dsh-audiogen 0.4.0 → 0.4.2

package/lib/index.js

@@ -1,8 +1,10 @@
 import { SettingsConflictError, installSettingsSection, settingsNamespace } from "@deepseek-ai/dsh-settings";
+import { copyFileSync, existsSync, mkdirSync, readdirSync } from "node:fs";
+import { fileURLToPath } from "node:url";
+import path, { dirname, join } from "node:path";
 import z from "schemastery";
 import { randomUUID } from "node:crypto";
 import { mkdir, readFile, rename, rmdir, unlink, writeFile } from "node:fs/promises";
-import path from "node:path";
 import os from "node:os";
 import { defineTool } from "@deepseek-ai/dsh-tools";
 //#region src/protocol.ts
@@ -20,6 +22,8 @@ const SETTINGS_API = {
 };
 /** The audio-generation proxy route. */
 const GENERATE_API = "/api/dsh-audiogen/generate";
+/** Loopback-only task cancellation route (aborts the host-side upstream call). */
+const TASK_API = { cancel: "/api/dsh-audiogen/task/cancel" };
 /** Host-mediated built-in provider catalog (channels the user can instantiate). */
 const PRESETS_API = "/api/dsh-audiogen/presets";
 /** Host-mediated model/voice discovery endpoint. */
@@ -50,6 +54,63 @@ const LIBRARY_TYPES = [
 	"tts"
 ];
 //#endregion
+//#region src/audio-scheduler.ts
+function createGenerationBudget(limit) {
+	let active = 0;
+	const waiting = [];
+	const clampLimit = () => {
+		const raw = Number(limit());
+		if (!Number.isFinite(raw) || raw < 1) return 5;
+		return Math.min(20, Math.floor(raw));
+	};
+	const pump = () => {
+		const max = clampLimit();
+		while (active < max && waiting.length > 0) {
+			const entry = waiting.shift();
+			if (entry.signal?.aborted === true) {
+				entry.reject(new DOMException("The operation was aborted.", "AbortError"));
+				continue;
+			}
+			entry.cleanup?.();
+			active += 1;
+			let released = false;
+			entry.resolve(() => {
+				if (released) return;
+				released = true;
+				active = Math.max(0, active - 1);
+				pump();
+			});
+		}
+	};
+	const acquire = (signal) => new Promise((resolve, reject) => {
+		const entry = {
+			resolve,
+			reject,
+			signal
+		};
+		const onAbort = () => {
+			const index = waiting.indexOf(entry);
+			if (index < 0) return;
+			waiting.splice(index, 1);
+			entry.cleanup = void 0;
+			reject(new DOMException("The operation was aborted.", "AbortError"));
+		};
+		entry.cleanup = () => {
+			signal?.removeEventListener("abort", onAbort);
+		};
+		if (signal !== void 0) {
+			if (signal.aborted === true) {
+				reject(new DOMException("The operation was aborted.", "AbortError"));
+				return;
+			}
+			signal.addEventListener("abort", onAbort, { once: true });
+		}
+		waiting.push(entry);
+		pump();
+	});
+	return { acquire };
+}
+//#endregion
 //#region src/audio-engine.ts
 /** An audio generation failure with a user-presentable message. */
 var AudioGenError = class extends Error {
@@ -1460,6 +1521,8 @@ const LIBRARY_TYPES_VALID = [
 //#endregion
 //#region src/routes.ts
 const MAX_JSON_BODY_BYTES = 16 * 1024 * 1024;
+/** 宿主侧任务取消注册表：taskId → 该任务当前在途请求的 AbortController 集合。 */
+const taskAborts = /* @__PURE__ */ new Map();
 function isLoopbackRequest(request) {
 	const address = request.socket.remoteAddress;
 	if (address !== "127.0.0.1" && address !== "::1" && address !== "::ffff:127.0.0.1") return false;
@@ -1863,8 +1926,21 @@ function makeRoutes(deps) {
 				}
 				const request = resolved.request;
 				const channel = view.channels.find((candidate) => candidate.id === request.channelId);
+				const taskId = typeof body?.taskId === "string" && body.taskId.trim() !== "" ? body.taskId.trim() : "";
+				const controller = new AbortController();
+				if (taskId !== "") {
+					const set = taskAborts.get(taskId) ?? /* @__PURE__ */ new Set();
+					set.add(controller);
+					taskAborts.set(taskId, set);
+				}
 				try {
-					const outputs = await generateAudio(channel, request);
+					const release = await deps.budget.acquire(controller.signal);
+					let outputs;
+					try {
