internal/agent/watch.go

@@ -145,9 +145,14 @@ func terminalState(st PRState) (bool, string) {
 	return false, ""
 }
 
-// conflictPolls is how many consecutive non-mergeable polls of an unchanged
-// merge computation confirm a real conflict.
-const conflictPolls = 2
+// conflictWindow is how long an unbroken run of non-mergeable polls must span
+// before it is reported as a conflict. What the run has to outlast is Gitea's
+// merge recompute, which is a duration, so counting polls cannot express it:
+// --interval varies from seconds to hours between callers. Recomputes have been
+// observed finishing in ~5-20s with no bound on the tail, so this is set well
+// clear of that; the cost of it being too long is only a later conflict alert,
+// while too short is a false one.
+const conflictWindow = 2 * time.Minute
 
 // prWatch tracks one PR across polls, because mergeability needs more memory
 // than the previous snapshot. Gitea reports mergeable=false while it recomputes
@@ -155,11 +160,15 @@ const conflictPolls = 2
 // seen a merge computation start: the PR was mergeable at some point, or its
 // head or base SHA moved. A bare false inherited from the baseline says nothing
 // -- it is equally a conflict the operator is already waiting on and a recompute
-// in flight -- so it arms nothing.
+// in flight -- so it arms nothing. Arming and the run of falses are independent:
+// movement only arms, because a base branch that moves under the PR on every
+// push to main would otherwise restart the run forever.
 type prWatch struct {
-	prev      PRState
-	armed     bool
-	conflicts int
+	prev  PRState
+	armed bool
+	// conflictSince is when the current unbroken run of non-mergeable polls
+	// began; zero when no run is in progress.
+	conflictSince time.Time
 }
 
 func newPRWatch(baseline PRState) *prWatch {
@@ -173,39 +182,48 @@ func mergeInputsChanged(prev, cur PRState) bool {
 }
 
 // track folds one snapshot's mergeability into the run of observations. The
-// polls that confirm a conflict must be adjacent, so anything but another
-// non-mergeable observation breaks the run.
-func (w *prWatch) track(st PRState) {
+// observations that confirm a conflict must be adjacent, so anything but
+// another non-mergeable one breaks the run.
+func (w *prWatch) track(st PRState, now time.Time) {
 	switch st.Mergeable {
 	case MergeNo:
-		w.conflicts++
+		if w.conflictSince.IsZero() {
+			w.conflictSince = now
+		}
 	case MergeYes:
 		w.armed = true
-		w.conflicts = 0
+		w.conflictSince = time.Time{}
 	default:
-		w.conflicts = 0
+		w.conflictSince = time.Time{}
 	}
 }
 
 // missed records a poll that never produced a snapshot; the run of adjacent
 // non-mergeable observations does not survive the gap.
 func (w *prWatch) missed() {
-	w.conflicts = 0
+	w.conflictSince = time.Time{}
 }
 
-// observe folds in the newest snapshot and reports whether the watch should end.
-func (w *prWatch) observe(cur PRState) (bool, string) {
+// confirmed reports whether the run of non-mergeable observations has spanned
+// the recompute window. The run starts at its first observation, so a lone
+// non-mergeable poll never confirms anything whatever the interval.
+func (w *prWatch) confirmed(now time.Time) bool {
+	return !w.conflictSince.IsZero() && now.Sub(w.conflictSince) >= conflictWindow
+}
+
+// observe folds in the newest snapshot, taken at now, and reports whether the
+// watch should end.
+func (w *prWatch) observe(cur PRState, now time.Time) (bool, string) {
 	changed, reason := MeaningfulChange(w.prev, cur)
 	if mergeInputsChanged(w.prev, cur) {
 		w.armed = true
-		w.conflicts = 0
 	}
 	w.prev = cur
-	w.track(cur)
+	w.track(cur, now)
 	if changed {
 		return true, reason
 	}
-	if w.armed && w.conflicts >= conflictPolls && cur.State == "open" {
+	if w.armed && w.confirmed(now) && cur.State == "open" {
 		return true, "PR lost mergeability (conflict)"
 	}
 	return false, ""
@@ -245,7 +263,9 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti
 		onBaseline(baselines)
 	}
 	fails := make(map[string]int, len(refs))
-	for range ticks {
+	// The tick carries the time it fired, which is the clock the conflict
+	// window is measured on.
+	for now := range ticks {
 		for _, ref := range refs {
 			key := ref.String()
 			cur, err := f.FetchState(ref, agentLogin)
@@ -264,7 +284,7 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti
 				continue
 			}
 			fails[key] = 0
-			if changed, reason := watches[key].observe(cur); changed {
+			if changed, reason := watches[key].observe(cur, now); changed {
 				return WatchResult{Ref: ref, Reason: reason, State: cur}, nil
 			}
 		}

