FabledSteward/steward/mcp/tools/_shape.py

"""Response shaping every tool shares: the conventions INSTRUCTIONS promise.

- Times are ISO-8601 UTC with a `Z`, and anything with a "when" also carries
  `age_s` so the agent never does clock arithmetic.
- Every list is bounded: a tool returns `total`, `truncated`, and when cut, a
  `more` line naming the argument that fetches the rest. Nothing is cut
  silently.
- A time series comes back as a summary plus a downsampled series, never raw
  rows.
- An entity is looked up by id or by name, and a miss raises ValueError naming
  the tool that lists the valid choices (the server turns it into a readable
  ToolError).
"""
from __future__ import annotations

import difflib
import math
from datetime import datetime, timezone
from typing import Callable, Iterable, TypeVar
from urllib.parse import urlsplit, urlunsplit

from steward.core.time_range import RANGES
from steward.mcp._context import mcp_app

T = TypeVar("T")

SERIES_POINTS = 60  # max points in any returned series
# The longest log line a tool returns whole (container logs, syslog).
LOG_LINE_CHARS = 2000


def db_session():
    """A session on the calling Steward's database; use as `async with db_session() as db`."""
    return mcp_app().db_sessionmaker()


def now_utc() -> datetime:
    return datetime.now(timezone.utc)


def _aware(dt: datetime) -> datetime:
    return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)


def iso(dt: datetime | None) -> str | None:
    if dt is None:
        return None
    return _aware(dt).astimezone(timezone.utc).isoformat(timespec="seconds").replace("+00:00", "Z")


def age_s(dt: datetime | None, now: datetime | None = None) -> int | None:
    if dt is None:
        return None
    return max(0, int(((now or now_utc()) - _aware(dt)).total_seconds()))


def rnd(value, digits: int = 2):
    return None if value is None else round(float(value), digits)


def clamp_limit(limit: int, default: int, maximum: int) -> int:
    """`limit` <= 0 means the default; anything above `maximum` is capped."""
    if not limit or limit <= 0:
        return default
    return min(int(limit), maximum)


def bounded(items: list, limit: int, *, key: str = "items", more: str = "") -> dict:
    """`{key: items[:limit], total, truncated}`, plus `more` when something was cut."""
    total = len(items)
    out = {key: items[:limit], "total": total, "truncated": total > limit}
    if total > limit:
        out["more"] = f"Showing {limit} of {total}. " + (more or "Pass a larger `limit`.")
    return out


def lookback(range_: str) -> tuple[datetime, str]:
    """A lookback window as (since, key). Unlike core parse_range, an unknown key
    is refused rather than quietly read as 24h: the agent should learn its typo."""
    key = (range_ or "24h").strip()
    if key not in RANGES:
        raise ValueError(f"range {range_!r} is not one of {', '.join(RANGES)}.")
    return now_utc() - RANGES[key], key


def downsample(points: list[tuple[datetime, float]], n: int = SERIES_POINTS) -> list[tuple[datetime, float]]:
    """Average consecutive points into at most n, each stamped with its first time."""
    if len(points) <= n:
        return points
    size = math.ceil(len(points) / n)
    out = []
    for i in range(0, len(points), size):
        chunk = points[i:i + size]
        out.append((chunk[0][0], sum(v for _, v in chunk) / len(chunk)))
    return out


def summarize(points: list[tuple[datetime, float]], n: int = SERIES_POINTS) -> dict:
    """min/avg/max/p95/last over oldest-first (time, value) points, plus a ≤n series."""
    if not points:
        return {"points": 0, "series": []}
    values = [v for _, v in points]
    ordered = sorted(values)
    p95 = ordered[max(0, math.ceil(0.95 * len(ordered)) - 1)]
    return {
        "points": len(values),
        "min": rnd(ordered[0]),
        "avg": rnd(sum(values) / len(values)),
        "max": rnd(ordered[-1]),
        "p95": rnd(p95),
        "last": rnd(values[-1]),
        "last_at": iso(points[-1][0]),
        "series": [[iso(t), rnd(v)] for t, v in downsample(points, n)],
    }


def pick(want: str, rows: Iterable[T], *, kind: str, list_tool: str,
         name: Callable[[T], str] = lambda r: r.name,
         ident: Callable[[T], str] = lambda r: r.id) -> T:
    """The row whose id is `want`, else the one whose name matches (case-insensitive)."""
    rows = list(rows)
    want = (want or "").strip()
    if not want:
        raise ValueError(f"pass a {kind} name or id; {list_tool} lists them.")
    for r in rows:
        if ident(r) == want:
            return r
    same = [r for r in rows if (name(r) or "").lower() == want.lower()]
    if len(same) == 1:
        return same[0]
    if same:
        ids = ", ".join(f"{ident(r)}" for r in same)
        raise ValueError(f"{len(same)} {kind}s are named {want!r}; pass one of these ids instead: {ids}.")
    close = difflib.get_close_matches(want.lower(), [(name(r) or "").lower() for r in rows], n=3, cutoff=0.5)
    hint = f" Did you mean {', '.join(repr(c) for c in close)}?" if close else ""
    raise ValueError(f"no {kind} named or with id {want!r}.{hint} {list_tool} lists them.")


def cut_middle(text: str, limit: int = LOG_LINE_CHARS) -> str:
    """Keep both ends of an over-long line and say how much of the middle went."""
    if text is None or len(text) <= limit:
        return text
    keep = limit // 2
    return f"{text[:keep]} [… {len(text) - 2 * keep} characters omitted …] {text[-keep:]}"


def redact_url(url: str) -> str:
    """Drop a password from a URL's userinfo; the rest stays readable."""
    try:
        parts = urlsplit(url)
    except ValueError:
        return url
    if parts.password is None:
        return url
    host = parts.hostname or ""
    if parts.port:
        host = f"{host}:{parts.port}"
    netloc = f"{parts.username}:***@{host}" if parts.username else f"***@{host}"
    return urlunsplit((parts.scheme, netloc, parts.path, parts.query, parts.fragment))