aiex-cli 0.1.0-beta.3 → 0.1.1-beta.1

package/README.md

@@ -38,7 +38,7 @@ aiex watch -s invoice -d ./watch_folder # watch folder daemon for automatic extr
 - **Interactive Mode** — Run `aiex extract` without arguments for a guided extraction workflow
 - **Batch Mode** — `aiex extract -d <dir>` processes entire directories with optional glob filtering
 - **Incremental Extraction** — File hash deduplication skips already-processed files; use `--force` to override
-- **Data Dump** — `aiex dump` exports SQLite tables to CSV or Excel (.xlsx)
+- **Web Data Export** — Export SQLite table data to CSV, Excel (.xlsx), or JSON from the Web UI
 - **Notion Sync** — Optionally sync CLI extraction results to configured Notion data sources
 - **Extraction Audit Trail** — Every extraction is recorded with status, input source, output path, token usage, database inserts, Notion pages, and errors
 - **Built-in Model Registry** — Knows capabilities of 2000+ models (vision, structured output) so you don't have to guess
@@ -73,10 +73,6 @@ aiex extract -s <schema> -f <file> --no-insert     # extract and save JSON witho
 aiex extract -s <schema> -f <file> --force         # force re-extraction even if already processed
 aiex extract -s <schema> -d <directory>            # batch extract all supported files in a directory
 aiex extract -s <schema> -d <dir> -g "*.pdf"       # batch with glob filter
-aiex extract history                               # list extraction audit records
-aiex extract show <audit-id>                       # show full audit record JSON
-aiex extract retry <audit-id>                      # retry a previous extraction
-aiex extract rm <audit-id>                         # delete an audit record and cached upload
 ```
 
 The AI reads your document and outputs structured JSON matching your schema.
@@ -89,33 +85,21 @@ aiex extract -s paper -f research.pdf --no-insert  # save result only, skip data
 aiex extract -s paper -f research.pdf -m gpt-4o    # use a specific model
 aiex extract -s paper -f research.pdf --force      # force re-extraction even if already processed
 aiex extract -s paper -d ./papers -g "*.pdf"       # batch extract PDFs from a directory
-aiex extract history                               # inspect recent extraction runs
 ```
 Saves the extracted result to `.aiex/extracted/<schema-name>-<timestamp>.json` with fields like `title`, `firstAuthor`, `journal`, `year` — exactly as defined in your schema. Data is automatically inserted into the SQLite database.
 
 By default, aiex automatically selects a model based on your input type (vision-capable for images, structured output for text). Use `--model` / `-m` to override and specify any model from your AI configuration.
 
-Every extraction is also recorded under `.aiex/extracted/_audit/`. Audit records include the run status (`running`, `succeeded`, `failed`, or `stale`), schema name, input source, output file, token usage, inserted table rows, synced Notion pages, retry lineage, and error message. Deleting an audit record removes its cached upload, but keeps extracted JSON result files to avoid accidental data loss.
+Every extraction is also recorded under `.aiex/extracted/_audit/`. Audit records include the run status (`running`, `succeeded`, `failed`, or `stale`), schema name, input source, output file, token usage, inserted table rows, synced Notion pages, retry lineage, and error message. Use the Web UI to inspect, retry, or delete extraction records.
 
 ### 4. Watch Folder Daemon (Auto-Extraction)
 
 ```bash
+aiex watch
 aiex watch -s <schema> -d <folder>
 ```
 
-Runs a background watcher daemon to monitor a folder for new incoming files (such as scanned documents or downloads), automatically performing offline data extraction, database insertion, and system notifications.
-
-### 5. Dump Data
-
-```bash
-aiex dump -s <schema>                          # dump to CSV (default)
-aiex dump -s <schema> -f xlsx -o output.xlsx   # dump to Excel
-aiex dump -t <table> -f csv -o output.csv      # dump a specific table by name
-```
-
-Dumps all extracted data for a given schema (or table) from the SQLite database to CSV or Excel format.
-
-<br>
+Runs a background watcher daemon to monitor a folder for new incoming files (such as scanned documents or downloads), automatically performing offline data extraction, database insertion, and system notifications. Run without arguments to choose a schema, watch directory, model, and insert mode interactively.
 
 ## 📖 Commands
 
@@ -131,15 +115,9 @@ Dumps all extracted data for a given schema (or table) from the SQLite database
 | `aiex extract -s <name> -f <file> --force` | Force re-extraction even if the file has already been processed |
 | `aiex extract -s <name> -d <dir>` | Batch extract all supported files in a directory |
 | `aiex extract -s <name> -d <dir> -g "*.pdf"` | Batch extract with glob filter |
-| `aiex extract history` | List extraction audit records |
-| `aiex extract show <audit-id>` | Show a full extraction audit record |
-| `aiex extract retry <audit-id>` | Retry a previous extraction run |
-| `aiex extract retry <audit-id> --no-insert` | Retry without inserting into SQLite |
-| `aiex extract rm <audit-id>` | Delete an audit record and its cached upload |
+| `aiex watch` | Guided setup for watching a directory and automatically extracting new files |
 | `aiex watch -s <name> -d <dir>` | Watch a directory for new files and automatically extract data |
 | `aiex watch -s <name> -d <dir> --no-insert` | Watch and save JSON without inserting into SQLite |
-| `aiex dump -s <name>` | Dump extracted data for a schema to CSV |
-| `aiex dump -s <name> -f xlsx -o <file>` | Dump to Excel (.xlsx) |
 | `aiex doctor` | System and configuration diagnostics |
 | `aiex completion bash\|zsh\|fish` | Generate shell completion scripts |
 

