fix(agent): gadfly round 3 — the pointer must be all there is

Round 2 fixed this class on isSummaryCloser and left its twin standing
on isWeakFinal. Three of the four findings are that twin, and every one
of them reproduced:

    "That's the chain above. Ship Tuesday."          weak=true
    "See the summary above. Option B wins."          weak=true
    "Anything above 100 boils. See the note above."  weak=true
    "Anything above, say, 40 degrees is a problem."  weak=true

Each of those is 37-58 bytes with the answer sitting right next to the
pointer, and each was disposable — a >=200-byte earlier turn replaced it
and "Ship Tuesday" went in the bin. pointsAbove asks whether a pointer is
PRESENT; disposability needs it to be ALL THERE IS.

bareAbovePointer cuts the reference's own clause — from the end of the
previous sentence through the match — and requires what remains to be
filler: nothing, punctuation, or a throat-clearing "Done —". Cutting the
clause rather than testing position is what makes the other two shapes
safe for free: a mixed terminal keeps its first sentence, and a
comparative "above," with an interjection keeps the rest of its own.

The fourth finding (kimi) is the same idea one level up:
compressionMarkerRe matched anywhere, so "Given the analysis above, the
bottom line is that we need a different vendor" read as an announced
summary when it is a conclusion. The marker must now OPEN a sentence.

Both classes now enforce one rule from opposite ends: a terminal is
disposable only when it carries no answer of its own — proved in
isWeakFinal by nothing standing beside the pointer, and in
isSummaryCloser by the model declaring what stands beside it a
compression.

One of my own round-1b fixtures had to change: "…is above, so there is
no point repeating it" is a pure pointer to a human, but prose after the
reference is indistinguishable from an answer, so the rule correctly
stops treating it as disposable. Replaced with a genuinely bare 96-byte
pointer, still sized so the two recovery bars disagree about it.

Break-check: thirteen mutations, each killed by a named test, control
survives. M12 initially "passed" by failing to compile — reformulated so
it builds, and TestIsWeakFinal/prepositional-then-deictic-with-content
kills it properly.

.gitea/workflows/adversarial-review.yml

@@ -42,17 +42,7 @@ jobs:
     # and cache the reusable-workflow ref, so a moved v1 tag keeps resolving to the
     # stale cached copy. A unique sha forces a cache miss → fresh fetch. Bump this
     # sha to adopt central swarm changes.
-    #
-    # NB: the reviewer IMAGE tag is no longer part of this pin. From @8adeeea on,
-    # the reusable workflow resolves it per run as
-    # `inputs.reviewer_tag || vars.GADFLY_REVIEWER_TAG || 'sha-b850e35'`, so
-    # retagging the reviewer is a user-scope variable edit with no commit here.
-    # The previous pin (@c9dab69d) hardcoded `docker://…gadfly:sha-b37cd09`, a tag
-    # that was never pushed to the registry — every review in this repo died in
-    # ~1s on "failed to resolve reference … not found", which reads exactly like a
-    # review that found nothing. Before bumping this pin again, check the tag its
-    # fallback names is really in the registry.
-    uses: steve/gadfly/.gitea/workflows/review-reusable.yml@8adeeeabe0738a797a1bdfc42c5176ea8ee627e4
+    uses: steve/gadfly/.gitea/workflows/review-reusable.yml@c9dab69d143cb614c1840a5b06d6ffc358f4752d
     # Least privilege: forward only the review secrets (not `secrets: inherit`,
     # which would expose every repo secret). GITEA_TOKEN is the automatic token.
     secrets:

