From 89d5bf9d6ad751899f33769d1a8f7fea0fc0d028 Mon Sep 17 00:00:00 2001 From: "Claude (backend session)" Date: Sun, 19 Jul 2026 20:11:05 +0300 Subject: [PATCH] Land R1 wave driver-switch (D39.17): parallel draft/edit waves with bank-mining stop, editor never re-renders draft, Sh-1/Sh-2, per-unit read-models; rubezh-2 clean bill, three MINOR mining-wiring fixes to pre-rerun; pack-11 complete --- backend/internal/config/book.go | 32 +- backend/internal/config/pipeline.go | 33 ++ backend/internal/pipeline/banknote.go | 2 +- backend/internal/pipeline/bookrun.go | 63 +-- backend/internal/pipeline/cheapgates.go | 4 +- backend/internal/pipeline/chunker.go | 8 +- backend/internal/pipeline/chunkrun.go | 177 ------ backend/internal/pipeline/disposition.go | 4 +- backend/internal/pipeline/escalation.go | 9 + backend/internal/pipeline/export.go | 98 ++-- backend/internal/pipeline/golden_test.go | 133 ++++- backend/internal/pipeline/memnorm.go | 9 +- backend/internal/pipeline/memory.go | 18 +- backend/internal/pipeline/memory_wave_test.go | 14 +- backend/internal/pipeline/memseed.go | 10 +- backend/internal/pipeline/miner_emit.go | 6 +- backend/internal/pipeline/miner_test.go | 6 +- backend/internal/pipeline/mining.go | 91 +++ backend/internal/pipeline/quality.go | 38 +- backend/internal/pipeline/ratelimit.go | 4 +- backend/internal/pipeline/render.go | 10 +- backend/internal/pipeline/runner.go | 82 ++- backend/internal/pipeline/runner_test.go | 34 +- backend/internal/pipeline/seeding.go | 30 +- backend/internal/pipeline/seedlint_test.go | 2 +- backend/internal/pipeline/snapshot.go | 45 +- .../internal/pipeline/snapshot_wave_test.go | 32 +- backend/internal/pipeline/status.go | 175 +++--- .../pipeline/testdata/golden/capture.golden | 238 ++++---- backend/internal/pipeline/wave.go | 56 +- backend/internal/pipeline/waverun.go | 535 ++++++++++++++++++ backend/internal/pipeline/waverun_test.go | 368 ++++++++++++ docs/PROGRESS.md | 4 + docs/README.md | 2 +- docs/architecture/05-decisions-log.md | 15 +- ...CKEND_PLAN11_SESSION_PROMPT_2026-07-19.md} | 2 + 36 files changed, 1825 insertions(+), 564 deletions(-) create mode 100644 backend/internal/pipeline/mining.go create mode 100644 backend/internal/pipeline/waverun.go create mode 100644 backend/internal/pipeline/waverun_test.go rename docs/{BACKEND_PLAN11_SESSION_PROMPT.md => archive/prompts/BACKEND_PLAN11_SESSION_PROMPT_2026-07-19.md} (98%) diff --git a/backend/internal/config/book.go b/backend/internal/config/book.go index 599602f..5446315 100644 --- a/backend/internal/config/book.go +++ b/backend/internal/config/book.go @@ -45,21 +45,32 @@ type Book struct { StyleAllowlist []string `yaml:"style_allowlist"` // Wiring: paths are resolved relative to the book.yaml location. - Pipeline string `yaml:"pipeline"` - ModelsFile string `yaml:"models"` - SourceFile string `yaml:"source_file"` // Фаза 0: один файл = один чанк + Pipeline string `yaml:"pipeline"` + ModelsFile string `yaml:"models"` + SourceFile string `yaml:"source_file"` // Фаза 0: один файл = один чанк // Encoding of the txt source: auto|utf8|gb18030 ("" defaults to auto). Real zh .txt are often // GB18030 (the 蛊真人 acceptance book is), which the auto-detect handles; declare it explicitly // to skip detection. Ignored for epub (its documents carry their own charset). See ingest.go. - Encoding string `yaml:"encoding"` - ProjectDB string `yaml:"project_db"` // default: .db рядом с book.yaml + Encoding string `yaml:"encoding"` + ProjectDB string `yaml:"project_db"` // default: .db рядом с book.yaml // GlossarySeed is the optional path to the manual glossary seed YAML (memory v2, // шаг 4). Its curated approved/draft terms + the classified ruby readings are the // deterministic inputs the glossary is REPLACED from each run; editing it changes the // materialized approved set → a loud --resnapshot (F1). Empty = ruby-seed only (or an // empty glossary → the injection is inert, a safe no-op). - GlossarySeed string `yaml:"glossary_seed"` - Ceilings BookCap `yaml:"ceilings"` + GlossarySeed string `yaml:"glossary_seed"` + // LangpackRoot is the optional root of the language-data packs (configs/langpacks/, D39.15/16): the + // miner reads configs/langpacks// (source morphology) + configs/langpacks/-/ (Palladius) + // from here. Resolved relative to book.yaml. Empty ⇒ no pack (the miner is inert / W1.5 auto-continues); + // set ⇒ the runner loads the pack in W0, failing LOUD when the pair's catalog dir exists but a file is + // missing/corrupt, and folds pack.Version() into the snapshot so a pack edit is a loud --resnapshot (R1). + LangpackRoot string `yaml:"langpack_root"` + // MinedDelta is the optional path to the owner-curated mined-term delta YAML (the W1.5 sign artifact, + // R1). Its terms are loaded as Source:"mined" (NOT Source:"seed"), so they fold into the ENRICHED bank + // version but NOT the base — adding them moves only snapshot_W2 («переоплата ОДНА»). Same seedTerm + // schema as glossary_seed; resolved relative to book.yaml. Empty = no mined terms. + MinedDelta string `yaml:"mined_delta"` + Ceilings BookCap `yaml:"ceilings"` } // BookCap are the ledger admission limits (Р7: потолок $ на книгу/день). @@ -90,6 +101,8 @@ func LoadBook(path string) (*Book, error) { b.ModelsFile = resolve(b.ModelsFile) b.SourceFile = resolve(b.SourceFile) b.GlossarySeed = resolve(b.GlossarySeed) + b.LangpackRoot = resolve(b.LangpackRoot) + b.MinedDelta = resolve(b.MinedDelta) if b.ProjectDB == "" { b.ProjectDB = filepath.Join(dir, b.BookID+".db") } else { @@ -123,6 +136,11 @@ func LoadBook(path string) (*Book, error) { bad("glossary_seed %s is not readable: %v", b.GlossarySeed, err) } } + if b.MinedDelta != "" { + if _, err := os.Stat(b.MinedDelta); err != nil { + bad("mined_delta %s is not readable: %v", b.MinedDelta, err) + } + } if b.Encoding == "" { b.Encoding = "auto" } diff --git a/backend/internal/config/pipeline.go b/backend/internal/config/pipeline.go index 690a533..213c502 100644 --- a/backend/internal/config/pipeline.go +++ b/backend/internal/config/pipeline.go @@ -29,6 +29,32 @@ type Pipeline struct { Gates Gates `yaml:"gates"` Escal Escalation `yaml:"escalation"` Fanout Fanout `yaml:"fanout"` + Waves Waves `yaml:"waves"` + Mining Mining `yaml:"mining"` +} + +// Waves configures the wave executor's parallelism (WS1 §1б / R1): how many worker goroutines fan out +// over the draft chunks (W1) and edit units (W2). It is a TRANSPORT axis — it changes NOTHING on the wire +// (each unit of work renders identical bytes regardless of which goroutine runs it), so it is deliberately +// NOT folded into the snapshot (folding it would make a worker-count edit a spurious --resnapshot / whole- +// book re-bill). The inner per-model cap stays RateLimit.MaxConcurrency (models.yaml). Workers ≤ 0 defaults +// to 1: a wave-STRUCTURED but sequential run (W1 all drafts → W1.5 → W2 all units), deterministic and safe; +// prod sets it higher (the COGS sim assumed 8). A run with workers=1 is byte-identical in results to +// workers=N (only request_log/wire ORDER differs — the golden capture sorts to absorb that). +type Waves struct { + Workers int `yaml:"workers"` +} + +// Mining configures the W1.5 bank-mining stop (WS3 / R1): the general-zh contrast corpus the WHICH-detector +// scores candidates against. It is OFF unless ContrastPath is set AND a language pack is loaded (book +// langpack_root): the miner then runs at the W1.5 boundary over the W1 drafts, emits the seed-delta + +// signature map, and STOPS for owner sign (or auto-continues on an empty delta). ContrastPath is the jieba- +// style word-freq artifact (large, deployment-specific, NOT in git), resolved relative to pipeline.yaml. It +// is NOT snapshot-folded: mining produces Source:mined PROPOSALS (status:auto, inert until owner-approved), +// so it touches no existing checkpoint's wire or verdict — only the langpack VERSION (which shapes the +// proposals) is folded, via the runner's pack.Version() (§8). Empty ContrastPath ⇒ W1.5 auto-continues. +type Mining struct { + ContrastPath string `yaml:"contrast_path"` } // Segmentation is the WS2 OUTPUT-token chunking budget (слой 1, L2-budget-wrong-unit fix): the @@ -309,6 +335,8 @@ func LoadPipeline(path string, models *Models) (*Pipeline, error) { p.Stages[i].Prompts[pair] = resolvePrompt(pr) } } + // The mining contrast artifact path is resolved like the prompts (relative to pipeline.yaml). + p.Mining.ContrastPath = resolvePrompt(p.Mining.ContrastPath) var problems []string bad := func(format string, a ...any) { problems = append(problems, fmt.Sprintf(format, a...)) } @@ -328,6 +356,11 @@ func LoadPipeline(path string, models *Models) (*Pipeline, error) { if p.Fanout.Candidates <= 0 { p.Fanout.Candidates = 1 } + // Wave workers default to 1 (a wave-structured but sequential, deterministic run). A negative value + // is a config typo, not a request — clamp loudly-neutral to 1 rather than fail (transport axis). + if p.Waves.Workers <= 0 { + p.Waves.Workers = 1 + } // WS2 segmentation defaults (ratified zh-ru, §2в): a config that omits the block gets the // output-token budget + independently-re-derived fertility. Zero/negative → default. if p.Segmentation.DraftBudgetOut <= 0 { diff --git a/backend/internal/pipeline/banknote.go b/backend/internal/pipeline/banknote.go index c3e5192..89b85ff 100644 --- a/backend/internal/pipeline/banknote.go +++ b/backend/internal/pipeline/banknote.go @@ -51,7 +51,7 @@ var bankTypeOK = map[string]bool{"name": true, "place": true, "title": true, "te // with Python's unicode \s around the pipe is exact on the term corpus.) var bankFieldSplit = regexp.MustCompile(`\t| {2,}|\s*\|\s*`) -// bankEntry is one parsed candidate line (evidence for W1.5 §C; NOT written to the store until owner +// bankEntry is one parsed candidate line (evidence for the bank-mining stop (§C); NOT written to the store until owner // signoff). Dst is the model's proposed translation — the direct dst delivery the co-occurrence // miner could not extract (蛊→гу, non-seed 龙公→Лун Гун). type bankEntry struct { diff --git a/backend/internal/pipeline/bookrun.go b/backend/internal/pipeline/bookrun.go index b42690e..f773a40 100644 --- a/backend/internal/pipeline/bookrun.go +++ b/backend/internal/pipeline/bookrun.go @@ -100,12 +100,12 @@ func (r *Runner) TranslateBook(ctx context.Context) (*BookResult, error) { return nil, err } - // W0: eager-build every reachable client BEFORE any wave goroutine, so the clients map is + // 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 } - // W0: build the per-model rate-guards (transport axis, read-only in the waves; a no-op until a + // 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() @@ -123,17 +123,6 @@ func (r *Runner) TranslateBook(ctx context.Context) (*BookResult, error) { 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, r.segBudget()) if len(chunks) == 0 { return nil, fmt.Errorf("pipeline: source file %s produced no chunks after normalization", r.Book.SourceFile) @@ -141,41 +130,23 @@ func (r *Runner) TranslateBook(ctx context.Context) (*BookResult, error) { // 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)) + r.Log.InfoContext(ctx, "book run started", "book", r.Book.BookID, + "chapters", len(doc.Chapters), "chunks", len(chunks), "stages", len(r.Pipeline.Stages)) - res := &BookResult{BookID: r.Book.BookID} - // W0: pre-compute the sticky-chain memory selection for EVERY chunk (WS1 §1б, precomputeSticky). The + // 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 W0 and - // consumed per-chunk below. This is byte-identical to the old inline computation (Select is $0 and - // pure; the golden test proves the injected bytes did not move) — and it is the exact precompute the - // parallel wave executor will consume (the cross-chunk state cannot be recomputed inside a wave). - stickySel := precomputeSticky(chunks, r.memory, r.Pipeline.Context.GlossaryTokenBudget) - prevChapter := 0 - for i, ch := range chunks { - if ch.Chapter != prevChapter { - 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, err := r.translateChunk(ctx, snapID, ch, stickySel[i]) - 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++ - } - } - 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 + // 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 diff --git a/backend/internal/pipeline/cheapgates.go b/backend/internal/pipeline/cheapgates.go index ca58aaf..4d41914 100644 --- a/backend/internal/pipeline/cheapgates.go +++ b/backend/internal/pipeline/cheapgates.go @@ -43,7 +43,9 @@ import ( // scale) and DC6 (register negative-list — the zh-ru pack, checkers_zh_ru.go). They are observability // (never a disposition), tuned precision-over-recall; the bump is a loud --resnapshot as the discipline // requires (a rule/pack edit shifts recorded counts). They fire 0 on a non-zh source / non-register text. -const cheapGateVersion = "cheapgate-v3-dc-checkers" +// Ш-2 (see memnorm.go): the cheap style/DC checkers classify via unicode predicates + NFC folding, so a +// toolchain Unicode bump that shifts a class is a loud --resnapshot rather than a silent count change. +const cheapGateVersion = "cheapgate-v3-dc-checkers+u" + unicode.Version // cheapGateConfig carries the brief-derived knobs: the ё-policy and the per-project allowlist of // surfaces that look like a blocklisted interjection but are legitimate here (e.g. a character diff --git a/backend/internal/pipeline/chunker.go b/backend/internal/pipeline/chunker.go index 6a90411..54353e6 100644 --- a/backend/internal/pipeline/chunker.go +++ b/backend/internal/pipeline/chunker.go @@ -48,8 +48,8 @@ type Chunk struct { OversizedSentence bool // EditUnitID is the 0-based book-global id of the coarse EDIT unit this draft chunk belongs to // (WS2 decoupling: draft = small chunk, edit = large unit). An edit unit is a greedy grouping of - // WHOLE draft chunks up to EditCeilingOut (per chapter), so W2's editor reads a unit's draft as - // the concatenation of its member chunks' W1 outputs — clean reconstruction by construction (no + // WHOLE draft chunks up to EditCeilingOut (per chapter), so the edit wave's editor reads a unit's draft as + // the concatenation of its member chunks' the draft wave outputs — clean reconstruction by construction (no // straddle; verified: grouping whole chunks reproduces the paragraph-packed count 37 with 0 // straddle on the rerun corpus). Draft chunks never cross an edit-unit boundary. EditUnitID int @@ -80,7 +80,7 @@ func (s SegBudget) estOut(cjk, other int) float64 { // cover/nav