import { test } from "node:test";
import assert from "node:assert/strict";
import {
  DIGEST_MAX_CUES_PER_CHUNK,
  PROMPT_VERSION,
  buildChapterPrompt,
  buildTagPrompt,
  maxCuesForContext,
  promptOffsetSeconds,
} from "./digestPrompt";
import {
  DEFAULT_DIGEST_MAX_CUES_PER_CHUNK,
  DEFAULT_DIGEST_NUM_CTX,
  DEFAULT_DIGEST_TIMESTAMP_MODE,
} from "./digest";

// The chunk size MUST track the configured context. Lowering num_ctx without
// lowering it feeds ollama more transcript than its window holds, and ollama
// truncates SILENTLY — the model then summarizes a fragment and the result reads
// as a bad model rather than as a misconfiguration.

test("the two copies of the default chunk size agree", () => {
  // digestPrompt.ts re-exports digest.ts's constant; this pins them equal so the
  // identity helper (which compares against digest.ts's copy) and the chunker
  // (which uses this one) can never drift apart.
  assert.equal(DIGEST_MAX_CUES_PER_CHUNK, DEFAULT_DIGEST_MAX_CUES_PER_CHUNK);
});

test("maxCuesForContext scales the slice with the window", () => {
  // Ratio-pinned to the 8192 -> 600 default pair.
  assert.equal(maxCuesForContext(8192), 600);
  assert.equal(maxCuesForContext(16384), 1200);
  assert.equal(maxCuesForContext(32768), 2400);
  assert.equal(maxCuesForContext(4096), 300);
  // Unset or nonsense falls back to the default window, never to zero cues.
  assert.equal(maxCuesForContext(undefined), DEFAULT_DIGEST_MAX_CUES_PER_CHUNK);
  assert.equal(maxCuesForContext(0), DEFAULT_DIGEST_MAX_CUES_PER_CHUNK);
  // Floored, so a tiny window still yields a usable slice rather than one cue.
  assert.equal(maxCuesForContext(256), 100);
});

test("the shipped defaults are the configuration the bake-off measured best", () => {
  // Round 2 (plans/bakeoff/round2.md) scored qwen2.5:7b@8192/chunk-local best on
  // zero-yield rate, chapters/hour and worst coverage gap. The decision was made
  // and then not shipped for a while — the defaults stayed at the losing
  // 16384/absolute pair — so this pins the two constants that carry it.
  assert.equal(DEFAULT_DIGEST_NUM_CTX, 8192);
  assert.equal(DEFAULT_DIGEST_MAX_CUES_PER_CHUNK, 600);
  assert.equal(DEFAULT_DIGEST_TIMESTAMP_MODE, "chunk-local");
});

test("PROMPT_VERSION was bumped with the defaults change", () => {
  // The pairing is the whole point. digestPromptVariant derives its string
  // RELATIVE to the defaults, so a record written under the old defaults carries
  // promptVariant: undefined and would compare EQUAL under the new ones —
  // freezing bake-off-losing output into the corpus as permanently "fresh".
  // isSectionFresh compares promptVersion, so the bump is what invalidates them.
  assert.ok(
    PROMPT_VERSION >= 2,
    "changing DEFAULT_DIGEST_* without bumping PROMPT_VERSION silently skips every existing digest as fresh",
  );
});

test("chunk-local re-bases the range the chapter prompt states", () => {
  const base = {
    title: "T",
    channel: "C",
    startSeconds: 5503, // 01:31:43 — the measured third chunk
    endSeconds: 8169, // 02:16:09
    transcript: "[00:00:00] hello",
  };
  const absolute = buildChapterPrompt(base);
  assert.match(absolute, /This section covers 01:31:43 to 02:16:09/);
  assert.match(absolute, /between 01:31:43 and 02:16:09 inclusive/);

  const local = buildChapterPrompt({ ...base, timestampMode: "chunk-local" });
  assert.match(local, /This section covers 00:00:00 to 00:44:26/);
  assert.match(local, /between 00:00:00 and 00:44:26 inclusive/);