agent/finalize.go

@@ -25,14 +25,21 @@ import (
 //     glm-5.2 "cite" pattern behind mort issue #1418). The citations are real,
 //     useful content — unlike a back-reference — so recover the prior answer and
 //     KEEP the citations, appended below it.
-//   - a bookkeeping closer ("Citations are logged. Short version: …"): the
-//     model acknowledged the citation round and compressed the answer it had
-//     already written into a one-liner (mort run b3cb9ee9 — a 2,089-char answer
-//     shrank to a 153-byte closer at delivery). The compression is strictly
-//     poorer than the front-loaded answer, so recover the prior turn and
-//     DISCARD the closer — but only when the prior turn clearly dwarfs it,
-//     because unlike a back-reference this closer DOES carry answer content
-//     (see modeSummary).
+//   - a deferring closer ("Citations are logged. Short version: …", "Done —
+//     that's the full chain above. Short version: …"): the model points at the
+//     answer it had already written and compresses it into a one-liner (mort
+//     run b3cb9ee9 — a 2,089-char answer shrank to a 153-byte closer; mort
+//     issue #1611 — a 2,245-char analysis shrank to 220 bytes). The
+//     compression is strictly poorer than the front-loaded answer, so recover
+//     the prior turn and DISCARD the closer — but only when the prior turn
+//     clearly dwarfs it, because unlike a bare back-reference this closer DOES
+//     carry answer content (see modeSummary).
+//
+// The last two shapes share one signal — the terminal DEFERS: it tells us the
+// answer is somewhere the user cannot see (pointsAbove, or the bookkeeping
+// ack). They differ only in whether the terminal also carries content of its
+// own, so a new deferral phrasing added to pointsAbove is covered in both the
+// bare and the "+ compression" variant at once.
 //
 // A citations addendum is tested first and wins over the other two (a short
 // terminal can match more than one shape), so its links are never discarded.
@@ -110,9 +117,109 @@ const (
 
 // backRefRe matches a terminal turn that merely points back to an earlier
 // message instead of stating the answer ("(Already answered above.)",
-// "see above", "as I said", ...).
+// "see above", "as I said", ...). It is a list of fixed phrasings; aboveRefRe
+// covers the open-ended half of the same family.
 var backRefRe = regexp.MustCompile(`(?i)(already answered|see above|as (i )?(said|mentioned|stated|noted)|answered (that )?above|per my (previous|earlier))`)
 
