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)
	// BankFlags carries the translator draft's banknote telemetry (WS4 point 10): accepted line count +
	// parse-fail / truncation flags. Zero-valued on every non-translator stage and every channel-off run.
	BankFlags bankFlags
}

// 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
	}

	// the precompute pass: eager-build every reachable client BEFORE any wave goroutine, so the clients map is
	// read-only in the waves (r.client is lock-free, a miss is loud — closes the D12 lazy-init race).
	if err := r.buildClients(); err != nil {
		return nil, err
	}
	// the precompute pass: build the per-model rate-guards (transport axis, read-only in the waves; a no-op until a
	// model configures rate_limit — WS1 §1б, the mistral-arm precondition WS6).
	r.buildRateGuards()

	// 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
	}

	chunks := SplitChunks(doc.Chapters, r.segBudget())
	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,
		"chapters", len(doc.Chapters), "chunks", len(chunks), "stages", len(r.Pipeline.Stages))

	// the precompute pass: pre-compute the sticky-chain memory selection for EVERY chunk (WS1 §1б, precomputeSticky). The
	// sticky window (A5 scene-inertia — the recent chunks' exact matches in the current chapter, reset at
	// a chapter boundary) is a CROSS-CHUNK sequential dependency, so it is computed once here in the precompute pass and
	// consumed by the parallel draft-wave workers (it cannot be recomputed inside a wave). Byte-identical to the
	// retired inline computation (Select is $0 and pure — the golden test proves the injected bytes hold).
	// The draft wave selects over the BASE bank (mined-excluded) so its injection is byte-identical across
	// a bank-mining enrichment (the review-confirmed «переоплата ОДНА» fix); the editor uses the enriched bank.
	stickySel := precomputeSticky(chunks, r.baseMemory, r.Pipeline.Context.GlossaryTokenBudget)

	// The wave executor (R1, waverun.go): the draft wave (draft ∥) → the bank-mining stop → the edit wave (edit ∥). It computes +
	// upserts the per-wave snapshots (draft-wave snapshot base-bank / edit-wave snapshot enriched) itself and pins each
	// wave's jobs to its own — a the bank-mining stop enrichment moves only edit-wave snapshot, keeping draft-wave checkpoints valid
	// («переоплата ОДНА»). Returns a *WaveSignatureStop when the bank-mining stop stops for owner sign.
	return r.translateBookWaves(ctx, chunks, stickySel)
}

// 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
}