feat(diagnostics): debug sessions — start, stop, the tag on every line, screenshots (E16 S1)

A session is one recording, capped at 60 minutes by the server. While it is
open, a request naming the caller's own session in X-Debug-Session is logged
at the session's level with every line tagged; a header naming anything else
is ignored. The browser's batches count a session as consent to its level and
keep the tag only on its own events. Screenshots are judged by their bytes,
capped in size and count, and served back to their owner only.

- debug_sessions / debug_screenshots tables, one open session per user
  (partial unique index), log_events.debug_session_id indexed
- /api/debug-sessions: start (joins a running one), stop, list, get, events,
  screenshots; /api/me reports the live session
- the hourly log job closes expired sessions and drops them with the logs
- logsink.serialize and routes._common.capped_body shared by their readers
This commit is contained in:
2026-09-19 21:38:53 +02:00
parent 44a792c34f
commit a7d7456279
18 changed files with 1133 additions and 54 deletions
+261
View File
@@ -0,0 +1,261 @@
"""Debug sessions (E16): Start → reproduce → Stop, and the evidence a bug report is built from.
While a session is open its user's browser names it in `X-Debug-Session` on every request. The auth
dependency accepts the header only for the caller's OWN open session (anything else is ignored, never
an error — a stale tab must not break the app) and then logs that request at the session's level with
every line tagged by its id; the browser tags its own events the same way. The issue is later built
from exactly the rows carrying the tag, so what the review list shows is what gets sent.
Starting a session IS the consent for its level, for its duration: the start dialog carries the
consent text. It needs no change to the user's own diagnostics level, and none is made — when the
session ends the level in force is simply the user's own again.
A session is capped at `MAX_MINUTES`, set by the server at Start. An open one past its cap is over
whether or not anything has closed it yet: it reads as over at once, a new Start closes it, and the
hourly log job sweeps the rest. Sessions go with the logs they point at, after `log_retention_days`.
Core layer: imports `models`, `diagnostics`.
"""
import secrets
from datetime import datetime, timedelta, timezone
from enum import StrEnum
from typing import Literal, get_args
from sqlalchemy import delete, func, select, update
from sqlalchemy.orm import Session, defer
from app import diagnostics
from app.models import DebugScreenshot, DebugSession, LogEvent, User
HEADER = "x-debug-session"
MAX_MINUTES = 60
SCREENSHOT_MAX_BYTES = 10 * 1024 * 1024
SCREENSHOTS_MAX = 8
# Rows an issue can carry. A 60-minute session at Teljes is a few thousand rows; past this the
# bundle says how many it left out rather than growing without bound.
BUNDLE_MAX = 5_000
SessionLevel = Literal["DEBUG", "TRACE"]
SESSION_LEVELS: tuple[str, ...] = get_args(SessionLevel)
# Detail order of the diagnostics levels: a session raises the level in force, never lowers it.
_DETAIL = {"INFO": 0, "DEBUG": 1, "TRACE": 2}
_ID_LEN = 16
class EndReason(StrEnum):
STOPPED = "stopped"
EXPIRED = "expired"
def _is_live(session: DebugSession, now: datetime) -> bool:
return session.ended_at is None and session.until > now
def open_session(db: Session, user: User) -> DebugSession | None:
"""The user's live session, or None. Read-only: one past its cap is over and reads as None;
`start` and the hourly sweep are what close it."""
session = _unclosed(db, user)
if session is None or not _is_live(session, datetime.now(timezone.utc)):
return None
return session
def _unclosed(db: Session, user: User) -> DebugSession | None:
return db.scalar(
select(DebugSession).where(DebugSession.user_id == user.id, DebugSession.ended_at.is_(None))
)
def start(db: Session, user: User, level: SessionLevel) -> DebugSession:
"""Open a session, or return the live one — a second tab pressing Start joins the recording
rather than ending it. One past its cap is closed first: the one-open-per-user index would
refuse the new row beside it. Flushes; the caller commits. Two concurrent Starts can still both
get here: the index refuses the second, and the caller retries once."""
now = datetime.now(timezone.utc)
current = _unclosed(db, user)
if current is not None:
if _is_live(current, now):
return current
end(current, EndReason.EXPIRED)
db.flush()
session = DebugSession(
id=secrets.token_hex(_ID_LEN // 2),
user_id=user.id,
level=level,
started_at=now,
until=now + timedelta(minutes=MAX_MINUTES),
)
db.add(session)
db.flush()
return session
def end(session: DebugSession, reason: EndReason) -> None:
"""Close a session. An expired one is dated at its cap, not at whenever it was noticed."""
if session.ended_at is not None:
return
session.ended_at = (
session.until
if reason is EndReason.EXPIRED
else min(datetime.now(timezone.utc), session.until)
)
session.ended_reason = reason
def from_header(db: Session, user: User, value: str | None) -> DebugSession | None:
"""The session a request names, if it is the caller's own and still live; else None."""