internal/agent/watch_test.go

@@ -791,11 +791,21 @@ func TestWatchAnonymousKeepsPolling(t *testing.T) {
 }
 
 // drainableTicks returns a channel holding n ticks and already closed, so Watch
-// polls exactly n times and then returns instead of blocking.
+// polls exactly n times and then returns instead of blocking. The ticks are
+// spaced far past conflictWindow, so a run of non-mergeable polls confirms on
+// its second observation; spacedTicks drives the intervals where it must not.
 func drainableTicks(n int) <-chan time.Time {
+	return spacedTicks(n, 10*time.Minute)
+}
+
+// spacedTicks is drainableTicks with the poll interval named. The tick carries
+// the time Watch measures the conflict window on, which makes every wall-clock
+// assertion in these tests exact and instant.
+func spacedTicks(n int, interval time.Duration) <-chan time.Time {
+	start := time.Date(2026, 9, 24, 12, 0, 0, 0, time.UTC)
 	ticks := make(chan time.Time, n)
-	for i := 0; i < n; i++ {
-		ticks <- time.Now()
+	for i := 1; i <= n; i++ {
+		ticks <- start.Add(time.Duration(i) * interval)
 	}
 	close(ticks)
 	return ticks
@@ -911,9 +921,10 @@ func TestPRWatchMergeability(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			w := newPRWatch(snap(tt.baseline))
+			start := time.Date(2026, 9, 24, 12, 0, 0, 0, time.UTC)
 			got := 0
 			for i, m := range tt.polls {
-				changed, reason := w.observe(snap(m))
+				changed, reason := w.observe(snap(m), start.Add(time.Duration(i+1)*10*time.Minute))
 				if !changed {
 					continue
 				}
@@ -958,13 +969,12 @@ func TestMergeabilityDecoding(t *testing.T) {
 	}
 }
 
-// The inverse of the bug this PR fixed: Gitea reports mergeable=false while it
-// recomputes the merge base after a push, and watchpr is normally started right
-// after the agent pushes, so the baseline can land inside that window. Demanding
-// a mergeable observation to arm the rule left a genuinely conflicted PR silent
-// forever. The new head is a new merge computation, so the conflict it confirms
-// belongs to this watch.
-func TestWatchAlertsWhenBaselineLandedInTheRecomputeWindow(t *testing.T) {
+// The inverse of the bug this PR fixed: demanding a mergeable observation to arm
+// the rule left a PR that was non-mergeable at baseline silent forever, even
+// after a push gave Gitea a fresh merge computation to answer for. A head that
+// moves during the watch arms the rule, so the conflict the new head keeps
+// reporting is attributable to this watch and is reported.
+func TestWatchAlertsWhenAPushArmsABaselineConflict(t *testing.T) {
 	baseline := base()
 	baseline.Mergeable = MergeNo // still recomputing; the push is not visible yet
 
