package pipeline

import (
	"encoding/json"
	"maps"
	"slices"
	"strings"
	"textmachine/backend/internal/store"
)

// chunkrun.go: disposition-петля уровня ЧАНКА (D2) — стадии по порядку, первый флаг
// останавливает чанк (дальше skipped, платной редактуры мусора нет), плюс горячий
// путь памяти v2 (Select→инъекция per-role→post-check E1) и дешёвые стиль-флаггеры.
// Новые роли-потребители инъекции Ф2 (annotator, voice-слой) добавляются здесь.

// classifyOutput resolves a completion's disposition: FIRST the always-on intrinsic
// classifier (echo/empty/refusal/length — Веха 2), then, only if that is ok AND the
// configurable coverage gate is enabled, the excision gate (шаг 6 / D12 Q3). Both are
// pure and deterministic over (source, output, finish), so a resumed checkpoint
// reproduces the identical verdict for free — the intrinsic part unconditionally, the
// gate part under the same coverage config (folded into the snapshot, so a gate change
// re-pins loudly). The coverage gate runs ONLY on the TRANSLATOR role's output (vs the
// original source): a monolingual editor legitimately restructures sentences, so gating
// it against the source would false-flag a correct edit (see the role check below).
// classifyOutput returns the disposition AND, for a cosmetic sanitizer strip, the resolved EXPORT
// text (the strip remainder) computed ONCE here (T3.4 / L8-stripcosmetic-recomputed-twice): the
// second return travels back to runStage as the authoritative export, so no site re-derives
// stripCosmetic and the "non-empty & clean" invariant is asserted over the very bytes that ship.
// The string is "" for every disposition except FlagSanitizerStripped.
func (r *Runner) classifyOutput(role, source, output, finish string, isFinal bool) (classification, string) {
	cls := classify(classifyInput{Source: source, Output: output, Finish: finish, TargetLang: r.Book.TargetLang})
	if !cls.ok() {
		return cls, ""
	}
	// Output-sanitizer gate (D30.3): a deterministic verdict-axis check for "instant unreadability"
	// defects no other gate catches — a leaked service preamble, a trailing note/edit block, a markdown
	// ### header, a Latin-script insertion, a contentless CJK-leak run. Opt-in (Gates.Sanitizer). Runs
	// ONLY on the FINAL stage's output (isFinal) — the text that SHIPS: an intermediate translator draft
	// is legitimately rough and the EDITOR's job is to clean it, so sanitizing the draft would wrongly
	// skip the recovering editor and drop the chunk to a placeholder (адверсариальное ревью). It is a
	// READABILITY gate whose patterns bake in Cyrillic/Russian conventions, so it is gated behind a
	// Russian target (D39 слой 7, L8-readability-gates-target-blind) — a no-op for any other pair, which
	// would false-flag (prod zh→ru is unaffected). Runs on the completion text like the intrinsic
	// classifier, so a resumed checkpoint re-derives the identical verdict; its rule version folds into
	// the snapshot only when enabled (sanitizerSnapshot).
	if isFinal && r.Pipeline.Gates.Sanitizer.Enabled && isRuTarget(r.Book.TargetLang) {
		if san := sanitizeOutput(output); san.total() > 0 {
			// Cosmetic-only leak (leading markdown header and/or contentless CJK-leak) → strip it and
			// export the remainder flagged, not drop the whole chunk (D35.4a). The guard is
			// load-bearing: we tag sanitizer_stripped ONLY when the strip yields a NON-EMPTY output that
			// is now clean, and we RETURN that stripped text so runStage/resume ship the exact bytes the
			// guard validated. Anything else falls through to the substantive skip. Pure over `output`,
			// so a resumed checkpoint re-derives the identical verdict.
			if san.cosmeticOnly() {
				if stripped := stripCosmetic(output); strings.TrimSpace(stripped) != "" && sanitizeOutput(stripped).total() == 0 {
					return classification{FlagSanitizerStripped, san.summary()}, stripped
				}
			}
			return classification{FlagSanitizerDefect, san.summary()}, ""
		}
	}
	if !r.Pipeline.Gates.Coverage.Enabled {
		return cls, ""
	}
	// The coverage gate compares the output against the ORIGINAL source, which is a
	// source→target translation only for the TRANSLATOR role. A monolingual editor
	// legitimately restructures/merges sentences, so gating ITS output against the
	// source with the translation corridor false-flags a correct edit as excision
	// (self-review finding). Editor/other-role fidelity is a Phase-2 concern (a
	// bilingual judge over the draft, §04 mode 2), not this excision gate.
	if role != roleTranslator {
		return cls, ""
	}
	if cov := coverageCheck(r.Pipeline.Gates.Coverage, source, output, r.Book.SourceLang, r.Book.TargetLang); !cov.cls.ok() {
		return cov.cls, ""
	}
	return cls, ""
}