+						outputs = await generateAudio(channel, request, controller.signal);
+					} finally {
+						release();
+					}
 					const generated = [];
 					for (const [index, output] of outputs.entries()) {
 						const saved = await saveAudioFile(output.data, output.mime, `generated-${index + 1}`);
@@ -1935,7 +2011,39 @@ function makeRoutes(deps) {
 						code: error instanceof AudioGenError ? error.code : "generate-failed",
 						message: messageOf(error)
 					});
+				} finally {
+					if (taskId !== "") {
+						const set = taskAborts.get(taskId);
+						set?.delete(controller);
+						if (set !== void 0 && set.size === 0) taskAborts.delete(taskId);
+					}
+				}
+			}
+		},
+		{
+			kind: "exact",
+			path: TASK_API.cancel,
+			handler: async (req, res) => {
+				if (!guard(req, res, "POST")) return;
+				const body = await readJsonBody(req);
+				const taskId = typeof body?.taskId === "string" ? body.taskId.trim() : "";
+				if (taskId === "") {
+					writeJson(res, 200, {
+						ok: false,
+						code: "bad-request",
+						message: "taskId is required"
+					});
+					return;
+				}
+				const controllers = taskAborts.get(taskId);
+				if (controllers !== void 0) {
+					for (const controller of controllers) controller.abort();
+					taskAborts.delete(taskId);
 				}
+				writeJson(res, 200, {
+					ok: true,
+					aborted: controllers !== void 0 ? controllers.size : 0
+				});
 			}
 		},
 		{
@@ -2215,6 +2323,29 @@ function makeRoutes(deps) {
 }
 //#endregion
 //#region src/agent-audio-tools.ts
+const audioRefSchema = {
+	type: "object",
+	additionalProperties: false,
+	properties: {
+		id: {
+			type: "string",
+			required: true
+		},
+		url: {
+			type: "string",
+			required: true
+		},
+		mime: {
+			type: "string",
+			required: true
+		},
+		bytes: {
+			type: "integer",
+			required: true
+		},
+		voiceId: { type: "string" }
+	}
+};
 const resultSchema = {
 	type: "object",
 	additionalProperties: false,
@@ -2244,34 +2375,35 @@ const resultSchema = {
 		audio: {
 			type: "array",
 			required: true,
+			items: audioRefSchema
+		},
+		resources: {
+			type: "array",
+			items: { type: "string" }
+		},
+		groups: {
+			type: "array",
 			items: {
 				type: "object",
 				additionalProperties: false,
 				properties: {
-					id: {
+					model: {
 						type: "string",
 						required: true
 					},
-					url: {
-						type: "string",
-						required: true
-					},
-					mime: {
-						type: "string",
-						required: true
+					audio: {
+						type: "array",
+						required: true,
+						items: audioRefSchema
 					},
-					bytes: {
-						type: "integer",
-						required: true
+					resources: {
+						type: "array",
+						items: { type: "string" }
 					},
-					voiceId: { type: "string" }
+					error: { type: "string" }
 				}
 			}
 		},
-		resources: {
-			type: "array",
-			items: { type: "string" }
-		},
 		error: { type: "string" }
 	}
 };
@@ -2333,6 +2465,16 @@ function registerAgentAudioTools(ctx, resolve) {
 				type: "string",
 				description: "One of the configured audio models/voices. Defaults to the first configured model."
 			},
+			models: {
+				type: "array",
+				items: { type: "string" },
+				description: "Optional: several configured model aliases to generate the SAME prompt with each one, sequentially, for comparison (e.g. [\"speech-2.8-hd\",\"speech-2.6-hd\"]). Cannot be combined with model; when present, models wins."
+			},
+			model_params: {
+				type: "object",
+				additionalProperties: true,
+				description: "Optional per-model parameter overrides used with \"models\" (automatic by default = all models share the global params). Keys are model aliases; values are partial param objects using the same param names (format, duration, voice, speed, emotion, vol, pitch, sample_rate, bitrate, lyrics, is_instrumental, loop, prompt_influence, seed, steps, cfg_scale, subtitle_enable, aigc_watermark, language_boost, pronunciation_tone, voice_modify, timbre_weights). Unset fields fall back to the global values."
