pipeline/apps/cli/src/commands/render.ts

import { Command } from "commander";
import { runPipeline, type PipelineConfig } from "@pipeline/core";
import { PLATFORM_PRESETS, TEMPLATE_TYPES, PLATFORM_PRESET_KEYS } from "@pipeline/shared";
import { getCollector, listCollectorNames } from "@pipeline/collect";
import { readFileSync, existsSync } from "node:fs";
import { resolve, dirname } from "node:path";
import { parse as parseYaml } from "yaml";

// Commander --no-tts sets opts.tts = false (not opts.noTts)
const skipTts = (opts: any) => opts.tts === false;

export const renderCommand = new Command("render")
  .description("Generate video from text, markdown, or structured JSON input")
  .argument("[input]", "Input file path (JSON, markdown, or plain text). Required unless --source is used.")
  .requiredOption("-t, --template <type>", `Template: ${TEMPLATE_TYPES.join("|")}`)
  .option("-p, --platform <preset>", "Platform preset", "bilibili")
  .option("-o, --output <dir>", "Output directory", "./output")
  .option("--assets-dir <dir>", "Image assets directory (defaults to JSON file location)")
  .option("--config <path>", "Config file path")
  .option("-v, --verbose", "Verbose logging")

  // Data source
  .option("--source <name>", "Collect data from source before rendering")
  .option("--source-owner <owner>", "Repo owner (for github-repo source)")
  .option("--source-repo <repo>", "Repo name (for github-repo source)")

  // LLM
  .option("--skip-llm", "Skip LLM processing (require valid VideoInputSchema JSON)")
  .option("--llm-model <model>", "LLM model name")
  .option("--llm-base-url <url>", "LLM API base URL")
  .option("--llm-api-key <key>", "LLM API key")

  // TTS — general
  .option("--tts-provider <provider>", "TTS provider (openai-tts|fish-audio|minimax|elevenlabs)")
  .option("--voice <id>", "Voice ID")
  .option("--tts-model <model>", "TTS model name (provider-specific)")
  .option("--tts-speed <speed>", "TTS speech speed (0.5-2.0)", parseFloat)
  .option("--tts-format <format>", "TTS audio format (mp3|wav|pcm)")
  .option("--no-tts", "Skip TTS (generate silent video)")

  // Alignment
  .option("--alignment <mode>", "Timestamp alignment: whisper|native")
  .option("--whisper-model <model>", "Whisper model size (tiny/base/small/medium/large)", "base")
  .option("--alignment-language <lang>", "Language hint for whisper (e.g. zh, en)")

  .action(async (input, opts) => {
    const template = opts.template as string;
    if (!TEMPLATE_TYPES.includes(template as any)) {
      console.error(`Error: Invalid template "${template}". Use: ${TEMPLATE_TYPES.join(", ")}`);
      process.exit(1);
    }

    const platformStr = opts.platform as string;
    const platforms = platformStr.split(",").map((p: string) => p.trim());
    const invalidPlatforms = platforms.filter((p: string) => !PLATFORM_PRESET_KEYS.includes(p as any));
    if (invalidPlatforms.length > 0) {
      console.error(`Error: Invalid platform(s): ${invalidPlatforms.join(", ")}. Use: ${PLATFORM_PRESET_KEYS.join(", ")}`);
      process.exit(1);
    }

    const config = loadConfig(opts.config);

    // Collect data from source or read from file
    let text: string;
    let inputDir: string;

    if (opts.source) {
      const available = listCollectorNames();
      if (!available.includes(opts.source)) {
        console.error(`Error: Unknown source "${opts.source}". Available: ${available.join(", ")}`);
        process.exit(1);
      }
      const collectorConfig = config?.collect?.[opts.source];
      const collector = getCollector(opts.source, collectorConfig);
      const args: Record<string, string> = {};
      if (opts.sourceOwner) args.owner = opts.sourceOwner;
      if (opts.sourceRepo) args.repo = opts.sourceRepo;

      console.log(`Collecting from ${opts.source}...`);
      const result = await collector.collect(
        Object.keys(args).length > 0 ? { args } : undefined
      );
      text = result.type === "json" ? JSON.stringify(result.content) : result.content;
      inputDir = resolve(process.cwd());
    } else {
      if (!input) {
        console.error("Error: <input> file path is required when --source is not provided");
        process.exit(1);
      }
      const inputPath = resolve(input);
      if (!existsSync(inputPath)) {
        console.error(`Error: Input file not found: ${inputPath}`);
        process.exit(1);
      }
      text = readFileSync(inputPath, "utf-8");
      inputDir = opts.assetsDir ? resolve(opts.assetsDir) : dirname(inputPath);
    }

    const providerName = opts.ttsProvider || config?.tts?.provider || "openai-tts";
    const providerConfig = config?.tts?.[providerName];