page) do NOT consume a chapter number, so numbering stays dense over // real content (Фаза-0 backward compat). Fully deterministic. Each chunk carries its // EstOut + OversizedSentence flag + EditUnitID (WS2); the edit-unit id is monotone across -// the book so a W2 unit is uniquely addressable. +// the book so a the edit wave unit is uniquely addressable. func SplitChunks(chapters []string, seg SegBudget) []Chunk { var out []Chunk chapterNo := 0 @@ -155,7 +155,7 @@ func chapterDraftChunks(chapterNo int, paras []string, seg SegBudget) []Chunk { // WHOLE draft chunks until the accumulated est_out would exceed EditCeilingOut — and stamps each // chunk's EditUnitID (monotone across the book via *nextID). Because units are formed from whole // draft chunks, a unit's source/draft span is exactly the concatenation of its member chunks (no -// straddle) and W2 reconstructs the unit's draft losslessly. A single draft chunk larger than the +// straddle) and the edit wave reconstructs the unit's draft losslessly. A single draft chunk larger than the // ceiling (an OversizedSentence, or a chapter whose first chunk already exceeds the ceiling) is its // own unit — grouping never splits a chunk (never-split-below-chunk mirrors never-split-paragraph). func assignEditUnits(chunks []Chunk, seg SegBudget, nextID *int) { diff --git a/backend/internal/pipeline/chunkrun.go b/backend/internal/pipeline/chunkrun.go index 5305025..4b6bac5 100644 --- a/backend/internal/pipeline/chunkrun.go +++ b/backend/internal/pipeline/chunkrun.go @@ -1,9 +1,7 @@ package pipeline import ( - "context" "encoding/json" - "fmt" "maps" "slices" "strings" @@ -79,181 +77,6 @@ func (r *Runner) classifyOutput(role, source, output, finish string, isFinal boo return cls, "" } -// translateChunk drives ONE chunk through the stage list. Stages run in order, -// each feeding the next; the FIRST flagged stage stops the chunk — later stages -// are recorded `skipped` (no paid edit over a garbage draft, D2). It also runs the -// memory bank v2 hot path: it Selects the glossary injection once ($0, deterministic), -// injects it into the TRANSLATOR stage, post-checks the translator output (E1), and -// persists the per-chunk retrieval-state (observability). Returns the chunk outcome, the -// exact-matched entity ids (the next chunk's sticky_prev, A5), and an error only on an -// infra failure. stickyPrev is the prior chunks' exact matches in this chapter. -func (r *Runner) translateChunk(ctx context.Context, snapID string, ch Chunk, memSel memorySelection) (*ChunkOutcome, error) { - out := &ChunkOutcome{Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Disposition: DispOK} - prev := "" - flagged := false - var flagReason FlagReason - // recovered carries a cosmetic sanitizer strip's cleaned export forward from the flagging - // stage (D35.4a): non-empty only when the FINAL stage flagged FlagSanitizerStripped, "" for a - // dropped substantive flag. Captured from the FIRST flagging stage (the sanitizer flags only - // the final stage, so an upstream substantive flag leaves it "" and the chunk exports empty). - recovered := "" - // draftText is the FIRST (translator) stage's output — the pre-reflow baseline for the opt-in - // regression guard's draft→final comparison (== final in a single-stage pipeline). - draftText := "" - // bankTelem carries the translator draft's banknote telemetry (WS4 point 10) into the per-chunk - // retrieval-state. Zero for every channel-off / non-banknote chunk. - var bankTelem bankFlags - - // Hot path: the glossary selection for this chunk is PRE-COMPUTED in W0 (precomputeSticky, WS1 §1б) - // and passed in — the sticky chain is a cross-chunk dependency the parallel waves cannot recompute. - // It is a pure deterministic function of (chunk, sticky_prev, frozen bank), so a resumed chunk - // reproduces the identical injected bytes. Serialize the per-role injection blocks via the - // role→renderer registry (D39 слой 7). - injectionByRole := map[string]string{} - if r.memory != nil { - for role, render := range roleInjectionRenderers { - injectionByRole[role] = render(memSel.injected) // pure → per-role result is map-order-independent - } - // The disposition-gated suppressor refused to let a lower-trust longer key eat a higher-trust - // nested one (D39 слой 4): the approved term survives, but surface the seed-hygiene collision - // loudly so an operator can reconcile the draft-nesting-over-approved seed (research/13 §7). - if len(memSel.trustGated) > 0 { - r.Log.WarnContext(ctx, "memory: lower-trust longer key refused from suppressing a higher-trust nested key (approved term preserved; reconcile the seed)", - "chapter", ch.Chapter, "chunk", ch.ChunkIdx, "trust_gated", len(memSel.trustGated), - "first", memSel.trustGated[0].Suppressor+"⊃"+memSel.trustGated[0].Protected) - } - } - - for stageIdx, st := range r.Pipeline.Stages { - if flagged { - // An earlier stage flagged → this stage is not attempted or billed. - detail := fmt.Sprintf("skipped: an upstream stage was flagged (%s)", flagReason) - if err := r.Store.UpsertChunkStatus(store.ChunkStatus{ - BookID: r.Book.BookID, Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Stage: st.Name, - SnapshotID: snapID, Disposition: string(DispSkipped), FlagReason: string(flagReason), - Detail: detail, - }); err != nil { - return out, fmt.Errorf("pipeline: record skipped chunk_status: %w", err) - } - out.Stages = append(out.Stages, StageResult{ - Stage: st.Name, Role: st.Role, Model: st.Model, - Disposition: DispSkipped, FlagReason: flagReason, Detail: detail, - }) - continue - } - - // Resolve the per-role memory injection from the registry (D39 слой 7): the TRANSLATOR gets the - // src→dst glossary block (keys matched against the source chunk); the BILINGUAL editor (D30.1) - // gets the CONFIRMED dst forms as target-consistency constraints; every other role gets none - // (empty string → the plain 2-message layout). The injection is a message, so it enters this - // stage's request_hash automatically (a resumed chunk reproduces it deterministically). - injection := injectionByRole[st.Role] - sr, err := r.runStage(ctx, st, stageIdx, snapID, ch, prev, injection) - if err != nil { - return out, err - } - out.Stages = append(out.Stages, *sr) - out.CostUSD += sr.CostUSD - if st.Role == roleTranslator { - bankTelem = sr.BankFlags // translator draft's banknote telemetry (WS4 point 10) - // FL-2: the resume fast-path (resumeFromChunkStatus) serves final_hash — the banknote-CLEANED - // derived checkpoint — and never re-parses the raw block, so it leaves BankFlags at the zero - // value. Restore the telemetry the fresh run persisted instead of letting persistRetrievalState - // zero the three banknote columns on every resume of a ready chunk (the comment below promises - // an identical row). Guarded on an EMPTY BankFlags so the attempt-loop path — which re-derives - // the telemetry correctly from the raw checkpoint — is never overwritten. Channel-off ⇒ always - // zero anyway, so the store read is skipped. - if bankTelem == (bankFlags{}) && sr.FromResume && r.Pipeline.Gates.Banknote.Enabled { - if prev, err := r.Store.GetRetrievalState(r.Book.BookID, ch.Chapter, ch.ChunkIdx); err == nil && prev != nil { - bankTelem = bankFlags{ - NLines: prev.NBanknoteLines, - ParseFail: prev.BanknoteParseFail != 0, - Truncated: prev.BanknoteTruncated != 0, - } - } - } - } - if sr.Disposition == DispFlagged { - flagged = true - flagReason = sr.FlagReason - recovered = sr.RecoveredText - continue - } - prev = sr.Text - if stageIdx == 0 { - draftText = sr.Text // the translator draft, before any reflow (regression-guard baseline) - } - } - - // Post-check the FINAL, exported output (E1): the reader sees the last stage's text - // (the editor's), not the translator draft — the monolingual editor can drift an - // approved term the translator got right, so checking the draft alone would miss it. - // Runs on the fresh OR fully-resumed chunk (both carry the final text through `prev`), - // so it is resume-reproducible. In the default FLAGGER mode a miss is recorded only in - // the retrieval-state (observability); with the opt-in gate a miss flags the chunk - // (glossary_miss). Skipped when a stage already flagged (no usable output to check). - var postMisses []postcheckMiss - outputChecked := false - if r.memory != nil && !flagged && prev != "" { - outputChecked = true - postMisses = r.memory.postcheck(memSel.injected, prev) - // The gate flips ONLY on CONFIRMED (approved) misses — an AMBIGUOUS miss is an - // unverified candidate the model may legitimately reject, so it must not discard a - // correct translation (external-review major #1). - if r.Pipeline.Gates.Glossary.PostcheckGate && countConfirmedMisses(postMisses) > 0 { - flagged = true - flagReason = FlagGlossaryMiss - r.Log.WarnContext(ctx, "glossary post-check gate flagged the chunk", - "chapter", ch.Chapter, "chunk", ch.ChunkIdx, "confirmed_misses", countConfirmedMisses(postMisses)) - } - } - - // Cheap deterministic style/number flaggers on the FINAL text (cheapgates.go): observability - // only, never a disposition. Runs on the same fresh-or-resumed output as the post-check, so it - // is resume-reproducible; skipped when a stage flagged (no usable output). Source is ch.Text - // (the 万/億 magnitude gate compares source↔output). These are READABILITY flaggers whose rules - // bake in Russian conventions (em-dash dialogue, ёфикатор, ru magnitude words), so they are 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 (target=ru). - var cheap cheapGateResult - if !flagged && prev != "" && isRuTarget(r.Book.TargetLang) { - cheap = runCheapGates(ch.Text, draftText, prev, r.cheapGateConfig()) - if cheap.total() > 0 { - r.Log.InfoContext(ctx, "cheap style gates flagged the chunk (observability, not a gate)", - "chapter", ch.Chapter, "chunk", ch.ChunkIdx, "style_flags", cheap.total(), - "dialogue_dash", cheap.DialogueDash, "yo", cheap.YoInconsistent, - "translit_interj", cheap.TranslitInterj, "number_magnitude", cheap.NumberMagnitude) - } - } - - // Persist the per-chunk retrieval-state (registry gate #4: convert silent memory - // degradation into a loud, visible record) plus the cheap style-flag counts. Deterministic + - // idempotent, so a resume reproduces the identical row — the memory/style counts re-derive from - // the deterministic selection + post-check, and the banknote columns are carried forward on resume - // (FL-2 above) since the raw block is not re-parsed on the fast-path. Only when a glossary is - // materialized (always true in a normal run — seedGlossary sets an at-least-empty bank). - if r.memory != nil { - if err := r.persistRetrievalState(snapID, ch, memSel, postMisses, outputChecked, cheap, bankTelem); err != nil { - return out, err - } - } - - // The export contract (D39 слой 6): NORMALISE every final text before it ships — clean OR - // flagged-stripped — so a cosmetic Unicode artifact (fullwidth glyph, U+3000 indent, stray CJK - // punctuation, a leaked combining stress mark) is fixed uniformly, not only on a flagged chunk - // (L5-normalization-fused-to-flag-path). A cosmetic sanitizer strip exports its cleaned remainder - // (recovered != ""); every other flag exports "" (the contaminated output never reaches TM/export, - // D2 / D35.4a), and exportNormalize("") == "". Pure ephemeral projection — no wire/checkpoint touch. - if flagged { - out.Disposition = DispFlagged - out.FlagReason = flagReason - out.FinalText = exportNormalize(recovered) - } else { - out.FinalText = exportNormalize(prev) - } - return out, nil -} - // injectionRenderer serializes a chunk's selected memory records into a role's injection message. type injectionRenderer func(injected []pickedEntry) string diff --git a/backend/internal/pipeline/disposition.go b/backend/internal/pipeline/disposition.go index 9ee043b..68459f2 100644 --- a/backend/internal/pipeline/disposition.go +++ b/backend/internal/pipeline/disposition.go @@ -111,7 +111,9 @@ const ( // re-runs a skipped stage (fresh spend), ok→flagged burns a fresh escalation hop. // Folded into the snapshot exactly like coverageGateVersion, so such a change is a // loud --resnapshot, not a silent divergence (external-review finding). -const classifierVersion = "classify-v1-refusal+echo015+loop" +// Ш-2 (see memnorm.go): unicode.Version is woven in so a toolchain Unicode bump that shifts the +// echo/refusal normalization or character classification re-verdicts a resumed chunk LOUDLY (--resnapshot). +const classifierVersion = "classify-v1-refusal+echo015+loop+u" + unicode.Version // decodeErrorFinish is the finish_reason the runner stores on a billed-but- // unreadable 2xx (BilledDecodeError). classify() recognises it so a RESUMED diff --git a/backend/internal/pipeline/escalation.go b/backend/internal/pipeline/escalation.go index 6bd13f6..2a566e7 100644 --- a/backend/internal/pipeline/escalation.go +++ b/backend/internal/pipeline/escalation.go @@ -109,6 +109,15 @@ func (r *Runner) maybeEscalate(ctx context.Context, st config.Stage, snapID stri } mayHop := fbExists != nil if !mayHop { + // Fresh hop: serialize the budget admission THROUGH the paid settle across the parallel the draft wave draft + // workers (R1, escMu). escalationBudgetRemains is a non-atomic read-then-act over EscalationSpentUSD, + // so without this N concurrent draft chunks could each read spent 0 { lastStage = r.Pipeline.Stages[n-1].Name } - // Index the final-stage rows by chunk key (the exported text + verdict live there) and record the - // snapshot ids the rows carry (for the drift check). + // Index the final-stage rows by their addressing key (the exported text + verdict live there) and + // record the snapshot ids they carry. Under the R1 wave model the SHIPPING stage is the editor, run + // per EDIT UNIT — so its chunk_status rows exist only at each unit's LEADER (chapter, firstChunkIdx), + // NOT per draft chunk. finalRow therefore holds one entry per output unit (per draft chunk for a + // draft-only pipeline). All these rows carry the FINAL wave's snapshot (edit-wave snapshot for an edit + // pipeline, draft-wave snapshot for draft-only). finalRow := map[chunkKey]store.ChunkStatus{} - snapSeen := map[string]bool{} for _, cs := range statuses { if cs.Stage != lastStage { - continue // the exported text and the chunk's final verdict live on the final stage's row + continue // the exported text and the unit's final verdict live on the final stage's row } finalRow[chunkKey{cs.Chapter, cs.ChunkIdx}] = cs - if cs.SnapshotID != "" { - snapSeen[cs.SnapshotID] = true - } } - // F4: the $0 source manifest is the authoritative chunk set — join it so a PENDING chunk is explicit - // and a GHOST (deleted-source) row is not exported as if live. + // F4: the $0 source manifest is authoritative. Under the wave model the export granularity is the EDIT + // UNIT (the editor collapses a unit's member chunks into ONE final text), so join the manifest into + // output units — each a (chapter, firstChunkIdx) key + the unit's joined source (the --pairs column + // aligned byte-for-byte to how the edit wave concatenated the members). A draft-only pipeline has one output per + // draft chunk (the draft ships). Iterating units keeps a PENDING unit explicit and a GHOST row visible. manifest, err := r.bookChunks() if err != nil { return nil, err } + units := r.outputUnits(manifest) exp := &BookExport{BookID: r.Book.BookID, Chunks: []ChunkExport{}} inManifest := map[chunkKey]bool{} - for _, ch := range manifest { - k := chunkKey{ch.Chapter, ch.ChunkIdx} - inManifest[k] = true + for _, u := range units { + key := chunkKey{u.Chapter, u.FirstChunkIdx} + inManifest[key] = true exp.TotalChunks++ - cs, ok := finalRow[k] + cs, ok := finalRow[key] if !ok { - pend := ChunkExport{Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Disposition: exportPending} + pend := ChunkExport{Chapter: u.Chapter, ChunkIdx: u.FirstChunkIdx, Disposition: exportPending} if pairs { - pend.Source = ch.Text + pend.Source = u.sourceText() } exp.PendingChunks++ exp.Chunks = append(exp.Chunks, pend) continue } - ce, err := r.chunkExport(cs, gateOn, missByChunk[k]) + ce, err := r.chunkExport(cs, gateOn, missByChunk[key]) if err != nil { return nil, err } if pairs { - ce.Source = ch.Text // the src↔target column for the DC1/DC2 FP-measure (--pairs) + ce.Source = u.sourceText() // the unit src↔target column for the DC1/DC2 FP-measure (--pairs) } exp.Chunks = append(exp.Chunks, ce) } - // F4: GHOST rows — a stored final row whose chunk is NOT in the current manifest (source shrunk since - // the run). Dropped (never exported as if live) but counted + WARNed so the drop is loud. + // F4: GHOST rows — a stored final row whose unit-leader key is NOT in the current manifest units + // (source shrunk since the run). Dropped (never exported as if live) but counted + WARNed. for k := range finalRow { if !inManifest[k] { exp.GhostRows++ @@ -158,23 +162,51 @@ func (r *Runner) Export(pairs bool) (*BookExport, error) { "book", r.Book.BookID, "ghost_rows", exp.GhostRows) } - // F3: config/gate drift — only meaningful on a single stored snapshot (multi-snapshot drift is - // already visible in the per-chunk snapshot_id). Compute the CURRENT config's projected snapshot - // read-only and compare; surface a mismatch as a flag + WARN, never silently. - if len(snapSeen) == 1 { - var stored string - for s := range snapSeen { - stored = s + // F3: config/gate drift — the stored rows carry PER-WAVE snapshots (draft rows → draft-wave snapshot, edit rows + // → edit-wave snapshot), so compare EACH wave against its current projection (like status). A change in EITHER + // wave means `translate` would --resnapshot (a draft-config change re-pins the draft wave and cascades + // to the edit via content-hash). Only meaningful when a wave's rows carry a single snapshot (a + // mid-book multi-snapshot drift is already visible in the per-row snapshot_id). + draftStageNames := stageNameSet(r.waveStagesIndexed(waveDraft)) + editStageNames := stageNameSet(r.waveStagesIndexed(waveEdit)) + draftSnaps, editSnaps := map[string]bool{}, map[string]bool{} + for _, cs := range statuses { + if cs.SnapshotID == "" { + continue } - if cur, serr := r.currentSnapshotProjected(); serr != nil { - r.Log.Warn("export: config-drift check failed; drift state unknown (reported as none)", "err", serr) - } else if cur != stored { - exp.ConfigDrift = true - exp.CurrentSnapshot = cur - r.Log.Warn("export: CONFIG-DRIFT — current config renders a different snapshot than the stored rows; the gate/stage re-derivation may not match the run (translate would require --resnapshot)", - "book", r.Book.BookID, "stored", stored, "current", cur) + switch { + case draftStageNames[cs.Stage]: + draftSnaps[cs.SnapshotID] = true + case editStageNames[cs.Stage]: + editSnaps[cs.SnapshotID] = true } } + if err := r.projectStoredMemory(); err != nil { + r.Log.Warn("export: config-drift check failed; drift state unknown (reported as none)", "err", err) + } else { + checkWave := func(snaps map[string]bool, w wave) { + if len(snaps) != 1 { + return + } + var stored string + for s := range snaps { + stored = s + } + cur, _, serr := r.snapshotIDForWave(w) + if serr != nil { + r.Log.Warn("export: config-drift check failed for a wave; drift state unknown", "err", serr) + return + } + if cur != stored { + exp.ConfigDrift = true + exp.CurrentSnapshot = cur + r.Log.Warn("export: CONFIG-DRIFT — current config renders a different snapshot than the stored rows; the gate/stage re-derivation may not match the run (translate would require --resnapshot)", + "book", r.Book.BookID, "stored", stored, "current", cur, "wave", w) + } + } + checkWave(draftSnaps, waveDraft) + checkWave(editSnaps, waveEdit) + } return exp, nil } diff --git a/backend/internal/pipeline/golden_test.go b/backend/internal/pipeline/golden_test.go index adca17d..75784ac 100644 --- a/backend/internal/pipeline/golden_test.go +++ b/backend/internal/pipeline/golden_test.go @@ -10,6 +10,7 @@ import ( "net/http/httptest" "os" "path/filepath" + "regexp" "sort" "strconv" "strings" @@ -35,21 +36,23 @@ import ( // // D28.2 fixture expansion (D30.9 diff-class, this package): three ratified behaviours now // PINNED by golden, not only by the dedicated unit tests — -// • FLOOR: fake-model floors max_tokens to 4000, fake-fallback to 6000 (per-model +// - FLOOR: fake-model floors max_tokens to 4000, fake-fallback to 6000 (per-model // capabilities.min_max_tokens) → the wire max_tokens and the resolved capability move, // and the escalation HOP takes ITS OWN model's floor (ch2 hop = 6000, primary = 4000); -// • UNION: ch5 fires an OBLIQUE-ONLY decl term (老人→старик) whose FINAL text carries the +// - UNION: ch5 fires an OBLIQUE-ONLY decl term (老人→старик) whose FINAL text carries the // NOMINATIVE «старик» → postcheck_miss=0 only because the base-dst∪decl union checks the // base (revert the union → this chunk false-flags a miss); -// • SANITIZER (SUBSTANTIVE): ch6 edit leaks a service preamble → the output-sanitizer gate (ON +// - SANITIZER (SUBSTANTIVE): ch6 edit leaks a service preamble → the output-sanitizer gate (ON // in the fixture pipeline) flags it FlagSanitizerDefect and the edit is DROPPED (final_text ""). +// // D38 infra-pack cells (pin the cosmetic strip-and-export path, D35.4a — final_hash points at a // derived $0 sanitized checkpoint so the export contract yields the cleaned text; resume re-serves // it identically at $0): -// • SANITIZER (COSMETIC markdown): ch7 edit leaks a leading «### Глава 7» → flagged +// - SANITIZER (COSMETIC markdown): ch7 edit leaks a leading «### Глава 7» → flagged // sanitizer_stripped, final_text = «Глава 7\n\n…» (the «### » stripped), a derived checkpoint holds it; -// • SANITIZER (COSMETIC CJK): ch8 edit leaks a sparse «特产» → flagged sanitizer_stripped, final_text +// - SANITIZER (COSMETIC CJK): ch8 edit leaks a sparse «特产» → flagged sanitizer_stripped, final_text // = the run removed and the seam tidied. +// // A cell with AMBIGUOUS>0 (an auto/draft candidate forcing a post-check) remains an OPTIONAL // future extension, deliberately NOT added here. // @@ -64,9 +67,9 @@ const ( goldenEchoMarker = "響動計画" goldenRefusalMarker = "拒絶計画" goldenUnionMarker = "老人の秘密" // ch5 — oblique-only decl union case - goldenSanitizerMarker = "序文漏洩" // ch6 — sanitizer preamble-leak case (SUBSTANTIVE → dropped) - goldenMarkdownMarker = "見出漏洩" // ch7 — cosmetic markdown «### Глава» leak (STRIPPED + exported) - goldenCJKMarker = "漢字漏洩" // ch8 — cosmetic CJK-leak «特产» (STRIPPED + exported) + goldenSanitizerMarker = "序文漏洩" // ch6 — sanitizer preamble-leak case (SUBSTANTIVE → dropped) + goldenMarkdownMarker = "見出漏洩" // ch7 — cosmetic markdown «### Глава» leak (STRIPPED + exported) + goldenCJKMarker = "漢字漏洩" // ch8 — cosmetic CJK-leak «特产» (STRIPPED + exported) ) // goldenRespond is the deterministic mock provider brain. The response text is a pure @@ -178,14 +181,35 @@ func captureGolden(t *testing.T, label string, r *Runner, res *BookResult, wireB fl := func(f float64) string { return strconv.FormatFloat(f, 'f', -1, 64) } w("==== run %s ====", label) - snapID, payload, err := r.snapshotID() + // R1: the driver pins each wave's jobs/rows to its OWN snapshot (draft rows → the draft-wave snapshot + // over the base bank, edit rows → the edit-wave snapshot over the enriched bank), so the golden pins + // BOTH — and the base/enriched split that keeps «переоплата ОДНА». + draftSnap, draftSnapPayload, err := r.snapshotIDForWave(waveDraft) if err != nil { t.Fatal(err) } - w("snapshot_id: %s", snapID) - w("snapshot_payload: %s", payload) + editSnap, editSnapPayload, err := r.snapshotIDForWave(waveEdit) + if err != nil { + t.Fatal(err) + } + w("snapshot_draft: %s", draftSnap) + w("snapshot_draft_payload: %s", draftSnapPayload) + w("snapshot_edit: %s", editSnap) + w("snapshot_edit_payload: %s", editSnapPayload) w("brief_hash: %s", r.Book.BriefHash()) w("memory_version: %s", r.memoryVersion()) + w("base_memory_version: %s", r.baseMemoryVersion()) + // stageWaveSnap maps a stage NAME to its wave's snapshot, so each stored row's snap_match compares + // against the RIGHT per-wave snapshot (a draft row against the draft-wave snapshot, an edit row against + // the edit-wave one). retrieval_state rows are draft-basis (written in the draft wave), so they compare + // against the draft-wave snapshot. + stageWaveSnap := map[string]string{} + for _, ws := range r.waveStagesIndexed(waveDraft) { + stageWaveSnap[ws.st.Name] = draftSnap + } + for _, ws := range r.waveStagesIndexed(waveEdit) { + stageWaveSnap[ws.st.Name] = editSnap + } w("-- book result --") w("chunks=%d flagged=%d exit=%d total_usd=%s", len(res.Chunks), res.Flagged, res.ExitCode(), fl(res.TotalUSD)) @@ -217,7 +241,7 @@ func captureGolden(t *testing.T, label string, r *Runner, res *BookResult, wireB }) for _, cs := range css { w("ch%d/%d %s snap_match=%t content_hash=%s disp=%s flag=%q attempts=%d final_hash=%s cost=%s escalated=%t esc_model=%q detail=%q", - cs.Chapter, cs.ChunkIdx, cs.Stage, cs.SnapshotID == snapID, cs.ContentHash, cs.Disposition, + cs.Chapter, cs.ChunkIdx, cs.Stage, cs.SnapshotID == stageWaveSnap[cs.Stage], cs.ContentHash, cs.Disposition, cs.FlagReason, cs.Attempts, cs.FinalHash, fl(cs.CostUSD), cs.Escalated, cs.EscalationModel, cs.Detail) } @@ -246,7 +270,7 @@ func captureGolden(t *testing.T, label string, r *Runner, res *BookResult, wireB }) for _, rs := range rss { w("ch%d/%d snap_match=%t exact=%d sticky=%d ambiguous=%d spoiler=%d evicted=%d postcheck_miss=%d style_flags=%d trust_gated=%d", - rs.Chapter, rs.ChunkIdx, rs.SnapshotID == snapID, rs.NExactHits, rs.NSticky, rs.NAmbiguousFlagged, + rs.Chapter, rs.ChunkIdx, rs.SnapshotID == draftSnap, rs.NExactHits, rs.NSticky, rs.NAmbiguousFlagged, rs.NSpoilerBlocked, rs.NEvicted, rs.NPostcheckMiss, rs.NStyleFlags, rs.NTrustGatedSuppress) w(" injected_ids=%s postcheck_detail=%s style_detail=%s trust_gate_detail=%s", rs.InjectedIDs, rs.PostcheckDetail, rs.StyleDetail, rs.TrustGateDetail) } @@ -304,6 +328,12 @@ func TestGoldenDeterminism(t *testing.T) { capture += captureGolden(t, "2 (resume)", r2, res2, nil) if os.Getenv("TM_UPDATE_GOLDEN") == "1" { + // Ш-1: print the masked structural diff BEFORE writing, so a re-capture is safe-by-construction — + // a version-only re-capture shows 0 verdict/wire changes; a ratified structural change (the R1 wave + // switch) shows them for a human to confirm (attached to the landing report). + if prev, rerr := os.ReadFile(goldenFile); rerr == nil { + t.Logf("%s", goldenMaskedDiff(string(prev), capture)) + } if err := os.WriteFile(goldenFile, []byte(capture), 0o644); err != nil { t.Fatal(err) } @@ -321,6 +351,83 @@ func TestGoldenDeterminism(t *testing.T) { } } +// goldenHexRE matches a hash-like run (≥12 hex chars) — snapshot ids, request/content/final hashes, the +// memory versions — everything that moves on a --resnapshot without a verdict change. +var goldenHexRE = regexp.MustCompile(`[0-9a-f]{12,}`) + +// goldenWireIdxRE matches a wire-body line's call index prefix ("[12] ") — normalised so a call reorder +// (the wave driver runs all drafts, then all edits) is not counted as a wire change. +var goldenWireIdxRE = regexp.MustCompile(`^\[\d+\] `) + +// maskGoldenLines masks the volatile hash/version fields of a golden capture: a snapshot PAYLOAD line +// (metadata whose version strings + field set move on a toolchain/table/schema bump) is blanked whole; every +// other line has its hash-like runs replaced. What survives is the verdict/wire content — final texts, +// dispositions, flags, counts, and the request BODIES (whose bytes are the wire). +func maskGoldenLines(s string) []string { + lines := strings.Split(s, "\n") + for i, ln := range lines { + if strings.HasPrefix(ln, "snapshot_draft_payload:") || strings.HasPrefix(ln, "snapshot_edit_payload:") || strings.HasPrefix(ln, "snapshot_payload:") { + lines[i] = "snapshot_payload: ⟨masked⟩" + continue + } + // Normalise the wire-body call index: the wave driver reorders the calls (all drafts, then all + // edits) vs the sequential interleave, so a byte-identical request body carries a different [N]. + // Masking the index lets a reordered-but-identical body match, so the diff shows only GENUINE + // wire changes (the concatenated edit input of a multi-chunk unit), not the reorder. + ln = goldenWireIdxRE.ReplaceAllString(ln, "[⟨i⟩] ") + lines[i] = goldenHexRE.ReplaceAllString(ln, "⟨hex⟩") + } + return lines +} + +// multisetDiff returns the lines of `a` that are not covered by `b` (multiset semantics), i.e. lines added +// or changed going b→a. Order-insensitive, so it survives the row insert/delete a structural change makes. +func multisetDiff(a, b []string) []string { + counts := map[string]int{} + for _, ln := range b { + counts[ln]++ + } + var out []string + for _, ln := range a { + if counts[ln] > 0 { + counts[ln]-- + continue + } + out = append(out, ln) + } + return out +} + +// goldenMaskedDiff (Ш-1) makes