"""What a reply cost, how fast it arrived, and how full the window is.

One shape, built either from a generation still being written or from the row
it left behind. That matters more than it looks: the finished bubble is
re-rendered from the database the instant the stream ends, so if the live
numbers and the stored ones came from different code they would visibly jump at
exactly the moment the reader is looking at them. Here the only thing that
changes when a reply finishes is that an estimate may become exact.

Nothing here is authoritative about tokens. `estimated` says which kind of
number this is, and every surface that shows one has to say so too.
"""

from __future__ import annotations

from dataclasses import dataclass
from typing import Any

from lembas.services import tokens

# Where the context bar changes colour. Not thresholds anyone tunes: they mark
# "worth noticing" and "about to be a problem", and the second is deliberately
# below the default compaction threshold so the warning arrives first.
WARNING_AT = 80
DANGER_AT = 95


@dataclass(frozen=True)
class Metrics:
    """Token counts and timing for one reply."""

    prompt_tokens: int = 0
    completion_tokens: int = 0
    total_tokens: int = 0
    # What the window holds after this turn: the last round's prompt plus its
    # completion. Distinct from prompt+completion summed over tool rounds, which
    # is what the reply *cost* -- a three-round reply pays for its prompt three
    # times but only ever occupies the window once.
    context_tokens: int = 0
    context_limit: int = 0
    estimated: bool = False
    elapsed_ms: int = 0
    rounds: int = 1

    @property
    def percent(self) -> int:
        """How full the window is, or 0 when nobody has said how big it is."""
        if self.context_limit <= 0 or self.context_tokens <= 0:
            return 0
        return min(100, round(self.context_tokens * 100 / self.context_limit))

    @property
    def tokens_per_second(self) -> float:
        if self.elapsed_ms <= 0 or self.completion_tokens <= 0:
            return 0.0
        return self.completion_tokens / (self.elapsed_ms / 1000)

    @property
    def pressure(self) -> str:
        """"", "warning" or "danger" -- the class the context chip takes."""
        percent = self.percent
        if not percent:
            return ""
        if percent >= DANGER_AT:
            return "danger"
        if percent >= WARNING_AT:
            return "warning"
        return ""

    @property
    def has_anything(self) -> bool:
        return bool(self.total_tokens or self.completion_tokens or self.elapsed_ms)


def from_generation(generation: Any) -> Metrics:
    """Metrics for a reply still being written.

    Usage arrives in a single chunk at the very end, so mid-stream there is
    nothing to report and everything is estimated. The counts stop being
    estimates the moment that chunk lands, which is usually a beat before the
    bubble is replaced.
    """
    import time

    completion = generation.completion_tokens or tokens.estimate(
        generation.text + generation.thinking
    )
    prompt = generation.prompt_tokens or generation.prompt_estimate
    elapsed = generation.elapsed_ms or (
        int((time.monotonic() - generation.started_at) * 1000) if generation.started_at else 0
    )

    return Metrics(
        prompt_tokens=prompt,
        completion_tokens=completion,
        total_tokens=prompt + completion,
        context_tokens=generation.context_tokens or (prompt + completion),
        context_limit=generation.context_limit,
        estimated=not (generation.prompt_tokens and generation.completion_tokens),
        elapsed_ms=elapsed,
        rounds=max(1, generation.rounds),
    )


def from_message(usage_json: dict[str, Any] | None) -> Metrics:
    """Metrics for a finished reply, read back off the row."""
    stored = usage_json or {}

    def _int(key: str) -> int:
        value = stored.get(key)
        return int(value) if isinstance(value, (int, float)) and not isinstance(value, bool) else 0

    return Metrics(
        prompt_tokens=_int("prompt_tokens"),
        completion_tokens=_int("completion_tokens"),
        total_tokens=_int("total_tokens"),
        context_tokens=_int("context_tokens"),
        context_limit=_int("context_limit"),
        estimated=bool(stored.get("estimated")),
        elapsed_ms=_int("elapsed_ms"),
        rounds=max(1, _int("rounds")),
    )


def to_json(metrics: Metrics) -> dict[str, Any]:
    """The shape stored in Message.usage_json."""
    return {
        "prompt_tokens": metrics.prompt_tokens,
        "completion_tokens": metrics.completion_tokens,
        "total_tokens": metrics.total_tokens,
        "context_tokens": metrics.context_tokens,
        "context_limit": metrics.context_limit,
        "estimated": metrics.estimated,
        "elapsed_ms": metrics.elapsed_ms,
        "rounds": metrics.rounds,
    }