package pipeline

import (
	"context"
	"fmt"
	"textmachine/backend/internal/llm"
)

// bookrun.go: цикл уровня КНИГИ (Веха 2) — ingest → сид/материализация памяти →
// снапшот → последовательный обход чанков с D2-дисциплиной (флаг не роняет прогон)
// и sticky-окном сцены (A5). Плюс типы результатов прогона и exit-контракт CLI.

// StageResult reports one executed stage of a chunk.
type StageResult struct {
	Stage        string
	Role         string
	Model        string // фактически ответившая модель
	FromResume   bool   // no provider call was made THIS run (fully served from checkpoints)
	Usage        llm.Usage
	CostUSD      float64 // THIS run's spend (0 when fully served from checkpoints)
	CumCostUSD   float64 // sum across ALL attempts of this chunk×stage (F3-honest, incl. retries)
	LatencyMS    int
	FinishReason string
	Text         string // the usable output (only on an ok disposition)
	// RecoveredText is the cosmetic-stripped export text (D35.4a): non-empty ONLY for a
	// FlagSanitizerStripped final stage, where the sanitizer removed a leading markdown header /
	// CJK-leak and committed the cleaned remainder. It carries the export forward on BOTH the
	// fresh path (runStage) and resume (resumeFromChunkStatus reads the derived checkpoint), so
	// translateChunk assembles the identical FinalText either way. "" for every other disposition.
	RecoveredText string
	Disposition   Disposition
	FlagReason    FlagReason // "" when ok
	Detail        string
	Attempts      int
	// Escalated — a single-hop fallback draft was tried this stage (D12); when the
	// fallback passed the re-gate, Model above is the fallback (it answered).
	Escalated       bool
	EscalationModel string // the fallback model when Escalated ("" otherwise)
}

// ChunkOutcome is one chunk's result across the stage list.
type ChunkOutcome struct {
	Chapter  int
	ChunkIdx int
	Stages   []StageResult
	// FinalText is the exported text: the last stage's output on ok; the cosmetic-stripped
	// remainder on a FlagSanitizerStripped flag (D35.4a — the chunk is exported flagged, not lost
	// to an empty placeholder); "" on any other flag (the contaminated output never exports).
	FinalText   string
	Disposition Disposition // ok | flagged (a chunk has no "skipped" — that is a per-later-stage state)
	FlagReason  FlagReason  // the flagging stage's reason ("" when ok)
	CostUSD     float64     // THIS run's spend on this chunk
}

// BookResult aggregates a whole run over every chapter×chunk.
type BookResult struct {
	BookID   string
	Chunks   []ChunkOutcome
	TotalUSD float64 // THIS run's spend across all chunks
	Flagged  int     // number of flagged chunks (acceptance допускает N)
}

// ExitCode is the run's shell disposition: 0 clean, 2 completed-with-flags
// (acceptance допускает N флагов — приёмка это разрешает). An infra failure is
// an error from TranslateBook, which the CLI maps to 1.
func (b *BookResult) ExitCode() int {
	if b.Flagged > 0 {
		return 2
	}
	return 0
}

// CompletedWithFlags is the typed sentinel the CLI maps to exit code 2: the book
// finished end-to-end but N chunks were flagged for a human. It is NOT an infra
// failure (a plain error → exit 1); it is a "clean run, attention needed" signal
// carried up through `func run() error` in the idiomatic Go way.
type CompletedWithFlags struct {
	Flagged int
	Total   int
}

func (e *CompletedWithFlags) Error() string {
	return fmt.Sprintf("completed with %d/%d chunk(s) flagged for review", e.Flagged, e.Total)
}

// TranslateBook runs the whole book: split the normalized source into
// chapter/chunk units (chunker.go) and drive each chunk through the stage list.
// A bad chunk is flagged and the loop CONTINUES (D2); only an infra failure
// (ceiling, config change without --resnapshot, unbilled call failure, store
// error) aborts with an error, from which resume continues.
func (r *Runner) TranslateBook(ctx context.Context) (*BookResult, error) {
	// Ingest reads + normalizes the source (txt/epub) into ordered per-chapter text
	// and captures ruby readings (ingest.go), decoding the txt source per book.encoding
	// (auto/utf8/gb18030). Offline and deterministic ($0, no LLM).
	doc, err := IngestEncoded(r.Book.SourceFile, r.Book.Encoding, r.Book.SourceLang)
	if err != nil {
		return nil, err
	}

