fix(ai): validate generated model data before builds

This commit is contained in:
Armin Ronacher
2026-07-20 22:28:48 +02:00
parent ff992261e2
commit c8c3cd499f
14 changed files with 700 additions and 103 deletions
+154 -48
View File
@@ -1,6 +1,6 @@
#!/usr/bin/env node
import { mkdirSync, readdirSync, rmSync, writeFileSync } from "fs";
import { existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, renameSync, rmSync, writeFileSync } from "fs";
import { dirname, join, resolve } from "path";
import { fileURLToPath } from "url";
import {
@@ -18,6 +18,14 @@ import type {
OpenAICompletionsCompat,
OpenAIResponsesCompat,
} from "../src/types.ts";
import {
createModelDataManifest,
type ModelDataStructure,
MODEL_DATA_MANIFEST_FILE,
readModelDataStructure,
validateGeneratedModelData,
validateModelDataDirectory,
} from "./model-data.ts";
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
@@ -25,11 +33,13 @@ const packageRoot = join(__dirname, "..");
function readGeneratorOptions(args: string[]): {
strict: boolean;
dataOnly: boolean;
jsonOnly: boolean;
jsonOutputDir: string | undefined;
pretty: boolean;
} {
let strict = false;
let dataOnly = false;
let jsonOnly = false;
let jsonOutputDir: string | undefined;
let pretty = false;
@@ -40,6 +50,10 @@ function readGeneratorOptions(args: string[]): {
strict = true;
continue;
}
if (arg === "--data-only") {
dataOnly = true;
continue;
}
if (arg === "--json-only") {
jsonOnly = true;
continue;
@@ -58,7 +72,8 @@ function readGeneratorOptions(args: string[]): {
}
if (jsonOnly && !jsonOutputDir) throw new Error("--json-only requires --json-output");
return { strict, jsonOnly, jsonOutputDir, pretty };
if (dataOnly && (jsonOnly || jsonOutputDir)) throw new Error("--data-only cannot be combined with JSON catalog output");
return { strict, dataOnly, jsonOnly, jsonOutputDir, pretty };
}
const generatorOptions = readGeneratorOptions(process.argv.slice(2));
@@ -2403,63 +2418,154 @@ async function generateModels() {
jsonProviders[providerId][modelId] = providers[providerId][modelId];
}
}
const writeJson = (path: string, value: unknown) =>
writeFileSync(path, `${JSON.stringify(value, null, generatorOptions.pretty ? 2 : undefined)}\n`);
const serializeJson = (value: unknown) => `${JSON.stringify(value, null, generatorOptions.pretty ? 2 : undefined)}\n`;
const writeJson = (path: string, value: unknown) => writeFileSync(path, serializeJson(value));
let generatedDataProviderIds = sortedProviderIds;
let generatedDataProviders = jsonProviders;
let modelDataStructure: ModelDataStructure = Object.fromEntries(
sortedProviderIds.map((providerId) => [
providerId,
Object.fromEntries(
Object.entries(jsonProviders[providerId]).map(([modelId, model]) => [modelId, model.api]),
),
]),
);
if (generatorOptions.dataOnly) {
modelDataStructure = readModelDataStructure(packageRoot);
generatedDataProviderIds = Object.keys(modelDataStructure);
const hydratedProviders: typeof jsonProviders = {};
const hydrationErrors: string[] = [];
for (const [providerId, expectedModels] of Object.entries(modelDataStructure)) {
hydratedProviders[providerId] = {};
for (const [modelId, expectedApi] of Object.entries(expectedModels)) {
const model = jsonProviders[providerId]?.[modelId];
if (!model) {
hydrationErrors.push(`missing ${providerId}/${modelId}`);
continue;
}
if (model.api !== expectedApi) {
hydrationErrors.push(`${providerId}/${modelId} uses ${model.api}, expected ${expectedApi}`);
continue;
}
hydratedProviders[providerId][modelId] = model;
}
}
if (hydrationErrors.length > 0) {
throw new Error(`Cannot hydrate the committed model catalog:\n${hydrationErrors.map((error) => ` - ${error}`).join("\n")}`);
}
generatedDataProviders = hydratedProviders;
}
if (!generatorOptions.jsonOnly) {
// Generate TypeScript structural catalogs and adjacent JSON values.
const generatedHeader = `// This file is auto-generated by scripts/generate-models.ts
// Stage and validate all provider values before replacing the current generated data.
const providersDir = join(packageRoot, "src/providers");
const dataDir = join(providersDir, "data");
const stagingRoot = mkdtempSync(join(providersDir, ".model-generation-"));
const stagedDataDir = join(stagingRoot, "data");
const previousDataDir = join(stagingRoot, "previous-data");
let restoreStructuralCatalog: (() => void) | undefined;
try {
mkdirSync(stagedDataDir, { recursive: true });
const fileContents: Record<string, string> = {};
for (const providerId of generatedDataProviderIds) {
const filename = `${providerId}.json`;
const content = serializeJson(generatedDataProviders[providerId]);
fileContents[filename] = content;
writeFileSync(join(stagedDataDir, filename), content);
}
writeJson(
join(stagedDataDir, MODEL_DATA_MANIFEST_FILE),
createModelDataManifest(modelDataStructure, fileContents),
);
validateModelDataDirectory(modelDataStructure, stagedDataDir);
if (!generatorOptions.dataOnly) {
// Generate TypeScript structural catalogs only after the model data is complete and valid.