@@ -1160,3 +1170,164 @@ func TestWatchReportsBaselineStates(t *testing.T) {
 		t.Errorf("baseline = %+v, want the conflicted, CI-red snapshot the watch started from", got[0])
 	}
 }
+
+// The residual gap, pinned so it is a decision rather than an accident: the
+// agent pushes, the push conflicts, watchpr starts inside Gitea's recompute and
+// nothing moves again. Every poll answers false and none of them is
+// attributable to this watch, so no alert is ever sent -- the baseline line is
+// the only notice. Gitea's payload carries no field that separates this from a
+// merge check still running.
+func TestWatchNeverAlertsOnAConflictLandedByThePushBeforeTheWatch(t *testing.T) {
+	pushed := base()
+	pushed.Mergeable = MergeNo
+	pushed.HeadSHA = "def456"
+	f := &fakeFetcher{states: []PRState{pushed}}
+
+	res, err := Watch(f, []PRRef{pushed.Ref}, "unkin-agent", drainableTicks(50), nil, nil)
+	if err != nil {
+		t.Fatalf("Watch: %v", err)
+	}
+	if res.Reason != "" {
+		t.Fatalf("Watch ended with %q; nothing distinguishes this conflict from a merge check in flight, so it must stay silent", res.Reason)
+	}
+}
+
+// The whole mergeability rule as a sequence table, driven through Watch at the
+// intervals that decide it. The debounce is wall-clock, so the same sequence of
+// snapshots must alert or stay silent according to how far apart the polls are.
+func TestWatchConflictSequences(t *testing.T) {
+	snap := func(m Mergeability, head, bse string) PRState {
+		st := base()
+		st.Mergeable = m
+		st.HeadSHA = head
+		st.BaseSHA = bse
+		return st
+	}
+	repeat := func(st PRState, n int) []PRState {
+		out := make([]PRState, n)
+		for i := range out {
+			out[i] = st
+		}
+		return out
+	}
+	movingBase := func(m Mergeability, n int) []PRState {
+		out := make([]PRState, n)
+		for i := range out {
+			out[i] = snap(m, "h1", fmt.Sprintf("b%d", i))
+		}
+		return out
+	}
+	const (
+		quick   = 5 * time.Second  // well inside conflictWindow
+		normal  = 60 * time.Second // watchpr's default
+		relaxed = 10 * time.Minute // past conflictWindow in a single gap
+	)
+	const conflict = "PR lost mergeability (conflict)"
+
+	yes := snap(MergeYes, "h1", "b1")
+	no := snap(MergeNo, "h1", "b1")
+	pushedNo := snap(MergeNo, "h2", "b1")
+	movedNo := snap(MergeNo, "h1", "b2")
+
+	tests := []struct {
+		name     string
+		interval time.Duration
+		baseline PRState
+		polls    []PRState
+		errs     []error
+		want     string
+	}{
+		{
+			name:     "a push then the recompute's falses is not a conflict",
+			interval: normal, baseline: yes, polls: repeat(pushedNo, 2), want: "",
+		},
+		{
+			name:     "a fast poller rides out the whole recompute after a push",
+			interval: quick, baseline: yes, polls: repeat(pushedNo, 20), want: "",
+		},
+		{
+			name:     "a base move then the recompute's falses is not a conflict",
+			interval: normal, baseline: no, polls: repeat(movedNo, 2), want: "",
+		},
+		{
+			name:     "a base moving under every poll still confirms a conflict",
+			interval: normal, baseline: yes, polls: movingBase(MergeNo, 20), want: conflict,
+		},
+		{
+			name:     "a conflict that predates the watch stays silent forever",
+			interval: relaxed, baseline: no, polls: repeat(no, 50), want: "",
+		},
+		{
+			name:     "a sustained loss after a mergeable baseline alerts",
+			interval: normal, baseline: yes, polls: repeat(no, 3), want: conflict,
+		},
+		{
+			name:     "a mergeable poll breaks the run however long it ran",
+			interval: relaxed, baseline: yes, polls: []PRState{no, yes, no}, want: "",
+		},
+		{
+			name:     "an unknown poll breaks the run however long it ran",
+			interval: relaxed, baseline: yes, polls: []PRState{no, snap(MergeUnknown, "h1", "b1"), no}, want: "",
+		},
+		{
+			name:     "a baseline conflict that clears and returns alerts",
+			interval: relaxed, baseline: no, polls: []PRState{yes, no, no}, want: conflict,
+		},
+		{
+			name:     "a failed poll breaks the run",
+			interval: relaxed, baseline: yes, polls: []PRState{no, no, no},
+			errs: []error{nil, nil, errors.New("HTTP 502"), nil}, want: "",
+		},
+		{
+			name:     "the run restarts after a failed poll and still confirms",
+			interval: relaxed, baseline: yes, polls: []PRState{no, no, no, no},
+			errs: []error{nil, nil, errors.New("HTTP 502"), nil, nil}, want: conflict,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			f := &fakeFetcher{states: append([]PRState{tt.baseline}, tt.polls...), errs: tt.errs}
+			res, err := Watch(f, []PRRef{tt.baseline.Ref}, "unkin-agent",
+				spacedTicks(len(tt.polls), tt.interval), nil, func(PRRef, error) {})
+			if err != nil {
+				t.Fatalf("Watch: %v", err)
+			}
+			if res.Reason != tt.want {
+				t.Fatalf("reason = %q, want %q", res.Reason, tt.want)
+			}
+		})
+	}
+}
+
+// Two refs watched together keep separate runs and separate clocks: a PR being
+// pushed to must neither delay nor trigger the conflict its neighbour is really
+// in, and the alert must name the conflicted one.
+func TestWatchConflictIsolatedFromANeighboursPushes(t *testing.T) {
+	conflicted := PRRef{Owner: "unkin", Repo: "repo", Number: 1}
+	pushing := PRRef{Owner: "unkin", Repo: "repo", Number: 2}
+	snap := func(ref PRRef, m Mergeability, head string) PRState {
+		st := base()
+		st.Ref = ref
+		st.Mergeable = m
+		st.HeadSHA = head
+		return st
+	}
+	f := &perRefFetcher{
+		states: map[string][]PRState{
+			conflicted.String(): {snap(conflicted, MergeYes, "a1"), snap(conflicted, MergeNo, "a1")},
+			pushing.String():    {snap(pushing, MergeYes, "b1"), snap(pushing, MergeYes, "b2"), snap(pushing, MergeYes, "b3")},
+		},
+		calls: map[string]int{},
+	}
+
+	res, err := Watch(f, []PRRef{conflicted, pushing}, "unkin-agent", drainableTicks(4), nil, nil)
+	if err != nil {
+		t.Fatalf("Watch: %v", err)
+	}
+	if res.Reason != "PR lost mergeability (conflict)" {
+		t.Fatalf("reason = %q, want the conflict on %s", res.Reason, conflicted)
+	}
+	if res.Ref != conflicted {
+		t.Errorf("alert names %s, want %s", res.Ref, conflicted)
+	}
+}