// injectionRenderer serializes a chunk's selected memory records into a role's injection message.
type injectionRenderer func(injected []pickedEntry) string

// roleInjectionRenderers maps a stage ROLE to the memory-injection renderer it consumes — a registry
// instead of a hand-edited switch (D39 слой 7, L8-role-injection-hardcoded-switch), so a new Ф2
// consumer role (annotator, voice-layer — README) is DATA + one renderer, not surgery on a switch.
// A role absent from the map gets no injection. Renderers are pure, so the per-role result is
// deterministic regardless of map iteration order (no map-order in OUTPUT — invariant #6).
var roleInjectionRenderers = map[string]injectionRenderer{
	roleTranslator: renderGlossaryBlock,         // src→dst glossary block
	roleEditor:     renderEditorConstraintBlock, // CONFIRMED dst forms (target-consistency constraints)
}

// persistRetrievalState writes the per-chunk observability record from the deterministic
// selection + the post-check result. n_exact_hits/n_sticky/n_ambiguous count the INJECTED
// records (what the model saw); spoiler/eviction are the dropped-and-logged totals;
// post-check misses are recorded only when the translator actually produced text.
func (r *Runner) persistRetrievalState(snapID string, ch Chunk, sel memorySelection, misses []postcheckMiss, outputChecked bool, cheap cheapGateResult, bank bankFlags) error {
	rs := store.RetrievalState{
		BookID: r.Book.BookID, Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, SnapshotID: snapID,
		NStyleFlags:       cheap.total(),
		NBanknoteLines:    bank.NLines,
		BanknoteParseFail: boolToStoreInt(bank.ParseFail),
		BanknoteTruncated: boolToStoreInt(bank.Truncated),
	}
	if cheap.total() > 0 {
		if b, err := json.Marshal(cheap); err == nil {
			rs.StyleDetail = string(b)
		}
	}
	for _, p := range sel.injected {
		if p.via == "sticky" {
			rs.NSticky++
		} else {
			rs.NExactHits++
		}
		if p.disp == memAmbiguous {
			rs.NAmbiguousFlagged++
		}
	}
	rs.NSpoilerBlocked = len(sel.rejected)
	rs.NEvicted = len(sel.evicted)
	// Loud record of the disposition-gated suppressor (D39 слой 4): a longer lower-trust key refused
	// from eating a nested higher-trust one — the term-drift code root, now visible instead of a
	// silent drop (research/13 §7). Detail carries the refused suppressor→protected pairs for a human.
	rs.NTrustGatedSuppress = len(sel.trustGated)
	if len(sel.trustGated) > 0 {
		if b, err := json.Marshal(sel.trustGated); err == nil {
			rs.TrustGateDetail = string(b)
		}
	}
	if outputChecked {
		// n_postcheck_miss is the CONFIRMED-miss count (the actionable consistency-failure
		// signal, external-review #1); the detail carries ALL misses (confirmed AND the
		// ambiguous forced-post-check ones, each disp-tagged) for the human.
		rs.NPostcheckMiss = countConfirmedMisses(misses)
		if len(misses) > 0 {
			if b, err := json.Marshal(misses); err == nil {
				rs.PostcheckDetail = string(b)
			}
		}
	}
	ids := slices.Sorted(maps.Keys(sel.activeIDs))
	if ids == nil {
		// slices.Sorted даёт NIL на пустой карте → json.Marshal рендерил бы "null",
		// а исторический формат персистентной колонки — "[]" (чанк без точных
		// матчей — обычный кейс); держим байты стабильными (находка селфревью №4).
		ids = []string{}
	}
	if b, err := json.Marshal(ids); err == nil {
		rs.InjectedIDs = string(b)
	}
	return r.Store.UpsertRetrievalState(rs)
}

// boolToStoreInt maps a bool telemetry flag to the store's 0/1 integer column form.
func boolToStoreInt(b bool) int {
	if b {
		return 1
	}
	return 0
}

// cheapGateConfig builds the cheap-gate knobs from the book brief: the ё-policy and the
// lower-cased per-project interjection allowlist. Pure, no store access.
func (r *Runner) cheapGateConfig() cheapGateConfig {
	allow := make(map[string]bool, len(r.Book.StyleAllowlist))
	for _, s := range r.Book.StyleAllowlist {
		allow[s] = true
	}
	return cheapGateConfig{
		yoPolicy:          r.Book.YoPolicy,
		allowlist:         allow,
		regressionEnabled: r.Pipeline.Gates.RegressionGuard.Enabled,
	}
}