+// aboveRefRe matches a DEICTIC "above" — one pointing at earlier text rather
+// than serving as a preposition. What follows the word separates the two uses:
+// the deictic use ends its clause ("that's the full chain above.", "as shown
+// above,", a line that simply ends in "above"), while the preposition always
+// continues into a noun phrase ("above 100°C", "above the fold", "above all,
+// the ..."). Only the clause-final form matches, so the open-ended half of the
+// back-reference family is covered without enumerating every phrasing a model
+// might invent — backRefRe's fixed list kept missing new ones (mort issue
+// #1611: "Done — that's the full chain above.").
+//
+// The terminator set deliberately excludes the ASCII hyphen. `\b` holds
+// between "above" and "-", so a literal '-' in the class made every
+// hyphenated compound — "above-average", "above-board", "above-ground" —
+// read as a clause-final deictic and put a legitimate short answer at risk of
+// being discarded. The em dash stays: a model writes "…above — see the
+// links", never "above-" as a separator. CR is listed alongside LF so a
+// CRLF transcript does not quietly lose every line-final "above".
+var aboveRefRe = regexp.MustCompile(`(?i)\babove\b[ \t]*([.,;:!?)\]"'’”—]|\r|\n|$)`)
+
+// pointsAbove reports whether a deictic "above" appears in the terminal's
+// OPENING. The offset bound is what makes a bare "above" safe to key on: with
+// almost no text before it in THIS message, the reference cannot be pointing
+// at the message's own content, so it must point at a turn the user never saw
+// (the harness delivers only the final turn).
+//
+// This is the DEFERRAL SIGNAL SHARED by both recovery shapes — isWeakFinal and
+// isSummaryCloser both call it, so a widening here reaches the bare closer and
+// the "+ compression" closer at once. Its sibling backRefRe is deliberately
+// NOT shared: those fixed phrases are matched anywhere in the text, which is
+// only safe under isWeakFinal's 120-byte cap. Folding the two into one
+// predicate for tidiness would hand isSummaryCloser an unanchored match across
+// 300 bytes — widening the gate, not deduplicating it.
+func pointsAbove(t string) bool {
+	loc := aboveRefRe.FindStringIndex(t)
+	return loc != nil && loc[0] <= backRefHeadChars
+}
+
+// bareAbovePointer reports whether the terminal is a deictic back-reference and
+// essentially NOTHING ELSE — the form isWeakFinal may discard outright.
+//
+// pointsAbove alone is not enough for that, because a pointer can share a short
+// terminal with the answer: "That's the chain above. Ship Tuesday." is 37 bytes
+// and the decision is the four words the pointer is not. Discarding it in
+// favour of an earlier turn throws away the only thing the user needed. Same
+// shape as the summary-closer fix — a pointer says where the detail is, it does
+// not say the text beside it is disposable.
+//
+// So the reference's own clause is cut out and whatever remains must be filler:
+// nothing, punctuation, or a throat-clearing "Done —". Cutting the CLAUSE (from
+// the end of the previous sentence through the reference) rather than testing
+// position is also what makes a mixed terminal safe — "Anything above 100
+// boils. See the note above." keeps its first sentence and is correctly not
+// bare, and a comparative "above," with an interjection after it keeps the rest
+// of its own sentence for the same reason.
+func bareAbovePointer(t string) bool {
+	loc := aboveRefRe.FindStringIndex(t)
+	if loc == nil || loc[0] > backRefHeadChars {
+		return false
+	}
+	start := 0
+	if k := strings.LastIndexAny(t[:loc[0]], ".!?\n"); k >= 0 {
+		start = k + 1
+	}
+	rest := strings.TrimSpace(t[:start]) + " " + strings.TrimSpace(t[loc[1]:])
+	return bareRemainderRe.MatchString(strings.Trim(rest, pointerResidueCutset))
+}
+
+// pointerResidueCutset is trimmed from both ends of what survives cutting the
+// pointer's clause — the brackets, quotes, and punctuation a model wraps a
+// back-reference in ("(Already answered above.)").
+const pointerResidueCutset = " \t\r\n.,;:!?()[]{}\"'“”‘’*_-—"
+
+// bareRemainderRe matches a remainder that carries no answer: empty, or only
+// the filler a closer opens with. Shares fillerWords with summaryPreface so the
+// two lists cannot drift.
+var bareRemainderRe = regexp.MustCompile(`(?i)^(` + fillerWords + `[\s,.!:—-]*)*$`)
+
+// compressionMarkerRe matches a model announcing that what follows is the
+// short form of something longer ("Short version: …", "TL;DR: …", "In short,
+// …"). It is the second half of the deictic summary-closer test: the pointer
+// says the full answer is elsewhere, and this says the text beside it is a
+// condensation rather than new reasoning.
+//
+// Both halves are required, because a deictic pointer alone does not mean the
+// terminal is disposable. "Given the analysis above, I recommend option B
+// because X" opens with a pointer and then states a CONCLUSION the earlier
+// turn never contained — discarding it in favour of that turn would throw away
+// the answer. A compression marker is the model telling us the opposite.
+//
+// A marker WITHOUT a pointer stays out of scope, as summaryCloserRe's own
+// comment explains: a user who asked for brevity is answered with exactly that
+// shape.
+// The marker must OPEN a sentence. Mid-sentence the same words are ordinary
+// prose carrying new content — "Given the analysis above, the bottom line is
+// that we need a different vendor" states a conclusion, it does not announce a
+// condensation — and treating that as disposable is the very failure the
+// two-part test exists to prevent.
+var compressionMarkerRe = regexp.MustCompile(`(?i)(^|[.!?:;—]\s*|\n\s*)(short version|shorter version|short answer|tl;?dr|in short|in brief|in summary|in sum|bottom line|net[- ]net|the gist)\b`)
+
 // summaryCloserRe matches a terminal turn that OPENS with a bookkeeping
 // acknowledgment of the citation round — "Citations are logged.", "Sources
 // cited.", "Logged the citations." — the shape a model produces when it
@@ -128,7 +235,11 @@ var backRefRe = regexp.MustCompile(`(?i)(already answered|see above|as (i )?(sai
 // behavior (fail closed). Assembled from named fragments so the alternations
 // stay legible and extendable.
 const (
-	summaryPreface = `((done|all set|ok(ay)?)[\s,.!:—-]+)?` // optional "Done —" style opener
+	// fillerWords are the throat-clearing tokens a closer opens with. Shared
+	// with bareRemainderRe, which has to recognise exactly the same set as
+	// "not answer content".
+	fillerWords    = `(done|all set|ok(ay)?)`
+	summaryPreface = `(` + fillerWords + `[\s,.!:—-]+)?` // optional "Done —" style opener
 	summaryNouns   = `(citations?|sources?|references?|claims?)`
 	// "all" appears here AND in summaryArticle on purpose: as a quantifier
 	// between noun and verb ("Citations all logged.") and as a determiner
@@ -180,6 +291,15 @@ const (
 	// genuine final answer that merely contains "as I said" mid-sentence is
 	// longer than this, so it is never treated as weak.
 	weakFinalMaxChars = 120
+	// backRefHeadChars bounds how far into the terminal a deictic "above" may
+	// sit and still read as pointing OUTSIDE this message (see pointsAbove).
+	// It IS weakFinalMaxChars — the same guard ("there is not enough text
+	// before the reference for it to be pointing at content inside this
+	// turn"), expressed as an offset because a summary closer carries a
+	// compression AFTER the pointer and so is not itself short. Defined by
+	// reference, not by repeating the literal: tuning the weak cap without the
+	// offset following it would split one rule into two.
+	backRefHeadChars = weakFinalMaxChars
 	// recoverMinChars: a prior assistant turn this long is treated as a real
 	// answer regardless of how it opens (the preamble filter is not applied at
 	// this length — see isSubstantiveAnswer).
@@ -203,13 +323,23 @@ const (
 )
 