package/dist/cli.mjs

@@ -1,4 +1,4 @@
-import { A as package_default, C as DEFAULT_PROMPT_CONFIG, D as seedConfig, E as createConfig, O as description, S as DEFAULT_MINERU_CONFIG, T as PLACEHOLDER_TEXT, _ as doctorDiagnosticsSeverityRows, a as recognizeImageText, b as DEFAULT_LITEPARSE_CONFIG, c as t, d as writeAIConfig, f as AIConfigSchema, h as toSnakeCase, j as version, k as name, l as getDefaultAIConfig, m as parseJsonSchema, n as collectDoctorDiagnostics, o as shouldUseImageOcrFallback, p as JsonSchemaDefinitionSchema, r as createMigrationConfig, s as initI18n, t as generateDrizzleSchema, u as readAIConfig, v as doctorDiagnosticsTableRows, w as PLACEHOLDER_SCHEMA, x as DEFAULT_MINERU_API_CONFIG, y as formatDoctorDiagnosticsJson } from "./generate-drizzle-schema-DsIHPNA4.mjs";
+import { A as package_default, C as DEFAULT_PROMPT_CONFIG, D as seedConfig, E as createConfig, O as description, S as DEFAULT_MINERU_CONFIG, T as PLACEHOLDER_TEXT, _ as doctorDiagnosticsSeverityRows, a as recognizeImageText, b as DEFAULT_LITEPARSE_CONFIG, c as t, d as writeAIConfig, f as AIConfigSchema, h as toSnakeCase, j as version, k as name, l as getDefaultAIConfig, m as parseJsonSchema, n as collectDoctorDiagnostics, o as shouldUseImageOcrFallback, p as JsonSchemaDefinitionSchema, r as createMigrationConfig, s as initI18n, t as generateDrizzleSchema, u as readAIConfig, v as doctorDiagnosticsTableRows, w as PLACEHOLDER_SCHEMA, x as DEFAULT_MINERU_API_CONFIG, y as formatDoctorDiagnosticsJson } from "./generate-drizzle-schema-CaSMqQWx.mjs";
 import { createRequire } from "node:module";
 import fs from "node:fs/promises";
 import os from "node:os";
@@ -13,13 +13,12 @@ import { defineCommand, runMain } from "citty";
 import { consola } from "consola";
 import updateNotifier from "update-notifier";
 import CliTable3 from "cli-table3";
-import fs$1 from "node:fs";
 import { confirm, intro, isCancel, outro, select, spinner, text } from "@clack/prompts";
 import pc from "picocolors";
-import { Buffer } from "node:buffer";
-import * as XLSX from "xlsx";
+import fs$1 from "node:fs";
 import { TextDecoder, promisify } from "node:util";
 import { fileTypeFromBuffer, fileTypeFromFile } from "file-type";
+import { Buffer } from "node:buffer";
 import { glob, globSync } from "tinyglobby";
 import { extractText, getDocumentProxy, getMeta } from "unpdf";
 import AdmZip from "adm-zip";
@@ -144,260 +143,9 @@ const doctorCommand = defineCommand({
 	}
 });
 
