"""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): search recall + full-corpus rerank + LLM batches
DEFAULT_SEARCH_RECALL_TOP_K = 500
DEFAULT_RERANK_HIGH_THRESHOLD = 0.5
DEFAULT_RERANK_HIGH_SKIP_COUNT = 1000
DEFAULT_REBUILD_LLM_BATCH_SIZE = 50
DEFAULT_REBUILD_MIN_LLM_BATCHES = 20
DEFAULT_REBUILD_MAX_LLM_BATCHES = 40
DEFAULT_REBUILD_IRRELEVANT_STOP_RATIO = 0.92
DEFAULT_REBUILD_IRRELEVANT_STOP_STREAK = 3