"""Paths and shared constants for search evaluation."""

from pathlib import Path

_PKG_DIR = Path(__file__).resolve().parent
_SCRIPTS_EVAL_DIR = _PKG_DIR.parent
PROJECT_ROOT = _SCRIPTS_EVAL_DIR.parents[1]

# Canonical English labels (must match LLM prompt output in prompts._CLASSIFY_TEMPLATE_EN)
RELEVANCE_EXACT = "Exact Match"
RELEVANCE_HIGH = "High Relevant"
RELEVANCE_LOW = "Low Relevant"
RELEVANCE_IRRELEVANT = "Irrelevant"

VALID_LABELS = frozenset({RELEVANCE_EXACT, RELEVANCE_HIGH, RELEVANCE_LOW, RELEVANCE_IRRELEVANT})

# Precision / MAP "positive" set (all non-irrelevant tiers)
RELEVANCE_NON_IRRELEVANT = frozenset({RELEVANCE_EXACT, RELEVANCE_HIGH, RELEVANCE_LOW})

_LEGACY_LABEL_MAP = {
    "Exact": RELEVANCE_EXACT,
    "Partial": RELEVANCE_HIGH,
}


def normalize_stored_label(label: str) -> str:
    """Map legacy 3-way SQLite labels to current 4-way strings; pass through canonical labels."""
    s = str(label).strip()
    if s in VALID_LABELS:
        return s
    return _LEGACY_LABEL_MAP.get(s, s)


DEFAULT_ARTIFACT_ROOT = PROJECT_ROOT / "artifacts" / "search_evaluation"
DEFAULT_QUERY_FILE = _SCRIPTS_EVAL_DIR / "queries" / "queries.txt"

# Judge LLM (eval_framework only; override via CLI --judge-model / constructor kwargs)
DEFAULT_JUDGE_MODEL = "qwen3.5-flash"
DEFAULT_JUDGE_ENABLE_THINKING = True
DEFAULT_JUDGE_DASHSCOPE_BATCH = False
DEFAULT_JUDGE_BATCH_COMPLETION_WINDOW = "24h"
DEFAULT_JUDGE_BATCH_POLL_INTERVAL_SEC = 10.0

# --- Rebuild annotation pool (``build --force-refresh-labels``) ---
# Flow: search recall pool (rerank_score=1, no rerank API) + rerank rest of corpus +
# LLM labels in fixed-size batches along global order (see ``framework._annotate_rebuild_batches``).
DEFAULT_SEARCH_RECALL_TOP_K = 200
DEFAULT_RERANK_HIGH_THRESHOLD = 0.5
DEFAULT_RERANK_HIGH_SKIP_COUNT = 1000
DEFAULT_REBUILD_LLM_BATCH_SIZE = 50
# At least this many LLM batches run before early-stop is considered.
DEFAULT_REBUILD_MIN_LLM_BATCHES = 10
# Hard cap on LLM batches per query (each batch labels up to ``DEFAULT_REBUILD_LLM_BATCH_SIZE`` docs).
DEFAULT_REBUILD_MAX_LLM_BATCHES = 40

# LLM early-stop (only after ``DEFAULT_REBUILD_MIN_LLM_BATCHES`` completed):
# A batch is "bad" when it has **no** ``Exact Match`` label AND either:
#   - irrelevant_ratio >= DEFAULT_REBUILD_IRRELEVANT_STOP_RATIO, or
#   - (Irrelevant + Low Relevant) / n >= DEFAULT_REBUILD_IRREL_LOW_COMBINED_STOP_RATIO.
# ``irrelevant_ratio`` = Irrelevant count / n; weak relevance is ``RELEVANCE_LOW`` ("Low Relevant").
# If a batch is bad, increment a streak; otherwise reset streak to 0. Stop when streak reaches
# ``DEFAULT_REBUILD_IRRELEVANT_STOP_STREAK`` (consecutive bad batches).
DEFAULT_REBUILD_IRRELEVANT_STOP_RATIO = 0.94
DEFAULT_REBUILD_IRREL_LOW_COMBINED_STOP_RATIO = 0.96
DEFAULT_REBUILD_IRRELEVANT_STOP_STREAK = 2