-//#endregion
-//#region src/application/export/export-manager.ts
-function formatRowsConformingToSchema(rows, columns, schema, format) {
-	return rows.map((row) => {
-		const newRow = {};
-		columns.forEach((col) => {
-			const colName = col.name;
-			const val = row[colName];
-			const type = (schema?.properties?.[colName])?.type || "";
-			if (val === null || val === void 0) newRow[colName] = "";
-			else if (type === "boolean") if (format === "xlsx") newRow[colName] = val === 1 || val === "1" || val === true;
-			else newRow[colName] = val === 1 || val === "1" || val === true ? "true" : "false";
-			else if (type === "number" || type === "integer") if (val === "") newRow[colName] = "";
-			else {
-				const num = Number(val);
-				newRow[colName] = Number.isNaN(num) ? val : num;
-			}
-			else if (typeof val === "object") newRow[colName] = JSON.stringify(val);
-			else {
-				const dbType = (col.type || "").toLowerCase();
-				if ((dbType.includes("int") || dbType.includes("real") || dbType.includes("num") || dbType.includes("double") || dbType.includes("float")) && typeof val === "string" && val !== "") {
-					const num = Number(val);
-					newRow[colName] = Number.isNaN(num) ? val : num;
-				} else newRow[colName] = val;
-			}
-		});
-		return newRow;
-	});
-}
-function generateExportBuffer(tableName, formattedRows, columns, format) {
-	const ws = XLSX.utils.json_to_sheet(formattedRows, { header: columns.map((col) => col.name) });
-	if (format === "xlsx") {
-		const wb = XLSX.utils.book_new();
-		XLSX.utils.book_append_sheet(wb, ws, tableName.slice(0, 31));
-		return XLSX.write(wb, {
-			bookType: "xlsx",
-			type: "buffer"
-		});
-	} else {
-		const csv = XLSX.utils.sheet_to_csv(ws);
-		return Buffer.from("" + csv, "utf8");
-	}
-}
-
-//#endregion
-//#region src/application/schema/load-schema.ts
-const JSON_EXT_RE$1 = /\.json$/;
-async function loadSchema(config, schemaName) {
-	const schemaPath = path.join(config.schemaPath, `${schemaName}.json`);
-	try {
-		const parsed = await readFile(schemaPath);
-		return { schema: JsonSchemaDefinitionSchema.parse(parsed) };
-	} catch (e) {
-		if (e instanceof ZodError) return {
-			schema: null,
-			error: t("errors.schema.validationFailed", {
-				name: `${schemaName}.json`,
-				issues: e.issues.map((i) => `  - ${i.path.join(".")}: ${i.message}`).join("\n")
-			})
-		};
-		if (e.code === "ENOENT") return {
-			schema: null,
-			error: t("errors.schema.cannotRead", { name: `${schemaName}.json` })
-		};
-		if (e instanceof SyntaxError) return {
-			schema: null,
-			error: t("errors.schema.invalidJson", { name: `${schemaName}.json` })
-		};
-		return {
-			schema: null,
-			error: String(e)
-		};
-	}
-}
-async function listSchemas(aiexDir) {
-	try {
-		const dir = path.join(aiexDir, "schema");
-		return (await fs.readdir(dir)).filter((f) => f.endsWith(".json")).map((f) => f.replace(JSON_EXT_RE$1, "")).sort();
-	} catch {
-		return [];
-	}
-}
-
-//#endregion
-//#region src/commands/utils.ts
-function failCommand(message) {
-	if (message) consola.error(message);
-	outro(t("common.failed"));
-	process.exitCode = 1;
-}
-
-//#endregion
-//#region src/commands/dump.ts
-const dumpCommand = defineCommand({
-	meta: {
-		name: "dump",
-		description: t("command.dump.description")
-	},
-	args: {
-		table: {
-			type: "string",
-			alias: "t",
-			description: t("command.dump.args.table")
-		},
-		schema: {
-			type: "string",
-			alias: "s",
-			description: t("command.dump.args.schema")
-		},
-		format: {
-			type: "string",
-			alias: "f",
-			description: t("command.dump.args.format")
-		},
-		output: {
-			type: "string",
-			alias: "o",
-			description: t("command.dump.args.output")
-		}
-	},
-	async run({ args }) {
-		intro(pc.inverse(" aiex dump "));
-		await initI18n();
-		if (!args.table && !args.schema) {
-			failCommand(t("command.dump.errors.tableOrSchemaRequired"));
-			return;
-		}
-		const cwd = process.cwd();
-		const config = createMigrationConfig(cwd);
-		const schemaDir = config.schemaPath;
-		let tableName = args.table || "";
-		let schema = null;
-		if (args.schema) {
-			const schemaLoad = await loadSchema(config, args.schema);
-			if (!schemaLoad.schema) {
-				failCommand(schemaLoad.error || t("command.dump.errors.schemaNotFound", { name: args.schema }));
-				return;
-			}
-			schema = schemaLoad.schema;
-			const tName = schema.table?.name;
-			if (!tName) {
-				failCommand(t("command.dump.errors.noTableName", { name: args.schema }));
-				return;
-			}
-			if (tableName && tableName !== tName) {
-				failCommand(t("command.dump.errors.tableMismatch", {
-					table: tableName,
-					schemaTable: tName
-				}));
-				return;
-			}
-			tableName = tName;
-		} else try {
-			if (fs$1.existsSync(schemaDir)) {
-				const files = fs$1.readdirSync(schemaDir).filter((f) => f.endsWith(".json"));
-				for (const file of files) {
-					const s$1 = await readFile(path.join(schemaDir, file));
-					if (s$1.table?.name === tableName) {
-						schema = s$1;
-						break;
-					}
-				}
-			}
-		} catch {}
-		let format = args.format?.toLowerCase();
-		const outputPathArg = args.output;
-		if (outputPathArg) {
-			const ext = path.extname(outputPathArg).toLowerCase();
-			if (!format) {
-				if (ext === ".xlsx") format = "xlsx";
-				else if (ext === ".csv") format = "csv";
-			}
-		}
-		if (!format) format = "csv";
-		if (format !== "csv" && format !== "xlsx") {
-			failCommand(t("command.dump.errors.unsupportedFormat", { format }));
-			return;
-		}
-		const resolvedOutput = outputPathArg ? path.resolve(outputPathArg) : path.resolve(cwd, `${tableName}.${format}`);
-		if (!fs$1.existsSync(config.databasePath)) {
-			failCommand(t("command.dump.errors.dbNotFound", {
-				path: config.databasePath,
-				cmd: "aiex schema"
-			}));
-			return;
-		}
-		const s = spinner();
-		s.start(t("command.dump.loading", { name: tableName }));
-		let columns = [];
-		let rows = [];
-		try {
-			const db = new Database(config.databasePath, { readonly: true });
-			if (!db.prepare(`
-        select name from sqlite_master
-        where type = 'table' and name = ?
-      `).get(tableName)) {
-				s.stop(t("command.dump.dbQueryFailed"));
-				failCommand(t("command.dump.errors.tableNotFound", {
-					name: tableName,
-					cmd: "aiex schema"
-				}));
-				db.close();
-				return;
-			}
-			columns = db.pragma(`table_info(${tableName})`);
-			rows = db.prepare(`select * from ${tableName}`).all();
-			db.close();
-		} catch (error) {
-			s.stop(t("command.dump.dbQueryFailed"));
-			failCommand(error instanceof Error ? error.message : String(error));
-			return;
-		}
-		if (rows.length === 0) {
-			s.stop(t("command.dump.emptyTable"));
-			consola.warn(t("command.dump.errors.tableEmpty", { name: tableName }));
-		} else s.stop(t("command.dump.loaded", { count: rows.length }));
-		const s2 = spinner();
-		s2.start(t("command.dump.formatting"));
-		let formattedRows;
-		try {
-			formattedRows = formatRowsConformingToSchema(rows, columns, schema, format);
-			s2.stop(t("command.dump.formatted"));
-		} catch (error) {
-			s2.stop(t("command.dump.dbQueryFailed"));
-			failCommand(error instanceof Error ? error.message : String(error));
-			return;
-		}
-		const s3 = spinner();
-		s3.start(t("command.dump.writing", {
-			format: format.toUpperCase(),
-			path: resolvedOutput
-		}));
-		try {
-			const buffer = generateExportBuffer(tableName, formattedRows, columns, format);
-			const outputDir = path.dirname(resolvedOutput);
-			if (!fs$1.existsSync(outputDir)) fs$1.mkdirSync(outputDir, { recursive: true });
-			fs$1.writeFileSync(resolvedOutput, buffer);
-			s3.stop(t("command.dump.dumpCompleted"));
-			consola.success(t("command.dump.successMsg", {
-				count: rows.length,
-				path: pc.cyan(resolvedOutput)
-			}));
-		} catch (error) {
-			s3.stop(t("command.dump.fileWriteFailed"));
-			failCommand(error instanceof Error ? error.message : String(error));
-			return;
-		}
-		outro(t("common.done"));
-	}
-});
-
 //#endregion
 //#region src/application/extraction/quality.ts
-function formatInputProcessing$1(input) {
+function formatInputProcessing(input) {
 	const handler = input.converter ? `${input.handler}(${input.converter})` : input.handler;
 	return `${input.mime ?? input.kind} -> ${handler}`;
 }
@@ -2166,6 +1914,45 @@ Please output the corrected JSON object now:`;
 	}
 }
 