a golden re-capture SAFE-BY-CONSTRUCTION: before overwriting the golden it +// masks every volatile hash/version field in BOTH the old golden and the new capture, then reports how many +// lines changed ONLY in masked fields ("version-only") vs in real verdict/wire content. A clean toolchain/ +// version re-capture reports ZERO verdict/wire changes; a ratified structural change (the R1 wave switch) +// reports them so a human confirms each is intended (the masked diff attached to the landing report). The +// masked lines are compared as multisets, so row insertions/deletions (the wave switch drops per-unit edit +// rows) do not smear the count across every following line. +func goldenMaskedDiff(oldGolden, newCapture string) string { + rawAdded := multisetDiff(strings.Split(newCapture, "\n"), strings.Split(oldGolden, "\n")) + rawRemoved := multisetDiff(strings.Split(oldGolden, "\n"), strings.Split(newCapture, "\n")) + maskedAdded := multisetDiff(maskGoldenLines(newCapture), maskGoldenLines(oldGolden)) + maskedRemoved := multisetDiff(maskGoldenLines(oldGolden), maskGoldenLines(newCapture)) + verdictChanges := len(maskedAdded) + len(maskedRemoved) + versionOnly := (len(rawAdded) + len(rawRemoved)) - verdictChanges + var b strings.Builder + fmt.Fprintf(&b, "golden masked-diff (Ш-1): %d verdict/wire change line(s), %d version-only line(s)\n", verdictChanges, versionOnly) + show := maskedAdded + if len(maskedRemoved) > len(show) { + show = maskedRemoved + } + for i, ln := range show { + if i >= 30 { + fmt.Fprintf(&b, " … (+%d more masked changes)\n", len(show)-i) + break + } + fmt.Fprintf(&b, " ~ %s\n", ln) + } + return b.String() +} + // diffHint points a human at the first diverging line — the full capture is too big // for a useful t.Fatalf dump. func diffHint(want, got string) string { diff --git a/backend/internal/pipeline/memnorm.go b/backend/internal/pipeline/memnorm.go index fa8e50b..1d522ba 100644 --- a/backend/internal/pipeline/memnorm.go +++ b/backend/internal/pipeline/memnorm.go @@ -40,7 +40,14 @@ var trad2simpRaw string // editing/completing the data file also invalidates — drift-proof (D8): you cannot // forget to bump a version when you change the table, because the table's bytes ARE // the version. -const memoryNormAlgoVersion = "memnorm-v3-nfkc+apos+stripignorable+trad+kana+lower/nfc+dash+apos+stripignorable+lower+yofold" +// Ш-2 (D39.16, folded here in R1): unicode.Version is woven into the algorithm tag so a Unicode-table +// bump (a go toolchain upgrade — NFKC/NFC via x/text, unicode.Is(Cf), the kana range, significantLen's +// unicode.Han/Cyrillic predicates) changes this version → the snapshot moves → a LOUD --resnapshot, +// never a silent match-behaviour change on already-checkpointed chunks. TRIPWIRE: do NOT bump the +// toolchain past the pinned Unicode edition without a --resnapshot (we are on go1.26.4 / Unicode 15.0.0). +// (x/text/norm carries its OWN Unicode edition independent of stdlib unicode.Version — a standalone x/text +// dependency bump must be treated like a toolchain bump, i.e. a deliberate --resnapshot; residual noted.) +const memoryNormAlgoVersion = "memnorm-v3-nfkc+apos+stripignorable+trad+kana+lower/nfc+dash+apos+stripignorable+lower+yofold+u" + unicode.Version var ( // trad2simp is the parsed Traditional→Simplified single-char map (data/trad2simp.txt). diff --git a/backend/internal/pipeline/memory.go b/backend/internal/pipeline/memory.go index 25e96eb..ce3404f 100644 --- a/backend/internal/pipeline/memory.go +++ b/backend/internal/pipeline/memory.go @@ -131,11 +131,11 @@ type MemoryBank struct { ac *ahoCorasick keyOwners map[string][]int // normalized key → indices of entries that contributed it // enrichedVersion folds ALL foldable rows incl Source:mined — the memory version of the EDIT - // wave (snapshot_W2). baseVersion EXCLUDES Source:mined — the memory version of the DRAFT wave - // (snapshot_W1), so a W1.5 bank-enrichment (adding mined rows) moves ONLY snapshot_W2, keeping - // W1 checkpoints valid (WS1 §1в, «переоплата ОДНА»). The two are DOMAIN-SEPARATED (a "base-excl- + // wave (edit-wave snapshot). baseVersion EXCLUDES Source:mined — the memory version of the DRAFT wave + // (draft-wave snapshot), so a the bank-mining stop bank-enrichment (adding mined rows) moves ONLY edit-wave snapshot, keeping + // draft-wave checkpoints valid (WS1 §1в, «переоплата ОДНА»). The two are DOMAIN-SEPARATED (a "base-excl- // mined" tag in the base fold), so base ≠ enriched for EVERY row set — even a mined-free book (a - // W1 job must never content-address to a W2 checkpoint). The load-bearing invariant is not + // the draft wave job must never content-address to a the edit wave checkpoint). The load-bearing invariant is not // equality but STABILITY: base stays fixed as mined rows are added; only enriched moves. enrichedVersion string baseVersion string @@ -182,7 +182,7 @@ type memorySelection struct { // Version is the ENRICHED memory version (all approved rows incl mined) — the edit-wave / whole-book // memory component. BaseVersion excludes Source:mined (the draft-wave component). They are // DOMAIN-SEPARATED — base ≠ enriched for ANY row set, including a mined-free book (never assert -// equality) — but base stays STABLE when a W1.5 pass adds mined rows, which is what keeps W1 +// equality) — but base stays STABLE when a the bank-mining stop pass adds mined rows, which is what keeps the draft wave // checkpoints valid («переоплата ОДНА»). func (b *MemoryBank) Version() string { return b.enrichedVersion } func (b *MemoryBank) BaseVersion() string { return b.baseVersion } @@ -256,8 +256,8 @@ func materializeMemory(rows []store.GlossaryEntry, gateOn bool) *MemoryBank { } sort.Strings(allKeys) // deterministic automaton construction b.ac = buildAC(allKeys) - b.enrichedVersion = computeMemoryVersion(rows, gateOn) // all approved incl mined (W2) - b.baseVersion = computeMemoryVersionScoped(rows, gateOn, true) // excl Source:mined (W1) + b.enrichedVersion = computeMemoryVersion(rows, gateOn) // all approved incl mined (the edit wave) + b.baseVersion = computeMemoryVersionScoped(rows, gateOn, true) // excl Source:mined (the draft wave) return b } @@ -278,8 +278,8 @@ func computeMemoryVersion(rows []store.GlossaryEntry, gateOn bool) string { // computeMemoryVersionScoped is computeMemoryVersion with an explicit Source-scope: excludeMined // drops every Source:"mined" row from the fold (WS1 §1в base-bank-version). The DRAFT-wave snapshot -// (snapshot_W1) folds base (excludeMined=true) so a W1.5 pass that ADDS mined rows moves ONLY the -// enriched (edit-wave) version — keeping W1 checkpoints valid, «переоплата ОДНА». Deterministic (a +// (draft-wave snapshot) folds base (excludeMined=true) so a the bank-mining stop pass that ADDS mined rows moves ONLY the +// enriched (edit-wave) version — keeping draft-wave checkpoints valid, «переоплата ОДНА». Deterministic (a // Source filter over the same ORDER BY-stable rows). excludeMined=false is BYTE-IDENTICAL to the // pre-split fold (no extra field), so the enriched hash / existing snapshots do not move; the // excludeMined=true variant adds a domain separator so base and enriched never collide. diff --git a/backend/internal/pipeline/memory_wave_test.go b/backend/internal/pipeline/memory_wave_test.go index ad72ed7..4cc0b1b 100644 --- a/backend/internal/pipeline/memory_wave_test.go +++ b/backend/internal/pipeline/memory_wave_test.go @@ -7,31 +7,31 @@ import ( ) // TestBaseEnrichedMemoryVersionSplit pins the WS1 §1в per-wave bank-version mechanism: the BASE -// version (draft wave / snapshot_W1) excludes Source:"mined" rows, so adding a mined approved row -// after W1 moves ONLY the ENRICHED version (edit wave / snapshot_W2) — keeping W1 checkpoints valid -// («переоплата ОДНА»). A broken split (base folding mined) would move snapshot_W1 and re-bill W1. +// version (draft wave / draft-wave snapshot) excludes Source:"mined" rows, so adding a mined approved row +// after the draft wave moves ONLY the ENRICHED version (edit wave / snapshot_W2) — keeping the draft wave checkpoints valid +// («переоплата ОДНА»). A broken split (base folding mined) would move draft-wave snapshot and re-bill the draft wave. func TestBaseEnrichedMemoryVersionSplit(t *testing.T) { seedRows := []store.GlossaryEntry{ {Src: "方源", Dst: "Фан Юань", Status: "approved", Source: "seed"}, {Src: "古月", Dst: "Гу Юэ", Status: "approved", Source: "ruby"}, } base0 := materializeMemory(seedRows, false) - // Same rows PLUS a mined approved row (as a W1.5 pass would add). + // Same rows PLUS a mined approved row (as a the draft wave.5 pass would add). enrichedRows := append([]store.GlossaryEntry{}, seedRows...) enrichedRows = append(enrichedRows, store.GlossaryEntry{Src: "蛊", Dst: "гу", Status: "approved", Source: "mined"}) bank1 := materializeMemory(enrichedRows, false) // 1) Base version is UNCHANGED by the mined addition (draft wave stays valid). if base0.BaseVersion() != bank1.BaseVersion() { - t.Fatalf("base version moved on a mined-row addition — snapshot_W1 would re-bill W1:\n before %s\n after %s", + t.Fatalf("base version moved on a mined-row addition — draft-wave snapshot would re-bill the draft wave:\n before %s\n after %s", base0.BaseVersion(), bank1.BaseVersion()) } // 2) Enriched version DID move (edit wave sees the new mined canon). if base0.Version() == bank1.Version() { t.Fatalf("enriched version did NOT move on a mined-row addition — the edit wave would miss the mined canon") } - // 3) Base ≠ enriched even before any mined row (domain-separated), so a W1 job can never - // accidentally content-address to a W2 checkpoint. + // 3) Base ≠ enriched even before any mined row (domain-separated), so a the draft wave job can never + // accidentally content-address to a the edit wave checkpoint. if base0.BaseVersion() == base0.Version() { t.Fatalf("base and enriched versions collide over identical rows — they must be domain-separated") } diff --git a/backend/internal/pipeline/memseed.go b/backend/internal/pipeline/memseed.go index b1cdfe6..f08e719 100644 --- a/backend/internal/pipeline/memseed.go +++ b/backend/internal/pipeline/memseed.go @@ -506,7 +506,7 @@ func hasAliasSurface(aliases []store.GlossaryAlias, surface string) bool { // loud error listing every problem (WS3 (д): "сухой прогон фейл-лаудов реального loadGlossarySeed по // дельте"). $0, no store, no LLM — it runs the same loader translate would, so a delta that lints clean // here is guaranteed loadable, and a shared-key livelock / duplicate / missing-dst is caught BEFORE the -// W1.5 reseed instead of aborting a paid run. +// bank-mining reseed instead of aborting a paid run. func SeedLint(path string) error { entries, err := loadGlossarySeed(path) if err != nil { @@ -518,13 +518,13 @@ func SeedLint(path string) error { return nil } -// --- mined → candidates (WS3 W1.5 mined-write path) ----------------------------- +// --- mined → candidates (WS3 bank-mining mined-write path) ----------------------------- -// minedToCandidates converts the miner's WHICH proposals (MineBank) into store candidates for the W1.5 +// minedToCandidates converts the miner's WHICH proposals (MineBank) into store candidates for the the bank-mining stop // reseed (WS3 / §1в mined-write path). It is the DEDICATED mined path the plan requires: it stamps // Source:"mined" (mirroring rubyToCandidates' Source:"ruby"), NOT the Source:"seed" that loadGlossarySeed -// hardcodes — so a mined row is EXCLUDED from the base-bank-version (BaseVersion) and the W1.5 bank -// enrichment moves ONLY snapshot_W2, keeping W1 checkpoints valid («переоплата ОДНА», §1в/F2). Every +// hardcodes — so a mined row is EXCLUDED from the base-bank-version (BaseVersion) and the the bank-mining stop bank +// enrichment moves ONLY snapshot_W2, keeping the draft wave checkpoints valid («переоплата ОДНА», §1в/F2). Every // candidate is status=auto with NO dst (the WHAT is delivered by the banknote/owner sign, WS4): inert on // the hot path until a human/batch promotes it, never a blind name-lock. A src already covered by the // manual seed is skipped (the curated entry wins), exactly like rubyToCandidates. Deterministic (MineBank diff --git a/backend/internal/pipeline/miner_emit.go b/backend/internal/pipeline/miner_emit.go index cc7e0cc..2737dae 100644 --- a/backend/internal/pipeline/miner_emit.go +++ b/backend/internal/pipeline/miner_emit.go @@ -15,7 +15,7 @@ import ( // which carries §B2 fragment noise), clusters aliases (tier-1), and emits one MinedTerm per NEW entity. // // Discipline: the miner NEVER writes `approved` — every emitted term is a `draft`/`auto` PROPOSAL for the -// owner to sign (§C2). In default B the WHAT (dst) is delivered by the banknote (WS4) at the W1.5 sign +// owner to sign (§C2). In default B the WHAT (dst) is delivered by the banknote (WS4) at the bank-mining sign // boundary, so the miner emits WHICH-only candidates (status:auto, no dst — inert until a dst + owner // promotion). A candidate that clusters with an existing seed surface is an alias-of-existing and is left // for the owner to attach (not emitted as a new entity), so the delta is genuinely new terms. @@ -31,7 +31,7 @@ const emitRankCap = 200 // MinedTerm is one WHICH candidate the miner proposes (a seed-delta entry). The miner never writes a dst // (default B) or `approved`; the caller persists it via the mined-write path (Source:"mined", status -// auto) and the owner signs it at W1.5. +// auto) and the owner signs it at the bank-mining stop. type MinedTerm struct { Src string Type string // name|place|title|term (the candidate's first pattern type; "" → term) @@ -157,7 +157,7 @@ func MineBank(chunks []MinerChunk, contrast *Contrast, seed []store.GlossaryEntr // MinedDeltaYAML serializes the mined delta into the seedTerm YAML schema (§C2-7) — the owner-sign // artifact and the `tmctl seed-lint` input. Every term is status:auto with NO dst (WHICH-only, default -// B; the WHAT is delivered by the banknote at W1.5). It reuses the EXISTING seedTerm schema (no new +// B; the WHAT is delivered by the banknote at the bank-mining stop). It reuses the EXISTING seedTerm schema (no new // fields — §3(б)); evidence / zones live in the sidecar sign-map, not the seed. The output is guaranteed // loadable by loadGlossarySeed (status:auto may lack a dst); seed-lint proves it against the real loader. func MinedDeltaYAML(mined []MinedTerm) (string, error) { diff --git a/backend/internal/pipeline/miner_test.go b/backend/internal/pipeline/miner_test.go