package agent

import (
	"regexp"
	"strings"

	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)

// finalOutput selects the user-facing answer when the loop reaches a clean
// terminal turn (one with no tool calls).
//
// Normally that terminal turn's text IS the answer: well-behaved models defer
// their answer to the final, tool-free turn. But some models — notably several
// open-weight ones — "front-load" their full answer into an earlier turn that
// ALSO calls a tool (e.g. answer text alongside a citation call), then close
// with a degenerate terminal turn that is not itself the answer. Two shapes are
// recovered from the transcript (zero extra model calls):
//
//   - a trivial back-reference ("(Already answered above.)", "see above", …):
//     the real answer sits earlier, so recover it and DISCARD the worthless
//     closer.
//   - a sources/citations-only addendum ("Sources: [x](…), [y](…)"): the model
//     front-loaded the prose answer and closed with just its citations (the
//     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 citations addendum is tested first and wins over the back-reference test (a
// short terminal can be both), so its links are never discarded. 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 bare
// sources list still beats nothing).
//
// msgs must already include the terminal assistant message as its last element
// (the loop appends it before calling this); terminal is that message's text.
func finalOutput(msgs []llm.Message, terminal string) string {
	citations := isCitationsOnly(terminal)
	if !citations && !isWeakFinal(terminal) {
		return terminal
	}
	rec, ok := lastSubstantiveAssistantText(msgs, terminal, citations)
	if !ok {
		return terminal
	}
	if citations {
		// Preserve the citations addendum below the recovered answer, unless the
		// recovered turn already carries it (guards against a duplicate sources
		// block when the front-loaded turn included its own citations). The
		// containment test ignores <url> angle-bracket wrappers so a turn that
		// listed the same sources unwrapped still suppresses the duplicate.
		if tail := strings.TrimSpace(terminal); !strings.Contains(stripURLAngles(rec), stripURLAngles(tail)) {
			return rec + "\n\n" + tail
		}
	}
	return rec
}

// stripURLAngles removes the <…> wrappers Discord uses to suppress link embeds,
// so the citations dedup compares URLs regardless of that formatting delta.
func stripURLAngles(s string) string {
	if !strings.ContainsAny(s, "<>") {
		return s
	}
	return strings.NewReplacer("<", "", ">", "").Replace(s)
}

// 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", ...).
var backRefRe = regexp.MustCompile(`(?i)(already answered|see above|as (i )?(said|mentioned|stated|noted)|answered (that )?above|per my (previous|earlier))`)

// preambleRe matches intent-announcing prefixes ("Let me search...", "I'll
// check...") so a preamble is never mistaken for the answer during recovery.
var preambleRe = regexp.MustCompile(`(?i)^(let me|let'?s|i'?ll|i will|first[, ]|sure[,. ]|okay[,. ]|on it|checking)`)

// citationLabelRe matches a terminal turn that OPENS with a sources/citations
// heading — the shape a model produces when it front-loads its answer into an
// earlier tool-call turn and closes with only its sources. Leading markdown
// emphasis (*, _), list (-, +, *), block-quote (>), and ATX-heading (#) markers
// — with their whitespace, since \s is in the class — are tolerated before the
// label, as is closing emphasis (** / __) plus whitespace between the label and
// 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*_]*[:：\-—]`)

// 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
// links out when measuring how citation-dominated the terminal is.
var linkRe = regexp.MustCompile(`\[[^\]]*\]\([^)]*\)|https?://\S+`)

