import * as z from "zod";
import { Id } from "./ids.js";

/**
 * Cut-point finding for talking-head and social video: the `remove_silence` step of
 * `edit_video` and the read-only `analyze_video` operation, which reports where cuts fit.
 */

/** Defaults of `remove_silence`; `analyze_video` reports silences with the same ones. */
export const SILENCE_DEFAULTS = {
  /** Quieter than this (dBFS) counts as silence: below speech, above a typical noise floor. */
  thresholdDb: -35,
  /** Shorter pauses are the rhythm of speech and stay. */
  minSilence: 0.6,
  /** Kept on both sides of what is cut, so breaths and word onsets are not clipped. */
  padding: 0.12,
} as const;

/** Cuts every pause and keeps sound and picture in sync, like a keep step over the speech. */
export const RemoveSilenceStepSchema = z.object({
  op: z.literal("remove_silence"),
  threshold_db: z.number().min(-60).max(-10).default(SILENCE_DEFAULTS.thresholdDb),
  min_silence: z.number().min(0.2).max(5).default(SILENCE_DEFAULTS.minSilence),
  padding: z.number().min(0).max(1).default(SILENCE_DEFAULTS.padding),
});
export type RemoveSilenceStep = z.infer<typeof RemoveSilenceStepSchema>;

export const AnalyzeVideoInputSchema = z.object({
  artifact_id: Id,
  scenes: z.boolean().default(true),
  silences: z.boolean().default(true),
  loudness: z.boolean().default(true),
  /** Written by the bot in the user's language; shown on the media card. */
  title: z.string().trim().min(1).max(120),
});
export type AnalyzeVideoInput = z.infer<typeof AnalyzeVideoInputSchema>;