+			},
 			voice: {
 				type: "string",
 				description: "Optional voice id/name for TTS providers. Required for MiniMax TTS (e.g. male-qn-qingse, female-shaonv); fetch the account voices in Settings > Plugins > AI Audio."
@@ -2463,10 +2605,15 @@ function registerAgentAudioTools(ctx, resolve) {
 					type: "object",
 					additionalProperties: false,
 					properties: {
-						voice_id: { type: "string" },
-						weight: { type: "integer" }
-					},
-					required: ["voice_id", "weight"]
+						voice_id: {
+							type: "string",
+							required: true
+						},
+						weight: {
+							type: "integer",
+							required: true
+						}
+					}
 				},
 				description: "MiniMax TTS dual-voice blend weights (timbre_weights)."
 			},
@@ -2504,156 +2651,229 @@ function registerAgentAudioTools(ctx, resolve) {
 			const config = resolve();
 			ensureConfigured(config);
 			const mode = args.mode === "music" ? "music" : args.mode === "sfx" ? "sfx" : args.mode === "voice_design" ? "voice_design" : "tts";
-			const picked = mode === "voice_design" ? (() => {
-				const usable = config.channels.filter((channel) => channel.apiUrl.trim() !== "" && channel.apiKey.trim() !== "");
-				const target = usable.find((channel) => channel.id === config.defaultChannelId) ?? usable[0];
-				if (target === void 0) throw new AudioGenError("No usable audio channel is configured for voice design.", "no-channel-available");
+			/** 把生成参数（snake_case 入参或 model_params 片段）映射为请求字段。 */
+			const mapParams = (raw) => {
+				const voiceModify = typeof raw.voice_modify === "object" && raw.voice_modify !== null ? (() => {
+					const src = raw.voice_modify;
+					const out = {};
+					if (typeof src.pitch === "number") out.pitch = src.pitch;
+					if (typeof src.intensity === "number") out.intensity = src.intensity;
+					if (typeof src.timbre === "number") out.timbre = src.timbre;
+					if (typeof src.sound_effects === "string" && src.sound_effects.trim() !== "") out.soundEffects = src.sound_effects.trim();
+					return Object.keys(out).length > 0 ? out : void 0;
+				})() : void 0;
+				const timbreWeights = Array.isArray(raw.timbre_weights) ? raw.timbre_weights.filter((item) => typeof item === "object" && item !== null && typeof item.voice_id === "string" && typeof item.weight === "number").map((item) => ({
+					voiceId: item.voice_id.trim(),
+					weight: item.weight
+				})).filter((item) => item.voiceId !== "") : void 0;
+				const stringOrEmpty = (key) => {
+					const value = raw[key];
+					return typeof value === "string" && value.trim() !== "" ? value.trim() : void 0;
+				};
+				const finiteOrUndefined = (key) => {
+					const value = raw[key];
+					return typeof value === "number" && Number.isFinite(value) ? value : void 0;
+				};
 				return {
-					channel: target,
-					alias: "",
-					upstream: ""
+					...stringOrEmpty("voice") !== void 0 ? { voice: stringOrEmpty("voice") } : {},
+					...stringOrEmpty("preview_text") !== void 0 ? { previewText: stringOrEmpty("preview_text") } : {},
+					...finiteOrUndefined("speed") !== void 0 ? { speed: finiteOrUndefined("speed") } : {},
+					...finiteOrUndefined("duration") !== void 0 ? { duration: finiteOrUndefined("duration") } : {},
+					...stringOrEmpty("lyrics") !== void 0 ? { lyrics: stringOrEmpty("lyrics") } : {},
+					...typeof raw.is_instrumental === "boolean" ? { isInstrumental: raw.is_instrumental } : {},
+					...typeof raw.loop === "boolean" ? { loop: raw.loop } : {},
+					...finiteOrUndefined("prompt_influence") !== void 0 ? { promptInfluence: finiteOrUndefined("prompt_influence") } : {},
+					...finiteOrUndefined("seed") !== void 0 ? { seed: finiteOrUndefined("seed") } : {},
+					...finiteOrUndefined("steps") !== void 0 ? { steps: finiteOrUndefined("steps") } : {},
+					...finiteOrUndefined("cfg_scale") !== void 0 ? { cfgScale: finiteOrUndefined("cfg_scale") } : {},