 // isWeakFinal reports whether a terminal turn's text fails to stand on its own
-// as the answer: empty/whitespace, or a short pure back-reference.
+// as the answer: empty/whitespace, or a short pure back-reference. The length
+// cap is what keeps a genuine answer that merely contains a back-reference
+// phrase mid-sentence out of the class; past the cap a deferring terminal is
+// isSummaryCloser's business, under the stricter dwarf bar.
+//
+// The deictic half additionally demands that the pointer be the WHOLE message
+// (bareAbovePointer), not merely present in it. Both classes now enforce the
+// same rule from opposite ends: a terminal is only disposable when it carries
+// no answer of its own — proved here by there being nothing beside the pointer,
+// and in isSummaryCloser by the model declaring what is beside it a
+// compression.
 func isWeakFinal(s string) bool {
 	t := strings.TrimSpace(s)
 	if t == "" {
 		return true
 	}
-	return len(t) <= weakFinalMaxChars && backRefRe.MatchString(t)
+	return len(t) <= weakFinalMaxChars && (backRefRe.MatchString(t) || bareAbovePointer(t))
 }
 
 // isCitationsOnly reports whether a terminal turn is essentially just a
@@ -238,19 +368,38 @@ func isCitationsOnly(s string) bool {
 	return len(residue) <= len(t)/citationDominatedDivisor
 }
 
-// isSummaryCloser reports whether a terminal turn is a bookkeeping closer: it
-// opens with a complete "citations are logged"-style ack sentence (see
-// summaryCloserRe) and is short enough that whatever follows the ack can only
-// be a compression of an earlier, fuller answer. Whether that fuller answer
-// actually exists is modeSummary's job — the dwarf ratio in
-// isSubstantiveAnswer keeps a matching closer in place when nothing earlier
-// clearly outweighs it.
+// isSummaryCloser reports whether a terminal turn defers to an earlier answer
+// and is short enough that whatever follows the deferral can only be a
+// compression of it. Two openers qualify:
+//
+//   - a complete bookkeeping ack sentence — "Citations are logged." — which is
+//     summaryCloserRe, and carries no answer content of its own;
+//   - a deictic back-reference in the opening PLUS a compression marker —
+//     mort issue #1611's "Done — that's the full chain above. Short version:
+//     …" — which the ack shape alone did not cover.
+//
+// The second opener needs both halves. A pointer on its own does not make a
+// terminal disposable: "Given the analysis above, I recommend option B because
+// X" points backwards and then states a conclusion the earlier turn never
+// contained, and replacing it with that turn would discard the answer. The
+// compression marker is the model saying the opposite — that what follows is
+// the short form of something it already wrote.
+//
+// Whether the fuller answer actually exists is modeSummary's job — the dwarf
+// ratio in isSubstantiveAnswer keeps a matching closer in place when nothing
+// earlier clearly outweighs it.
+//
+// pointsAbove is used here; its sibling backRefRe is NOT. Those fixed phrases
+// are matched anywhere in the text, and a 300-byte closer has room for a real
+// answer that merely mentions "as I said" mid-sentence. pointsAbove is
+// offset-bounded, so it stays anchored to the opening.
 func isSummaryCloser(s string) bool {
 	t := strings.TrimSpace(s)
 	if t == "" || len(t) > summaryCloserMaxChars {
 		return false
 	}
-	return summaryCloserRe.MatchString(t)
+	return summaryCloserRe.MatchString(t) ||
+		(pointsAbove(t) && compressionMarkerRe.MatchString(t))
 }
 
