fix(agent): gadfly round 1 — user-boundary scan, back-ref precedence, regex legibility

Two behavioral fixes from the review:

- modeSummary's backward scan now stops at the most recent user message.
  With the dwarf ratio rejecting the current turn's 1x-3x answer, the old
  unbounded scan could walk into WithHistory content and resurrect a stale
  answer to a DIFFERENT question — strictly worse than keeping the closer
  (opus, correctness). Other modes keep their historical unbounded scan.
- A terminal matching BOTH the ack shape and a back-reference is now
  classified back-ref: it carries no answer content, so the looser bar is
  the right one (opus, error-handling).

Plus the nits: summaryCloserRe assembled from named fragments, the leading
marker class gains '+' (parity with citationLabelRe), verb-first form takes
'all the', dwarf ratio hoisted into one named local, and the 151-vs-153
char/byte comment inaccuracy corrected.

Co-Authored-By: Claude Fable 5 <[email protected]>

agent/finalize.go

@@ -28,15 +28,18 @@ import (
 //   - 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 151 chars at delivery). The compression is strictly poorer than
+//     shrank to a 153-byte closer at delivery). The compression is strictly
-//     the front-loaded answer, so recover the prior turn and DISCARD the
+//     poorer than the front-loaded answer, so recover the prior turn and
-//     closer — but only when the prior turn clearly dwarfs it, because unlike a
+//     DISCARD the closer — but only when the prior turn clearly dwarfs it,
-//     back-reference this closer DOES carry answer content (see modeSummary).
+//     because unlike a back-reference this closer DOES carry answer content
+//     (see modeSummary).
 //
 // 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;
+// terminal can match more than one shape), so its links are never discarded.
-// the summary closer is tested before the plain weak-final test so the
+// The back-reference test wins over the summary-closer test: a terminal
-// stricter recovery bar applies when both match. When the terminal text stands
+// matching both ("Citations are logged. As I said above…") carries no answer
+// content of its own, so the looser back-ref recovery bar — not the summary
+// closer's dwarf ratio — is the right one. When the terminal text stands
 // on its own it is returned unchanged; when it is degenerate but nothing
 // better can be recovered, it is returned as-is (a compressed answer still
 // beats nothing).
@@ -48,9 +51,11 @@ func finalOutput(msgs []llm.Message, terminal string) string {
 	switch {
 	case isCitationsOnly(terminal):
 		mode = modeCitations
+	case isWeakFinal(terminal):
+		// modeBackRef
 	case isSummaryCloser(terminal):
 		mode = modeSummary
-	case !isWeakFinal(terminal):
+	default:
 		return terminal
 	}
 	rec, ok := lastSubstantiveAssistantText(msgs, terminal, mode)
@@ -95,8 +100,11 @@ const (
 	// modeSummary: the terminal acknowledges the citation round and may carry
 	// a short compression of the front-loaded answer. Unlike a back-reference
 	// it DOES contain answer content, so it is only replaced when a prior turn
-	// clearly dwarfs it — the ratio is mandatory at every length, and the
+	// clearly dwarfs it — the ratio is mandatory at every length, the recovery
-	// closer is discarded (its content is a strict subset of what it replaced).
+	// scan stops at the most recent user message (a compression can only be of
+	// THIS turn's answer; never resurrect one from an earlier question), and
+	// the closer is discarded (its content is a strict subset of what it
+	// replaced).
 	modeSummary
 )
 