+					...stringOrEmpty("format") !== void 0 ? { format: stringOrEmpty("format") } : {},
+					...stringOrEmpty("emotion") !== void 0 ? { emotion: stringOrEmpty("emotion") } : {},
+					...finiteOrUndefined("vol") !== void 0 ? { vol: finiteOrUndefined("vol") } : {},
+					...finiteOrUndefined("pitch") !== void 0 ? { pitch: finiteOrUndefined("pitch") } : {},
+					...typeof raw.text_normalization === "boolean" ? { textNormalization: raw.text_normalization } : {},
+					...typeof raw.latex_read === "boolean" ? { latexRead: raw.latex_read } : {},
+					...Array.isArray(raw.pronunciation_tone) && raw.pronunciation_tone.length > 0 ? { pronunciationTone: raw.pronunciation_tone.filter((item) => typeof item === "string" && item.trim() !== "").map((item) => item.trim()) } : {},
+					...finiteOrUndefined("sample_rate") !== void 0 ? { sampleRate: finiteOrUndefined("sample_rate") } : {},
+					...finiteOrUndefined("bitrate") !== void 0 ? { bitrate: finiteOrUndefined("bitrate") } : {},
+					...finiteOrUndefined("channel") !== void 0 ? { audioChannel: finiteOrUndefined("channel") } : {},
+					...typeof raw.force_cbr === "boolean" ? { forceCbr: raw.force_cbr } : {},
+					...typeof raw.subtitle_enable === "boolean" ? { subtitleEnable: raw.subtitle_enable } : {},
+					...typeof raw.aigc_watermark === "boolean" ? { aigcWatermark: raw.aigc_watermark } : {},
+					...stringOrEmpty("language_boost") !== void 0 ? { languageBoost: stringOrEmpty("language_boost") } : {},
+					...voiceModify !== void 0 ? { voiceModify } : {},
+					...timbreWeights !== void 0 && timbreWeights.length > 0 ? { timbreWeights } : {}
 				};
-			})() : resolveModel(config, args.model);
-			const voiceModify = typeof args.voice_modify === "object" && args.voice_modify !== null ? (() => {
-				const raw = args.voice_modify;
-				const out = {};
-				if (typeof raw.pitch === "number") out.pitch = raw.pitch;
-				if (typeof raw.intensity === "number") out.intensity = raw.intensity;
-				if (typeof raw.timbre === "number") out.timbre = raw.timbre;
-				if (typeof raw.sound_effects === "string" && raw.sound_effects.trim() !== "") out.soundEffects = raw.sound_effects.trim();
-				return Object.keys(out).length > 0 ? out : void 0;
-			})() : void 0;
-			const timbreWeights = Array.isArray(args.timbre_weights) ? args.timbre_weights.filter((item) => typeof item === "object" && item !== null && typeof item.voice_id === "string" && typeof item.weight === "number").map((item) => ({
-				voiceId: item.voice_id.trim(),
-				weight: item.weight
-			})).filter((item) => item.voiceId !== "") : void 0;
-			const request = {
-				mode,
-				model: picked.alias,
-				upstream: picked.upstream,
-				channelId: picked.channel.id,
-				channel: picked.channel.name,
-				prompt: args.prompt.trim(),
-				...typeof args.voice === "string" && args.voice.trim() !== "" ? { voice: args.voice.trim() } : {},
-				...typeof args.preview_text === "string" && args.preview_text.trim() !== "" ? { previewText: args.preview_text.trim() } : {},
-				...typeof args.speed === "number" ? { speed: args.speed } : {},
-				...typeof args.duration === "number" ? { duration: args.duration } : {},
-				...typeof args.lyrics === "string" && args.lyrics.trim() !== "" ? { lyrics: args.lyrics.trim() } : {},
-				...typeof args.is_instrumental === "boolean" ? { isInstrumental: args.is_instrumental } : {},
-				...typeof args.loop === "boolean" ? { loop: args.loop } : {},
-				...typeof args.prompt_influence === "number" && Number.isFinite(args.prompt_influence) ? { promptInfluence: args.prompt_influence } : {},
-				...typeof args.seed === "number" && Number.isFinite(args.seed) ? { seed: args.seed } : {},
-				...typeof args.steps === "number" && Number.isFinite(args.steps) ? { steps: args.steps } : {},