 // lastSubstantiveAssistantText scans msgs newest→oldest (skipping the terminal

agent/finalize_test.go

@@ -26,6 +26,23 @@ func TestIsWeakFinal(t *testing.T) {
 		{"crisp-yes", "Yes.", false},
 		{"crisp-status", "It's down, restarting now.", false},
 		{"long-with-as-i-said", long, false}, // >120 chars: not weak despite the phrase
+
+		// The deictic half of the class, inside the length cap. A pointer only
+		// counts when it is ALL there is — see bareAbovePointer.
+		{"bare-above-pointer", "That's the full chain above.", true},
+		{"above-pointer-in-parens", "(the breakdown is above)", true},
+		{"bare-pointer-with-filler-opener", "Done. See the chain above.", true},
+
+		// A pointer sharing the terminal with real content is NOT weak: the
+		// content beside it is the answer, and discarding the terminal would
+		// throw it away.
+		{"pointer-plus-a-decision", "That's the chain above. Ship Tuesday.", false},
+		{"pointer-plus-a-choice", "See the summary above. Option B wins.", false},
+		{"pointer-mid-sentence-then-answer", "As shown above, the answer is sixty minutes.", false},
+		{"prepositional-then-deictic-with-content", "Anything above 100 boils. See the note above.", false},
+		{"comparative-with-an-interjection", "Anything above, say, 40 degrees is a problem for the pump.", false},
+		{"prepositional-above-not-weak", "Anything above 100 degrees boils off.", false},
+		{"1611-closer-too-long-for-weak", closer1611, false}, // 220 bytes: isSummaryCloser's job
 	}
 	for _, c := range cases {
 		t.Run(c.name, func(t *testing.T) {
@@ -36,6 +53,91 @@ func TestIsWeakFinal(t *testing.T) {
 	}
 }
 
