"""Emergent stress test — random word triangulation against the substrate.

Pick three random words from /usr/share/dict/words, ask Hermes at
temp 0.8 to weave them into a creative question paragraph, send that
paragraph to arborist, log the whole journey (words → question →
answer → audit_mode → sources → timings) as a single JSONL line.

Designed for **blue moon cadence**, NOT every-commit benching. The
combinatoric word space surfaces failure modes the curated bench
(`bench/qa_questions.txt`) doesn't reach: question shapes the
authors didn't anticipate, vocabulary the corpus barely covers,
adversarial premises that emerge by accident.

The teacher review step is intentionally **not** automated here.
Fox brings interesting log entries to a teacher model (Claude
Opus 4.7 in the current setup) and asks for guidance:

  - did the answer match the question? (mismatch → bench-max signal)
  - novelty class: known_truth_grounding / emergent_synthesis /
    novel_claim / no_signal (accounting for the 2010-11 Wikipedia
    corpus legitimately lacking post-2010 advances in science /
    math / engineering)
  - which hyperparam to tune for the next iteration

Future: `--generator-endpoint` & `--student-endpoint` to swap
upstreams (different model per role), and a separate review-side
script that prompts a teacher model via API.

Usage:
    make bench-emergent                 # 10 cycles, default
    make bench-emergent N=50 SEED=42    # bigger sample, reproducible
    python scripts/bench_emergent.py --n 10 --seed 42
    python scripts/bench_emergent.py --print-pending   # show un-reviewed entries
"""

from __future__ import annotations

import argparse
import json
import os
import random
import re
import sys
import time
from pathlib import Path

# All paths default to the repo's bench/ tree so re-running across
# branches accumulates a continuous log of every emergent cycle.
DEFAULT_WORDS_PATH = Path("/usr/share/dict/words")
DEFAULT_LOG_PATH = Path("bench/emergent_log.jsonl")

# Word filter: skip too-short / proper-noun / abbreviation / weird
# punctuation. The goal is "common English content tokens" that
# Hermes can actually weave into a coherent paragraph.
_WORD_RE = re.compile(r"^[a-z]{5,12}$")


def pick_words(
    n: int = 3,
    *,
    words_path: Path = DEFAULT_WORDS_PATH,
    rng: random.Random | None = None,
) -> list[str]:
    """Sample N random words satisfying the content-token filter."""
    rng = rng or random.Random()
    pool = [
        w for w in words_path.read_text().splitlines()
        if _WORD_RE.fullmatch(w.strip().lower())
    ]
    if len(pool) < n:
        raise RuntimeError(
            f"word pool too small ({len(pool)} usable words at "
            f"{words_path}); expected ≥{n}"
        )
    return rng.sample(pool, n)


GENERATOR_PROMPT = """\
Write a single short paragraph (2-3 sentences) that uses ALL THREE \
of these words:

  - {w1}
  - {w2}
  - {w3}

Then phrase the paragraph as a question that explores the connections \
between them. The question should be the kind a curious reader would \
genuinely ask about how these three concepts relate.

Output ONLY the question paragraph. No prefix, no commentary, no \
quotes around it, no numbering. Just the question.\
"""


def generate_question(
    client,
    model_id: str,
    words: list[str],
    *,
    temperature: float = 0.8,
    max_tokens: int = 256,
) -> str:
    """Hermes at creative temperature weaves the 3 words into a question."""
    prompt = GENERATOR_PROMPT.format(w1=words[0], w2=words[1], w3=words[2])
    response = client.chat_completion(
        messages=[{"role": "user", "content": prompt}],
        model=model_id,
        temperature=temperature,
        max_tokens=max_tokens,
    )
    text = response.strip() if isinstance(response, str) else str(response).strip()
    # Strip wrapping quotes / leading "Question:" labels in case the
    # model ignored the no-prefix instruction.
    text = text.removeprefix("Question:").strip()
    if text.startswith('"') and text.endswith('"'):
        text = text[1:-1]
    return text


def run_one_cycle(
    *,
    words: list[str],
    client,
    model_id: str,
    qa_db: Path,
    shards_dir: Path,
    answer_mode: str,
    top_k: int,
) -> dict:
    """One emergent cycle: words → question → answer → log entry dict."""
    from arborist.qa.query import DEFAULT_QUERY_POLICY, query

    t_pick = time.time()
    question = generate_question(client, model_id, words)
    t_question = time.time()

    policy = dict(DEFAULT_QUERY_POLICY)
    policy["answer_mode"] = answer_mode

    try:
        result = query(
            question=question,
            qa_db=qa_db,
            chat_client=client,
            model_id=model_id,
            shards_dir=shards_dir,
            top_k=top_k,
            policy=policy,
            burn_existing=True,  # always fresh — this is an emergent test
        )
        student_error = None
    except Exception as e:
        result = {}
        student_error = f"{type(e).__name__}: {e}"

    t_answer = time.time()