  // The SPAN is unchanged, so the density target and the schema's minItems floor
  // are identical in both modes — only the numbering moves.
  assert.match(absolute, /44 minutes of material/);
  assert.match(local, /44 minutes of material/);
});

test("the tag prompt is re-based the same way", () => {
  // It sees the same rendered transcript, so a range stated in the other
  // numbering would contradict the markers in front of it.
  const base = {
    title: "T",
    channel: "C",
    startSeconds: 5503,
    endSeconds: 8169,
    transcript: "[00:00:00] hello",
  };
  assert.match(buildTagPrompt(base), /covering 01:31:43 to 02:16:09/);
  assert.match(
    buildTagPrompt({ ...base, timestampMode: "chunk-local" }),
    /covering 00:00:00 to 00:44:26/,
  );
});

test("absolute mode renders byte-identically to the pre-timestampMode prompt", () => {
  // The compatibility guarantee that let PROMPT_VERSION stay at 1: adding the
  // mode must not change what the default configuration sends, or every digest
  // on disk would have been invalidated.
  const base = {
    title: "T",
    channel: "C",
    startSeconds: 100,
    endSeconds: 700,
    transcript: "[00:01:40] hello",
  };
  assert.equal(
    buildChapterPrompt(base),
    buildChapterPrompt({ ...base, timestampMode: "absolute" }),
  );
});

test("a prompt with no speakerRoster renders byte-identically to today", () => {
  // THE SAME COMPATIBILITY ARGUMENT AS absolute-mode ABOVE, and the reason
  // adding the roster field needed no PROMPT_VERSION bump: the shipped lane
  // never sets it, so every digest the sweep produces is byte-for-byte what it
  // produced before the field existed. It is also what makes the bake-off's
  // speakers-OFF arm a real control rather than a third variant.
  const base = {
    title: "T",
    channel: "C",
    startSeconds: 100,
    endSeconds: 700,
    transcript: "[00:01:40] hello",
  };
  const shipped = buildChapterPrompt(base);
  assert.equal(buildChapterPrompt({ ...base, speakerRoster: undefined }), shipped);
  // Whitespace-only is treated as absent, so a caller that builds an empty
  // roster string cannot accidentally change the prompt.
  assert.equal(buildChapterPrompt({ ...base, speakerRoster: "   \n" }), shipped);
  assert.equal(buildChapterPrompt({ ...base, speakerRoster: "" }), shipped);
});

test("a speakerRoster is stated separately from the channel context note", () => {
  const base = {
    title: "T",
    channel: "C",
    startSeconds: 100,
    endSeconds: 700,
    transcript: "[00:01:40] hello",
    contextNote: "The host is Alice.",
    speakerRoster: "Speakers in this section:\n- Alice\n- Bob",
  };
  const prompt = buildChapterPrompt(base);
  // Both present, and the roster is NOT filed under "context for this channel"
  // — it is per-chunk and derived, not hand-authored per channel.
  assert.match(prompt, /Context for this channel[^\n]*\nThe host is Alice\./);
  assert.match(prompt, /Speakers in this section:\n- Alice\n- Bob/);
  // The guard against titling chapters after whoever is speaking.
  assert.match(prompt, /A title still names the SUBJECT under discussion/);
  // The transcript still comes last, so the body is what the model ends on.
  assert.ok(prompt.indexOf("Speakers in this section") < prompt.indexOf("Transcript section:"));
});

test("promptOffsetSeconds is zero in absolute mode by construction", () => {
  assert.equal(promptOffsetSeconds({ startSeconds: 5503 }), 0);
  assert.equal(
    promptOffsetSeconds({ startSeconds: 5503, timestampMode: "absolute" }),
    0,
  );
  assert.equal(
    promptOffsetSeconds({ startSeconds: 5503, timestampMode: "chunk-local" }),
    5503,
  );
});