mangaBookmark/backend/internal/latest/faults.go

package latest

import (
	"context"
	"fmt"
	"time"

	"bookmarkmanager/backend/internal/store"
)

// ConditionStall is the owner-notice machine word for a Lane that owed Polls,
// made none, and has nothing to say for it. The word is the message's footer
// and its suppression key; it is wire-stable. #172 declares the other three
// words (no-browser-route, sidecar-down, adapter-broken); this ticket
// declares only the stall.
const ConditionStall = "stall"
// ConditionNoBrowserRoute is the owner-notice machine word for a Site whose
// challenge refuses for longer than the owner window with no browser route
// to clear it — the 403-with-interstitial the reader maps to
// errChallengeHeld (read.go), which plain TLS cannot clear. The word is the
// message's footer and its suppression key; it is wire-stable.
const ConditionNoBrowserRoute = "no-browser-route"

// ConditionSidecarDown is the owner-notice machine word for a browser
// sidecar no Lane has reached for longer than the owner window: every
// browser-backed Lane's latest pass is a sidecar skip. The word is the
// message's footer and its suppression key; it is wire-stable, and its
// suppression row holds the empty Site (AC4).
const ConditionSidecarDown = "sidecar-down"

// ConditionAdapterBroken is the owner-notice machine word for a Site whose
// adapter stopped finding chapters: more than half of its Series hold an
// old no-chapter failure row. The word is the message's footer and its
// suppression key; it is wire-stable.
const ConditionAdapterBroken = "adapter-broken"

// OwnerWindow is the class-level staleness boundary every owner-notice
// condition measures against — the same twelve hours the Lanes page's
// "not checked in 12h" filter uses (internal/web/admin.go). Declared here
// once so #172's three conditions and the admin filters share one figure.
const OwnerWindow = 12 * time.Hour

// Fault is one condition the owner is told about, judged from durable rows
// alone. Site is "" for a fault that is not one Site's.
type Fault struct {
	Condition string // one of the Condition* words
	Site      string
	Since     int64 // unix ms the episode began; the message's age
}

// FaultInput is everything the judgement reads. A struct so #172's three
// conditions can add inputs without changing either caller.
type FaultInput struct {
	Passes []store.LanePass
	// RefusingSince is, per Site, the unix ms when that Site's current
	// unbroken run of refusing passes began, or absent when its latest pass
	// did not refuse. Its zero value is an empty map, which contributes no
	// fault.
	RefusingSince map[string]int64

	// SidecarOK is, per browser-backed Site, the unix ms of that Site's most
	// recent pass that actually reached the sidecar. Zero when the pass log
	// holds none — an asleep Lane never reached it and never counts as
	// evidence either way. Its zero value is an empty map.
	SidecarOK map[string]int64

	// NoChapterShare is, per Site, the share of that Site's Series holding a
	// no-chapter failure row older than the owner window. Its zero value is
	// an empty map, which contributes no fault.
	NoChapterShare map[string]float64
}

// FaultsFrom judges the owner-notice conditions from durable rows alone, so
// the poller and the landing page cannot disagree about what a fault is.
//
// A Lane stalls when its latest pass shows due > 0, none checked, no skip
// value and no refusal — exactly the row the mid-loop browser loss writes
// (see the comment at the outcomeUnreachable return in runLanePass), so a
// Lane that owed Polls, made none, and has nothing to say for it is a fault.
// The three #172 conditions share the same OwnerWindow boundary and the same
// fail-open shape: an input's absence contributes no fault, never a false
// one.
//
//   - no-browser-route: a Site whose refusing run began before the window
//     and that has no browser route to clear the challenge (AC2). Both
//     refusal shapes count — the gate's skip='refusing' rows and the loop's
//     refused>0 rows (the twice-refused break writes skip="") — so the run
//     stays unbroken across them, and one healthy pass ends it.
//   - sidecar-down: every browser-backed Site's latest pass is a sidecar
//     skip — SkipSidecarDown or SkipNoFetcher, the two early returns that
//     record a skip value — and each Site's most recent sidecar-reaching
//     pass is older than the window (AC4). The skip clause is what keeps
//     SkipAsleep out: a Lane under both wake thresholds is the commonest
//     healthy state, never reached the sidecar, and would otherwise age into
//     a false alarm. Emitted once, with Site "" (AC4's one row per episode).
//   - adapter-broken: more than half of one Site's Series hold a no-chapter
//     failure row older than the window (AC6). Strictly above half: the
//     filter is the tool, and one Site change makes hundreds of rows, so a
//     single failing Series never fires (AC7). The episode's age is the
//     window — the old rows prove the episode is at least that old.
func FaultsFrom(in FaultInput, now time.Time) []Fault {
	var faults []Fault
	for _, p := range in.Passes {
		if p.Due > 0 && p.Checked == 0 && p.Skip == "" && p.Refused == 0 {
			faults = append(faults, Fault{Condition: ConditionStall, Site: p.Site, Since: p.RanAt})
		}
	}
	cutoff := now.Add(-OwnerWindow).UnixMilli()
	for site, since := range in.RefusingSince {
		if since < cutoff && !isBrowserSite(site) {
			faults = append(faults, Fault{Condition: ConditionNoBrowserRoute, Site: site, Since: since})
		}
	}
	if since, down := sidecarDownSince(in.Passes, in.SidecarOK, cutoff); down {
		faults = append(faults, Fault{Condition: ConditionSidecarDown, Site: "", Since: since})
	}
	for site, share := range in.NoChapterShare {
		if share > 0.5 {
			faults = append(faults, Fault{Condition: ConditionAdapterBroken, Site: site, Since: now.Add(-OwnerWindow).UnixMilli()})
		}
	}
	return faults
}