index c6e1091..7606c47 100644 --- a/backend/internal/pipeline/miner_test.go +++ b/backend/internal/pipeline/miner_test.go @@ -325,19 +325,19 @@ func TestMinedToCandidatesStampsMinedSource(t *testing.T) { func TestMinedDeltaStaysBaseBankStable(t *testing.T) { // The mined delta (Source:"mined") must NOT move BaseVersion — the load-bearing «переоплата ОДНА» - // invariant (§1в): a W1.5 mined-row addition moves only the enriched version. (Sibling of the + // invariant (§1в): a the draft wave.5 mined-row addition moves only the enriched version. (Sibling of the // Block-A TestBaseEnrichedMemoryVersionSplit, here through the real mined-write path.) seed := []store.GlossaryEntry{{Src: "方源", Dst: "Фан Юань", Status: "approved", Source: "seed"}} base0 := materializeMemory(seed, false) mined := minedToCandidates([]MinedTerm{{Src: "龙公", Type: "name", SinceCh: 1, Freq: 5}}, map[string]bool{"方源": true}) // A mined candidate is status=auto (not folded even into enriched when gate off) — promote it to - // approved to exercise the split, as the owner sign would at W1.5. + // approved to exercise the split, as the owner sign would at the draft wave.5. mined[0].Status = "approved" mined[0].Dst = "Лун Гун" enriched := append(append([]store.GlossaryEntry{}, seed...), mined...) bank1 := materializeMemory(enriched, false) if base0.BaseVersion() != bank1.BaseVersion() { - t.Fatalf("base-bank-version moved on a Source:mined addition — snapshot_W1 would re-bill W1") + t.Fatalf("base-bank-version moved on a Source:mined addition — draft-wave snapshot would re-bill the draft wave") } if base0.Version() == bank1.Version() { t.Fatalf("enriched version must move on a mined approved addition") diff --git a/backend/internal/pipeline/mining.go b/backend/internal/pipeline/mining.go new file mode 100644 index 0000000..b910515 --- /dev/null +++ b/backend/internal/pipeline/mining.go @@ -0,0 +1,91 @@ +package pipeline + +import ( + "context" + "fmt" + "os" + + "textmachine/backend/internal/store" +) + +// mining.go: bank-mining stop boundary (WS3 wired live, R1). Between the drafts done and the edit wave, the +// miner scores WHICH-candidates over the the draft wave source (the detector is offline — it reads the SOURCE, not the +// drafts; drafts only mark that a chapter was reached) against the general-zh contrast, emits an +// alias-clustered seed-delta (default B, WHICH-only — the dst is the owner's to attach via the banknote at +// sign time), and — on a NON-EMPTY delta — writes the owner SIGNATURE MAP and STOPS before the edit wave. The owner +// reviews it, promotes terms into the mined-delta file (approved + dst), and re-runs: seedGlossary loads +// those as Source:mined (moving only edit-wave snapshot), the draft wave resumes at $0, the bank-mining stop re-mines (the now-seeded terms are +// excluded → the delta empties), and the edit wave runs. Mining is OFF (auto-continue) unless a langpack AND a contrast +// artifact are both configured — so every $0 test / the golden fixture (no contrast) auto-continues. + +// signatureMapPath is where the bank-mining stop writes the mined-delta YAML for owner sign — beside the project DB, so it +// travels with the book state (never in git, like the DB). Deterministic (no time/rand). +func (r *Runner) signatureMapPath() string { + return r.Book.ProjectDB + ".mined-signature.yaml" +} + +// runBankMiningStop executes the bank-mining stop. Returns stopped=true (with the signature map written and +// r.lastMinedCount set) when the miner proposes a non-empty delta; stopped=false (auto-continue) when mining +// is unconfigured or the delta is empty. $0 to providers (the detector is deterministic + offline). +func (r *Runner) runBankMiningStop(ctx context.Context, chunks []Chunk) (stopped bool, err error) { + if r.pack == nil || r.Pipeline.Mining.ContrastPath == "" { + return false, nil // mining not configured → auto-continue to the edit wave + } + f, err := os.Open(r.Pipeline.Mining.ContrastPath) + if err != nil { + return false, fmt.Errorf("pipeline: the bank-mining stop open mining contrast %s: %w", r.Pipeline.Mining.ContrastPath, err) + } + defer f.Close() + contrast, err := LoadContrast(f) + if err != nil { + return false, fmt.Errorf("pipeline: the bank-mining stop load mining contrast %s: %w", r.Pipeline.Mining.ContrastPath, err) + } + + // The miner works over the memnorm-normalized SOURCE of every chunk (the candidate space matches the + // glossary/GT space). Deterministic; the annotation/blurb rule is handled inside MineBank's filters. + minerChunks := make([]MinerChunk, len(chunks)) + for i, ch := range chunks { + minerChunks[i] = MinerChunk{Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, NSource: normalizeSourceKey(ch.Text)} + } + seed, err := r.Store.GlossaryForBook(r.Book.BookID) + if err != nil { + return false, fmt.Errorf("pipeline: the bank-mining stop read glossary for mining: %w", err) + } + mined := MineBank(minerChunks, contrast, seed, frozenMinerConfig(), r.pack) + r.lastMinedCount = len(mined) + if len(mined) == 0 { + r.Log.InfoContext(ctx, "bank-mining: empty delta, auto-continuing to the edit wave", "book", r.Book.BookID) + return false, nil + } + + // Non-empty delta → write the owner signature map (the mined seed-delta YAML) and STOP before the edit wave. + yamlDelta, err := MinedDeltaYAML(mined) + if err != nil { + return false, fmt.Errorf("pipeline: the bank-mining stop marshal mined delta: %w", err) + } + if err := os.WriteFile(r.signatureMapPath(), []byte(yamlDelta), 0o644); err != nil { + return false, fmt.Errorf("pipeline: the bank-mining stop write signature map %s: %w", r.signatureMapPath(), err) + } + r.Log.WarnContext(ctx, "bank-mining: new terms await owner signature; run STOPPED before the edit wave (review the signature map, promote terms into the mined-delta file, then resume)", + "book", r.Book.BookID, "terms", len(mined), "signature_map", r.signatureMapPath()) + return true, nil +} + +// loadMinedDelta reads the owner-curated mined-delta YAML (book.MinedDelta) and stamps every entry +// Source:"mined" — NOT via loadGlossarySeed (which hardcodes Source:"seed", memseed.go, moving the base +// bank / draft-wave snapshot). This is the mined-write path (plan §1(в), F2): the mined terms land in the ENRICHED +// bank version but NOT the base, so adding them moves ONLY edit-wave snapshot («переоплата ОДНА»). Reuses +// loadGlossarySeed's parser/validation, then re-stamps the Source. Empty path → nil (no mined terms). +func (r *Runner) loadMinedDelta() ([]store.GlossaryEntry, error) { + if r.Book.MinedDelta == "" { + return nil, nil + } + entries, err := loadGlossarySeed(r.Book.MinedDelta) + if err != nil { + return nil, fmt.Errorf("pipeline: load mined-delta %s: %w", r.Book.MinedDelta, err) + } + for i := range entries { + entries[i].Source = "mined" // override the seed loader's Source:seed → mined (base-excluded) + } + return entries, nil +} diff --git a/backend/internal/pipeline/quality.go b/backend/internal/pipeline/quality.go index 523caff..fd70910 100644 --- a/backend/internal/pipeline/quality.go +++ b/backend/internal/pipeline/quality.go @@ -102,8 +102,25 @@ func (r *Runner) QualityReport() (*QualityReport, error) { if err != nil { return nil, err } + // Total = the SHIPPING units (the manifest re-chunk, $0), matching status/export + the per-unit + // BookResult (R1): under the wave model the editor's final text is per EDIT UNIT, so ProcessedChunks + // (the lastStage rows, one per unit leader) and TotalChunks agree at unit granularity. The per-unit + // KPI/echo/strip signals land on the leader's edit row; a non-leader member's ChunkQuality row carries + // only its draft-side signals (trust-gated) with a 0 structural KPI — observability, never a gate. + chunks, err := r.bookChunks() + if err != nil { + return nil, err + } + units := r.outputUnits(chunks) + // GHOST guard (parity with Export/Status): a stored row whose unit-leader key is NOT in the current + // manifest (source shrank since the run) is a ghost — dropping it keeps ProcessedChunks ≤ TotalChunks + // and the echo/strip rates over live units only, instead of mixing in stale leader rows. + inManifest := map[chunkKey]bool{} + for _, u := range units { + inManifest[chunkKey{u.Chapter, u.FirstChunkIdx}] = true + } - rep := &QualityReport{BookID: r.Book.BookID} + rep := &QualityReport{BookID: r.Book.BookID, TotalChunks: len(units)} byChunk := map[chunkKey]*ChunkQuality{} order := []chunkKey{} chunkOf := func(k chunkKey) *ChunkQuality { @@ -124,7 +141,17 @@ func (r *Runner) QualityReport() (*QualityReport, error) { withheld := map[chunkKey]bool{} // Aggregate the stored retrieval-state signals (glossary consistency, style breakdown, trust-gated). + // A retrieval_state row is keyed per DRAFT chunk, so it is live iff its chunk is still in the manifest; + // a chunk that left the source is a ghost. (A leader row also carries the unit's post-check; if the + // leader survives, so does the unit.) + liveChunks := map[chunkKey]bool{} + for _, ch := range chunks { + liveChunks[chunkKey{ch.Chapter, ch.ChunkIdx}] = true + } for _, rs := range states { + if !liveChunks[chunkKey{rs.Chapter, rs.ChunkIdx}] { + continue // ghost retrieval_state row (chunk dropped from source) + } q := chunkOf(chunkKey{rs.Chapter, rs.ChunkIdx}) q.GlossaryMisses += rs.NPostcheckMiss q.TrustGated += rs.NTrustGatedSuppress @@ -151,15 +178,10 @@ func (r *Runner) QualityReport() (*QualityReport, error) { if n := len(r.Pipeline.Stages); n > 0 { lastStage = r.Pipeline.Stages[n-1].Name } - seen := map[chunkKey]bool{} for _, cs := range statuses { k := chunkKey{cs.Chapter, cs.ChunkIdx} - if !seen[k] { - seen[k] = true - rep.TotalChunks++ - } - if cs.Stage != lastStage { - continue // the exported text and the final verdict live on the final stage's row + if cs.Stage != lastStage || !inManifest[k] { + continue // the final verdict lives on the final stage's row (per unit); drop ghost leader rows } // Every chunk that REACHED the final stage has exactly one lastStage row (ok, cosmetic-strip, // or skipped-because-an-upstream-stage-flagged). This is the common rate denominator so the diff --git a/backend/internal/pipeline/ratelimit.go b/backend/internal/pipeline/ratelimit.go index fc07f8c..7e16233 100644 --- a/backend/internal/pipeline/ratelimit.go +++ b/backend/internal/pipeline/ratelimit.go @@ -12,7 +12,7 @@ import ( // parallelism (a token-bucket / concurrency cap, tier-dependent — 00-provider-quirks §Транспорт), // while grok is 0%. A model caps its own wave concurrency (max_concurrency) and, optionally, paces // call STARTS (min_interval). This is a TRANSPORT axis: it never touches the request bytes, so it is -// wire-neutral and NOT snapshot-folded. Guards are built once in W0, read-only in the waves; each +// wire-neutral and NOT snapshot-folded. Guards are built once in the precompute pass, read-only in the waves; each // guard's internals (a buffered-channel semaphore + a mutex-protected pacer) are concurrency-safe, // so acquiring from N wave goroutines is race-clean. @@ -79,7 +79,7 @@ func (g *rateGuard) acquire(ctx context.Context) (func(), error) { return release, nil } -// buildRateGuards constructs a guard for every reachable model in W0 (read-only in the waves). +// buildRateGuards constructs a guard for every reachable model in the precompute pass (read-only in the waves). // A model with no rate_limit config gets an unlimited (no-op) guard, so rateGuard(model) is always // non-nil and lookup-safe. func (r *Runner) buildRateGuards() { diff --git a/backend/internal/pipeline/render.go b/backend/internal/pipeline/render.go index 663fc1e..87c3ac8 100644 --- a/backend/internal/pipeline/render.go +++ b/backend/internal/pipeline/render.go @@ -47,13 +47,19 @@ import ( // (ru) tokens via fertility (est_out), draft chunks decoupled from coarse EDIT units (grouped whole // chunks to EditCeilingOut), oversized-sentence flag added. The budget itself is ALSO folded via // segmentationSnap (snapshot.go), so this version covers only the algorithm shape. -const chunkerVersion = "chunker-v5-output-budget-editunit" +// Ш-2 EXTENSION (see memnorm.go; beyond the owner-named memnorm/classifier/style set — justified: same +// silent-drift class): tokenClassCounts (chunker.go) classifies source runes via unicode.Han/Hiragana/ +// Katakana/Hangul to compute est_out, which SETS chunk boundaries → the wire. A toolchain Unicode bump that +// reclassifies a rune would silently re-chunk the book; weaving unicode.Version makes it a loud --resnapshot. +const chunkerVersion = "chunker-v5-output-budget-editunit+u" + unicode.Version // estimatorVersion versions EstimateTokens: его выход входит в max_tokens и // через него в request-hash, поэтому перекалибровка весов — тоже явная // инвалидация через snapshot, а не тихий промах всех чекпоинтов (находка // ревью: code-only правка эстиматора пере-оплатила бы полкниги). -const estimatorVersion = "estimator-v0" +// Ш-2 EXTENSION (see memnorm.go): EstimateTokens classifies runes via the same unicode ranges to size +// max_tokens (∈ request_hash), so a toolchain Unicode reclassification shifts the wire — folded loudly. +const estimatorVersion = "estimator-v0+u" + unicode.Version // maxTokensPolicyVersion versions the attempt→max_tokens scaling // (maxTokensForAttempt, disposition.go). attempt-0 budget is already covered by diff --git a/backend/internal/pipeline/runner.go b/backend/internal/pipeline/runner.go index b62ea9a..9693590 100644 --- a/backend/internal/pipeline/runner.go +++ b/backend/internal/pipeline/runner.go @@ -5,8 +5,11 @@ import ( "fmt" "log/slog" "os" + "path/filepath" + "sync" "textmachine/backend/internal/config" + "textmachine/backend/internal/lang" "textmachine/backend/internal/ledger" "textmachine/backend/internal/llm" "textmachine/backend/internal/store" @@ -44,7 +47,7 @@ type Runner struct { clients map[string]llm.LLMClient templates map[string]*PromptTemplate - // rateGuards is the per-model wave-concurrency guard set (WS1 §1б), built once in W0 and + // rateGuards is the per-model wave-concurrency guard set (WS1 §1б), built once in the precompute pass and // read-only in the waves — a transport axis, never snapshot-folded. nil until buildRateGuards. rateGuards map[string]*rateGuard @@ -54,6 +57,36 @@ type Runner struct { // nil until materialized (report path / no glossary) → memoryVersion() falls back // to the empty-materialization hash, a stable constant. memory *MemoryBank + + // baseMemory is the DRAFT-wave glossary bank: