refactor(agent): gadfly round 2 — shared leadingMarkers, explicit mode, comment altitude

All tidiness, no behavior change: the leading-marker class is one shared
constant for citationLabelRe and summaryCloserRe (hand-copying it is how
'+' went missing the first time); the deliberate 'all' duplication across
summaryCopulas/summaryArticle is now stated at both sites; the weak-final
switch case assigns modeBackRef explicitly; test comments state the
constraint they guard instead of which reviewer asked for them.

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

agent/finalize.go

@@ -52,7 +52,7 @@ func finalOutput(msgs []llm.Message, terminal string) string {
 	case isCitationsOnly(terminal):
 		mode = modeCitations
 	case isWeakFinal(terminal):
-		// modeBackRef
+		mode = modeBackRef
 	case isSummaryCloser(terminal):
 		mode = modeSummary
 	default:
@@ -128,15 +128,17 @@ 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 (
-	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?)`
+	// "all" appears here AND in summaryArticle on purpose: as a quantifier
+	// between noun and verb ("Citations all logged.") and as a determiner
+	// before the noun ("All claims cited.", "Logged all the citations.").
 	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 +
+var summaryCloserRe = regexp.MustCompile(`(?i)^` + leadingMarkers + summaryPreface +
 	`(` + summaryArticle + summaryNouns + `\s+` + summaryCopulas + summaryVerbs +
 	`|logged\s+` + summaryArticle + summaryNouns + `)[.!]`)
 
@@ -153,7 +155,15 @@ var preambleRe = regexp.MustCompile(`(?i)^(let me|let'?s|i'?ll|i will|first[, ]|
 // the colon/dash separator. Anchored at ^ so a normal answer that merely
 // mentions "sources" mid-sentence, or ends with a "Sources:" section AFTER its
 // prose, is never matched.
-var citationLabelRe = regexp.MustCompile(`(?i)^[\s>#*_+-]*(sources?|references?|citations?|works cited|further reading)\b[\s*_]*[:：\-—]`)
+var citationLabelRe = regexp.MustCompile(`(?i)^` + leadingMarkers +
+	`(sources?|references?|citations?|works cited|further reading)\b[\s*_]*[:：\-—]`)
+
+// leadingMarkers tolerates markdown noise before a label: emphasis (*, _),
+// list (-, +, *), block-quote (>), and ATX-heading (#) markers, with their
+// whitespace. Shared by citationLabelRe and summaryCloserRe so the two
+// classifiers cannot drift apart (the first draft of the summary class
+// dropped '+' by hand-copying this set).
+const leadingMarkers = `[\s>#*_+-]*`
 
 // linkRe matches a whole markdown link "[label](url)" or a bare URL. Used both
 // to require that a citations terminal carries at least one link and to strip

agent/finalize_test.go

@@ -354,11 +354,11 @@ func TestFinalOutput(t *testing.T) {
 			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.
+			// 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?"),
@@ -388,11 +388,11 @@ func TestFinalOutput(t *testing.T) {
 			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.
+			// 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?"),