-				...typeof args.cfg_scale === "number" && Number.isFinite(args.cfg_scale) ? { cfgScale: args.cfg_scale } : {},
-				...typeof args.format === "string" && args.format.trim() !== "" ? { format: args.format.trim() } : {},
-				...typeof args.emotion === "string" && args.emotion.trim() !== "" ? { emotion: args.emotion.trim() } : {},
-				...typeof args.vol === "number" && Number.isFinite(args.vol) ? { vol: args.vol } : {},
-				...typeof args.pitch === "number" && Number.isFinite(args.pitch) ? { pitch: args.pitch } : {},
-				...typeof args.text_normalization === "boolean" ? { textNormalization: args.text_normalization } : {},
-				...typeof args.latex_read === "boolean" ? { latexRead: args.latex_read } : {},
-				...Array.isArray(args.pronunciation_tone) && args.pronunciation_tone.length > 0 ? { pronunciationTone: args.pronunciation_tone.filter((item) => typeof item === "string" && item.trim() !== "").map((item) => item.trim()) } : {},
-				...typeof args.sample_rate === "number" && Number.isFinite(args.sample_rate) ? { sampleRate: args.sample_rate } : {},
-				...typeof args.bitrate === "number" && Number.isFinite(args.bitrate) ? { bitrate: args.bitrate } : {},
-				...typeof args.channel === "number" && Number.isFinite(args.channel) ? { audioChannel: args.channel } : {},
-				...typeof args.force_cbr === "boolean" ? { forceCbr: args.force_cbr } : {},
-				...typeof args.subtitle_enable === "boolean" ? { subtitleEnable: args.subtitle_enable } : {},
-				...typeof args.aigc_watermark === "boolean" ? { aigcWatermark: args.aigc_watermark } : {},
-				...typeof args.language_boost === "string" && args.language_boost.trim() !== "" ? { languageBoost: args.language_boost.trim() } : {},
-				...voiceModify !== void 0 ? { voiceModify } : {},
-				...timbreWeights !== void 0 && timbreWeights.length > 0 ? { timbreWeights } : {}
 			};
-			try {
-				const outputs = await generateAudio(picked.channel, request, exec.signal);
-				const audio = [];
-				const saved = [];
-				for (const [index, output] of outputs.entries()) {
-					const stored = await saveAudioFile(output.data, output.mime, `generated-${index + 1}`);
-					saved.push({
-						id: stored.id,
-						url: `/api/dsh-audiogen/audio/${encodeURIComponent(stored.file)}`,
-						file: stored.file,
-						mime: stored.mime,
-						bytes: stored.bytes,
-						...output.voiceId === void 0 ? {} : { voiceId: output.voiceId }
-					});
-					audio.push({
-						id: stored.id,
-						url: `/api/dsh-audiogen/audio/${encodeURIComponent(stored.file)}`,
-						mime: stored.mime,
-						bytes: stored.bytes,
-						...output.voiceId === void 0 ? {} : { voiceId: output.voiceId }
-					});
+			const buildRequest = (picked) => {
+				const base = mapParams(args);
+				let override = {};
+				if (typeof args.model_params === "object" && args.model_params !== null) {
+					const perModel = args.model_params[picked.alias];
+					if (typeof perModel === "object" && perModel !== null) override = mapParams(perModel);
 				}
+				return {
+					mode,
+					model: picked.alias,
+					upstream: picked.upstream,
+					channelId: picked.channel.id,
+					channel: picked.channel.name,
+					prompt: typeof args.prompt === "string" ? args.prompt.trim() : "",
+					...base,
+					...override
+				};
+			};
+			/** 单模型执行：生成 + 保存文件 + 历史 + 可选资源库；错误收敛为分组结果。 */
+			const runOne = async (picked) => {
+				const request = buildRequest(picked);
 				try {
-					await appendHistory({
-						id: randomUUID(),
-						createdAt: Date.now(),
-						mode: request.mode,
-						model: picked.alias,
-						prompt: request.prompt,
-						...request.voice === void 0 ? {} : { voice: request.voice },
-						...request.speed === void 0 ? {} : { speed: request.speed },
-						...request.duration === void 0 ? {} : { duration: request.duration },
-						...request.format === void 0 ? {} : { format: request.format },