// sidecarDownSince reports whether no browser Lane has reached the sidecar
// for longer than the owner window and, when it has, the last moment any
// Lane reached it. The skip clause — every browser-backed Site's latest pass
// must be SkipSidecarDown or SkipNoFetcher — keeps SkipAsleep out (see
// FaultsFrom). A Site with no pass row at all is not judged down either: a
// fresh database is not a dead sidecar.
func sidecarDownSince(passes []store.LanePass, ok map[string]int64, cutoff int64) (since int64, down bool) {
	latest := make(map[string]store.LanePass, len(passes))
	for _, p := range passes {
		latest[p.Site] = p
	}
	for _, site := range browserBackedSites() {
		p, found := latest[site]
		if !found || (p.Skip != SkipSidecarDown && p.Skip != SkipNoFetcher) {
			return 0, false
		}
		reached := ok[site]
		if reached > 0 && reached >= cutoff {
			return 0, false
		}
		if reached > since {
			since = reached
		}
	}
	return since, true
}

// Notifier delivers one owner notice. The poller neither retries nor queues:
// an error is logged and the suppression row left unwritten, so the next pass
// tries again while the condition holds.
type Notifier interface {
	Notify(ctx context.Context, f Fault, sentence, href string) error
}

// ownerNoticeConditions is every condition this package judges, for the
// clear loop in recordPass: a condition absent from a pass's fault list
// forgets its episode, so the next occurrence sends again. #172 extends the
// list when it adds its conditions.
var ownerNoticeConditions = []string{ConditionStall, ConditionNoBrowserRoute, ConditionSidecarDown, ConditionAdapterBroken}

// noticeFor renders one fault's message: the description sentence — condition,
// age, repair — and the deep link the embed's title points at. Each condition
// provides its own wording; the stall is the only one today (issue #171).
func noticeFor(f Fault, row store.LanePass, now time.Time) (sentence, href string) {
	switch f.Condition {
	case ConditionStall:
		return fmt.Sprintf(
			"%s owed %d Polls and made none — %s; check the Lane's browser sidecar and the Site's challenge state",
			f.Site, row.Due, humanAge(now.Sub(time.UnixMilli(f.Since)))), "/admin/lanes"
	case ConditionNoBrowserRoute:
		return fmt.Sprintf(
			"%s has refused for %s with no browser route — the challenge does not clear on plain TLS; redeploy or add a browser route",
			f.Site, humanAge(now.Sub(time.UnixMilli(f.Since)))), "/admin/lanes"
	case ConditionSidecarDown:
		return fmt.Sprintf(
			"no browser Lane has reached the sidecar for %s — the browser sidecar is down; start or repair the browser machine",
			humanAge(now.Sub(time.UnixMilli(f.Since)))), "/admin/lanes"
	case ConditionAdapterBroken:
		return fmt.Sprintf(
			"more than half of %s's Series have failed no-chapter reads for at least %s — the Site's layout changed and the adapter is broken",
			f.Site, humanAge(now.Sub(time.UnixMilli(f.Since)))), "/admin/lanes"
	}
	return "", ""
}

// humanAge renders a duration the way an owner reads it in a message: minutes
// under an hour, then hours, then days; a stall that was just born reads
// "just now".
func humanAge(d time.Duration) string {
	switch {
	case d < time.Minute:
		return "just now"
	case d < time.Hour:
		return fmt.Sprintf("%dm", int(d.Minutes()))
	case d < 24*time.Hour:
		return fmt.Sprintf("%dh", int(d.Hours()))
	default:
		return fmt.Sprintf("%dd", int(d.Hours()/24))
	}
}