+// closer1611 is the verbatim terminal turn from mort run
+// 8eea3e82-b61b-4174-9750-9aa2f4bde4d4 (issue #1611): the model front-loaded a
+// 2,245-char analysis into the cite-call turn and closed with this 220-byte
+// pointer-plus-compression. Too long for the weak-final cap and carrying no
+// citations ack, it matched none of the three original shapes and was
+// delivered verbatim — the user saw a summary referring to a "chain above"
+// that had never been posted.
+const closer1611 = "Done — that's the full chain above. Short version: it's not one incident, it's the confluence of the Iran war, the Epstein files, and three ex-allies now openly plotting a third-party movement that finally set him off."
+
+// analysis1611 stands in for that run's front-loaded analysis: long enough to
+// dwarf closer1611 (>3x its 220 bytes). Shared by the finalOutput table and
+// the end-to-end Run test so the two cannot drift apart.
+func analysis1611() string {
+	return strings.TrimSpace(strings.Repeat("The break was the Iran strikes, then the Epstein files. ", 12))
+}
+
+func TestPointsAbove(t *testing.T) {
+	cases := []struct {
+		name string
+		in   string
+		want bool
+	}{
+		// Deictic: "above" ends its clause, so it points at earlier text.
+		{"1611-verbatim", closer1611, true},
+		{"sentence-final", "That's the full chain above.", true},
+		{"comma", "As shown above, the answer is 60 minutes.", true},
+		{"end-of-string", "The full breakdown is above", true},
+		{"line-final", "Everything is above\n\nShort version: yes.", true},
+		{"line-final-crlf", "Everything is above\r\nShort version: yes.", true},
+		{"crlf-at-end", "The full breakdown is above\r\n", true},
+		{"closing-paren", "(the detail is above).", true},
+		{"semicolon", "It's above; the short answer is no.", true},
+
+		// Prepositional: "above" continues into a noun phrase.
+		{"above-a-number", "Anything above 100 degrees boils off.", false},
+		{"above-the-fold", "The banner sits above the fold on every page.", false},
+		{"above-all", "Above all, keep the deploy green.", false},
+		{"above-average", "Turnout was above average in three counties.", false},
+
+		// Hyphenated compounds. \b holds between "above" and "-", so a literal
+		// '-' in the terminator class makes all of these read as deictic. The
+		// space-separated cases above do NOT cover this: they are a different
+		// character, and one passed while the other was broken.
+		{"hyphen-above-average", "Turnout was above-average in three counties.", false},
+		{"hyphen-above-board", "The deal was above-board from the start.", false},
+		{"hyphen-above-ground", "Run the above-ground cable along the fence.", false},
+		{"hyphen-above-mentioned", "The above-mentioned findings are attached.", false},
+
+		{"no-above-at-all", "42", false},
+		{"empty", "", false},
+
+		// Offset bound: past backRefHeadChars there IS enough text before the
+		// reference for it to be pointing inside this same message. The
+		// lengths are LITERALS, not backRefHeadChars +/- n: a case sized from
+		// the constant it is meant to pin moves with it, and a break-check
+		// that widened the bound to 100000 sailed straight through.
+		{"late-reference-not-a-pointer", strings.Repeat("x", 200) + " as shown above.", false},
+		// The exact boundary, both sides: "above" starts at index 120 (allowed,
+		// the bound is <=) and at 121 (rejected). 119/120 x's plus the space
+		// puts the 'a' on 120/121 — the separator is needed because \b will not
+		// hold between "x" and "above".
+		{"reference-exactly-at-the-bound", strings.Repeat("x", 119) + " above.", true},
+		{"reference-one-past-the-bound", strings.Repeat("x", 120) + " above.", false},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			if got := pointsAbove(c.in); got != c.want {
+				t.Errorf("pointsAbove(%q) = %v, want %v", c.in, got, c.want)
+			}
+		})
+	}
+
+	// The two bounds are ONE guard expressed two ways (see backRefHeadChars).
+	// Pinned here so decoupling them is a test failure, not a silent drift.
+	if backRefHeadChars != weakFinalMaxChars {
+		t.Errorf("backRefHeadChars = %d, weakFinalMaxChars = %d: the offset bound and the "+
+			"weak-final cap are the same guard and must stay equal",
+			backRefHeadChars, weakFinalMaxChars)
