"""Canonical version constants for SniperGold Data Engine v1.

Every constant in this module is binding for v1 (spec section 26). No
constant here may change without a DATASET/schema version bump governed by
the human decision gates (G-4/G-5). Producer and independent verifier share
ONLY this table (spec 18.1).
"""

# --- Engine / algorithm identity -------------------------------------------
ENGINE_VERSION = "1.1.0"          # any Engine behavior change (semver) -- amended P3-DE-004
PARSER_VERSION = "PARSER_V1.1"    # any CSV/timestamp/price parsing rule change -- amended P3-DE-004
ALGORITHM_VERSION = "ALG_V1"      # serialization / chunking / aggregation semantic change
DATASET_VERSION = "DS_V1.0.0"     # human decision gate only (G-5)

# --- Source-grammar registry (P3-DATA-ENGINE-004, spec 8.1 amendment) --------
# Two named, fully-specified, versioned grammar presets. Selection is NEVER
# silent or per-row: the configured grammar must equal the certificate's
# grammar_id at init, else the run is blocked (certificate/config mismatch).
GRAMMAR_TICKSTORY_MT5 = "tickstory_mt5"   # 6-col YYYYMMDD,HH:MM:SS,bid,ask,last,volume
GRAMMAR_DOTTED = "dotted_v1"              # YYYY.MM.DD HH:MM:SS[.mmm], 3/4 columns
GRAMMAR_ID_TICKSTORY = "tickstory_mt5_v1"
GRAMMAR_ID_DOTTED = "dotted_v1"
SUPPORTED_GRAMMARS = (GRAMMAR_TICKSTORY_MT5, GRAMMAR_DOTTED)

# --- Schema identities ------------------------------------------------------
SCHEMA_TICKS = "CTS_V1"
SCHEMA_BARS = "CBS_V1"
CERT_SCHEMA_VERSION = "CERT_V1"
MANIFEST_SCHEMA_VERSION = "MS_V1"
CHECKPOINT_SCHEMA_VERSION = "CP_V1"
RUN_COMPLETE_SCHEMA_VERSION = "RC_V1"

# --- Scale constants (frozen) ------------------------------------------------
PRICE_SCALE = 1_000_000          # micro-USD per USD unit (CTS_V1)
PRICE_SCALE_BAR = 2_000_000      # 2 x PRICE_SCALE (mid-based OHLC, CBS_V1)

# --- Chunking / workload (frozen; G-7, G-8) ----------------------------------
CHUNK_BYTES_NOMINAL = 25_165_824      # 24 MiB
WORKLOAD_BYTES_NOMINAL = 536_870_912  # 512 MiB

# --- Timeframes (frozen; spec 11.1) -------------------------------------------
# Only M1, M5, M15, M30, H1 are permitted in v1.
TIMEFRAMES = {
    "M1": 60_000,
    "M5": 300_000,
    "M15": 900_000,
    "M30": 1_800_000,
    "H1": 3_600_000,
}
DEFAULT_TIMEFRAMES = ["M1", "M5", "M15", "M30", "H1"]

# --- Lock policy (G-11) --------------------------------------------------------
LOCK_HEARTBEAT_SEC = 60
LOCK_STALE_SEC = 300

# --- Malformed policy (spec 8.3, F02) ------------------------------------------
MALFORMED_RATE_LIMIT = 0.001
MALFORMED_ABS_CAP = 10_000
DUPLICATE_TRACKER_CAP = 4_000_000   # bounded in-memory duplicate set per chunk

# --- Timestamp validity window (spec 8.1) -------------------------------------
TS_MIN_EPOCH_MS = 946684800000  # 2000-01-01T00:00:00Z in epoch ms
TS_RANGE_FUTURE_DAYS = 7

# --- Worker policy (G-2) --------------------------------------------------------
WORKERS_REQUESTED_DEFAULT = 24

# --- Determinism pins (spec 26) -------------------------------------------------
PYTHONHASHSEED_PIN = "0"
PYARROW_VERSION_PIN = "25.0.0"     # must match the installed pyarrow
PYTHON_MIN_VERSION = (3, 11)


def tf_period_ms(timeframe):
    """Return the period in ms for a v1 timeframe symbol."""
    try:
        return TIMEFRAMES[timeframe]
    except KeyError:
        raise ValueError("unsupported timeframe %r (v1 allows %s)"
                         % (timeframe, sorted(TIMEFRAMES)))