@@ -117,8 +125,20 @@ var backRefRe = regexp.MustCompile(`(?i)(already answered|see above|as (i )?(sai
 // ("Short version: no.") is deliberately out of scope — a user who asked for
 // brevity would be answered with exactly that shape, and misclassifying it
 // would hijack a legitimate answer; an unmatched closer merely keeps today's
-// behavior (fail closed).
+// behavior (fail closed). Assembled from named fragments so the alternations
-var summaryCloserRe = regexp.MustCompile(`(?i)^[\s>#*_-]*((done|all set|ok(ay)?)[\s,.!:—-]+)?(((all|the)\s+)?(citations?|sources?|references?|claims?)\s+((are|were|have\s+been|all)\s+)*(logged|recorded|cited|saved|noted|captured|filed)|logged\s+((all|the)\s+)*(citations?|sources?|references?))[.!]`)
+// stay legible and extendable.
+const (
+	summaryLead    = `[\s>#*_+-]*`                          // leading markdown/list markers, as in citationLabelRe
+	summaryPreface = `((done|all set|ok(ay)?)[\s,.!:—-]+)?` // optional "Done —" style opener
+	summaryNouns   = `(citations?|sources?|references?|claims?)`
+	summaryCopulas = `((are|were|have\s+been|all)\s+)*`
+	summaryVerbs   = `(logged|recorded|cited|saved|noted|captured|filed)`
+	summaryArticle = `((all|the)\s+)*` // star, not ?: "Logged all the citations."
+)
+
+var summaryCloserRe = regexp.MustCompile(`(?i)^` + summaryLead + summaryPreface +
+	`(` + summaryArticle + summaryNouns + `\s+` + summaryCopulas + summaryVerbs +
+	`|logged\s+` + summaryArticle + summaryNouns + `)[.!]`)
 
 // preambleRe matches intent-announcing prefixes ("Let me search...", "I'll
 // check...") so a preamble is never mistaken for the answer during recovery.
@@ -165,9 +185,10 @@ const (
 	// "Source:" and cites a URL mid-sentence is not mistaken for a bare list.
 	citationDominatedDivisor = 3
 	// summaryCloserMaxChars bounds a summary closer: room for the ack sentence
-	// plus a couple of compression sentences (the b3cb9ee9 closer was 151).
+	// plus a couple of compression sentences (the b3cb9ee9 closer was 153
-	// Beyond this the "short version" is substantial enough that replacing it
+	// bytes — Go len(), which is what every threshold here compares). Beyond
-	// risks losing content the front-loaded turn never had.
+	// this the "short version" is substantial enough that replacing it risks
+	// losing content the front-loaded turn never had.
 	summaryCloserMaxChars = 300
 )
 
@@ -230,6 +251,16 @@ func lastSubstantiveAssistantText(msgs []llm.Message, terminal string, mode reco
 	tt := strings.TrimSpace(terminal)
 	for i := len(msgs) - 1; i >= 0; i-- {
 		m := msgs[i]
+		if mode == modeSummary && m.Role == llm.RoleUser {
+			// A summary closer compresses THIS turn's front-loaded answer, so
+			// the scan must not cross into an earlier question: once the dwarf
+			// ratio has rejected the current turn's text, walking further back
+			// would resurrect a stale answer to a DIFFERENT question — strictly
+			// worse than keeping the closer. (A mid-run steer message is also a
+			// user-role boundary; recovery then fails closed, which is fine.)
+			// The other modes keep their historical unbounded scan.
+			break
+		}
 		if m.Role != llm.RoleAssistant {
 			continue
 		}
@@ -261,7 +292,8 @@ func lastSubstantiveAssistantText(msgs []llm.Message, terminal string, mode reco
 // addendum is not a rival answer, so its length is irrelevant; a summary
 // closer already proved the ratio above).
 func isSubstantiveAnswer(txt, terminal string, mode recoveryMode) bool {
-	if mode == modeSummary && len(txt) < recoverRatio*len(terminal) {
+	dwarfs := len(txt) >= recoverRatio*len(terminal)
+	if mode == modeSummary && !dwarfs {
 		return false
 	}
 	if len(txt) >= recoverMinChars {
@@ -270,5 +302,5 @@ func isSubstantiveAnswer(txt, terminal string, mode recoveryMode) bool {
 	if len(txt) < recoverFloorChars || preambleRe.MatchString(txt) {
 		return false
 	}
-	return mode != modeBackRef || len(txt) >= recoverRatio*len(terminal)
+	return mode != modeBackRef || dwarfs
 }

agent/finalize_test.go

@@ -73,8 +73,9 @@ func TestIsCitationsOnly(t *testing.T) {
 }
 
 // b3cb9ee9Closer is the verbatim terminal turn from mort run b3cb9ee9: a
-// 2,089-char answer was front-loaded into the cite-call turn and this 151-char
+// 2,089-char answer was front-loaded into the cite-call turn and this 153-byte
-// compression was all that got delivered.
+// compression (151 runes — the em dash is 3 bytes, and byte length is what the
+// thresholds compare) was all that got delivered.
 const b3cb9ee9Closer = "Citations are logged. Short version: the bulk of that ~$64M was AIPAC and dark-money super PACs, not the party committees — and it still wasn't enough."
 