+	}
+	if weakFinalMaxChars != 120 {
+		t.Errorf("weakFinalMaxChars = %d, want 120: the literal-length cases in this table "+
+			"pin the bound at 120 and must be resized with it", weakFinalMaxChars)
+	}
+}
+
 func TestIsCitationsOnly(t *testing.T) {
 	cases := []struct {
 		name string
@@ -102,6 +204,27 @@ func TestIsSummaryCloser(t *testing.T) {
 		{"mentions-citations-midsentence", "The paper's citations are what got it retracted.", false},
 		{"crisp-number", "42", false},
 		{"over-cap", "Citations are logged. " + strings.Repeat("The long version has many more details worth keeping. ", 6), false}, // >300: too substantial to replace
+
+		// A deictic back-reference opener also qualifies — the #1611 shape,
+		// which carries no citations ack at all.
+		{"1611-verbatim", closer1611, true},
+		{"above-pointer-plus-tldr", "That's the whole picture above. In short: the merger fell through.", true},
+		{"prepositional-above-is-not-a-closer", "Anything above 100 degrees boils off, which is why the sample evaporated.", false},
+
+		// The compression marker has to OPEN a sentence. Mid-sentence the same
+		// words are prose carrying NEW content, not an announcement that what
+		// follows is a condensation.
+		{"marker-mid-sentence-is-new-content", "Given the analysis above, the bottom line is that we need a different vendor entirely.", false},
+		{"marker-mid-sentence-in-short", "That is the chain above, and in short supply of alternatives we went with B.", false},
+		{"marker-opening-after-a-colon", "That's the chain above: in short, the merger fell through.", true},
+
+		// A deictic pointer WITHOUT a compression marker is not a summary
+		// closer: these state a conclusion the earlier turn never contained,
+		// so replacing them with that turn would discard the answer.
+		{"pointer-then-a-recommendation", "Given the analysis above, I recommend option B: it is the only one that survives a regional outage.", false},
+		{"pointer-then-a-decision", "Based on everything above, we should ship Tuesday and hold the migration until the following sprint.", false},
+		{"pointer-then-a-new-caveat", "That is the chain above. One thing it misses: the Senate vote is scheduled before any of this takes effect.", false},
+		{"1611-over-cap", closer1611 + " " + strings.Repeat("Plenty more detail worth keeping here. ", 4), false}, // >300
 	}
 	for _, c := range cases {
 		t.Run(c.name, func(t *testing.T) {
@@ -147,6 +270,25 @@ func TestFinalOutput(t *testing.T) {
 	// Matches BOTH the summary ack and backRefRe, within the 120-byte weak cap,
 	// and long enough (>~92 bytes) that longAnswer would fail the summary bar.
 	bothMatchCloser := "Citations are logged. As I mentioned above, the full detail on the money sources is in my earlier message."
+	// The #1611 pair: a front-loaded analysis that dwarfs its 220-byte closer.
+	analysis := analysis1611()
+	// A 96-byte BARE deictic closer: nothing but filler and the pointer's own
+	// clause, inside the weak-final cap (120), and sized so the two bars
+	// actually DISAGREE — 3x96 = 288 > longAnswer's 275, so the summary
+	// closer's dwarf ratio would reject longAnswer while the modeBackRef bar
+	// (>=200 bytes, no ratio) accepts it. A shorter closer would pass under
+	// either bar and prove nothing. It must also stay BARE: an earlier draft
+	// ended "…so there is no point repeating it", and prose after the
+	// reference is indistinguishable from an answer, so bareAbovePointer
+	// correctly stopped treating it as disposable.
+	shortAbovePointer := "Done — that is the complete chain, start to finish, exactly as I worked it out for you, above."
+	// A deictic pointer followed by a NEW conclusion (no compression marker):
+	// >120 bytes so isWeakFinal cannot claim it, and it must not be treated as
+	// a summary closer either.
+	pointerThenConclusion := "Given the analysis above, I recommend option B: it is the only one that survives a regional outage without a manual failover step."
+	// A terminal using "above" as a PREPOSITION — not a back-reference, so it
+	// must survive verbatim next to a dwarfing prior turn.
+	prepositionalTerminal := "Anything above 100 degrees boils off, which is exactly why the sample evaporated overnight in the unsealed tray."
 
