// Per-channel context notes and the `contextHash` every generated section
// records.
//
// This is the MINIMUM of PLAN.md's Phase 1.5, deliberately: the full
// channel-context feature (structured frontmatter, per-channel entity lists) is
// not built here, but the KEY is plumbed now. PLAN.md's "do not backfill before
// 1.5" trap is exactly this — a digest generated without a contextHash cannot
// tell whether it predates a channel's context note, so adding notes later would
// invalidate the whole corpus. Hashing the (currently usually empty) note from
// day one means adding a note later invalidates only that channel.
//
// The note is a plain Markdown file in the channel dir, hand-authored. Stage B's
// compounding step is writing a correction here — "the co-host is Sam, not Sand"
// — rather than patching individual videos, because a note improves every future
// generation for that channel.

import path from "node:path";
import { readFile } from "node:fs/promises";
import { createHash } from "node:crypto";
import type { Paths } from "./paths";

export const DIGEST_CONTEXT_FILENAME = "digest-context.md";

// Cap what reaches the prompt: a note is guidance, not a second transcript, and
// an unbounded one would eat the context window the transcript needs.
const MAX_CONTEXT_CHARS = 4000;

export type DigestContext = {
  // The note text to embed in the prompt. "" when the channel has none.
  note: string;
  // Stable hash of every context input. Recorded in each section's provenance and
  // compared on re-run. The empty-note hash is a real, stable value — NOT "" —
  // so "no note" and "note removed" are the same state and neither is confused
  // with "generated before contextHash existed" (which reads as "" and is stale).
  hash: string;
};

export function digestContextPath(paths: Paths, channelSlug: string): string {
  return path.join(paths.channelsDir, channelSlug, DIGEST_CONTEXT_FILENAME);
}

// Hash the context inputs. Versioned by a literal prefix so the hashing scheme
// itself can change later without colliding with old values.
//
// DECIDED 2026-07-29, BEFORE THE BACKFILL SWEEP: this stays at **v1**.
//
// The decision had to be made explicitly and in advance, because the prefix is
// folded into every section's `contextHash` and bumping it after the sweep would
// invalidate all ~77k videos — GPU-weeks thrown away by a one-character edit.
//
// v1 is correct because the EMPTY note already hashes stably. Adding a per-channel
// context note later (Phase 1.5) changes `note`, not the scheme, so it invalidates
// only the channels that get a note — which is the desired behaviour, not a
// problem to be versioned around. **Only a change to the hashing SCHEME itself
// needs v2** (a different algorithm, or folding in a second input).
export function hashDigestContext(note: string): string {
  return createHash("sha1")
    .update(`digest-context-v1\n${note}`)
    .digest("hex")
    .slice(0, 16);
}

export async function readDigestContext(
  paths: Paths,
  channelSlug: string,
): Promise<DigestContext> {
  let note = "";
  try {
    const raw = await readFile(digestContextPath(paths, channelSlug), "utf8");
    note = raw.trim().slice(0, MAX_CONTEXT_CHARS);
  } catch {
    note = "";
  }
  return { note, hash: hashDigestContext(note) };
}