// Audio-first ("walking mode") TTS routes. Turns a saved recap's per-topic
// summaries into spoken MP3 clips (via the relay's /relay/tts → Kokoro),
// caches them next to the session JSON, and serves them to the player.
//
// Endpoints (all scope-isolated to the requesting user's library):
//   GET  /api/tts/availability         — { has_tts, allowed, default_voice }
//   POST /api/tts/generate/:id/:index  — synthesize + cache ONE topic clip
//                                        (idempotent, retried, deduped by job
//                                        id). The player calls this on demand
//                                        as it reaches each topic + prefetches
//                                        the next, so clips are generated when
//                                        needed and retried until they succeed
//                                        rather than skipped.
//   GET  /api/tts/status/:id           — { total, ready:[idx...], done }
//   GET  /api/tts/audio/:id/:index     — serve a cached topic clip (mp3)
//
// Access policy (the "Max gate"):
//   - single mode: the operator owns the box AND the TTS hardware, so no
//     tier gate — TTS is available whenever the relay advertises has_tts.
//   - multi mode admin: the operator; allowed.
//   - multi-tenant cloud users: any paid subscription (Pro or Max). The
//     operator can tighten this to Max-only here if shared TTS hardware
//     throughput becomes a constraint.
//
// Billing: all of a recap's topics share ONE relay job id (`tts:<id>`), so
// the relay charges at most 1 credit to voice an entire recap.

import fs from "fs/promises";
import path from "path";

import {
  scopeForRequest,
  sessionAudioDir,
  loadSession,
  patchSession,
} from "./history.js";
import { getProvider, resolveProviderOpts } from "./providers/index.js";
import { getRelayCapabilities } from "./relay-capabilities.js";

const CLIP_FORMAT = "mp3";
const CLIP_EXT = "mp3";

// Whether THIS request's user may generate TTS. See the policy note above.
export function userHasTtsAccess(req) {
  // Single mode (or no request context): operator owns the hardware.
  if (!req || req.recapMode !== "multi") return true;
  // Multi-mode admin = the operator.
  if (req.user && req.user.is_admin) return true;
  // Multi-tenant cloud user: Pro or Max. Core-decoupling — the tier is the
  // relay-owned subscription tier, cached on the Recaps account
  // (req.user.tier), kept in sync by the operator grant flow.
  const tier = req.user?.tier;
  return tier === "pro" || tier === "max";
}

// The text we speak for a topic: its title as a lead-in, then the summary,
// so an eyes-free listener hears what the topic is before its recap.
export function chunkSpeechText(chunk) {
  const title = (chunk?.title || "").trim();
  const summary = (chunk?.summary || "").trim();
  if (title && summary) return `${title}. ${summary}`;
  return summary || title || "";
}

function clipFileName(index) {
  return `topic-${index}.${CLIP_EXT}`;
}

// Server-side retries per clip on a transient (5xx/network) relay failure,
// on top of any retry the relay itself does.
const GEN_RETRIES = 2;

// Generate + cache ONE topic clip. Idempotent: returns {cached:true} if the
// file already exists. Retries transient failures; a 4xx (e.g. bad voice) or
// empty summary is permanent (no retry). Returns
// { ok, cached?, empty?, error?, voice? }.
async function generateClip({ scope, id, index, chunk, provider, jobId, voice }) {
  const dir = sessionAudioDir(scope, id);
  const file = path.join(dir, clipFileName(index));
  try {
    await fs.access(file);
    return { ok: true, cached: true };
  } catch {}
  const text = chunkSpeechText(chunk);
  if (!text) return { ok: false, empty: true, error: "empty_summary" };
  await fs.mkdir(dir, { recursive: true }).catch(() => {});
  let lastErr = null;
  for (let attempt = 1; attempt <= GEN_RETRIES + 1; attempt++) {
    try {
      const r = await provider.tts({ text, voice, format: CLIP_FORMAT, jobId });
      await fs.writeFile(file, r.audio);
      return { ok: true, voice: r.voice, backend: r.backend };
    } catch (err) {
      lastErr = err;
      const status = err?.status || 0;
      console.warn(
        `[tts] clip ${index} attempt ${attempt}/${GEN_RETRIES + 1} failed (${status || "net"}): ${err?.message || err}`,
      );
      if (status >= 400 && status < 500) break; // client error → permanent
      if (attempt <= GEN_RETRIES) await new Promise((r2) => setTimeout(r2, 600));
    }
  }
  return { ok: false, error: (lastErr?.message || "tts_failed").slice(0, 200) };
}

function resolveScope(req, res) {
  try {
    return scopeForRequest(req);
  } catch {
    res.status(401).json({ error: "no_scope" });
    return null;
  }
}

export function setupTtsRoutes(app) {
  // Lightweight probe for the frontend: should it show the "Listen"
  // affordance, and what's the default voice?
  app.get("/api/tts/availability", (req, res) => {
    const caps = getRelayCapabilities();
    res.json({
      has_tts: !!caps.has_tts,
      tts_backend: caps.tts_backend || null,
      default_voice: caps.tts_default_voice || null,
      allowed: userHasTtsAccess(req) && !!caps.has_tts,
    });
  });