-						audio: outputs.map((output, index) => ({
-							id: saved[index].id,
-							file: saved[index].file,
-							b64: Buffer.from(output.data).toString("base64"),
-							mime: saved[index].mime,
-							bytes: saved[index].bytes,
-							url: saved[index].url,
+					const release = await (config.budget?.acquire(exec.signal) ?? Promise.resolve(() => {}));
+					let outputs;
+					try {
+						outputs = await generateAudio(picked.channel, request, exec.signal);
+					} finally {
+						release();
+					}
+					const audio = [];
+					const saved = [];
+					for (const [index, output] of outputs.entries()) {
+						const stored = await saveAudioFile(output.data, output.mime, `generated-${index + 1}`);
+						saved.push({
+							id: stored.id,
+							url: `/api/dsh-audiogen/audio/${encodeURIComponent(stored.file)}`,
+							file: stored.file,
+							mime: stored.mime,
+							bytes: stored.bytes,
 							...output.voiceId === void 0 ? {} : { voiceId: output.voiceId }
-						})),
-						channelId: picked.channel.id,
-						channel: picked.channel.name,
-						params: { ...request }
-					});
-				} catch {}
-				const wantSave = args.save_to_library === true || config.autoSaveToLibrary && args.save_to_library !== false;
-				let resources;
-				if (wantSave) try {
-					resources = [(await saveToLibrary({
-						audioFiles: saved.map((item) => ({
-							id: item.id,
-							file: item.file,
-							mime: item.mime,
-							...item.voiceId === void 0 ? {} : { voiceId: item.voiceId }
-						})),
-						type: libraryTypeOf(request.mode, args.library_type),
-						...typeof args.library_name === "string" && args.library_name.trim() !== "" ? { name: args.library_name.trim() } : {},
-						...Array.isArray(args.library_tags) ? { tags: args.library_tags.filter((tag) => typeof tag === "string" && tag.trim() !== "").map((tag) => tag.trim()) } : {},
-						provenance: {
+						});
+						audio.push({
+							id: stored.id,
+							url: `/api/dsh-audiogen/audio/${encodeURIComponent(stored.file)}`,
+							mime: stored.mime,
+							bytes: stored.bytes,
+							...output.voiceId === void 0 ? {} : { voiceId: output.voiceId }
+						});
+					}
+					try {
+						await appendHistory({
+							id: randomUUID(),
+							createdAt: Date.now(),
 							mode: request.mode,
-							prompt: request.prompt,
-							channel: picked.channel.name,
-							channelId: picked.channel.id,
-							apiUrl: picked.channel.apiUrl,
 							model: picked.alias,
-							upstream: picked.upstream,
+							prompt: request.prompt,
 							...request.voice === void 0 ? {} : { voice: request.voice },
+							...request.speed === void 0 ? {} : { speed: request.speed },
+							...request.duration === void 0 ? {} : { duration: request.duration },
+							...request.format === void 0 ? {} : { format: request.format },
+							audio: outputs.map((output, index) => ({
+								id: saved[index].id,
+								file: saved[index].file,
+								b64: Buffer.from(output.data).toString("base64"),
+								mime: saved[index].mime,
+								bytes: saved[index].bytes,
+								url: saved[index].url,
+								...output.voiceId === void 0 ? {} : { voiceId: output.voiceId }
+							})),
+							channelId: picked.channel.id,
+							channel: picked.channel.name,
 							params: { ...request }
-						}
-					})).id];
-				} catch {}
+						});
+					} catch {}
+					const wantSave = args.save_to_library === true || config.autoSaveToLibrary && args.save_to_library !== false;
+					let resources;
+					if (wantSave) try {
+						resources = [(await saveToLibrary({
+							audioFiles: saved.map((item) => ({
+								id: item.id,
+								file: item.file,
+								mime: item.mime,
+								...item.voiceId === void 0 ? {} : { voiceId: item.voiceId }
+							})),
+							type: libraryTypeOf(request.mode, args.library_type),
