mesh-catalog/modules/mesh-issues/cmd/mesh-issues/delivery.go

package main

// Whether an issue's fix is delivered (novox/hq ADR 0281). The tracker hears mesh-delivery's `transition` event
// for every pull request an issue's fixed-by names and keeps, per pull request, the state the delivery last said
// — merged or not, held and why, covered by a later merge, delivered. From that it derives one line for `get` and
// `list`: a measured fact, never set by a verb. Delivered is not resolved: when every fix of an issue not yet
// resolved is delivered, the issue gains a note and the event `ready-to-verify`, and an agent proves its
// acceptance live before resolving it. A fix merged and not delivered past a bound is said on the issue and to
// the operator's channel.

import (
	"encoding/json"
	"errors"
	"fmt"
	"sort"
	"strings"
	"time"

	stdio "git.novox.be/novox/mesh-sdk/go"
)

// EventReadyToVerify is said once when every fix of an issue not yet resolved is delivered.
const EventReadyToVerify = "ready-to-verify"

// DefaultStuckAfter is how long a fix may be merged and not delivered before it is said stuck: a walk takes
// minutes, a gate ten at most, and a hold waits for a person; two hours is past every ordinary delivery and
// still the same working day.
const DefaultStuckAfter = 2 * time.Hour

// Fix is one pull request of an issue's fixed-by, as the delivery last said it.
type Fix struct {
	PullRequest string     `json:"pull-request"`
	State       string     `json:"state"`
	Why         string     `json:"why,omitempty"`
	Merged      bool       `json:"merged,omitempty"`
	MergedAt    *time.Time `json:"merged-at,omitempty"`
	Since       time.Time  `json:"since"`
	// StuckSaid says it was said stuck, on the issue and to the operator's channel.
	StuckSaid bool `json:"stuck-said,omitempty"`
}

// reached says whether a delivery's state says the change reached the machines (mesh-delivery's Reached).
func reached(state string) bool {
	return state == "delivered" || state == "covered" || state == "retired"
}

// Whether a pull request is merged is what the delivery says of the pull request itself — `merged_as` on a
// transition, the pull request's `merged` in checks — never read from the state: `stopped` is also what a pull
// request closed without merging becomes (mesh-delivery's `closed` event), and read as merged it was said stuck to
// the operator for good (novox/hq issue 483).

// withdrawn says whether a fix is a pull request closed without merging: no fix at all, neither awaiting delivery,
// delivered, nor open.
func withdrawn(f *Fix) bool { return f != nil && f.State == "stopped" && !f.Merged }

// liveFixes is an issue's fixes less those withdrawn: what its delivery, readiness to verify, the stuck sweep and a
// abandoned issue are measured on. fixPullRequests still names the withdrawn ones, so a pull request reopened is heard.
func liveFixes(is *Issue) []string {
	var out []string
	for _, pr := range fixPullRequests(is) {
		if !withdrawn(fixOf(is, pr)) {
			out = append(out, pr)
		}
	}
	return out
}

// withdrawnFixes is the pull requests of an issue closed without merging.
func withdrawnFixes(is *Issue) []string {
	var out []string
	for _, pr := range fixPullRequests(is) {
		if withdrawn(fixOf(is, pr)) {
			out = append(out, pr)
		}
	}
	return out
}

func fixOf(is *Issue, pr string) *Fix {
	for i := range is.Fixes {
		if is.Fixes[i].PullRequest == pr {
			return &is.Fixes[i]
		}
	}
	return nil
}

// allDelivered says whether an issue names a pull request and every one is delivered.
func allDelivered(is *Issue) bool {
	prs := liveFixes(is)
	if len(prs) == 0 {
		return false
	}
	for _, pr := range prs {
		if !contains(is.Delivered, pr) {
			return false
		}
	}
	return true
}