  // Generate (or return cached) the audio for ONE topic. The player calls
  // this on demand as it reaches each topic — and prefetches the next — so a
  // clip is generated when needed and RETRIED until it succeeds, rather than
  // skipped. Idempotent + deduped by the shared job id (≤1 credit/recap).
  //
  // Responses:
  //   200 { ok:true, index, cached }   — clip is ready to play
  //   200 { ok:false, empty:true }     — topic has no summary text (permanent;
  //                                      client should not retry)
  //   502 { ok:false, error }          — transient failure; client retries
  app.post("/api/tts/generate/:id/:index", async (req, res) => {
    const scope = resolveScope(req, res);
    if (!scope) return;
    if (!userHasTtsAccess(req)) {
      return res.status(403).json({
        error: "tts_requires_subscription",
        message: "Audio recaps are available to Pro and Max subscribers.",
      });
    }
    const caps = getRelayCapabilities();
    if (!caps.has_tts) {
      return res.status(503).json({
        error: "tts_unavailable",
        message: "Text-to-speech isn't available on this relay right now.",
      });
    }
    const id = req.params.id;
    const index = parseInt(req.params.index, 10);
    const session = await loadSession(scope, id);
    if (!session) return res.status(404).json({ error: "session_not_found" });
    const chunks = Array.isArray(session.chunks) ? session.chunks : [];
    if (!Number.isInteger(index) || index < 0 || index >= chunks.length) {
      return res.status(400).json({ error: "bad_index" });
    }
    let provider;
    try {
      provider = getProvider("relay", resolveProviderOpts("relay", { req }));
    } catch (err) {
      return res.status(503).json({
        error: "relay_unavailable",
        message: err?.message || "Relay is not configured.",
      });
    }
    const voice =
      typeof req.query.voice === "string" && req.query.voice.trim()
        ? req.query.voice.trim()
        : undefined;
    const result = await generateClip({
      scope,
      id,
      index,
      chunk: chunks[index],
      provider,
      jobId: `tts:${id}`, // one credit for the whole recap
      voice,
    });
    if (result.ok) {
      patchSession(scope, id, {
        summaryAudio: {
          ready: true,
          total: chunks.length,
          voice: result.voice || caps.tts_default_voice || null,
          format: CLIP_FORMAT,
          updatedAt: new Date().toISOString(),
        },
      }).catch(() => {});
      return res.json({ ok: true, index, cached: !!result.cached, voice: result.voice || null });
    }
    if (result.empty) {
      return res.json({ ok: false, index, empty: true, error: "empty_summary" });
    }
    return res.status(502).json({ ok: false, index, error: result.error || "tts_failed" });
  });

  // Which topics are already synthesized for a recap.
  app.get("/api/tts/status/:id", async (req, res) => {
    const scope = resolveScope(req, res);
    if (!scope) return;
    const session = await loadSession(scope, req.params.id);
    if (!session) return res.status(404).json({ error: "session_not_found" });
    const total = Array.isArray(session.chunks) ? session.chunks.length : 0;
    const dir = sessionAudioDir(scope, req.params.id);
    let files = [];
    try {
      files = await fs.readdir(dir);
    } catch {}
    const ready = files
      .map((f) => {
        const m = new RegExp(`^topic-(\\d+)\\.${CLIP_EXT}$`).exec(f);
        return m ? Number(m[1]) : null;
      })
      .filter((n) => n !== null)
      .sort((a, b) => a - b);
    const caps = getRelayCapabilities();
    res.json({
      total,
      ready,
      done: total > 0 && ready.length >= total,
      allowed: userHasTtsAccess(req) && !!caps.has_tts,
      voice: session.summaryAudio?.voice || caps.tts_default_voice || null,
    });
  });

  // Serve one cached topic clip. sendFile handles Range requests (so the
  // <audio> element can seek) and 404s cleanly when the clip isn't ready.
  app.get("/api/tts/audio/:id/:index", async (req, res) => {
    const scope = resolveScope(req, res);
    if (!scope) return;
    const idx = parseInt(req.params.index, 10);
    if (!Number.isInteger(idx) || idx < 0) {
      return res.status(400).json({ error: "bad_index" });
    }
    const file = path.join(sessionAudioDir(scope, req.params.id), clipFileName(idx));
    res.sendFile(
      file,
      {
        headers: {
          "Content-Type": "audio/mpeg",
          // Content is immutable for a given (session, topic) — safe to
          // cache hard, which also primes the Phase 4 offline service worker.
          "Cache-Control": "private, max-age=31536000, immutable",
        },
      },
      (err) => {
        if (err && !res.headersSent) {
          res.status(404).json({ error: "clip_not_ready" });
        }
      }
    );
  });
}