    # Sidecar smell signal: metaphorical question framing the answer
    # ignored. Surfaced 2026-05-02 by the swallowtail/upbraided/rockiest
    # emergent log entry. Off-the-binary-chain — gives the teacher
    # reviewer a flag for poetic-question-vs-literal-answer mismatches.
    from arborist.qa.inspect import diagnose_metaphor_deflection
    metaphor = diagnose_metaphor_deflection(
        question or "", result.get("answer_text") or ""
    )

    return {
        "ts": int(t_pick),
        "iso_ts": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime(t_pick)),
        "words": words,
        "question": question,
        "question_gen_seconds": round(t_question - t_pick, 2),
        "answer": result.get("answer_text"),
        "audit_mode": result.get("audit_mode"),
        "verifier_method": result.get("verifier_method"),
        "n_quotes": result.get("n_quotes"),
        "n_verified": result.get("n_verified"),
        "violation_kinds": sorted(
            {v.get("kind") for v in (result.get("violations") or []) if v.get("kind")}
        ),
        "metaphor_deflection_kind": metaphor["kind"],
        "metaphor_cue_count": metaphor["cue_count"],
        "metaphor_overlap_count": metaphor["answer_overlap_count"],
        "sources": [
            {"title": s.get("title"), "uri": s.get("document_uri"), "used": s.get("used")}
            for s in (result.get("sources") or [])
        ],
        "cache_key": result.get("cache_key"),
        "answer_mode": answer_mode,
        "answer_seconds": round(t_answer - t_question, 2),
        "total_seconds": round(t_answer - t_pick, 2),
        "student_error": student_error,
        # Teacher review fields — left null on generation, populated
        # by a separate review pass (fox brings entries to Opus, gets
        # back an entry to append to the same log).
        "teacher": None,
    }


def append_log(entry: dict, log_path: Path) -> None:
    log_path.parent.mkdir(parents=True, exist_ok=True)
    with log_path.open("a") as f:
        f.write(json.dumps(entry, ensure_ascii=False) + "\n")


def emit_unfirehose_session(entry: dict, model_id: str) -> None:
    """Write one unfirehose/1.0 session for this bench cycle.

    Same auto-discovery path as `arborist.cli._emit_query_journal`:
    ~/.arborist/unfirehose/{slug}/{session_uuid}.jsonl. Each cycle gets
    its own session file (one prompt → one answer = one session).
    Failures must NEVER break the bench loop — wrapped at the call
    site.
    """
    from arborist.journal import SessionWriter
    arborist_meta = {
        "audit_mode": entry.get("audit_mode"),
        "verifier_method": entry.get("verifier_method"),
        "n_quotes": entry.get("n_quotes"),
        "n_verified": entry.get("n_verified"),
        "cache_key": entry.get("cache_key"),
        "violation_kinds": entry.get("violation_kinds"),
        "metaphor_deflection_kind": entry.get("metaphor_deflection_kind"),
        "answer_mode": entry.get("answer_mode"),
        "sources": entry.get("sources"),
        "timings": {
            "question_gen_seconds": entry.get("question_gen_seconds"),
            "answer_seconds": entry.get("answer_seconds"),
            "total_seconds": entry.get("total_seconds"),
        },
        "bench": "emergent",
        "words": entry.get("words"),
        "student_error": entry.get("student_error"),
    }
    with SessionWriter(first_prompt=entry.get("question") or "") as s:
        s.system_message(
            "bench-emergent cycle: 3-word triangulation",
            subtype="init",
            arborist_meta={"words": entry.get("words"), "harness_role": "generator"},
        )
        s.user_message(entry.get("question") or "")
        s.assistant_message(
            entry.get("answer") or "",
            model=model_id,
            provider="hermes",
            duration_ms=int((entry.get("answer_seconds") or 0) * 1000) or None,
            arborist_meta=arborist_meta,
        )