	// Persist captured ruby readings (idempotent; consumed by seedGlossary below into
	// auto glossary candidates — шаг 4). Never injected into a prompt here (§7d); a
	// resume re-persists the same rows at $0.
	if err := r.persistRuby(doc.Ruby); err != nil {
		return nil, fmt.Errorf("pipeline: persist ruby readings: %w", err)
	}

	// Seed + materialize the glossary BEFORE the snapshot: the frozen approved rows feed
	// memoryVersion() → the snapshot (F1), so the snapshot must be computed with the bank
	// already materialized. Deterministic and $0 (seed file + classified ruby, no LLM).
	if err := r.seedGlossary(ctx); err != nil {
		return nil, err
	}

	// Snapshot is book-level (brief + stage plan + memory), computed once and
	// upserted before the loop; every job pins to it. memoryVersion() now reflects the
	// materialized bank, so a changed approved glossary re-pins loudly (F1).
	snapID, snapPayload, err := r.snapshotID()
	if err != nil {
		return nil, err
	}
	if err := r.Store.UpsertSnapshot(snapID, r.Book.BriefHash(), snapPayload); err != nil {
		return nil, fmt.Errorf("pipeline: upsert snapshot %.12s: %w", snapID, err)
	}

	chunks := SplitChunks(doc.Chapters)
	if len(chunks) == 0 {
		return nil, fmt.Errorf("pipeline: source file %s produced no chunks after normalization", r.Book.SourceFile)
	}

	// Масштаб прогона — одной строкой на stderr (боль smoke-прогона: N/M и знаменатель
	// прогресса не появлялись в логах вообще, только в stdout/status).
	r.Log.InfoContext(ctx, "book run started", "book", r.Book.BookID, "snapshot", snapID[:12],
		"chapters", len(doc.Chapters), "chunks", len(chunks), "stages_per_chunk", len(r.Pipeline.Stages))

	res := &BookResult{BookID: r.Book.BookID}
	// Sticky scene-inertia state (A5): the exact-matched ids of the recent chunks in
	// the CURRENT chapter, reset at a chapter boundary (a new chapter is a scene change).
	// Rebuilt deterministically each run because translateChunk recomputes the ($0)
	// selection for EVERY chunk, resumed ones included — so sticky is resume-stable.
	var stickyWin []map[string]injectionDisposition
	prevChapter := 0
	for i, ch := range chunks {
		if ch.Chapter != prevChapter {
			stickyWin = nil
			prevChapter = ch.Chapter
			// Пульс прогресса на границе главы: done/total + деньги ЭТОГО прогона —
			// оператор длинной книги видит движение, не открывая status.
			r.Log.InfoContext(ctx, "chapter started", "chapter", ch.Chapter,
				"chunks_done", i, "chunks_total", len(chunks), "run_usd", fmt.Sprintf("%.6f", res.TotalUSD))
		}
		outcome, activeIDs, err := r.translateChunk(ctx, snapID, ch, unionSticky(stickyWin))
		if err != nil {
			// Infra failure: abort. Chunks already committed are checkpointed;
			// resume continues from here at $0 for the done work.
			return res, err
		}
		res.Chunks = append(res.Chunks, *outcome)
		res.TotalUSD += outcome.CostUSD
		if outcome.Disposition == DispFlagged {
			res.Flagged++
		}
		// Advance the sticky window (keep the last stickyDepth chunks' exact matches).
		stickyWin = append(stickyWin, activeIDs)
		if len(stickyWin) > stickyDepth {
			stickyWin = stickyWin[len(stickyWin)-stickyDepth:]
		}
	}
	r.Log.InfoContext(ctx, "book run finished", "book", r.Book.BookID,
		"chunks", len(res.Chunks), "flagged", res.Flagged, "run_usd", fmt.Sprintf("%.6f", res.TotalUSD))
	return res, nil
}

// unionSticky merges the recent chunks' exact-matched ids into one sticky_prev, carrying
// each id's DISPOSITION (D16.2). When an id fired in several recent chunks, the MOST RECENT
// firing wins (win is ordered oldest→newest), so a re-established CONFIRMED match overrides
// an older collision-prone AMBIGUOUS one — and vice-versa, never silently upgrading.
func unionSticky(win []map[string]injectionDisposition) map[string]injectionDisposition {
	if len(win) == 0 {
		return nil
	}
	out := map[string]injectionDisposition{}
	for _, s := range win {
		for id, disp := range s {
			out[id] = disp
		}
	}
	return out
}