// DeliveryLine is the derived delivery state of an issue's fix, in words; empty when fixed-by names no pull
// request.
func DeliveryLine(is *Issue) string {
	prs := liveFixes(is)
	if len(prs) == 0 {
		if w := withdrawnFixes(is); len(w) > 0 {
			return "fix withdrawn: " + strings.Join(w, ", ") + " closed without merging"
		}
		return ""
	}
	var held, failed, merged, open, unheard []string
	covered := false
	for _, pr := range prs {
		f := fixOf(is, pr)
		switch {
		case contains(is.Delivered, pr):
			covered = covered || (f != nil && f.State == "covered")
		case f == nil:
			unheard = append(unheard, pr)
		case f.State == "held":
			held = append(held, strings.TrimSpace(pr+": "+f.Why))
		case f.State == "failed" || f.State == "stopped":
			failed = append(failed, strings.TrimSpace(pr+" "+f.State+": "+f.Why))
		case f.Merged:
			merged = append(merged, pr)
		default:
			open = append(open, pr)
		}
	}
	switch {
	case len(failed) > 0:
		return "fix not delivered: " + strings.Join(failed, "; ")
	case len(held) > 0:
		return "held: " + strings.Join(held, "; ")
	case len(merged) > 0:
		return "fix merged, not delivered: " + strings.Join(merged, ", ")
	case len(open) > 0:
		return "fix not merged: " + strings.Join(open, ", ")
	case len(unheard) > 0:
		return "nothing heard from the delivery of " + strings.Join(unheard, ", ")
	case covered:
		return "delivered to every machine it should reach (by a later merge that contains it)"
	}
	return "delivered to every machine it should reach"
}

// recordFix keeps what the delivery said of a pull request on every issue whose fixed-by names it (only, when
// given, on that one issue), and answers the issues it changed.
func (t *Tracker) recordFix(pr, state, why string, merged bool, at time.Time, only uint64) ([]uint64, error) {
	all, err := t.allIssues()
	if err != nil {
		return nil, err
	}
	var changed []uint64
	for n, is := range all {
		if (only != 0 && n != only) || !contains(fixPullRequests(is), pr) {
			continue
		}
		kept := cut(why, MostReasonKept)
		if f := fixOf(is, pr); f != nil && (at.Before(f.Since) || (f.State == state && f.Why == kept && f.Merged == (merged || f.Merged))) {
			// Older than what is kept, or nothing new: transitions can arrive out of order.
			continue
		}
		if contains(is.Delivered, pr) && !reached(state) {
			// Delivered stays delivered: a later state that has not reached the machines is a newer delivery of
			// the same pull request at most, and an older one is history.
			continue
		}
		if _, err := t.change(n, Act{Op: "delivery", By: Seat}, func(i *Issue) error {
			f := fixOf(i, pr)
			if f == nil {
				i.Fixes = append(i.Fixes, Fix{PullRequest: pr})
				f = &i.Fixes[len(i.Fixes)-1]
			}
			f.State, f.Why, f.Since = state, kept, at
			if merged && !f.Merged {
				f.Merged = true
				m := at
				f.MergedAt = &m
			}
			if reached(state) && !contains(i.Delivered, pr) {
				i.Delivered = append(i.Delivered, pr)
			}
			return nil
		}); err != nil {
			return changed, err
		}
		changed = append(changed, n)
	}
	sort.Slice(changed, func(i, j int) bool { return changed[i] < changed[j] })
	return changed, nil
}