+//#endregion
+//#region src/application/schema/load-schema.ts
+const JSON_EXT_RE$1 = /\.json$/;
+async function loadSchema(config, schemaName) {
+	const schemaPath = path.join(config.schemaPath, `${schemaName}.json`);
+	try {
+		const parsed = await readFile(schemaPath);
+		return { schema: JsonSchemaDefinitionSchema.parse(parsed) };
+	} catch (e) {
+		if (e instanceof ZodError) return {
+			schema: null,
+			error: t("errors.schema.validationFailed", {
+				name: `${schemaName}.json`,
+				issues: e.issues.map((i) => `  - ${i.path.join(".")}: ${i.message}`).join("\n")
+			})
+		};
+		if (e.code === "ENOENT") return {
+			schema: null,
+			error: t("errors.schema.cannotRead", { name: `${schemaName}.json` })
+		};
+		if (e instanceof SyntaxError) return {
+			schema: null,
+			error: t("errors.schema.invalidJson", { name: `${schemaName}.json` })
+		};
+		return {
+			schema: null,
+			error: String(e)
+		};
+	}
+}
+async function listSchemas(aiexDir) {
+	try {
+		const dir = path.join(aiexDir, "schema");
+		return (await fs.readdir(dir)).filter((f) => f.endsWith(".json")).map((f) => f.replace(JSON_EXT_RE$1, "")).sort();
+	} catch {
+		return [];
+	}
+}
+
 //#endregion
 //#region src/infrastructure/extraction/insert-extracted-data.ts
 function convertValue(value, column) {
@@ -2511,7 +2298,7 @@ async function runAuditedExtraction(options) {
 			filePath = input.filePath;
 			inputProcessing = input.inputProcessing;
 			inputQuality = input.quality;
-			if (!quiet) consola.info(`Input: ${formatInputProcessing$1(inputProcessing)}`);
+			if (!quiet) consola.info(`Input: ${formatInputProcessing(inputProcessing)}`);
 			await updateExtractionAuditRecord(aiexDir, audit.id, {
 				inputProcessing,
 				quality: inputQuality
@@ -2719,36 +2506,15 @@ async function runBatchExtraction(aiexDir, config, aiConfig, schemaName, dir, gl
 }
 