const previousShardContents = new Map(
readdirSync(providersDir)
.filter((entry) => entry.endsWith(".models.ts"))
.map((entry) => [entry, readFileSync(join(providersDir, entry), "utf8")] as const),
);
const aggregatorPath = join(packageRoot, "src/models.generated.ts");
const previousAggregator = readFileSync(aggregatorPath, "utf8");
restoreStructuralCatalog = () => {
for (const entry of readdirSync(providersDir)) {
if (entry.endsWith(".models.ts")) rmSync(join(providersDir, entry));
}
for (const [entry, content] of previousShardContents) {
writeFileSync(join(providersDir, entry), content);
}
writeFileSync(aggregatorPath, previousAggregator);
};
const generatedHeader = `// This file is auto-generated by scripts/generate-models.ts
// Do not edit manually - run 'npm run generate-models' to update
`;
const catalogConstName = (providerId: string) =>
`${providerId.toUpperCase().replace(/[^A-Z0-9]+/g, "_")}_MODELS`;
const providersDir = join(packageRoot, "src/providers");
const dataDir = join(providersDir, "data");
const catalogConstName = (providerId: string) =>
`${providerId.toUpperCase().replace(/[^A-Z0-9]+/g, "_")}_MODELS`;
const generatedShardFiles = new Set<string>();
function emitModelShape(model: Model<any>, indent: string): string {
return `${indent}${JSON.stringify(model.id)}: Model<${JSON.stringify(model.api)}> & {\n${indent}\tid: ${JSON.stringify(model.id)};\n${indent}\tprovider: ${JSON.stringify(model.provider)};\n${indent}};\n`;
}
function emitModelShape(model: Model<any>, indent: string): string {
return `${indent}${JSON.stringify(model.id)}: Model<${JSON.stringify(model.api)}> & {\n${indent}\tid: ${JSON.stringify(model.id)};\n${indent}\tprovider: ${JSON.stringify(model.provider)};\n${indent}};\n`;
}
// Remove stale per-provider catalogs and their generated values.
for (const entry of readdirSync(providersDir)) {
if (entry.endsWith(".models.ts")) {
rmSync(join(providersDir, entry));
for (const providerId of sortedProviderIds) {
const models = providers[providerId];
let output = generatedHeader;
output += `import values from "./data/${providerId}.json" with { type: "json" };\n`;
output += `import type { Model } from "../types.ts";\n\n`;
output += `export const ${catalogConstName(providerId)} = values as {\n`;
for (const modelId of Object.keys(models).sort()) {
output += emitModelShape(models[modelId], "\t");
}
output += `};\n`;
const filename = `${providerId}.models.ts`;
generatedShardFiles.add(filename);
writeFileSync(join(providersDir, filename), output);
}
for (const entry of readdirSync(providersDir)) {
if (entry.endsWith(".models.ts") && !generatedShardFiles.has(entry)) rmSync(join(providersDir, entry));
}
console.log(`Generated ${sortedProviderIds.length} catalog structures under src/providers/`);
let output = generatedHeader;
for (const providerId of sortedProviderIds) {
output += `import { ${catalogConstName(providerId)} } from "./providers/${providerId}.models.ts";\n`;
}
output += `\nexport const MODELS = {\n`;
for (const providerId of sortedProviderIds) {
output += `\t${JSON.stringify(providerId)}: ${catalogConstName(providerId)},\n`;
}
output += `} as const;\n`;
writeFileSync(aggregatorPath, output);
console.log("Generated src/models.generated.ts");
}
}
rmSync(dataDir, { recursive: true, force: true });
mkdirSync(dataDir, { recursive: true });
// Per-provider catalog structure and values (sorted for deterministic output).
for (const providerId of sortedProviderIds) {
const models = providers[providerId];
const sortedModelIds = Object.keys(models).sort();
let output = generatedHeader;
output += `import values from "./data/${providerId}.json" with { type: "json" };\n`;
output += `import type { Model } from "../types.ts";\n\n`;
output += `export const ${catalogConstName(providerId)} = values as {\n`;
for (const modelId of sortedModelIds) {
output += emitModelShape(models[modelId], "\t");
const hadPreviousData = existsSync(dataDir);
if (hadPreviousData) renameSync(dataDir, previousDataDir);
try {
renameSync(stagedDataDir, dataDir);
validateGeneratedModelData(packageRoot);
} catch (error) {
rmSync(dataDir, { recursive: true, force: true });
if (hadPreviousData && existsSync(previousDataDir)) renameSync(previousDataDir, dataDir);
throw error;
}
output += `};\n`;
writeFileSync(join(providersDir, `${providerId}.models.ts`), output);
writeJson(join(dataDir, `${providerId}.json`), jsonProviders[providerId]);
restoreStructuralCatalog = undefined;
console.log(
generatorOptions.dataOnly
? "Hydrated JSON model values under src/providers/data/"
: "Generated JSON model values under src/providers/data/",
);
} catch (error) {
restoreStructuralCatalog?.();
throw error;
} finally {
rmSync(stagingRoot, { recursive: true, force: true });
}
console.log(`Generated ${sortedProviderIds.length} catalog structures under src/providers/`);
console.log("Generated JSON model values under src/providers/data/");
// Aggregator
let output = generatedHeader;
for (const providerId of sortedProviderIds) {
output += `import { ${catalogConstName(providerId)} } from "./providers/${providerId}.models.ts";\n`;
}
output += `\nexport const MODELS = {\n`;
for (const providerId of sortedProviderIds) {
output += `\t${JSON.stringify(providerId)}: ${catalogConstName(providerId)},\n`;
}
output += `} as const;\n`;
writeFileSync(join(packageRoot, "src/models.generated.ts"), output);
console.log("Generated src/models.generated.ts");
}
if (generatorOptions.jsonOutputDir) {