// afterFix is what follows a change of an issue's fixes: ready to verify, once, when every fix is delivered and
// the issue is not yet resolved; a stuck fix delivered at last cleared on the operator's channel; and what
// waited on it let go.
func (t *Tracker) afterFix(n uint64) error {
	is, _, err := read(t.Store, n)
	if err != nil {
		return err
	}
	if err := t.clearStuck(is); err != nil {
		t.Logf("[mesh-issues] the stuck fix of %d could not be cleared on the operator's channel (tried again at the next sweep): %v", n, err)
	}
	if err := t.clearNotResolved(is); err != nil {
		t.Logf("[mesh-issues] the warning that %d is delivered and not resolved could not be cleared on the operator's channel (tried again at the next sweep): %v", n, err)
	}
	if allDelivered(is) {
		if unresolved(is) {
			prs := liveFixes(is)
			sort.Strings(prs)
			if strings.Join(is.VerifyFor, ",") != strings.Join(prs, ",") {
				// The note first, kept once by its words; then the claim; then the event. A failure before the claim
				// is tried again at the next offer, and the note is not written twice. It names when each fix was
				// delivered and who works on the issue: no channel of the tracker reaches a worker, so the note
				// and the event are how the worker hears it (novox/hq issue 483).
				var when []string
				for _, pr := range prs {
					if f := fixOf(is, pr); f != nil {
						when = append(when, pr+" at "+f.Since.Format(time.RFC3339))
					} else {
						when = append(when, pr)
					}
				}
				prefix := fmt.Sprintf("Ready to verify: every fix of this issue is delivered (%s).", strings.Join(when, ", "))
				worker := ""
				if is.Worker != nil {
					worker = is.Worker.By
				}
				if !noted(is, prefix) {
					text := prefix
					if worker != "" {
						text += fmt.Sprintf(" %s works on it: prove the acceptance live and resolve it, or say what is left. "+
							"In fixing and not resolved %s after its delivery, it is said to the operator.", worker,
							t.deliveredNotResolvedAfter())
					}
					text += " Delivered is not resolved: prove the acceptance live, then resolve it, from fixing: move it " +
						"to fixing with by first if it is not there. (novox/hq ADR 0281, ADR 0284, issue 483)"
					if _, err := t.note(GroomBy, n, text); err != nil {
						return err
					}
				}
				claimed := false
				if _, err := t.change(n, Act{Op: EventReadyToVerify, By: Seat}, func(i *Issue) error {
					claimed = false
					if strings.Join(i.VerifyFor, ",") == strings.Join(prs, ",") {
						return nil
					}
					i.VerifyFor, claimed = prs, true
					return nil
				}); err != nil {
					return err
				}
				if claimed {
					body := map[string]any{"number": n, "fixed-by": prs, "at": t.now(), "delivered-at": deliveredAt(is)}
					if worker != "" {
						body["worker"] = worker
					}
					t.emit(EventReadyToVerify, body)
				}
			}
		}
	}
	return t.letGo(n)
}

// stillStuck says whether an issue has a fix said stuck that is still named, not delivered, and the issue not
// closed. A closed issue is the end of its warning: resolved means its worker proved the acceptance live, so a fix
// the tracker never heard delivered is not waited for any more (a failed walk that a later merge carried stays
// failed, novox/hq issue 547), and wontfix waits for nothing.
func stillStuck(is *Issue) bool {
	if closedStatus(is.Status) {
		return false
	}
	named := liveFixes(is)
	for _, f := range is.Fixes {
		if f.StuckSaid && contains(named, f.PullRequest) && !contains(is.Delivered, f.PullRequest) {
			return true
		}
	}
	return false
}

// clearStuck clears the warning said for an issue on the operator's channel once nothing it was said for is
// stuck — delivered, no longer named, or the issue closed (resolved or wontfix); one that fails is tried again at
// the next sweep.
func (t *Tracker) clearStuck(is *Issue) error {
	if !is.StuckOpen || stillStuck(is) || t.Notify == nil {
		return nil
	}
	if err := t.Notify(stuckKey(is.Number), "", "", "", "", stuckEnded(is), true); err != nil {
		return err
	}
	_, err := t.change(is.Number, Act{Op: "warned", By: Seat}, func(i *Issue) error { i.StuckOpen = false; return nil })
	return err
}

// stuckEnded is what the operator's channel says when a stuck warning ends.
func stuckEnded(is *Issue) string {
	switch is.Status {
	case StatusResolved:
		return "resolved: issue " + keyOf(is.Number) + " was proven live by its worker"
	case StatusWontfix:
		return "issue " + keyOf(is.Number) + " was closed as wontfix: its fix is no longer waited for"
	}
	return "the fix of issue " + keyOf(is.Number) + " is delivered or no longer waited for"
}

func stuckKey(n uint64) string { return "issue-tracker.fix-stuck." + keyOf(n) }

func prKey(repository string, number int) string {
	_, repo, ok := strings.Cut(repository, "/")
	if !ok {
		repo = repository
	}
	return fmt.Sprintf("%s#%d", strings.ToLower(repo), number)
}