 //#endregion
-//#region src/commands/extract.ts
-function getIdArg(args) {
-	if (typeof args.id === "string") return args.id;
-	const positional = args._;
-	return Array.isArray(positional) && typeof positional[0] === "string" ? positional[0] : "";
-}
-function isExtractSubCommand(rawArgs) {
-	if (!Array.isArray(rawArgs)) return false;
-	return rawArgs.some((arg) => typeof arg === "string" && [
-		"history",
-		"show",
-		"retry",
-		"rm"
-	].includes(arg));
-}
-function formatSource(source) {
-	return source.type === "file" ? source.fileName || "file" : "unknown";
-}
-function formatInputProcessing(input) {
-	if (!input) return "";
-	const handler = input.converter ? `${input.handler}(${input.converter})` : input.handler;
-	return ` [${input.mime ?? input.kind} -> ${handler}]`;
-}
-function formatQuality(quality, failureStage) {
-	if (failureStage) return ` [failed:${failureStage}]`;
-	if (quality?.input?.pdf) return ` [pdf:${quality.input.pdf.pageCount}p/${quality.input.pdf.textLength}chars${quality.input.pdf.fallbackUsed ? "/fallback" : ""}]`;
-	if (quality?.input?.ocr) return ` [ocr:${Math.round(quality.input.ocr.confidence * 100)}%/${quality.input.ocr.textLength}chars]`;
-	if (quality?.ai?.missingFieldRate !== void 0) return ` [missing:${Math.round(quality.ai.missingFieldRate * 100)}%]`;
-	return "";
+//#region src/commands/utils.ts
+function failCommand(message) {
+	if (message) consola.error(message);
+	outro(t("common.failed"));
+	process.exitCode = 1;
 }
+
+//#endregion
+//#region src/commands/extract.ts
 async function loadConfiguredAI(aiexDir) {
 	const aiConfig = await readAIConfig(aiexDir);
 	if (!aiConfig) {
@@ -2777,143 +2543,11 @@ function resolveModelOverride(aiConfig, modelName) {
 	}
 	return matched;
 }
-const historyCommand = defineCommand({
-	meta: {
-		name: "history",
-		description: t("command.extract.history.description")
-	},
-	async run() {
-		const config = createMigrationConfig(process.cwd());
-		const records = await listExtractionAuditRecords(path.dirname(config.schemaPath));
-		if (records.length === 0) {
-			consola.info(t("command.extract.history.empty"));
-			return;
-		}
-		for (const record of records) {
-			const suffix = record.error ? ` — ${record.error}` : record.outputName ? ` — ${record.outputName}` : "";
-			consola.info(`${record.status.padEnd(9)} ${record.id}  ${record.schemaName}  ${formatSource(record.source)}${formatInputProcessing(record.inputProcessing)}${formatQuality(record.quality, record.failureStage)}${suffix}`);
-		}
-	}
-});
-const showCommand = defineCommand({
-	meta: {
-		name: "show",
-		description: t("command.extract.show.description")
-	},
-	args: { id: {
-		type: "string",
-		description: t("command.extract.show.args.id")
-	} },
-	async run({ args }) {
-		const id = getIdArg(args);
-		if (!id) {
-			failCommand(t("command.extract.history.errors.idRequired"));
-			return;
-		}
-		const config = createMigrationConfig(process.cwd());
-		const record = await readExtractionAuditRecord(path.dirname(config.schemaPath), id);
-		if (!record) {
-			failCommand(t("command.extract.history.errors.recordNotFound", { id }));
-			return;
-		}
-		consola.info(JSON.stringify(record, null, 2));
-	}
-});
-const retryCommand = defineCommand({
-	meta: {
-		name: "retry",
-		description: t("command.extract.retry.description")
-	},
-	args: {
-		id: {
-			type: "string",
-			description: t("command.extract.retry.args.id")
-		},
-		noInsert: {
-			type: "boolean",
-			description: t("command.extract.retry.args.noInsert"),
-			default: false
-		}
-	},
-	async run({ args }) {
-		intro(pc.inverse(" aiex extract retry "));
-		await initI18n();
-		const id = getIdArg(args);
-		if (!id) {
-			failCommand(t("command.extract.history.errors.idRequired"));
-			return;
-		}
-		const config = createMigrationConfig(process.cwd());
-		const aiexDir = path.dirname(config.schemaPath);
-		const record = await readExtractionAuditRecord(aiexDir, id);
-		if (!record) {
-			failCommand(t("command.extract.history.errors.recordNotFound", { id }));
-			return;
-		}
-		const aiConfig = await loadConfiguredAI(aiexDir);
-		if (!aiConfig) return;
-		const modelOverride = resolveModelOverride(aiConfig, record.modelName);
-		if (modelOverride === null) return;
-		try {
-			const result = await runAuditedExtraction({
-				aiexDir,
-				config,
-				aiConfig,
-				schemaName: record.schemaName,
-				source: record.source,
-				modelOverride,
-				retryOf: record.id,
-				insert: !args.noInsert,
-				force: true
-			});
-			if (!result.success) {
-				failCommand(result.error);
-				return;
-			}
-			outro(t("common.done"));
-		} catch (error) {
-			if (isMissingUploadFileError(error)) {
-				failCommand(MISSING_UPLOAD_FILE_TEXT);
-				return;
-			}
-			failCommand(error instanceof Error ? error.message : String(error));
-		}
-	}
-});
-const rmCommand = defineCommand({
-	meta: {
-		name: "rm",
-		description: t("command.extract.rm.description")
-	},
-	args: { id: {
-		type: "string",
-		description: t("command.extract.rm.args.id")
-	} },
-	async run({ args }) {
-		const id = getIdArg(args);
-		if (!id) {
-			failCommand(t("command.extract.history.errors.idRequired"));
-			return;
-		}
-		const config = createMigrationConfig(process.cwd());
-		if (!await deleteExtractionAuditRecord(path.dirname(config.schemaPath), id)) {
-			failCommand(t("command.extract.history.errors.recordNotFound", { id }));
-			return;
-		}
-		consola.success(t("command.extract.history.deleted", { id }));
-	}
-});
 const extractCommand = defineCommand({
 	meta: {
 		name: "extract",
 		description: t("command.extract.description")
 	},
-	subCommands: {
-		history: historyCommand,
-		show: showCommand,
-		retry: retryCommand,
-		rm: rmCommand
-	},
 	args: {
 		schema: {
 			type: "string",
@@ -2951,8 +2585,7 @@ const extractCommand = defineCommand({
 			default: false
 		}
 	},
-	async run({ args, rawArgs }) {
-		if (isExtractSubCommand(rawArgs)) return;
+	async run({ args }) {
 		intro(pc.inverse(" aiex extract "));
 		await initI18n();
 		const config = createMigrationConfig(process.cwd());
@@ -3033,7 +2666,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 		}))
 	});
 	if (isCancel(schemaName)) {
-		cancel(t("common.cancelled"));
+		cancel$1(t("common.cancelled"));
 		return false;
 	}
 	const inputSource = await select({
@@ -3049,7 +2682,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 		}]
 	});
 	if (isCancel(inputSource)) {