    const cliDir = dirname(new URL(import.meta.url).pathname);
    const projectRoot = resolve(cliDir, "../../../../");
    const templatesEntry = resolve(projectRoot, "packages/templates/src/entry.ts");
    const assetsRoot = resolve(projectRoot, "assets");

    const noTts = skipTts(opts);
    const flags: string[] = [];
    if (noTts) flags.push("no-tts");

    const pipelineConfig: PipelineConfig = {
      llm: {
        baseURL: opts.llmBaseUrl || config?.llm?.baseURL,
        apiKey: opts.llmApiKey || config?.llm?.apiKey,
        model: opts.llmModel || config?.llm?.model || "gpt-4o",
      },
      tts: {
        provider: providerName,
        voiceId: opts.voice || providerConfig?.defaultVoice,
        model: opts.ttsModel || providerConfig?.model,
        format: opts.ttsFormat || config?.tts?.format || "mp3",
        speed: opts.ttsSpeed || config?.tts?.speed || 1.0,
      },
      output: {
        dir: resolve(opts.output || config?.output?.dir || "./output"),
      },
      assets: { root: assetsRoot, inputDir },
      templates: { entryPoint: templatesEntry },
      skipTts: noTts,
      skipLlm: opts.skipLlm,
      alignment: buildAlignmentConfig(opts, config),
    };

    const stages = ["parse", "tts", "assets", "compose", "render", "export"];

    console.log(`\nPipeline: generating ${template} video for ${platforms.join(", ")}`);
    console.log(`Input: ${text.length} chars${flags.length ? " | Flags: " + flags.join(", ") : ""}\n`);

    const job = await runPipeline(
      {
        text,
        template: template as any,
        platforms: platforms as any,
        ttsProvider: providerName as any,
        voiceId: pipelineConfig.tts.voiceId,
        outputPath: resolve(opts.output || "./output"),
      },
      pipelineConfig,
      {
        onStageStart: (stage) => {
          const [name, plat] = stage.split(":");
          const platformLabel = plat ? ` [${plat}]` : "";
          const labels: Record<string, string> = {
            parse: opts.skipLlm ? "Parsing JSON input" : "Parsing input (AI-assisted if needed)",
            tts: noTts ? "Generating silent audio" : `Generating narration${pipelineConfig.alignment?.provider === "whisper" ? " (whisper alignment)" : ""}`,
            assets: "Resolving assets",
            compose: "Composing scenes",
            render: "Rendering video",
            export: "Exporting",
          };
          const stepNum = stages.indexOf(name as string) + 1;
          console.log(`  [${stepNum}/6] ${labels[name] || name}${platformLabel}...`);
        },
        onStageComplete: (stage) => {
          const [name, plat] = stage.split(":");
          const platformLabel = plat ? ` [${plat}]` : "";
          const stepNum = stages.indexOf(name as string) + 1;
          console.log(`  [${stepNum}/6] ${name}${platformLabel} done`);
        },
        onError: (stage, error) => {
          console.error(`\n  Error in ${stage}: ${error.message}`);
          if (error.message.includes("API_KEY") || error.message.includes("apiKey")) {
            console.error("\n  Hint: Use --no-tts to skip TTS:");
            console.error("        pipeline render <file> -t <template> --no-tts\n");
          }
        },
      }
    );

    if (job.status === "completed" && job.exported) {
      console.log(`\nCompleted! Job ID: ${job.id}`);
      for (const file of job.exported.files) {
        console.log(`  -> ${file.filePath} (${(file.fileSizeBytes / 1024 / 1024).toFixed(1)}MB, ${file.width}x${file.height})`);
      }
    } else {
      console.error(`\nFailed: ${job.error}`);
      process.exit(1);
    }
  });

function buildAlignmentConfig(
  opts: any,
  config: Record<string, any> | null
): PipelineConfig["alignment"] {
  const mode = opts.alignment || config?.alignment?.provider;
  if (mode !== "whisper" && mode !== "native") return undefined;
  return {
    provider: mode,
    whisperModel: opts.whisperModel || config?.alignment?.whisperModel || "base",
    language: opts.alignmentLanguage || config?.alignment?.language,
  };
}

function loadConfig(configPath?: string): Record<string, any> | null {
  const cliDir = dirname(new URL(import.meta.url).pathname);
  const projectRoot = resolve(cliDir, "../../../../");

  const paths = [
    configPath,
    "pipeline.config.yaml",
    "pipeline.config.yml",
    resolve(projectRoot, "config/default.yaml"),
    "config/default.yaml",
  ].filter(Boolean) as string[];

  for (const p of paths) {
    const resolved = resolve(p);
    if (existsSync(resolved)) {
      const content = readFileSync(resolved, "utf-8");
      return parseYaml(content);
    }
  }
  return null;
}