def print_pending(log_path: Path) -> int:
    """Print every log entry with `teacher: None` — what fox should
    bring to a teacher model for review."""
    if not log_path.exists():
        print(f"no log at {log_path}")
        return 0
    pending = 0
    for line in log_path.read_text().splitlines():
        if not line.strip():
            continue
        try:
            entry = json.loads(line)
        except json.JSONDecodeError:
            continue
        if entry.get("teacher") is None:
            pending += 1
            print(json.dumps(entry, indent=2))
            print()  # blank line between entries
    print(f"\n>> {pending} entry/entries awaiting teacher review", file=sys.stderr)
    return pending


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description=__doc__.strip().splitlines()[0])
    parser.add_argument("--n", type=int, default=10, help="cycles to run")
    parser.add_argument("--seed", type=int, default=None, help="RNG seed for reproducibility")
    parser.add_argument(
        "--words-path",
        type=Path,
        default=DEFAULT_WORDS_PATH,
        help="path to a unix-style words file",
    )
    parser.add_argument("--log-path", type=Path, default=DEFAULT_LOG_PATH)
    parser.add_argument(
        "--shards-dir",
        type=Path,
        default=Path.home() / ".arborist" / "shards",
    )
    parser.add_argument(
        "--qa-db",
        type=Path,
        default=Path.home() / ".arborist" / "shards" / "qa.db",
    )
    parser.add_argument("--answer-mode", default="claim_lattice")
    parser.add_argument("--top-k", type=int, default=8)
    parser.add_argument(
        "--endpoint",
        default=os.environ.get("ARBORIST_LLM_ENDPOINT", "https://hermes.ai.unturf.com/v1"),
    )
    parser.add_argument(
        "--model",
        default=os.environ.get(
            "ARBORIST_LLM_MODEL",
            "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic",
        ),
    )
    parser.add_argument(
        "--print-pending",
        action="store_true",
        help="print log entries with teacher==null & exit",
    )
    ns = parser.parse_args(argv)

    if ns.print_pending:
        return 0 if print_pending(ns.log_path) >= 0 else 1

    if not ns.words_path.exists():
        parser.error(f"words file not found: {ns.words_path}")
    if not ns.shards_dir.exists():
        parser.error(f"shards dir not found: {ns.shards_dir}")

    rng = random.Random(ns.seed)
    from arborist.qa.client import OpenAICompatibleClient

    api_key = os.environ.get("ARBORIST_LLM_API_KEY")
    client = OpenAICompatibleClient(base_url=ns.endpoint, api_key=api_key)

    print(f">> emergent bench: {ns.n} cycles · seed={ns.seed} · log={ns.log_path}", flush=True)
    for i in range(ns.n):
        words = pick_words(3, words_path=ns.words_path, rng=rng)
        print(f"[{i+1}/{ns.n}] words={words}", flush=True)
        entry = run_one_cycle(
            words=words,
            client=client,
            model_id=ns.model,
            qa_db=ns.qa_db,
            shards_dir=ns.shards_dir,
            answer_mode=ns.answer_mode,
            top_k=ns.top_k,
        )
        append_log(entry, ns.log_path)
        # Mirror to unfirehose-compatible journal so the bench cycles
        # show up in the unfirehose dashboard alongside Claude Code /
        # Fetch sessions. Best-effort — never break the bench on a
        # journal write failure.
        try:
            emit_unfirehose_session(entry, ns.model)
        except Exception:  # pragma: no cover
            pass
        # Compact stdout summary so a long sweep is observable.
        audit = entry.get("audit_mode") or "?"
        ratio = (
            f"{entry['n_verified']}/{entry['n_quotes']}"
            if entry.get("n_quotes") is not None else "?/?"
        )
        err = entry.get("student_error")
        if err:
            print(f"   → ERROR: {err}", flush=True)
        else:
            print(
                f"   → {audit}  {ratio}  {entry['total_seconds']}s  "
                f"q={entry['question'][:60]!r}",
                flush=True,
            )

    print(f"\n>> done. log: {ns.log_path}")
    print(
        f">> review: bring un-reviewed entries to Opus via\n"
        f"   python scripts/bench_emergent.py --print-pending"
    )
    return 0


if __name__ == "__main__":
    sys.exit(main())