-		cancel(t("common.cancelled"));
+		cancel$1(t("common.cancelled"));
 		return false;
 	}
 	if (inputSource === "file") {
@@ -3060,7 +2693,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 			}
 		});
 		if (isCancel(filePathStr)) {
-			cancel(t("common.cancelled"));
+			cancel$1(t("common.cancelled"));
 			return false;
 		}
 		const fp = filePathStr;
@@ -3069,7 +2702,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 			initialValue: false
 		});
 		if (isCancel(force)) {
-			cancel(t("common.cancelled"));
+			cancel$1(t("common.cancelled"));
 			return false;
 		}
 		return (await runAuditedExtraction({
@@ -3092,7 +2725,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 			}
 		});
 		if (isCancel(dirPath)) {
-			cancel(t("common.cancelled"));
+			cancel$1(t("common.cancelled"));
 			return false;
 		}
 		const force = await confirm({
@@ -3100,7 +2733,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 			initialValue: false
 		});
 		if (isCancel(force)) {
-			cancel(t("common.cancelled"));
+			cancel$1(t("common.cancelled"));
 			return false;
 		}
 		const result = await runBatchExtraction(aiexDir, config, aiConfig, schemaName, dirPath, void 0, modelOverride, { force });
@@ -3109,7 +2742,7 @@ async function runInteractive(aiexDir, config, aiConfig, modelOverride) {
 	}
 	return false;
 }
-function cancel(msg) {
+function cancel$1(msg) {
 	consola.info(msg);
 	outro(t("common.cancelled"));
 	process.exitCode = 0;
@@ -3549,6 +3182,14 @@ const watchCommand = defineCommand({
 	async run({ args }) {
 		intro(pc.inverse(" aiex watch "));
 		await initI18n();
+		const config = createMigrationConfig(process.cwd());
+		const aiexDir = path.dirname(config.schemaPath);
+		if (!args.schema && !args.dir && !args.model) {
+			const aiConfig$1 = await loadConfiguredAI(aiexDir);
+			if (!aiConfig$1) return;
+			if (await runInteractiveWatch(aiexDir, config, aiConfig$1)) consola.info(t("command.watch.events.pressCtrlC"));
+			return;
+		}
 		if (!args.schema) {
 			failCommand(t("command.watch.errors.schemaRequired"));
 			return;
@@ -3557,33 +3198,18 @@ const watchCommand = defineCommand({
 			failCommand(t("command.watch.errors.dirRequired"));
 			return;
 		}
-		const config = createMigrationConfig(process.cwd());
-		const aiexDir = path.dirname(config.schemaPath);
 		const schemaLoad = await loadSchema(config, args.schema);
 		if (!schemaLoad.schema) {
 			failCommand(schemaLoad.error || t("command.watch.errors.schemaNotFound", { name: args.schema }));
 			return;
 		}
-		let watchDirStat;
-		try {
-			watchDirStat = fs$1.statSync(args.dir);
-		} catch (e) {
-			failCommand(t("command.watch.errors.dirNotExist", {
-				dir: args.dir,
-				error: e instanceof Error ? e.message : String(e)
-			}));
-			return;
-		}
-		if (!watchDirStat.isDirectory()) {
-			failCommand(t("command.watch.errors.notADirectory", { dir: args.dir }));
-			return;
-		}
 		const watchDirAbs = path.resolve(args.dir);
+		if (!validateWatchDir(watchDirAbs)) return;
 		const aiConfig = await loadConfiguredAI(aiexDir);
 		if (!aiConfig) return;
 		const modelOverride = resolveModelOverride(aiConfig, args.model);
 		if (modelOverride === null) return;
-		const watcher = startWatcher({
+		registerCleanup(startWatch({
 			aiexDir,
 			config,
 			aiConfig,
@@ -3591,18 +3217,112 @@ const watchCommand = defineCommand({
 			watchDir: watchDirAbs,
 			modelOverride,
 			insert: !args.noInsert
-		});
-		const cleanup = async () => {
-			consola.info(t("command.watch.events.stopped"));
-			await watcher.close();
-			consola.success(t("command.watch.events.stoppedOk"));
-			process.exit(0);
-		};
-		process.on("SIGINT", cleanup);
-		process.on("SIGTERM", cleanup);
+		}));
 		consola.info(t("command.watch.events.pressCtrlC"));
 	}
 });
+async function runInteractiveWatch(aiexDir, config, aiConfig) {
+	const schemas = await listSchemas(aiexDir);
+	if (schemas.length === 0) {
+		failCommand(t("command.extract.errors.noSchemas", {
+			path: pc.cyan(".aiex/schema/"),
+			cmd: pc.cyan("aiex web")
+		}));
+		return false;
+	}
+	const schemaName = await select({
+		message: t("command.watch.interactive.selectSchema"),
+		options: schemas.map((s) => ({
+			label: s,
+			value: s
+		}))
+	});
+	if (isCancel(schemaName)) {
+		cancel(t("common.cancelled"));
+		return false;
+	}
+	const dirPath = await text({
+		message: t("command.watch.interactive.enterDirPath"),
+		validate(value) {
+			if (!value || value.trim().length === 0) return t("command.watch.interactive.dirPathRequired");
+		}
+	});
+	if (isCancel(dirPath)) {
+		cancel(t("common.cancelled"));
+		return false;
+	}
+	const selectedModel = await select({
+		message: t("command.watch.interactive.selectModel"),
+		options: [{
+			label: t("command.watch.interactive.autoModel"),
+			value: ""
+		}, ...aiConfig.provider.models.map((model) => ({
+			label: model.name,
+			value: model.name
+		}))]
+	});
+	if (isCancel(selectedModel)) {
+		cancel(t("common.cancelled"));
+		return false;
+	}
+	const noInsert = await confirm({
+		message: t("command.watch.interactive.askNoInsert"),
+		initialValue: false
+	});
+	if (isCancel(noInsert)) {
+		cancel(t("common.cancelled"));
+		return false;
+	}
+	const watchDir = path.resolve(dirPath);
+	if (!validateWatchDir(watchDir)) return false;
+	const modelOverride = resolveModelOverride(aiConfig, selectedModel ? selectedModel : void 0);
+	if (modelOverride === null) return false;
+	registerCleanup(startWatch({
+		aiexDir,
+		config,
+		aiConfig,
+		schemaName,
+		watchDir,
+		modelOverride,
+		insert: !noInsert
+	}));
+	return true;
+}
+function validateWatchDir(dir) {
+	let watchDirStat;
+	try {
+		watchDirStat = fs$1.statSync(dir);
+	} catch (e) {
+		failCommand(t("command.watch.errors.dirNotExist", {
+			dir,
+			error: e instanceof Error ? e.message : String(e)
+		}));
+		return false;
+	}
+	if (!watchDirStat.isDirectory()) {
+		failCommand(t("command.watch.errors.notADirectory", { dir }));
+		return false;
+	}
+	return true;
+}
+function startWatch(options) {
+	return startWatcher(options);
+}
+function registerCleanup(watcher) {
+	const cleanup = async () => {
+		consola.info(t("command.watch.events.stopped"));
+		await watcher.close();
+		consola.success(t("command.watch.events.stoppedOk"));
+		process.exit(0);
+	};
+	process.on("SIGINT", cleanup);
+	process.on("SIGTERM", cleanup);
+}
+function cancel(msg) {
+	consola.info(msg);
+	outro(t("common.cancelled"));
+	process.exitCode = 0;
+}
 