// OnTransition is the handler of mesh-delivery's `transition` event: every state a pull request's delivery moves
// to is kept on each issue whose fixed-by names it.
func (t *Tracker) OnTransition(e stdio.Envelope) error {
	var body struct {
		Repository string    `json:"repository"`
		Number     int       `json:"number"`
		To         string    `json:"to"`
		Why        string    `json:"why"`
		MergedAs   string    `json:"merged_as"`
		At         time.Time `json:"at"`
	}
	if err := json.Unmarshal(e.Body, &body); err != nil || body.To == "" || body.Number <= 0 {
		return nil
	}
	at := body.At.UTC()
	if at.IsZero() {
		at = t.now()
	}
	merged := body.MergedAs != ""
	changed, err := t.recordFix(prKey(body.Repository, body.Number), body.To, body.Why, merged, at, 0)
	if err != nil {
		return err
	}
	for _, n := range changed {
		if err := t.afterFix(n); err != nil {
			return err
		}
	}
	return nil
}

// Delivery is a pull request's delivery as mesh-delivery's `checks` answers it; a test stubs the asking.
type Delivery struct {
	State string
	Why   string
	// Since is when the delivery entered its state, as it says; zero when it does not.
	Since time.Time
	// Merged is the pull request's own merged flag, as the forge says it.
	Merged bool
}

// DeliveryState asks mesh-delivery for one pull request's delivery.
type DeliveryState func(repository string, number string) (Delivery, error)

// busDeliveryState asks mesh-delivery's checks over the bus.
func busDeliveryState(owner string) DeliveryState {
	return func(repository, number string) (Delivery, error) {
		raw, err := stdio.Ask("seat:mesh-delivery.checks", map[string]any{"repository": owner + "/" + repository, "number": number})
		if err != nil {
			return Delivery{}, err
		}
		var out struct {
			Delivery struct {
				State string    `json:"state"`
				Waits string    `json:"waits"`
				Since time.Time `json:"since"`
			} `json:"delivery"`
			Pull struct {
				Merged bool `json:"merged"`
			} `json:"pull"`
		}
		if err := json.Unmarshal(raw, &out); err != nil {
			return Delivery{}, fmt.Errorf("mesh-delivery's checks answered no delivery: %.200s", raw)
		}
		return Delivery{State: out.Delivery.State, Why: out.Delivery.Waits, Since: out.Delivery.Since.UTC(), Merged: out.Pull.Merged}, nil
	}
}

// OnMoved is the handler of the tracker's own `moved` event: each pull request of the issue's fix not heard of
// yet is asked of mesh-delivery, at most a few per handling, for a delivery that moved before the issue named
// it; then what follows its fixes, and an issue closed lets go what waited on it.
func (t *Tracker) OnMoved(e stdio.Envelope) error {
	var body struct {
		Number uint64 `json:"number"`
	}
	if err := json.Unmarshal(e.Body, &body); err != nil || body.Number == 0 {
		return nil
	}
	is, _, err := read(t.Store, body.Number)
	if errors.Is(err, ErrNoIssue) {
		return nil
	}
	if err != nil {
		return err
	}
	if t.Deliveries != nil {
		// Each ask up to the bus's 30 seconds, under the runtime's two minutes; one that fails, or more left to
		// ask, has the event offered again, so a delivery never asked ends in max-deliveries, not in silence.
		asked := 0
		for _, pr := range fixPullRequests(is) {
			if fixOf(is, pr) != nil {
				continue
			}
			if asked == MostDeliveryAsks {
				return fmt.Errorf("issue %d names more pull requests than are asked at once; the rest at the next offer", body.Number)
			}
			asked++
			repo, number, _ := strings.Cut(pr, "#")
			d, err := t.Deliveries(repo, number)
			if err != nil {
				return fmt.Errorf("the delivery of %s (issue %d) could not be asked: %v", pr, body.Number, err)
			}
			state := d.State
			if state == "" {
				// The delivery knows nothing of it yet: not kept, so it is asked again at the next move, and its own
				// events say it when they come.
				continue
			}
			// The delivery's own time, so a transition stamped the same moment is not taken as older.
			since := d.Since
			if since.IsZero() {
				since = t.now()
			}
			if _, err := t.recordFix(pr, state, d.Why, d.Merged, since, body.Number); err != nil {
				return err
			}
		}
	}
	return t.afterFix(body.Number)
}

// Notifier tells the operator's channel something (operator-channel.notify), or clears it.
type Notifier func(key, severity, summary, headline, explanation, resolved string, clear bool) error