// citationResidueCutset is trimmed from the ends of a citations terminal's
// non-link remainder before measuring it — list bullets, separators, and the
// short per-source annotations models add in parentheses.
const citationResidueCutset = " \t\r\n,;.:|·•*_()[]—-"

const (
	// weakFinalMaxChars bounds how long a back-reference closer can be. A
	// genuine final answer that merely contains "as I said" mid-sentence is
	// longer than this, so it is never treated as weak.
	weakFinalMaxChars = 120
	// 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).
	recoverMinChars = 200
	// recoverFloorChars / recoverRatio gate the borderline band: a shorter
	// prior turn must clear the floor and — unless the terminal is a citations
	// addendum, which is not a rival answer — also clearly dwarf the (very
	// short) terminal. See isSubstantiveAnswer.
	recoverFloorChars = 80
	recoverRatio      = 3
	// citationDominatedDivisor: a citations terminal's non-link remainder must
	// be at most len/N of the whole, so a prose answer that merely opens with
	// "Source:" and cites a URL mid-sentence is not mistaken for a bare list.
	citationDominatedDivisor = 3
)

// 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.
func isWeakFinal(s string) bool {
	t := strings.TrimSpace(s)
	if t == "" {
		return true
	}
	return len(t) <= weakFinalMaxChars && backRefRe.MatchString(t)
}

// isCitationsOnly reports whether a terminal turn is essentially just a
// sources/citations addendum: it OPENS with a citations heading, carries at
// least one link, and — once the heading and links are removed — is dominated
// by that citation structure (only list punctuation and short per-source
// annotations remain). The dominance check is what separates a bare sources
// list (recover the front-loaded answer, keep the links) from a real prose
// answer that merely opens with "Source:" and references a URL mid-sentence
// (leave it as the answer). Unlike a back-reference closer the links are worth
// keeping, so finalOutput appends them to the recovered answer.
//
// A citations terminal whose sources are bare domains (no scheme, no markdown
// link) is intentionally out of scope — there is no reliable link signal, so it
// is left as-is rather than risk misclassifying prose.
func isCitationsOnly(s string) bool {
	t := strings.TrimSpace(s)
	if !citationLabelRe.MatchString(t) {
		return false
	}
	body := citationLabelRe.ReplaceAllString(t, "")
	if !linkRe.MatchString(body) {
		return false
	}
	residue := strings.Trim(linkRe.ReplaceAllString(body, ""), citationResidueCutset)
	return len(residue) <= len(t)/citationDominatedDivisor
}

// lastSubstantiveAssistantText scans msgs newest→oldest (skipping the terminal
// turn and empty tool-only turns) for the most recent assistant turn whose text
// reads like a real answer. citations selects the recovery bar (see
// isSubstantiveAnswer). Returns ("", false) when nothing qualifies.
func lastSubstantiveAssistantText(msgs []llm.Message, terminal string, citations bool) (string, bool) {
	tt := strings.TrimSpace(terminal)
	for i := len(msgs) - 1; i >= 0; i-- {
		m := msgs[i]
		if m.Role != llm.RoleAssistant {
			continue
		}
		txt := strings.TrimSpace(m.Text())
		if txt == "" || txt == tt {
			continue // the terminal turn itself, or an empty tool-only turn
		}
		if isSubstantiveAnswer(txt, tt, citations) {
			return txt, true
		}
	}
	return "", false
}

// isSubstantiveAnswer reports whether txt (a prior assistant turn) reads like a
// real answer rather than a preamble, relative to the terminal text.
//
// A sufficiently long turn (>= recoverMinChars) is accepted unconditionally: a
// multi-hundred-char turn is an answer even when it opens conversationally
// ("Sure, here's…", "Let me explain: …"), so the preamble filter is NOT applied
// to it — applying it there would drop a legitimate long front-loaded answer.
// Only in the borderline band does a turn have to clear a floor, not read like a
// short planning preamble ("Let me look that up…"), and — unless the terminal is
// a citations addendum (not a rival answer, so its length is irrelevant) — also
// clearly dwarf the terminal.
func isSubstantiveAnswer(txt, terminal string, citations bool) bool {
	if len(txt) >= recoverMinChars {
		return true
	}
	if len(txt) < recoverFloorChars || preambleRe.MatchString(txt) {
		return false
	}
	return citations || len(txt) >= recoverRatio*len(terminal)
}