||||
drop constraint sensitive_data_suggestion_runs_model_id_check,
|
||||
add constraint sensitive_data_suggestion_runs_model_id_check
|
||||
check (model_id ~ '${legacyModelPattern}')`).execute(db);
|
||||
await sql.raw(`alter table description_generation_runs
|
||||
drop constraint description_generation_runs_model_id_check,
|
||||
add constraint description_generation_runs_model_id_check
|
||||
check (model_id ~ '${legacyModelPattern}')`).execute(db);
|
||||
}
|
||||
Reference in New Issue
Block a user