+							...typeof args.library_name === "string" && args.library_name.trim() !== "" ? { name: args.library_name.trim() } : {},
+							...Array.isArray(args.library_tags) ? { tags: args.library_tags.filter((tag) => typeof tag === "string" && tag.trim() !== "").map((tag) => tag.trim()) } : {},
+							provenance: {
+								mode: request.mode,
+								prompt: request.prompt,
+								channel: picked.channel.name,
+								channelId: picked.channel.id,
+								apiUrl: picked.channel.apiUrl,
+								model: picked.alias,
+								upstream: picked.upstream,
+								...request.voice === void 0 ? {} : { voice: request.voice },
+								params: { ...request }
+							}
+						})).id];
+					} catch {}
+					return {
+						model: picked.alias,
+						audio,
+						...resources === void 0 ? {} : { resources }
+					};
+				} catch (error) {
+					if (exec.signal?.aborted === true) throw error;
+					return {
+						model: picked.alias,
+						audio: [],
+						error: error instanceof Error ? error.message : String(error)
+					};
+				}
+			};
+			const requestedModels = Array.isArray(args.models) ? [...new Set(args.models.filter((item) => typeof item === "string" && item.trim() !== "").map((item) => item.trim()))] : [];
+			if (requestedModels.length > 0 && mode !== "voice_design") {
+				const groups = [];
+				let succeeded = 0;
+				for (const alias of requestedModels) {
+					let picked;
+					try {
+						picked = resolveModel(config, alias);
+					} catch (error) {
+						groups.push({
+							model: alias,
+							audio: [],
+							error: error instanceof Error ? error.message : String(error)
+						});
+						continue;
+					}
+					const group = await runOne(picked);
+					groups.push(group);
+					if (group.error === void 0) succeeded++;
+				}
 				return {
-					status: "completed",
-					message: "Audio generation completed. The audio files can be played/downloaded from the returned URLs.",
-					mode: request.mode,
-					model: picked.alias,
-					audio,
-					...resources === void 0 ? {} : { resources }
+					status: succeeded > 0 ? "completed" : "failed",
+					message: succeeded > 0 ? `Generated ${succeeded}/${groups.length} model(s) with the same prompt for comparison. The audio files can be played/downloaded from the returned URLs.` : "All model generations failed.",
+					mode,
+					model: groups[0]?.model ?? requestedModels[0],
+					audio: groups.flatMap((group) => group.audio),
+					groups,
+					...succeeded === 0 ? { error: groups.map((group) => `${group.model}: ${group.error ?? ""}`).filter((item) => !item.endsWith(": ")).join("；") } : {}
 				};
-			} catch (error) {
-				if (exec.signal?.aborted === true) throw error;
+			}
+			const one = await runOne(mode === "voice_design" ? (() => {
+				const usable = config.channels.filter((channel) => channel.apiUrl.trim() !== "" && channel.apiKey.trim() !== "");
+				const target = usable.find((channel) => channel.id === config.defaultChannelId) ?? usable[0];
+				if (target === void 0) throw new AudioGenError("No usable audio channel is configured for voice design.", "no-channel-available");
 				return {
-					status: "failed",
-					message: "Audio generation failed.",
-					mode: request.mode,
-					model: picked.alias,
-					audio: [],
-					error: error instanceof Error ? error.message : String(error)
+					channel: target,
+					alias: "",
+					upstream: ""
 				};
-			}
+			})() : resolveModel(config, args.model));
+			if (one.error !== void 0) return {
+				status: "failed",
+				message: "Audio generation failed.",
+				mode,
+				model: one.model,
+				audio: [],
+				error: one.error
+			};
+			return {
+				status: "completed",
+				message: "Audio generation completed. The audio files can be played/downloaded from the returned URLs.",
+				mode,
+				model: one.model,