 //#endregion
 //#region src/domain/ai-extraction/model-capabilities.json
@@ -17062,7 +16782,6 @@ const subCommands = {
 	schema: schemaCommand,
 	extract: extractCommand,
 	watch: watchCommand,
-	dump: dumpCommand,
 	completion: completionCommand,
 	doctor: doctorCommand
 };

package/dist/{generate-drizzle-schema-DsIHPNA4.mjs → generate-drizzle-schema-CaSMqQWx.mjs}

@@ -11,7 +11,7 @@ import { z } from "zod";
 
 //#region package.json
 var name = "aiex-cli";
-var version = "0.1.0-beta.3";
+var version = "0.1.1-beta.1";
 var description = "JSON Schema → SQLite with AI-powered data extraction";
 var package_default = {
 	name,
@@ -862,30 +862,6 @@ const en = {
 				fileRequiredSingle: "Please provide a file (-f) to extract from",
 				noSchemas: "No schema files found in {{path}}. Run {{cmd}} to create and configure schemas first."
 			},
-			history: {
-				description: "List extraction audit records",
-				empty: "No extraction history found",
-				errors: {
-					idRequired: "Audit record id is required",
-					recordNotFound: "Extraction record not found: {{id}}"
-				},
-				deleted: "Deleted extraction record: {{id}}"
-			},
-			show: {
-				description: "Show an extraction audit record",
-				args: { id: "Audit record id" }
-			},
-			retry: {
-				description: "Retry an extraction audit record",
-				args: {
-					id: "Audit record id",
-					noInsert: "Extract and save JSON without inserting into SQLite"
-				}
-			},
-			rm: {
-				description: "Delete an extraction audit record and cached upload",
-				args: { id: "Audit record id" }
-			},
 			batch: {
 				scanning: "Scanning {{dir}} for supported files...",
 				found: "Found {{count}} file(s) to process",
@@ -932,6 +908,14 @@ const en = {
 				model: "AI model to use for extraction (overrides default/auto-selected model)",
 				noInsert: "Extract and save JSON without inserting into SQLite database"
 			},
+			interactive: {
+				selectSchema: "Select a schema to watch with:",
+				enterDirPath: "Enter directory path to watch:",
+				dirPathRequired: "Please enter a directory path",
+				selectModel: "Select an AI model:",
+				autoModel: "Auto-select model",
+				askNoInsert: "Save extracted JSON without inserting into SQLite?"
+			},
 			errors: {
 				schemaRequired: "Schema name (-s) is required",
 				dirRequired: "Watch directory path (-d) is required",
@@ -963,35 +947,6 @@ const en = {
 				failTitle: "AIEX Watch Failed: {{file}}"
 			}
 		},
-		dump: {
-			description: "Dump SQLite database table to Excel (.xlsx) or CSV (.csv)",
-			args: {
-				table: "SQLite table name to export",
-				schema: "Schema name (without .json extension) to export",
-				format: "Export format: csv or xlsx (default: inferred from output or csv)",
-				output: "Output file path (default: ./<tableName>.<format>)"
-			},
-			errors: {
-				tableOrSchemaRequired: "Either table name (--table / -t) or schema name (--schema / -s) is required",
-				schemaNotFound: "Schema file for \"{{name}}\" not found",
-				noTableName: "Schema \"{{name}}\" does not define a database table name.",
-				tableMismatch: "Specified table name \"{{table}}\" does not match schema table name \"{{schemaTable}}\"",
-				unsupportedFormat: "Unsupported dump format: \"{{format}}\". Supported formats: csv, xlsx",
-				dbNotFound: "Database file not found at {{path}}. Please run \"{{cmd}}\" to create the database first.",
-				tableNotFound: "Table \"{{name}}\" not found in database. Run \"{{cmd}}\" first to migrate.",
-				tableEmpty: "Table \"{{name}}\" is empty. Exporting empty file..."
-			},
-			loading: "Loading data from table \"{{name}}\"...",
-			loaded: "Loaded {{count}} row(s)",
-			emptyTable: "Empty table",
-			formatting: "Formatting data...",
-			formatted: "Data formatted",
-			writing: "Writing {{format}} file to {{path}}...",
-			dumpCompleted: "Dump completed successfully",
-			successMsg: "Successfully dumped {{count}} row(s) to {{path}}",
-			fileWriteFailed: "File write failed",
-			dbQueryFailed: "Database query failed"
-		},
 		doctor: {
 			description: "Print environment and configuration diagnostics",
 			args: { json: "Print diagnostics as JSON" },
@@ -1295,7 +1250,7 @@ async function initI18n(lng) {
 			fallbackLng: "en",
 			resources: {
 				"en": { translation: en },
-				"zh-CN": { translation: await import("./zh-CN-B2yrInX9.mjs").then((m) => m.zhCN) }
+				"zh-CN": { translation: await import("./zh-CN-Cs4MViVi.mjs").then((m) => m.zhCN) }
 			},
 			interpolation: { escapeValue: false },
 			returnNull: false