 	tests := []struct {
 		name     string
@@ -387,6 +529,99 @@ func TestFinalOutput(t *testing.T) {
 			terminal: b3cb9ee9Closer,
 			want:     hugeAnswer,
 		},
+		{
+			// mort issue #1611: a pointer-plus-compression closer with no
+			// citations ack. The 2,245-char analysis was front-loaded into the
+			// cite turn; the closer pointed at a "chain above" the user never
+			// saw. Recover the analysis and discard the closer.
+			name: "above-pointer closer discarded when the front-loaded answer dwarfs it",
+			msgs: []llm.Message{
+				llm.UserText("what set off the Truth Social rant?"),
+				asst(analysis, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(closer1611),
+			},
+			terminal: closer1611,
+			want:     analysis,
+		},
+		{
+			// The dwarf ratio governs the new opener too: a prior turn that is
+			// longer but not clearly the fuller original (here ~275 bytes vs a
+			// 220-byte closer, under 3x) must not displace a closer that
+			// carries real answer content.
+			name: "above-pointer closer kept when the prior turn does not dwarf it",
+			msgs: []llm.Message{
+				llm.UserText("q?"),
+				asst(longAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(closer1611),
+			},
+			terminal: closer1611,
+			want:     closer1611,
+		},
+		{
+			// A prepositional "above" is not a back-reference: this terminal
+			// stands on its own and must be returned verbatim even though a
+			// much longer prior turn exists.
+			name: "prepositional above is not hijacked by a longer prior turn",
+			msgs: []llm.Message{
+				llm.UserText("why did the sample evaporate?"),
+				asst(hugeAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(prepositionalTerminal),
+			},
+			terminal: prepositionalTerminal,
+			want:     prepositionalTerminal,
+		},
+		{
+			// A SHORT deictic closer takes the modeBackRef bar, not the summary
+			// closer's mandatory dwarf ratio — even though it carries a scrap
+			// of answer content ("Done."). Deliberate, and the same contract a
+			// short "see above" closer has always had: within the 120-byte cap
+			// there is no room for both a pointer and a real answer, so a
+			// >=200-byte prior turn wins without having to be 3x. Here the
+			// ratio would demand ~330 bytes and wrongly keep the pointer.
+			// (gadfly/sonnet flagged the asymmetry; this pins it.)
+			name: "short above-pointer closer uses the back-ref bar, not the dwarf ratio",
+			msgs: []llm.Message{
+				llm.UserText("q?"),
+				asst(longAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(shortAbovePointer),
+			},
+			terminal: shortAbovePointer,
+			want:     longAnswer,
+		},
+		{
+			// The isWeakFinal twin of the case below: a SHORT pointer that
+			// shares its terminal with the decision. Before bareAbovePointer
+			// this was weak, so a >=200-byte prior turn replaced it and "Ship
+			// Tuesday" — the only thing the user needed — was discarded.
+			name: "short above-pointer sharing the terminal with the answer is not discarded",
+			msgs: []llm.Message{
+				llm.UserText("when do we ship?"),
+				asst(hugeAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst("That's the chain above. Ship Tuesday."),
+			},
+			terminal: "That's the chain above. Ship Tuesday.",
+			want:     "That's the chain above. Ship Tuesday.",
+		},
+		{
+			// A pointer plus a NEW conclusion is not a compression, so it must
+			// survive verbatim even though a much longer prior turn exists —
+			// otherwise the recommendation is thrown away in favour of the
+			// analysis it was drawn from.
+			name: "above-pointer closer with a new conclusion is not discarded",
+			msgs: []llm.Message{
+				llm.UserText("which option?"),
+				asst(hugeAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(pointerThenConclusion),
+			},
+			terminal: pointerThenConclusion,
+			want:     pointerThenConclusion,
+		},
 		{
 			// A closer matching BOTH the ack shape and a back-reference
 			// carries no answer content, so the back-ref test must win and the
@@ -536,3 +771,34 @@ func TestRun_RecoversFrontLoadedAnswerWithCitations(t *testing.T) {
 		t.Errorf("model calls = %d, want 2 (no extra nudge turn)", n)
 	}
 }
+
+// TestRun_RecoversFrontLoadedAnswerOverAboveRefCloser reproduces mort issue
+// #1611 end-to-end: the model front-loads its analysis into the cite-call turn
+// and closes with a pointer at that invisible text plus a one-line
+// compression. The delivered output must be the front-loaded analysis, with no
+// extra model call.
+func TestRun_RecoversFrontLoadedAnswerOverAboveRefCloser(t *testing.T) {
+	analysis := analysis1611()
+	fp := fake.New("fp")
+	fp.Enqueue("test-model",
+		fake.ReplyWith(llm.Response{
+			Parts:        []llm.Part{llm.Text(analysis)},
+			ToolCalls:    []llm.ToolCall{{ID: "c1", Name: "cite", Arguments: json.RawMessage(`{}`)}},
+			FinishReason: llm.FinishToolCalls,
+			Usage:        llm.Usage{InputTokens: 10, OutputTokens: 5},
+		}),
+		fake.Reply(closer1611),
+	)
+
+	a := New(newModel(t, fp), "sys", WithToolbox(citeToolbox(t)))
+	res, err := a.Run(context.Background(), "what set off the Truth Social rant?")
+	if err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+	if res.Output != analysis {
+		t.Errorf("Output = %q, want recovered front-loaded analysis %q", res.Output, analysis)
+	}
+	if n := len(fp.Calls()); n != 2 {
+		t.Errorf("model calls = %d, want 2 (no extra nudge turn)", n)
+	}
+}