// busNotifier asks the operator's channel over the bus.
func busNotifier() Notifier {
	return func(key, severity, summary, headline, explanation, resolved string, clear bool) error {
		body := map[string]any{"key": key, "subject": "the issue tracker"}
		if clear {
			body["clear"] = true
			body["resolved"] = resolved
		} else {
			body["severity"], body["summary"], body["headline"], body["explanation"] = severity, summary, headline, explanation
		}
		_, err := stdio.Ask("seat:operator-channel.notify", body)
		return err
	}
}

// stuckAfter is the setting's bound, or the default.
func (t *Tracker) stuckAfter() time.Duration {
	if s, err := t.Settings(); err == nil && strings.TrimSpace(s.StuckAfter) != "" {
		if d, err := time.ParseDuration(strings.TrimSpace(s.StuckAfter)); err == nil && d > 0 {
			return d
		}
	}
	return DefaultStuckAfter
}

// Sweep says every fix of an issue not closed merged and not delivered past the bound: a note on its issue and a warning on the
// operator's channel, once; and every issue in fixing whose fixes were all delivered past its own bound and is not
// resolved (novox/hq issue 483). First it asks the delivery of a few fixes never heard of. It answers how many
// warnings it said. Run every few minutes.
func (t *Tracker) Sweep() (int, error) {
	if err := t.askUnheard(); err != nil {
		t.Logf("[mesh-issues] the sweep could not ask a fix's delivery (asked again at the next sweep): %v", err)
	}
	all, err := t.allIssues()
	if err != nil {
		return 0, err
	}
	bound, now := t.stuckAfter(), t.now()
	said := 0
	for n, is := range all {
		ok, err := t.sayNotResolved(is, now)
		if err != nil {
			t.Logf("[mesh-issues] that %d is delivered and not resolved could not be said on the operator's channel (said at the next sweep): %v", n, err)
		} else if ok {
			said++
		}
		if err := t.clearStuck(is); err != nil {
			t.Logf("[mesh-issues] the stuck fix of %d could not be cleared on the operator's channel: %v", n, err)
		}
		if closedStatus(is.Status) {
			// A resolved or wontfix issue waits for no fix: never said stuck (novox/hq issue 547).
			continue
		}
		named := liveFixes(is)
		for _, f := range is.Fixes {
			if !contains(named, f.PullRequest) || contains(is.Delivered, f.PullRequest) || !f.Merged || f.MergedAt == nil ||
				reached(f.State) || f.StuckSaid || now.Sub(*f.MergedAt) < bound {
				continue
			}
			state := f.State
			if f.Why != "" {
				state += ": " + f.Why
			}
			prefix := fmt.Sprintf("Stuck: the fix %s", f.PullRequest)
			if !noted(is, prefix) {
				if _, err := t.note(GroomBy, n, fmt.Sprintf("%s was merged %s ago and is not delivered (%s). A merged fix "+
					"that does not reach the machines is said on the operator's channel. (novox/hq ADR 0281)", prefix,
					now.Sub(*f.MergedAt).Round(time.Minute), state)); err != nil {
					return said, err
				}
			}
			if t.Notify != nil {
				if err := t.Notify(stuckKey(n), "warning",
					fmt.Sprintf("issue %d: fix %s merged %s ago, not delivered", n, f.PullRequest, now.Sub(*f.MergedAt).Round(time.Minute)),
					fmt.Sprintf("A fix is merged and not delivered (issue %d)", n),
					fmt.Sprintf("The fix of issue %d was merged %s ago and has not reached the machines: %s. Look at its "+
						"delivery; nothing else is needed from you unless it waits for a person.", n,
						now.Sub(*f.MergedAt).Round(time.Minute), state), "", false); err != nil {
					// Tried again at the next sweep: the note is not written twice.
					t.Logf("[mesh-issues] the stuck fix of %d could not be said on the operator's channel: %v", n, err)
					continue
				}
			}
			pr := f.PullRequest
			if _, err := t.change(n, Act{Op: "warned", By: Seat}, func(i *Issue) error {
				if g := fixOf(i, pr); g != nil {
					g.StuckSaid = true
				}
				i.StuckOpen = t.Notify != nil
				return nil
			}); err != nil {
				return said, err
			}
			said++
		}
	}
	return said, nil
}