 func TestIsSummaryCloser(t *testing.T) {
@@ -91,6 +92,8 @@ func TestIsSummaryCloser(t *testing.T) {
 		{"done-prefix", "Done — citations logged.", true},
 		{"ack-then-tldr", "Sources have been recorded! TL;DR: the GPU was the bottleneck.", true},
 		{"references-noted", "References noted. In short: yes, it ships Tuesday.", true},
+		{"plus-list-marker", "+ Citations are logged.", true},
+		{"logged-all-the", "Logged all the citations.", true},
 
 		{"empty", "", false},
 		{"ack-continues-midsentence", "The citations are recorded in the court transcript, which shows the filing dates.", false},
@@ -141,6 +144,9 @@ func TestFinalOutput(t *testing.T) {
 	// A >=200-byte real answer that merely OPENS with a conversational word
 	// ("Sure,"). The preamble filter must NOT veto it (gadfly regression guard).
 	longConversationalAnswer := "Sure, here's the rundown: it currently sells for about $2,700 used on eBay, typically $2,400 to $2,900 depending on condition and bundle, with the sealed Founders Edition commanding the top of that range while used AIB cards go a bit lower."
+	// 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."
 
 	tests := []struct {
 		name     string
@@ -347,6 +353,56 @@ func TestFinalOutput(t *testing.T) {
 			terminal: b3cb9ee9Closer,
 			want:     b3cb9ee9Closer,
 		},
+		{
+			// Gadfly (opus, correctness): the modeSummary scan must stop at the
+			// most recent user message. Here the current turn's answer sits in
+			// the 1x-3x band (rejected by the ratio) while a dwarfing answer to
+			// a DIFFERENT question sits in history — resurrecting it would be
+			// strictly worse than keeping the closer.
+			name: "summary closer never resurrects a stale answer across the user boundary",
+			msgs: []llm.Message{
+				llm.UserText("earlier, unrelated question?"),
+				asst(hugeAnswer),
+				llm.UserText("q?"),
+				asst(conciseAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(b3cb9ee9Closer),
+			},
+			terminal: b3cb9ee9Closer,
+			want:     b3cb9ee9Closer,
+		},
+		{
+			// The boundary must not break the legitimate multi-turn case: the
+			// dwarfing front-loaded answer in THIS turn's window is recovered
+			// even with history behind it.
+			name: "summary closer recovery still works with history present",
+			msgs: []llm.Message{
+				llm.UserText("earlier, unrelated question?"),
+				asst(longAnswer),
+				llm.UserText("q?"),
+				asst(hugeAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(b3cb9ee9Closer),
+			},
+			terminal: b3cb9ee9Closer,
+			want:     hugeAnswer,
+		},
+		{
+			// Gadfly (opus, error-handling): a closer matching BOTH the ack
+			// shape and a back-reference carries no answer content, so the
+			// back-ref test must win and the ordinary recovery bar apply —
+			// under the summary bar this ~106-byte terminal would demand a
+			// ~318-byte prior and wrongly keep the closer over longAnswer.
+			name: "back-reference wins over the summary ack when both match",
+			msgs: []llm.Message{
+				llm.UserText("q?"),
+				asst(longAnswer, cite...),
+				llm.ToolResultsMessage(llm.ToolResult{ID: "c1", Name: "cite", Content: "ok"}),
+				asst(bothMatchCloser),
+			},
+			terminal: bothMatchCloser,
+			want:     longAnswer,
+		},
 	}
 	for _, tc := range tests {
 		t.Run(tc.name, func(t *testing.T) {