+				audio: one.audio,
+				...one.resources === void 0 ? {} : { resources: one.resources }
+			};
 		}
 	}));
 	const searchDisposer = ctx.tools.register(defineTool({
@@ -2796,6 +3016,7 @@ const name = "audiogen";
 const inject = ["webServer", "systemPrompt"];
 /** The branded settings namespace of this plugin. */
 const AudioGenSettingsNamespace = settingsNamespace(AUDIOGEN_SETTINGS_NAMESPACE);
+const DEFAULT_MAX_CONCURRENT = 5;
 const Config = z.object({
 	enabled: z.boolean().default(true),
 	announceToAgent: z.boolean().default(true),
@@ -2813,7 +3034,8 @@ const Config = z.object({
 	channelSecrets: z.dict(z.string().role("secret")).default({}),
 	defaultChannelId: z.string().default(""),
 	defaultModel: z.string().default(""),
-	autoSaveToLibrary: z.boolean().default(false)
+	autoSaveToLibrary: z.boolean().default(false),
+	maxConcurrentGenerations: z.number().default(DEFAULT_MAX_CONCURRENT)
 });
 const DEFAULT_ENABLED = true;
 const DEFAULT_ANNOUNCE = true;
@@ -2831,6 +3053,29 @@ function guidanceFor(channels, defaultChannelId) {
 	}).join("；");
 	return `${AUDIOGEN_GUIDANCE} 当前渠道与模型：${table}。`;
 }
+/**
+* 把随包分发的技能（skills/<id>/SKILL.md，含 frontmatter）同步到 DSH 用户技能根
+* `~/.dsh/skills/<id>/SKILL.md` —— DSH web 会话的 skill-filesystem（standard 等
+* preset 行）会扫描用户根，使会话可直接触发这些技能。仅创建缺失文件，绝不覆盖
+* 用户已有内容；任何失败仅告警，不影响插件本身。
+*/
+function syncBundledSkills() {
+	try {
+		const sourceRoot = join(dirname(dirname(fileURLToPath(import.meta.url))), "skills");
+		if (existsSync(sourceRoot) !== true) return;
+		const targetRoot = join(process.env.DSH_HOME ?? join(process.env.HOME ?? "", ".dsh"), "skills");
+		for (const entry of readdirSync(sourceRoot, { withFileTypes: true })) {
+			if (entry.isDirectory() !== true) continue;
+			const sourceFile = join(sourceRoot, entry.name, "SKILL.md");
+			if (existsSync(sourceFile) !== true) continue;
+			const targetDir = join(targetRoot, entry.name);
+			const targetFile = join(targetDir, "SKILL.md");
+			if (existsSync(targetFile)) continue;
+			mkdirSync(targetDir, { recursive: true });
+			copyFileSync(sourceFile, targetFile);
+		}
+	} catch {}
+}
 function normalizeChannels(value) {
 	if (!Array.isArray(value)) return [];
 	const out = [];
@@ -2862,6 +3107,7 @@ function normalizeChannels(value) {
 	return out;
 }
 function apply(ctx, config) {
+	syncBundledSkills();
 	let current = () => config ?? {};
 	const resolve = () => {
 		const value = current() ?? {};
@@ -2882,9 +3128,11 @@ function apply(ctx, config) {
 			})),
 			defaultChannelId,
 			defaultModel: typeof value.defaultModel === "string" ? value.defaultModel.trim() : "",
-			autoSaveToLibrary: value.autoSaveToLibrary === true
+			autoSaveToLibrary: value.autoSaveToLibrary === true,
+			maxConcurrentGenerations: typeof value.maxConcurrentGenerations === "number" && Number.isFinite(value.maxConcurrentGenerations) ? Math.max(1, Math.min(20, Math.floor(value.maxConcurrentGenerations))) : DEFAULT_MAX_CONCURRENT
 		};
 	};
+	const budget = createGenerationBudget(() => resolve().maxConcurrentGenerations);
 	const channelsView = () => {
 		const value = resolve();
 		return {
@@ -2898,7 +3146,8 @@ function apply(ctx, config) {
 			const disposers = makeRoutes({
 				settings: seam,
 				resolveChannels: channelsView,
-				autoSave: () => resolve().autoSaveToLibrary
+				autoSave: () => resolve().autoSaveToLibrary,
+				budget
 			}).map((route) => ctx.webServer.register(route));
 			return () => {
 				for (const dispose of disposers) dispose();
@@ -2913,7 +3162,8 @@ function apply(ctx, config) {
 				allowAgentAudioGeneration: value.allowAgentAudioGeneration,
 				channels: value.channels,
 				defaultChannelId: value.defaultChannelId,
-				autoSaveToLibrary: value.autoSaveToLibrary
+				autoSaveToLibrary: value.autoSaveToLibrary,
+				budget
 			};
 		}), "dsh-audiogen: agent audio tools");
 	});