if not value or len(value) != _ID_LEN or not all(c in "0123456789abcdef" for c in value):
return None
session = db.get(DebugSession, value)
if (
session is None
or session.user_id != user.id
or not _is_live(session, datetime.now(timezone.utc))
):
return None
return session
def level_for(user: User, session: DebugSession | None) -> tuple[str, datetime | None]:
"""The diagnostics level (and its expiry) a request is logged at: the user's own, raised to the
session's while one is named — whichever records more."""
own = diagnostics.effective_level(user)
until = user.diagnostics_until if own != diagnostics.BASE else None
if session is None or _DETAIL[session.level] <= _DETAIL[own]:
return own, until
return session.level, session.until
def serialize(session: DebugSession | None, screenshots: int = 0) -> dict | None:
if session is None:
return None
return {
"id": session.id,
"level": session.level,
"started_at": session.started_at.isoformat(),
"until": session.until.isoformat(),
"ended_at": session.ended_at.isoformat() if session.ended_at else None,
"ended_reason": session.ended_reason,
"issue_url": session.issue_url,
"screenshots": screenshots,
}
def screenshot_count(db: Session, session: DebugSession) -> int:
return (
db.scalar(
select(func.count())
.select_from(DebugScreenshot)
.where(DebugScreenshot.session_id == session.id)
)
or 0
)
# --- screenshots ---------------------------------------------------------------------------
# By content, not by the declared type: what is stored is served back to a browser as an image.
_SIGNATURES = (
(b"\x89PNG\r\n\x1a\n", "image/png"),
(b"\xff\xd8\xff", "image/jpeg"),
)
def sniff(data: bytes) -> str | None:
"""The image type `data` really is — PNG, JPEG or WebP — or None."""
for magic, mime in _SIGNATURES:
if data.startswith(magic):
return mime
if len(data) >= 12 and data[:4] == b"RIFF" and data[8:12] == b"WEBP":
return "image/webp"
return None
class ScreenshotRefused(Exception):
"""A screenshot that cannot be kept; `code` is the refusal's machine word."""
def __init__(self, code: str) -> None:
super().__init__(code)
self.code = code
def add_screenshot(db: Session, session: DebugSession, data: bytes) -> DebugScreenshot:
"""Keep one screenshot. Flushes; the caller commits. Refused once the issue was sent (it can no
longer carry it), past the per-session count, or when it is not an image we can show."""
if session.issue_url is not None:
raise ScreenshotRefused("already_sent")
if not data:
raise ScreenshotRefused("empty")
mime = sniff(data)
if mime is None:
raise ScreenshotRefused("not_an_image")
if screenshot_count(db, session) >= SCREENSHOTS_MAX:
raise ScreenshotRefused("too_many")
shot = DebugScreenshot(
session_id=session.id,
created_at=datetime.now(timezone.utc),
mime=mime,
size=len(data),
data=data,
)
db.add(shot)
db.flush()
return shot
def screenshots(db: Session, session: DebugSession) -> list[DebugScreenshot]:
"""The session's screenshots, oldest first, WITHOUT their bytes loaded."""
return list(
db.scalars(
select(DebugScreenshot)
.where(DebugScreenshot.session_id == session.id)
.options(defer(DebugScreenshot.data))
.order_by(DebugScreenshot.id)
)
)
# --- the evidence --------------------------------------------------------------------------
def bundle(db: Session, session: DebugSession) -> tuple[list[LogEvent], int]:
"""The session's log rows, browser and server interleaved in time, capped at BUNDLE_MAX — and
how many rows it has in all, so a cut bundle can say so."""
rows = list(
db.scalars(
select(LogEvent)
.where(LogEvent.debug_session_id == session.id)
.order_by(LogEvent.ts, LogEvent.id)
.limit(BUNDLE_MAX)
)
)
total = len(rows)
if total == BUNDLE_MAX:
total = (
db.scalar(
select(func.count())
.select_from(LogEvent)
.where(LogEvent.debug_session_id == session.id)
)
or total
)
return rows, total
# --- housekeeping (the hourly log job) -----------------------------------------------------
def sweep(db: Session) -> int:
"""Stage closing every open session past its cap; returns how many."""
now = datetime.now(timezone.utc)
result = db.execute(
update(DebugSession)
.where(DebugSession.ended_at.is_(None), DebugSession.until <= now)
.values(ended_at=DebugSession.until, ended_reason=EndReason.EXPIRED.value)
.execution_options(synchronize_session=False)
)
return result.rowcount or 0
def gc(db: Session, retention_days: int) -> int:
"""Stage deleting sessions (and by cascade their screenshots) started before the log retention
window — the rows they would bundle are gone by then too. Returns how many."""
cutoff = datetime.now(timezone.utc) - timedelta(days=max(1, retention_days))
result = db.execute(delete(DebugSession).where(DebugSession.started_at < cutoff))
return result.rowcount or 0