package/dist/index.mjs

@@ -1,3 +1,3 @@
-import { _ as doctorDiagnosticsSeverityRows, g as buildDoctorDiagnostics, i as generateDrizzleConfig, m as parseJsonSchema, n as collectDoctorDiagnostics, p as JsonSchemaDefinitionSchema, r as createMigrationConfig, t as generateDrizzleSchema, v as doctorDiagnosticsTableRows, y as formatDoctorDiagnosticsJson } from "./generate-drizzle-schema-DsIHPNA4.mjs";
+import { _ as doctorDiagnosticsSeverityRows, g as buildDoctorDiagnostics, i as generateDrizzleConfig, m as parseJsonSchema, n as collectDoctorDiagnostics, p as JsonSchemaDefinitionSchema, r as createMigrationConfig, t as generateDrizzleSchema, v as doctorDiagnosticsTableRows, y as formatDoctorDiagnosticsJson } from "./generate-drizzle-schema-CaSMqQWx.mjs";
 
 export { JsonSchemaDefinitionSchema, buildDoctorDiagnostics, collectDoctorDiagnostics, createMigrationConfig, doctorDiagnosticsSeverityRows, doctorDiagnosticsTableRows, formatDoctorDiagnosticsJson, generateDrizzleConfig, generateDrizzleSchema, parseJsonSchema };

package/dist/{zh-CN-B2yrInX9.mjs → zh-CN-Cs4MViVi.mjs}

@@ -78,30 +78,6 @@ const zhCN = {
 				fileRequiredSingle: "请提供文件路径（-f）进行抽取",
 				noSchemas: "在 {{path}} 未找到 schema 文件。运行 {{cmd}} 创建和配置 schemas"
 			},
-			history: {
-				description: "列出抽取审计记录",
-				empty: "未找到抽取历史记录",
-				errors: {
-					idRequired: "需要提供审计记录 ID",
-					recordNotFound: "未找到抽取记录: {{id}}"
-				},
-				deleted: "已删除抽取记录: {{id}}"
-			},
-			show: {
-				description: "查看抽取审计记录详情",
-				args: { id: "审计记录 ID" }
-			},
-			retry: {
-				description: "重试抽取审计记录",
-				args: {
-					id: "审计记录 ID",
-					noInsert: "仅保存 JSON，不插入 SQLite"
-				}
-			},
-			rm: {
-				description: "删除抽取审计记录及其缓存的上传文件",
-				args: { id: "审计记录 ID" }
-			},
 			batch: {
 				scanning: "正在扫描 {{dir}} 中支持的文件...",
 				found: "找到 {{count}} 个待处理的文件",
@@ -148,6 +124,14 @@ const zhCN = {
 				model: "用于抽取的 AI 模型（覆盖默认/自动选择的模型）",
 				noInsert: "仅保存 JSON，不插入 SQLite"
 			},
+			interactive: {
+				selectSchema: "选择用于监听抽取的 schema:",
+				enterDirPath: "输入要监听的目录路径:",
+				dirPathRequired: "请输入目录路径",
+				selectModel: "选择 AI 模型:",
+				autoModel: "自动选择模型",
+				askNoInsert: "是否仅保存 JSON，不插入 SQLite？"
+			},
 			errors: {
 				schemaRequired: "需要指定 schema 名称（-s）",
 				dirRequired: "需要指定监听目录路径（-d）",
@@ -179,35 +163,6 @@ const zhCN = {
 				failTitle: "AIEX 监听失败: {{file}}"
 			}
 		},
-		dump: {
-			description: "导出 SQLite 数据库表到 Excel（.xlsx）或 CSV（.csv）",
-			args: {
-				table: "要导出的 SQLite 表名",
-				schema: "要导出的 schema 名称（不含 .json 扩展名）",
-				format: "导出格式: csv 或 xlsx（默认: 从输出文件名推断或 csv）",
-				output: "输出文件路径（默认: ./<表名>.<格式>）"
-			},
-			errors: {
-				tableOrSchemaRequired: "需要指定表名（--table / -t）或 schema 名称（--schema / -s）",
-				schemaNotFound: "未找到 schema 文件 \"{{name}}\"",
-				noTableName: "Schema \"{{name}}\" 没有定义数据库表名",
-				tableMismatch: "指定的表名 \"{{table}}\" 与 schema 表名 \"{{schemaTable}}\" 不匹配",
-				unsupportedFormat: "不支持的导出格式: \"{{format}}\"。支持的格式: csv, xlsx",
-				dbNotFound: "在 {{path}} 未找到数据库文件。请先运行 \"{{cmd}}\" 创建数据库。",
-				tableNotFound: "在数据库中未找到表 \"{{name}}\" 。请先运行 \"{{cmd}}\" 迁移。",
-				tableEmpty: "表 \"{{name}}\" 为空。正在导出空文件..."
-			},
-			loading: "正在从表 \"{{name}}\" 加载数据...",
-			loaded: "已加载 {{count}} 行",
-			emptyTable: "空表",
-			formatting: "正在格式化数据...",
-			formatted: "数据已格式化",
-			writing: "正在写入 {{format}} 文件到 {{path}}...",
-			dumpCompleted: "导出完成",
-			successMsg: "已成功导出 {{count}} 行到 {{path}}",
-			fileWriteFailed: "文件写入失败",
-			dbQueryFailed: "数据库查询失败"
-		},
 		doctor: {
 			description: "打印环境和配置诊断信息",
 			args: { json: "以 JSON 格式输出诊断信息" },

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "aiex-cli",
   "type": "module",
-  "version": "0.1.0-beta.3",
+  "version": "0.1.1-beta.1",
   "description": "JSON Schema → SQLite with AI-powered data extraction",
   "author": "OSpoon <zxin088@gmail.com>",
   "license": "MIT",