Refactor speech providers to stream-first local/openai architecture

packages/cli/src/cli.ts

@@ -3,6 +3,7 @@ import { createAgentCommand } from './commands/agent/index.js'
 import { createDaemonCommand } from './commands/daemon/index.js'
 import { createPermitCommand } from './commands/permit/index.js'
 import { createProviderCommand } from './commands/provider/index.js'
+import { createSpeechCommand } from './commands/speech/index.js'
 import { createWorktreeCommand } from './commands/worktree/index.js'
 import { runLsCommand } from './commands/agent/ls.js'
 import { runRunCommand } from './commands/agent/run.js'
@@ -134,6 +135,9 @@ export function createCli(): Command {
   // Provider commands
   program.addCommand(createProviderCommand())
 
+  // Speech model commands
+  program.addCommand(createSpeechCommand())
+
   // Worktree commands
   program.addCommand(createWorktreeCommand())
 

packages/cli/src/commands/speech/download.ts

@@ -0,0 +1,68 @@
+import type { Command } from "commander";
+import type {
+  CommandError,
+  CommandOptions,
+  ListResult,
+  OutputSchema,
+} from "../../output/index.js";
+import { connectToDaemon } from "../../utils/client.js";
+
+interface SpeechDownloadRow {
+  modelId: string;
+  status: "downloaded";
+}
+
+const speechDownloadSchema: OutputSchema<SpeechDownloadRow> = {
+  idField: "modelId",
+  columns: [
+    { header: "MODEL", field: "modelId", width: 36 },
+    { header: "STATUS", field: "status", width: 12, color: () => "green" },
+  ],
+};
+
+export type SpeechDownloadResult = ListResult<SpeechDownloadRow>;
+
+export interface SpeechDownloadOptions extends CommandOptions {
+  host?: string;
+  model?: string[];
+}
+
+export async function runSpeechDownloadCommand(
+  options: SpeechDownloadOptions,
+  _command: Command
+): Promise<SpeechDownloadResult> {
+  const client = await connectToDaemon({ host: options.host });
+  try {
+    const response = await client.downloadSpeechModels({
+      modelIds: options.model && options.model.length > 0 ? options.model : undefined,
+    });
+    if (response.error) {
+      const commandError: CommandError = {
+        code: "SPEECH_MODELS_DOWNLOAD_FAILED",
+        message: response.error,
+      };
+      throw commandError;
+    }
+
+    return {
+      type: "list",
+      data: response.downloadedModelIds.map((modelId) => ({
+        modelId,
+        status: "downloaded" as const,
+      })),
+      schema: speechDownloadSchema,
+    };
+  } catch (error) {
+    if (typeof error === "object" && error && "code" in error && "message" in error) {
+      throw error;
+    }
+    const message = error instanceof Error ? error.message : String(error);
+    const commandError: CommandError = {
+      code: "SPEECH_MODELS_DOWNLOAD_FAILED",
+      message: `Failed to download speech models: ${message}`,
+    };
+    throw commandError;
+  } finally {
+    await client.close().catch(() => {});
+  }
+}

packages/cli/src/commands/speech/index.ts

@@ -0,0 +1,29 @@
+import { Command } from "commander";
+import { withOutput } from "../../output/index.js";
+import { runSpeechModelsCommand } from "./models.js";
+import { runSpeechDownloadCommand } from "./download.js";
+
+function collectMultiple(value: string, previous: string[]): string[] {
+  return previous.concat([value]);
+}
+
+export function createSpeechCommand(): Command {
+  const speech = new Command("speech").description("Manage local speech models");
+
+  speech
+    .command("models")
+    .description("List local speech model download status")
+    .option("--json", "Output in JSON format")
+    .option("--host <host>", "Daemon host:port (default: localhost:6767)")
+    .action(withOutput(runSpeechModelsCommand));
+
+  speech
+    .command("download")
+    .description("Download local speech models")
+    .option("--model <id>", "Model ID to download (repeatable)", collectMultiple, [])
+    .option("--json", "Output in JSON format")
+    .option("--host <host>", "Daemon host:port (default: localhost:6767)")
+    .action(withOutput(runSpeechDownloadCommand));
+
+  return speech;
+}

packages/cli/src/commands/speech/models.ts

@@ -0,0 +1,72 @@
+import type { Command } from "commander";
+import type {
+  CommandError,
+  CommandOptions,
+  ListResult,
+  OutputSchema,
+} from "../../output/index.js";
+import { connectToDaemon } from "../../utils/client.js";
+
+interface SpeechModelListItem {
+  id: string;
+  kind: string;
+  status: "downloaded" | "missing";
+  modelDir: string;
+  missingFiles: string;
+}
+
+const speechModelsSchema: OutputSchema<SpeechModelListItem> = {
+  idField: "id",
+  columns: [
+    { header: "MODEL", field: "id", width: 36 },
+    { header: "KIND", field: "kind", width: 12 },
+    {
+      header: "STATUS",
+      field: "status",
+      width: 12,
+      color: (value) => (value === "downloaded" ? "green" : "yellow"),
+    },
+    { header: "MODEL DIR", field: "modelDir", width: 44 },
+    { header: "MISSING FILES", field: "missingFiles", width: 40 },
+  ],
+};
+
+export type SpeechModelsResult = ListResult<SpeechModelListItem>;
+
+export interface SpeechModelsOptions extends CommandOptions {
+  host?: string;
+}
+
+export async function runSpeechModelsCommand(
+  options: SpeechModelsOptions,
+  _command: Command
+): Promise<SpeechModelsResult> {
+  const client = await connectToDaemon({ host: options.host });
+  try {
+    const response = await client.listSpeechModels();
+    const rows: SpeechModelListItem[] = response.models
+      .slice()
+      .sort((a, b) => a.kind.localeCompare(b.kind) || a.id.localeCompare(b.id))
+      .map((model) => ({
+        id: model.id,
+        kind: model.kind,
+        status: model.isDownloaded ? "downloaded" : "missing",
+        modelDir: model.modelDir,
+        missingFiles: model.missingFiles?.join(", ") ?? "",
+      }));
+    return {
+      type: "list",
+      data: rows,
+      schema: speechModelsSchema,
+    };
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error);
+    const commandError: CommandError = {
+      code: "SPEECH_MODELS_LIST_FAILED",
+      message: `Failed to list speech models: ${message}`,
+    };
+    throw commandError;
+  } finally {
+    await client.close().catch(() => {});
+  }
+}