the BASE rows only (Source∈{seed,ruby,auto}, EXCLUDING + // Source:mined). The draft wave's injection MUST be selected over this — not the enriched `memory` — + // so it is BYTE-IDENTICAL across a bank-mining enrichment, matching the draft-wave snapshot which folds + // baseMemoryVersion (mined-excluded). Otherwise signing a mined term would change the draft wire (the + // injection is a message folded into request_hash) and silently re-bill the draft wave on the owner + // re-run — even though the base snapshot is unchanged (the review-confirmed «переоплата ОДНА» hole). + // When the book has NO mined rows (every $0 test / the golden), it is the SAME object as `memory` + // (identical content) — no double materialization, the injection is unchanged. The editor keeps the + // enriched `memory`. nil ⇔ memory is nil (materialized together in seedGlossary). + baseMemory *MemoryBank + + // pack is the book's language-data pack (internal/lang), loaded once in openRunner from + // book.LangpackRoot (D39.15/16). The the bank-mining stop bank-miner reads its tables; pack.Version() is folded into + // the snapshot (a pack edit is a loud --resnapshot). nil when the book declares no langpack_root, or + // its pair has no catalog dir — then the miner is inert (the bank-mining stop auto-continues) and the fold is omitted. + pack *lang.Pack + + // escMu serializes the single-hop escalation budget admission across the PARALLEL draft workers + // (R1). escalationBudgetRemains is a non-atomic read-then-act over EscalationSpentUSD, so N concurrent + // draft chunks could each read spent-/) +// loads FAIL-LOUD (a missing/corrupt file stops the run, never a silently-empty miner); a pair WITHOUT a +// catalog — or a book with no langpack_root — runs with a nil pack (the miner is inert, the bank-mining stop auto-continues, +// and the snapshot fold is omitted). Presence of the pair directory is the "catalog exists" signal. +func (r *Runner) loadLangPack() error { + if r.Book.LangpackRoot == "" { + return nil // no langpack declared → nil pack, miner inert + } + pairDir := filepath.Join(r.Book.LangpackRoot, r.Book.LangPair()) + if fi, err := os.Stat(pairDir); err != nil || !fi.IsDir() { + // No catalog for this pair → nil-and-run (a ja book against a zh-only root just runs без майнинга). + return nil + } + pack, err := lang.Load(r.Book.LangpackRoot, r.Book.SourceLang, r.Book.TargetLang) + if err != nil { + return fmt.Errorf("pipeline: load langpack for %s: %w", r.Book.LangPair(), err) + } + r.pack = pack + return nil +} + +// packVersion is the snapshot-folded language-pack version: pack.Version() when a pack is loaded, "" when +// not (omitted from the snapshot so a no-pack book is byte-stable and never re-billed for a feature it does +// not use). A pack DATA edit changes Version() → the snapshot moves → a loud --resnapshot (R1, drift-proof). +func (r *Runner) packVersion() string { + if r.pack != nil { + return r.pack.Version() + } + return "" +} + func (r *Runner) Close() error { return r.Store.Close() } func (r *Runner) loadTemplates() error { @@ -186,7 +256,7 @@ func (r *Runner) segBudget() SegBudget { // reachableModels enumerates every model a run can call: the union of the stage models and their // single-hop escalate_to fallbacks (stagerun.go calls r.client ONLY with model∈{st.Model, EscalateTo}). -// This set is complete and static for a book, which is what lets W0 pre-build every client (a third +// This set is complete and static for a book, which is what lets the precompute pass pre-build every client (a third // model axis — channel B / annotator — must extend this to stay race-free). Deterministic order. func (r *Runner) reachableModels() []string { seen := map[string]bool{} @@ -204,7 +274,7 @@ func (r *Runner) reachableModels() []string { return out } -// buildClients EAGER-constructs every reachable LLM client BEFORE any wave goroutine starts (W0). +// buildClients EAGER-constructs every reachable LLM client BEFORE any wave goroutine starts (the precompute pass). // After this the clients map is READ-ONLY in the waves, so r.client is lock-free and a miss is a // loud error, not a lazy build under a data race — closing the runner.go lazy-init race (D12) and // tripwiring a future un-enumerated model axis. Idempotent; BuildClient needs only the provider @@ -216,7 +286,7 @@ func (r *Runner) buildClients() error { } c, err := BuildClient(r.Models, m, r.Log) if err != nil { - return fmt.Errorf("pipeline: eager-build client for model %q (W0): %w", m, err) + return fmt.Errorf("pipeline: eager-build client for model %q (the precompute pass): %w", m, err) } r.clients[m] = c } @@ -224,11 +294,11 @@ func (r *Runner) buildClients() error { } // client returns the PRE-BUILT client for a model. Read-only (no lazy build, no lock): buildClients -// constructed every reachable client in W0, so the map is only read in the waves; a miss means an +// constructed every reachable client in the precompute pass, so the map is only read in the waves; a miss means an // un-enumerated model reached the wire and is a loud error, never a silent lazy build under a race. func (r *Runner) client(model string) (llm.LLMClient, error) { if c, ok := r.clients[model]; ok { return c, nil } - return nil, fmt.Errorf("pipeline: no pre-built client for model %q — W0 buildClients enumerates stage models ∪ escalate_to; a model outside that set reached the wire, add it to the eager set to keep the waves race-free", model) + return nil, fmt.Errorf("pipeline: no pre-built client for model %q — the precompute pass buildClients enumerates stage models ∪ escalate_to; a model outside that set reached the wire, add it to the eager set to keep the waves race-free", model) } diff --git a/backend/internal/pipeline/runner_test.go b/backend/internal/pipeline/runner_test.go index f17deef..e255bc8 100644 --- a/backend/internal/pipeline/runner_test.go +++ b/backend/internal/pipeline/runner_test.go @@ -102,16 +102,17 @@ func maxTokensOf(t *testing.T, body string) int { const fakeCallUSD = (800*1.0 + 200*0.1 + 500*2.0) / 1e6 type projectOpts struct { - source string - epub []epubChapter // when set, the source is an epub (source.epub) instead of txt - spine []string // spine order for epub - regenerate int - minMaxTokens int - bookUSD float64 - gatesYAML string // optional gates:/... block appended to pipeline.yaml - glossarySeed string // optional glossary seed YAML content; "" = no glossary - postcheckGate bool // enable the memory post-check hard gate (assumes gatesYAML is empty) - banknote bool // enable the banknote channel gate (WS4; assumes gatesYAML/postcheckGate empty) + source string + epub []epubChapter // when set, the source is an epub (source.epub) instead of txt + spine []string // spine order for epub + regenerate int + minMaxTokens int + bookUSD float64 + gatesYAML string // optional gates:/... block appended to pipeline.yaml + glossarySeed string // optional glossary seed YAML content; "" = no glossary + postcheckGate bool // enable the memory post-check hard gate (assumes gatesYAML is empty) + banknote bool // enable the banknote channel gate (WS4; assumes gatesYAML/postcheckGate empty) + waveWorkers int // wave-executor parallelism (0 → default 1, a deterministic sequential-structured run) } func setupProjectOpts(t *testing.T, providerURL string, o projectOpts) string { @@ -159,10 +160,11 @@ version: 1 defaults: { max_output_ratio: 2.0, min_max_tokens: %d } retries: { regenerate_before_escalate: %d } context: { glossary_injection: selective, glossary_token_budget: 800 } +waves: { workers: %d } stages: - { name: draft, role: translator, model: fake-model, prompt: prompts/translator.md, prompt_version: v-test, temperature: 0.3, reasoning: "off" } - { name: edit, role: editor, model: fake-model, prompt: prompts/editor.md, prompt_version: v-test, temperature: 0.4, reasoning: "off" } -%s`, o.minMaxTokens, o.regenerate, gatesBlock)) +%s`, o.minMaxTokens, o.regenerate, o.waveWorkers, gatesBlock)) sourceName := "source.txt" if len(o.epub) > 0 { @@ -375,8 +377,14 @@ func TestRunnerSnapshotPinning(t *testing.T) { if err != nil { t.Fatal(err) } - if rec.count() != 4 { - t.Fatalf("resnapshot run must re-call both stages, calls=%d", rec.count()) + // R1 per-wave --resnapshot is SURGICAL, not all-or-nothing: the changed TRANSLATOR prompt moves only + // snapshot_W1, so the DRAFT wave re-pins and re-calls (+1). The EDITOR resumes: snapshot_W2 is unchanged + // AND its wire input (the mock draft "ЧЕРНОВИК ПЕРЕВОДА" is prompt-independent) is byte-identical, so + // its content-addressed checkpoint hits — re-billing a byte-identical wire request is exactly the D15 + // waste the per-wave snapshot avoids. Total = 2 (fresh) + 1 (draft re-call) = 3. In production a draft + // prompt change WOULD change the draft output, cascading to the editor via its content-hash (→ 4). + if rec.count() != 3 { + t.Fatalf("resnapshot run must re-call only the changed (draft) wave; the editor resumes on an unchanged wire, calls=%d", rec.count()) } if res.TotalUSD <= 0 { t.Fatal("re-translation must be billed") diff --git a/backend/internal/pipeline/seeding.go b/backend/internal/pipeline/seeding.go index 871c10f..37785ba 100644 --- a/backend/internal/pipeline/seeding.go +++ b/backend/internal/pipeline/seeding.go @@ -43,7 +43,16 @@ func (r *Runner) seedGlossary(ctx context.Context) error { r.Log.WarnContext(ctx, "ruby kana-alias skipped as a homophone collision (kana form left unmatchable; disambiguate in the seed if needed)", "skipped", strings.Join(skipped, "; ")) } - entries = append(entries, rubyToCandidates(ruby, manualSrcs)...) + // Mined-write path (R1, plan §1(в)/F2): the owner-curated mined-delta file joins the seed as + // Source:"mined" (loadMinedDelta re-stamps the seed loader's Source), so its terms fold into the + // ENRICHED bank version but NOT the base — a re-run that adds signed mined terms moves ONLY snapshot_W2. + // Loaded AFTER the seed/ruby so manualSrcs already reflects the curated seed. A `mined` term that + // duplicates a seed src is caught by approvedSharedKeyCollisions below like any other collision. + minedDelta, err := r.loadMinedDelta() + if err != nil { + return err + } + entries = append(entries, minedDelta...) for i := range entries { entries[i].BookID = r.Book.BookID } @@ -61,6 +70,25 @@ func (r *Runner) seedGlossary(ctx context.Context) error { return fmt.Errorf("pipeline: read glossary for %s: %w", r.Book.BookID, err) } r.memory = materializeMemory(rows, r.Pipeline.Gates.Glossary.PostcheckGate) + // The DRAFT wave selects over a BASE-scoped bank (Source:mined excluded) so its injection is + // byte-identical across a bank-mining enrichment — matching the draft-wave snapshot (baseMemoryVersion), + // which keeps «переоплата ОДНА» honest at the WIRE level, not only the version-hash level. Only the + // editor sees mined terms (the enriched `memory`). When there are no mined rows (every $0 test / the + // golden) the base bank IS the enriched one — share the object, no double materialization, no drift. + baseRows := rows[:0:0] + hasMined := false + for _, row := range rows { + if row.Source == "mined" { + hasMined = true + continue + } + baseRows = append(baseRows, row) + } + if hasMined { + r.baseMemory = materializeMemory(baseRows, r.Pipeline.Gates.Glossary.PostcheckGate) + } else { + r.baseMemory = r.memory + } if cols := injectivityCollisions(rows); len(cols) > 0 { r.Log.WarnContext(ctx, "glossary approved dst-collisions (B2: two source terms share one Russian surface — the reader cannot tell them apart)", "collisions", strings.Join(cols, "; ")) diff --git a/backend/internal/pipeline/seedlint_test.go b/backend/internal/pipeline/seedlint_test.go index 5d98bdd..a1c5001 100644 --- a/backend/internal/pipeline/seedlint_test.go +++ b/backend/internal/pipeline/seedlint_test.go @@ -51,7 +51,7 @@ func TestSeedLintCatchesDefects(t *testing.T) { func TestSeedLintEmittedMinedDelta(t *testing.T) { // The emitted mined delta must be loadable by the REAL loader (0 fail-louds) — the pre-condition for - // the W1.5 reseed. + // the bank-mining reseed. chunks := mchunks(strings.Repeat("龙公来到青茅山。龙公很强。青茅山很高。", 4)) seed := []store.GlossaryEntry{{Src: "青茅山", Dst: "гора Цинмао", Type: "place", Status: "approved", Source: "seed"}} mined := MineBank(chunks, smallContrast(t), seed, frozenMinerConfig(), testLangPack(t)) diff --git a/backend/internal/pipeline/snapshot.go b/backend/internal/pipeline/snapshot.go index 21c6bcd..0056cf9 100644 --- a/backend/internal/pipeline/snapshot.go +++ b/backend/internal/pipeline/snapshot.go @@ -148,8 +148,8 @@ func (r *Runner) memoryVersion() string { type wave int const ( - waveW1 wave = iota // DRAFT wave: translator-role stages + the BASE bank version (excl Source:mined) - waveW2 // EDIT wave: non-translator stages + the ENRICHED bank version (all approved incl mined) + waveDraft wave = iota // DRAFT wave: translator-role stages + the BASE bank version (excl Source:mined) + waveEdit // EDIT wave: non-translator stages + the ENRICHED bank version (all approved incl mined) ) // snapshotID materializes the BOOK-GLOBAL job-context snapshot (§3.2): brief_hash, chunker version, @@ -161,35 +161,47 @@ func (r *Runner) snapshotID() (id, payload string, err error) { } // snapshotIDForWave computes the PER-WAVE snapshot (WS1 §1в, ADDITIVE — the wave executor residual pins -// each wave's jobs to it; the sequential driver still uses snapshotID). W1 folds the DRAFT stages -// (translator role) + the BASE bank version (Source∈{seed,ruby,auto}, EXCL mined); W2 folds the EDIT -// stages (non-translator) + the ENRICHED bank version (all approved incl Source:mined). A W1.5 bank -// enrichment (adding mined rows) moves ONLY the enriched version → ONLY snapshot_W2, keeping W1 +// each wave's jobs to it; the sequential driver still uses snapshotID). the draft wave folds the DRAFT stages +// (translator role) + the BASE bank version (Source∈{seed,ruby,auto}, EXCL mined); the edit wave folds the EDIT +// stages (non-translator) + the ENRICHED bank version (all approved incl Source:mined). A the bank-mining stop bank +// enrichment (adding mined rows) moves ONLY the enriched version → ONLY edit-wave snapshot, keeping the draft wave // checkpoints valid («переоплата ОДНА»). Byte-consistent with snapshotID's building — the SAME payload // struct, only the stage subset and the memory version differ. func (r *Runner) snapshotIDForWave(w wave) (id, payload string, err error) { - memVer := r.memoryVersion() // enriched (W2) - if w == waveW1 { + memVer := r.memoryVersion() // enriched (the edit wave) + if w == waveDraft { memVer = r.baseMemoryVersion() } return r.buildSnapshotID(waveStages(r.Pipeline.Stages, w), memVer) } -// waveStages partitions the pipeline stages by role for a wave: W1 = the translator-role (draft) stages, -// W2 = every non-translator (editor/other) stage. Order preserved. The prod C1 core is one draft + one +// finalStageWave is the wave that owns the SHIPPING (last) stage: the edit wave when the last stage is an editor/other +// role (the normal 2-stage pipeline — the edit unit ships), the draft wave when the pipeline is draft-only (the draft +// itself ships). The wave-aware read-models (export/status) use it to compare a stored final-stage row +// against the correct per-wave snapshot and to know whether the shipping unit is an edit unit or a chunk. +func (r *Runner) finalStageWave() wave { + n := len(r.Pipeline.Stages) + if n > 0 && r.Pipeline.Stages[n-1].Role != roleTranslator { + return waveEdit + } + return waveDraft +} + +// waveStages partitions the pipeline stages by role for a wave: the draft wave = the translator-role (draft) stages, +// the edit wave = every non-translator (editor/other) stage. Order preserved. The prod C1 core is one draft + one // edit, so this yields [draft] and [edit] respectively. func waveStages(stages []config.Stage, w wave) []config.Stage { var out []config.Stage for _, st := range stages { isDraft := st.Role == roleTranslator - if (w == waveW1) == isDraft { + if (w == waveDraft) == isDraft { out = append(out, st) } } return out } -// baseMemoryVersion is the DRAFT-wave (W1) memory component: the BASE bank version (excl Source:mined). +// baseMemoryVersion is the DRAFT-wave (the draft wave) memory component: the BASE bank version (excl Source:mined). // nil bank → the empty-materialization base hash (a stable constant), mirroring memoryVersion(). func (r *Runner) baseMemoryVersion() string { if r.memory != nil { @@ -294,6 +306,14 @@ func (r *Runner) buildSnapshotID(stages []config.Stage, memVersion string) (id, // src→dst layout (WS2 §2в) and the gender-constraint render (WS5). A format change shifts the // injected bytes → the wire, so folding it separately keeps a flip a loud --resnapshot. RenderFormatVersion string `json:"render_format_version"` + // LangpackVersion — the loaded language-data pack's content hash (internal/lang, D39.15/16), + // folded ONLY when a pack is present (omitempty otherwise, so a no-pack book is byte-stable and + // never re-billed for a feature it does not use). The pack feeds the the bank-mining stop bank-miner; a pack DATA + // edit changes what it proposes, so folding its version makes a pack edit a loud --resnapshot, + // drift-proof by mechanism (the pack's bytes ARE its version). Wire-neutral for existing + // checkpoints (the miner produces Source:mined proposals, inert until owner-approved), but folded + // per the R1 directive so the run's snapshot durably records which pack version produced it. + LangpackVersion string `json:"langpack_version,omitempty"` // MemoryVersion — content-hash детерминированно материализованной инъекти- // руемой памяти (approved-глоссарий+резюме+series-bible). Не bump-счётчик // (D8): забыть пересчитать нельзя, а забытый bump переоткрыл бы класс тихой @@ -341,6 +361,7 @@ func (r *Runner) buildSnapshotID(stages []config.Stage, memVersion string) (id, }, Segmentation: r.segmentationSnapshot(), RenderFormatVersion: renderFormatVersion, + LangpackVersion: r.packVersion(), MemoryVersion: memVersion, PostcheckGate: r.Pipeline.Gates.Glossary.PostcheckGate, Coverage: r.coverageSnapshot(), diff --git a/backend/internal/pipeline/snapshot_wave_test.go b/backend/internal/pipeline/snapshot_wave_test.go index f9d626b..47dda7e 100644 --- a/backend/internal/pipeline/snapshot_wave_test.go +++ b/backend/internal/pipeline/snapshot_wave_test.go @@ -21,35 +21,35 @@ func TestSnapshotIDForWave(t *testing.T) { } r.memory = materializeMemory(seed, false) - w1id, w1p, err := r.snapshotIDForWave(waveW1) + w1id, w1p, err := r.snapshotIDForWave(waveDraft) if err != nil { t.Fatal(err) } - w2id, w2p, err := r.snapshotIDForWave(waveW2) + w2id, w2p, err := r.snapshotIDForWave(waveEdit) if err != nil { t.Fatal(err) } - // W1 and W2 differ (different stage subset AND different bank version). + // the draft wave and the edit wave differ (different stage subset AND different bank version). if w1id == w2id { - t.Fatalf("snapshot_W1 must differ from snapshot_W2 (stage subset + bank version)") + t.Fatalf("draft-wave snapshot must differ from snapshot_W2 (stage subset + bank version)") } - // The stage PARTITION: W1 folds the draft (translator) stage, W2 folds the edit (editor) stage. + // The stage PARTITION: the draft wave folds the draft (translator) stage, the edit wave folds the edit (editor) stage. if !strings.Contains(w1p, `"name":"draft"`) || strings.Contains(w1p, `"name":"edit"`) { - t.Fatalf("snapshot_W1 must fold ONLY the draft stage, payload: %s", w1p) + t.Fatalf("draft-wave snapshot must fold ONLY the draft stage, payload: %s", w1p) } if !strings.Contains(w2p, `"name":"edit"`) || strings.Contains(w2p, `"name":"draft"`) { t.Fatalf("snapshot_W2 must fold ONLY the edit stage, payload: %s", w2p) } - // «Переоплата ОДНА» at the snapshot level (§1в): a W1.5 mined-approved addition moves ONLY W2. + // «Переоплата ОДНА» at the snapshot level (§1в): a the draft wave.5 mined-approved addition moves ONLY the edit wave. enriched := append(append([]store.GlossaryEntry{}, seed...), store.GlossaryEntry{ Src: "蛊", Dst: "гу", Status: "approved", Source: "mined", }) r.memory = materializeMemory(enriched, false) - w1id2, _, _ := r.snapshotIDForWave(waveW1) - w2id2, _, _ := r.snapshotIDForWave(waveW2) + w1id2, _, _ := r.snapshotIDForWave(waveDraft) + w2id2, _, _ := r.snapshotIDForWave(waveEdit) if w1id2 != w1id { - t.Fatalf("snapshot_W1 moved on a mined-approved addition — W1 checkpoints would re-bill («переоплата ОДНА» broken)") + t.Fatalf("draft-wave snapshot moved on a mined-approved addition — the draft wave checkpoints would re-bill («переоплата ОДНА» broken)") } if w2id2 == w2id { t.Fatalf("snapshot_W2 did NOT move on a mined-approved addition — the edit wave would miss the mined canon") @@ -60,12 +60,12 @@ func TestSnapshotIDForWave(t *testing.T) { func TestWaveStagesPartition(t *testing.T) { r := newRunner(t, setupProject(t, "http://127.0.0.1:1")) defer r.Close() - w1 := waveStages(r.Pipeline.Stages, waveW1) - w2 := waveStages(r.Pipeline.Stages, waveW2) - if len(w1) != 1 || w1[0].Role != roleTranslator { - t.Fatalf("W1 must be the translator stage(s), got %+v", w1) + draftStages := waveStages(r.Pipeline.Stages, waveDraft) + editStages := waveStages(r.Pipeline.Stages, waveEdit) + if len(draftStages) != 1 || draftStages[0].Role != roleTranslator { + t.Fatalf("the draft wave must be the translator stage(s), got %+v", draftStages) } - if len(w2) != 1 || w2[0].Role != roleEditor { - t.Fatalf("W2 must be the editor stage(s), got %+v", w2) + if len(editStages) != 1 || editStages[0].Role != roleEditor { + t.Fatalf("the edit wave must be the editor stage(s), got %+v", editStages) } } diff --git a/backend/internal/pipeline/status.go b/backend/internal/pipeline/status.go index 88895a8..a80f16f 100644 --- a/backend/internal/pipeline/status.go +++ b/backend/internal/pipeline/status.go @@ -193,16 +193,12 @@ func (r *Runner) Status(ctx context.Context) (*StatusReport, error) { return nil, err } byChunk := map[chunkKey][]store.ChunkStatus{} - snapSeen := map[string]bool{} for _, cs := range statuses { byChunk[chunkKey{cs.Chapter, cs.ChunkIdx}] = append(byChunk[chunkKey{cs.Chapter, cs.ChunkIdx}], cs) - if cs.SnapshotID != "" { - snapSeen[cs.SnapshotID] = true - } } - // Per-chunk post-check misses (retrieval_state) — the glossary-consistency signal that is - // re-derived each run and NOT a chunk_status disposition (default flagger mode). + // Post-check misses + style flags (retrieval_state) — the unit-level signal the the edit-wave editor merged onto + // its LEADER chunk's row (a non-leader member carries only its draft injection, post-check=0). states, err := r.Store.RetrievalStatesForBook(r.Book.BookID) if err != nil { return nil, err @@ -214,40 +210,51 @@ func (r *Runner) Status(ctx context.Context) (*StatusReport, error) { styleByChunk[chunkKey{rs.Chapter, rs.ChunkIdx}] = rs.NStyleFlags } - stagesTotal := len(r.Pipeline.Stages) - // The post-check GATE (opt-in) flags a chunk at the CHUNK level AFTER the stage loop, so it - // is NEVER written as a chunk_status row (every stage stays DispOK). Without accounting for - // it here, status would report a gate-flagged chunk as done/pass while `tmctl translate` - // exits 2 (finding #2). When the gate is ON, promote an otherwise-done chunk with a CONFIRMED - // post-check miss to flagged/glossary_miss so status matches the run. + // The shipping granularity is the OUTPUT UNIT (edit unit for an edit pipeline, draft chunk for a + // draft-only one) — status projects it like export + the per-unit BookResult. A unit is DONE when every + // member draft AND the unit's edit resolved ok, so its expected-ok count is len(members)·|draft stages| + + // |edit stages| (a non-leader member has draft rows only; the single edit row lives at the leader). + draftStages := r.waveStagesIndexed(waveDraft) + editStages := r.waveStagesIndexed(waveEdit) + draftStageNames, editStageNames := stageNameSet(draftStages), stageNameSet(editStages) + units := r.outputUnits(chunks) + + // The post-check GATE (opt-in) flags a unit at the CHUNK level AFTER the stage loop, so it is NEVER + // written as a chunk_status row (every stage stays DispOK). Without accounting for it here, status + // would report a gate-flagged unit as done/pass while `tmctl translate` exits 2 (finding #2). gateOn := r.Pipeline.Gates.Glossary.PostcheckGate - rep := &StatusReport{BookID: r.Book.BookID, TotalChunks: len(chunks)} + rep := &StatusReport{BookID: r.Book.BookID, TotalChunks: len(units)} passports := map[int]*ChapterPassport{} var chapterOrder []int - var processedCost float64 // spend of PROCESSED chunks (done+flagged) — the projection base (finding #7) + var processedCost float64 // spend of PROCESSED units (done+flagged) — the projection base (finding #7) - for _, ch := range chunks { - p := passports[ch.Chapter] + for _, u := range units { + p := passports[u.Chapter] if p == nil { - p = &ChapterPassport{Chapter: ch.Chapter, Verdict: "pass"} - passports[ch.Chapter] = p - chapterOrder = append(chapterOrder, ch.Chapter) + p = &ChapterPassport{Chapter: u.Chapter, Verdict: "pass"} + passports[u.Chapter] = p + chapterOrder = append(chapterOrder, u.Chapter) } p.ChunksTotal++ - key := chunkKey{ch.Chapter, ch.ChunkIdx} - state, reason, cost, escalated, skipped := resolveChunkState(byChunk[key], stagesTotal) + leader := chunkKey{u.Chapter, u.FirstChunkIdx} + var rows []store.ChunkStatus + for _, m := range u.Members { + rows = append(rows, byChunk[chunkKey{m.Chapter, m.ChunkIdx}]...) + } + expected := len(u.Members)*len(draftStages) + len(editStages) + state, reason, cost, escalated, skipped := resolveChunkState(rows, expected) p.CostUSD += cost p.StagesSkipped += skipped - miss := missByChunk[key] + miss := missByChunk[leader] // the unit's post-check ran once, at the leader row p.PostcheckMisses += miss rep.PostcheckMisses += miss - style := styleByChunk[key] + style := styleByChunk[leader] p.StyleFlags += style rep.StyleFlags += style if gateOn && state == ChunkDone && miss > 0 { - // Matches translateChunk: the gate flags only an otherwise-ok chunk. Not re-drivable - // (the miss re-derives from the unchanged glossary; a fix is a glossary edit = - // --resnapshot, not a redrive) — counted separately so the CLI advises the right action. + // Matches the wave editor: the gate flags only an otherwise-ok unit. Not re-drivable (the miss + // re-derives from the unchanged glossary; a fix is a glossary edit = --resnapshot, not a + // redrive) — counted separately so the CLI advises the right action. state, reason = ChunkFlagged, string(FlagGlossaryMiss) rep.GlossaryMissFlagged++ } @@ -273,11 +280,12 @@ func (r *Runner) Status(ctx context.Context) (*StatusReport, error) { p.ChunksPending++ } if state == ChunkDone || state == ChunkFlagged { - processedCost += cost // a fully-attempted chunk's cost feeds the projection + processedCost += cost // a fully-attempted unit's cost feeds the projection } } - // Chapter verdicts (exp07 chapter rule: 0 flagged = pass, 1 = attention, ≥2 = fail). + // Chapter verdicts (exp07 chapter rule: 0 flagged = pass, 1 = attention, ≥2 = fail — over UNITS: a + // flagged edit unit counts once, not per member chunk). sort.Ints(chapterOrder) for _, n := range chapterOrder { p := passports[n] @@ -295,31 +303,59 @@ func (r *Runner) Status(ctx context.Context) (*StatusReport, error) { if rep.TotalChunks > 0 { rep.PercentDone = 100 * float64(rep.Done) / float64(rep.TotalChunks) } - if len(snapSeen) == 1 { - for s := range snapSeen { + + // Per-wave snapshot drift (finding #3, wave-aware): the rows carry draft-wave snapshot (draft) + edit-wave snapshot + // (edit), so a normal book has TWO snapshots — that is NOT drift. SnapshotDrift means a disagreement + // WITHIN a wave (a config changed mid-book without a full re-pin). ConfigDrift compares each wave's + // single stored snapshot against the CURRENT projection of THAT wave (materialize the stored glossary + // once, then project both). rep.Snapshot reports the SHIPPING wave's snapshot. + draftSnaps, editSnaps := map[string]bool{}, map[string]bool{} + for _, cs := range statuses { + if cs.SnapshotID == "" { + continue + } + switch { + case draftStageNames[cs.Stage]: + draftSnaps[cs.SnapshotID] = true + case editStageNames[cs.Stage]: + editSnaps[cs.SnapshotID] = true + } + } + rep.SnapshotDrift = len(draftSnaps) > 1 || len(editSnaps) > 1 + finalSnaps := editSnaps + if r.finalStageWave() == waveDraft { + finalSnaps = draftSnaps + } + if len(finalSnaps) == 1 { + for s := range finalSnaps { rep.Snapshot = s } - } else if len(snapSeen) > 1 { - rep.SnapshotDrift = true } - - // Config-drift (finding #3): compute the CURRENT config's snapshot READ-ONLY (materialize - // the STORED glossary — no re-seed, no write) and compare to the single snapshot the stored - // rows carry. A wire/verdict-affecting config edit since the last run (a prompt bump, a gate - // flip — this very package bumps the editor prompt_version) is otherwise hidden behind - // "done/pass" until translate forces a --resnapshot. Only meaningful when a single snapshot - // is on record (multi-snapshot is already flagged as SnapshotDrift). Note: a change to the - // seed FILE that was not re-run is NOT detected here (the stored glossary is what status - // projects); it surfaces on the next translate's re-seed. - if rep.Snapshot != "" { - if curSnap, serr := r.currentSnapshotProjected(); serr != nil { - // Не молчать: провал проекции раньше тихо читался как «дрифта нет», и - // оператор верил чистому статусу при реально изменённом конфиге (аудит - // цепочек). Drift остаётся false (проекция неизвестна), но с WARN. - r.Log.WarnContext(ctx, "config-drift check failed; drift state unknown (reported as none)", "err", serr) - } else if curSnap != rep.Snapshot { - rep.ConfigDrift = true - rep.CurrentSnapshot = curSnap + if !rep.SnapshotDrift && (len(draftSnaps) > 0 || len(editSnaps) > 0) { + if err := r.projectStoredMemory(); err != nil { + // Не молчать: провал проекции раньше тихо читался как «дрифта нет» (аудит цепочек). + r.Log.WarnContext(ctx, "config-drift check failed; drift state unknown (reported as none)", "err", err) + } else { + checkWave := func(snaps map[string]bool, w wave) { + if len(snaps) != 1 { + return + } + var stored string + for s := range snaps { + stored = s + } + cur, _, serr := r.snapshotIDForWave(w) + if serr != nil { + r.Log.WarnContext(ctx, "config-drift check failed for a wave; drift state unknown", "err", serr) + return + } + if cur != stored { + rep.ConfigDrift = true + rep.CurrentSnapshot = cur + } + } + checkWave(draftSnaps, waveDraft) + checkWave(editSnaps, waveEdit) } } @@ -361,21 +397,17 @@ func (r *Runner) Status(ctx context.Context) (*StatusReport, error) { return rep, nil } -// currentSnapshotProjected computes the CURRENT config's snapshotID from the STORED glossary -// (read-only: materialize what is persisted, no re-seed, no write) — the single projection -// Status uses for ConfigDrift and Redrive uses to guard its destructive reset. Side effect -// (deliberate, on the read path): it sets r.memory to the stored-glossary materialization, the -// same as Status did inline. A seed-FILE edit not yet re-run is NOT reflected here (the STORED -// glossary is projected, not the seed file) — that drift surfaces on the next translate's +// projectStoredMemory materializes r.memory from the STORED glossary (read-only: no re-seed, no write) — +// the side effect the wave-snapshot projections need. A seed-FILE edit not yet re-run is NOT reflected here +// (the STORED glossary is projected, not the seed file) — that drift surfaces on the next translate's // re-seed, exactly as it does for `translate` itself. -func (r *Runner) currentSnapshotProjected() (string, error) { +func (r *Runner) projectStoredMemory() error { rows, err := r.Store.GlossaryForBook(r.Book.BookID) if err != nil { - return "", err + return err } r.memory = materializeMemory(rows, r.Pipeline.Gates.Glossary.PostcheckGate) - id, _, err := r.snapshotID() - return id, err + return nil } // RedriveSelector picks the flagged chunks to re-attack. -1 on Chapter/ChunkIdx means "any" @@ -508,13 +540,26 @@ func (r *Runner) Redrive(ctx context.Context, sel RedriveSelector) (*RedriveSumm // (the operator explicitly accepts the re-pin/re-pay) — but ONLY the snapshot COMPARISON is skipped, // never the seed-error-before-reset protection above. if !r.Resnapshot { - curSnap, _, serr := r.snapshotID() - if serr != nil { - return summary, nil, fmt.Errorf("pipeline: redrive snapshot check: %w", serr) + // Per-wave drift (R1): a stored row carries its WAVE's snapshot (draft rows → draft-wave snapshot, edit + // rows → edit-wave snapshot), never the whole-pipeline one — so compare each row against the current + // projection of ITS wave (from the SEEDED r.memory seedGlossary just set, matching what the re-run + // will render). A whole-pipeline comparison would abort every redrive spuriously. + w1cur, _, e1 := r.snapshotIDForWave(waveDraft) + if e1 != nil { + return summary, nil, fmt.Errorf("pipeline: redrive draft-wave snapshot check: %w", e1) } + w2cur, _, e2 := r.snapshotIDForWave(waveEdit) + if e2 != nil { + return summary, nil, fmt.Errorf("pipeline: redrive edit-wave snapshot check: %w", e2) + } + draftStageNames := stageNameSet(r.waveStagesIndexed(waveDraft)) for _, cs := range statuses { - if cs.SnapshotID != "" && cs.SnapshotID != curSnap { - return summary, nil, fmt.Errorf("pipeline: redrive прерван — строки книги под снапшотом %.12s, а текущий конфиг/сид рендерит %.12s (конфиг/промпты/капабилити/сид-глоссарий изменились): сброс сейчас пере-оплатил бы книгу и уничтожил бы флаг-телеметрию; повторите `translate --resnapshot`, чтобы принять пере-оплату явно, либо верните конфиг/сид", cs.SnapshotID, curSnap) + cur := w2cur + if draftStageNames[cs.Stage] { + cur = w1cur + } + if cs.SnapshotID != "" && cs.SnapshotID != cur { + return summary, nil, fmt.Errorf("pipeline: redrive прерван — строки книги под снапшотом %.12s, а текущий конфиг/сид рендерит %.12s (конфиг/промпты/капабилити/сид-глоссарий изменились): сброс сейчас пере-оплатил бы книгу и уничтожил бы флаг-телеметрию; повторите `translate --resnapshot`, чтобы принять пере-оплату явно, либо верните конфиг/сид", cs.SnapshotID, cur) } } } diff --git a/backend/internal/pipeline/testdata/golden/capture.golden b/backend/internal/pipeline/testdata/golden/capture.golden index 9a119d0..3817cc6 100644 --- a/backend/internal/pipeline/testdata/golden/capture.golden +++ b/backend/internal/pipeline/testdata/golden/capture.golden @@ -1,20 +1,20 @@ ==== run 1 (fresh) ==== -snapshot_id: 263b1c4baad731258ef34bcfee11c12de767737c3f282ec2561f66b8ce90f669 -snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit","estimator_version":"estimator-v0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"636d2a6993285e433ce25bad2f5da01c1bcc19a4682dc9fe1efb15e5feb92f53","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"draft","role":"translator","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"26d0245a56d180eafd200ebe5311aab2488142c4a98dcddee21ea457814aa21a","temperature":0.3,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000},"escalate_to":"fake-fallback","escalate_capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":6000}},{"name":"edit","role":"editor","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"6a8e7f71139d6bc09a95159d1cb895e05b56d2f2f7417c5e20a7073c517c79f6","temperature":0.4,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000}}]} +snapshot_draft: 914c9434d646ec173dbafbac5f2355d9bd4920bf9e3499f237a97c046d82c84d +snapshot_draft_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit+u15.0.0","estimator_version":"estimator-v0+u15.0.0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop+u15.0.0","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"173e87fc011e832c108711097eeffc05db95ab56eafe2ef913b43829505cdfdd","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers+u15.0.0","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"draft","role":"translator","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"26d0245a56d180eafd200ebe5311aab2488142c4a98dcddee21ea457814aa21a","temperature":0.3,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000},"escalate_to":"fake-fallback","escalate_capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":6000}}]} +snapshot_edit: 6fe7e9463b2bb3a93c602468201d650ffcc489c02042099351ac8e66be6f17ed +snapshot_edit_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit+u15.0.0","estimator_version":"estimator-v0+u15.0.0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop+u15.0.0","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"740aefe880a34396172775751d41d0e9ef136d053f3200a4f94391fa72aee7e4","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers+u15.0.0","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"edit","role":"editor","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"6a8e7f71139d6bc09a95159d1cb895e05b56d2f2f7417c5e20a7073c517c79f6","temperature":0.4,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000}}]} brief_hash: c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df -memory_version: 636d2a6993285e433ce25bad2f5da01c1bcc19a4682dc9fe1efb15e5feb92f53 +memory_version: 740aefe880a34396172775751d41d0e9ef136d053f3200a4f94391fa72aee7e4 +base_memory_version: 173e87fc011e832c108711097eeffc05db95ab56eafe2ef913b43829505cdfdd -- book result -- -chunks=9 flagged=4 exit=2 total_usd=0.041859999999999994 -chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 2de18cd1c124. Судзуки шёл по коридорам Академии магии." cost=0.00364 +chunks=8 flagged=4 exit=2 total_usd=0.04003999999999999 +chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 22c30f20dea6. Судзуки шёл по коридорам Академии магии." cost=0.00546 stage=draft role=translator model=fake-model resume=false disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" stage_text="ЧЕРНОВИК ПЕРЕВОДА a62fff0a94c2. Судзуки шёл по коридорам Академии магии." recovered="" - stage=edit role=editor model=fake-model resume=false disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" - stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 2de18cd1c124. Судзуки шёл по коридорам Академии магии." recovered="" -chunk ch1/1 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 838537705d66. Судзуки шёл по коридорам Академии магии." cost=0.00364 stage=draft role=translator model=fake-model resume=false disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" stage_text="ЧЕРНОВИК ПЕРЕВОДА f543c12a3d62. Судзуки шёл по коридорам Академии магии." recovered="" stage=edit role=editor model=fake-model resume=false disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" - stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 838537705d66. Судзуки шёл по коридорам Академии магии." recovered="" + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 22c30f20dea6. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 5abc35ddfb65. Судзуки шёл по коридорам Академии магии." cost=0.0091 stage=draft role=translator model=fake-fallback resume=false disp=ok flag="" attempts=1 escalated=true esc_model="fake-fallback" finish="stop" cum_usd=0.00728 detail="" stage_text="ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из Академии магии." recovered="" @@ -23,7 +23,7 @@ chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫ chunk ch3/0 disposition=flagged flag="hard_refusal" final_text="" cost=0.00728 stage=draft role=translator model=fake-model resume=false disp=flagged flag="hard_refusal" attempts=1 escalated=true esc_model="fake-fallback" finish="refusal" cum_usd=0.00728 detail="provider finish_reason=refusal" stage_text="" recovered="" - stage=edit role=editor model=fake-model resume=false disp=skipped flag="hard_refusal" attempts=0 escalated=false esc_model="" finish="" cum_usd=0 detail="skipped: an upstream stage was flagged (hard_refusal)" + stage=edit role=editor model=fake-model resume=false disp=skipped flag="hard_refusal" attempts=0 escalated=false esc_model="" finish="" cum_usd=0 detail="skipped: a member draft chunk of this edit unit was flagged (hard_refusal)" stage_text="" recovered="" chunk ch4/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 035dad4c3958. Судзуки шёл по коридорам Академии магии." cost=0.00364 stage=draft role=translator model=fake-model resume=false disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" @@ -51,44 +51,42 @@ chunk ch8/0 disposition=flagged flag="sanitizer_stripped" final_text="Судзу stage=edit role=editor model=fake-model resume=false disp=flagged flag="sanitizer_stripped" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="CJK-утечка в ru-выходе: 特产" stage_text="" recovered="Судзуки нашёл древний камень на каменном алтаре." -- chunk_status -- -ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=0dcdc0ec5804cb4724522fa5430c82e11e63fe268551831a525223e12d986773 cost=0.00182 escalated=false esc_model="" detail="" -ch1/0 edit snap_match=true content_hash=3c8d82d49806a85aee173bbbf0fb2136c73238056cab87df0127fdc7650a999c disp=ok flag="" attempts=1 final_hash=6eade8f5698c8eb88f5d1262a94056be4cae227b6ec56e1dda601eace14ee6e5 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=73d8ca5c2b4686c7af6325355e39dfa97b1c08514920cad5300bc227c3e67f7e cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 edit snap_match=true content_hash=d80847cc32e983dd19a71c2972a58e1b31a87363adcec42fdccc14a21d0ac9dc disp=ok flag="" attempts=1 final_hash=0fb66113726b6614be47ce6c90a101cbc9bfce1d547479c27ecdabeab1ca8c02 cost=0.00182 escalated=false esc_model="" detail="" -ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=75c33fde9dfdefa90047f6879603bafc2648a33023195937f3f716a58a3e0b4e cost=0.00728 escalated=true esc_model="fake-fallback" detail="" -ch2/0 edit snap_match=true content_hash=5a5397d41bcfa9326b5fe67c70aca8d9ef14ef89af2dbe1a758e25d364226fc5 disp=ok flag="" attempts=1 final_hash=f21f5490bcba6e6eb8810b2fbce38a9e0c91be87705326c8a642aab7a1405a22 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=96f55c8caeec48506a73141758fe8e819c9da32c9f6d969e02b83057cc2a7af3 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 edit snap_match=true content_hash=8a4e763f79c94ad20a1bac0231a8c1376ccd4f5a71c53cdfcb4de146c0b48b42 disp=ok flag="" attempts=1 final_hash=dd9978846ec37ddde3e4db428582661271fd51e8cccbce1374fd2200800e9614 cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=c9b9807b0279cb186cfae7e1255b2ea6e608b994b3429df9e7cb48f40c21b520 cost=0.00182 escalated=false esc_model="" detail="" +ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=999ab8cd87c3505efaade5cc30b7f2d38a4e3fc6183250f34906e5c2db84f078 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" +ch2/0 edit snap_match=true content_hash=5a5397d41bcfa9326b5fe67c70aca8d9ef14ef89af2dbe1a758e25d364226fc5 disp=ok flag="" attempts=1 final_hash=894afeaecfc7bef655d937d01a1c69b920c9500d10e4de9d1095f4391a55adac cost=0.00182 escalated=false esc_model="" detail="" ch3/0 draft snap_match=true content_hash=733fc6a89215efe112cfadd1d1fb361bb8a7ab1013994248a49da0dbd137548e disp=flagged flag="hard_refusal" attempts=1 final_hash= cost=0.00728 escalated=true esc_model="fake-fallback" detail="provider finish_reason=refusal" -ch3/0 edit snap_match=true content_hash= disp=skipped flag="hard_refusal" attempts=0 final_hash= cost=0 escalated=false esc_model="" detail="skipped: an upstream stage was flagged (hard_refusal)" -ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=368928e6b6ebc6422df723a726b99152b999e293dbcd2b38ae1a977d3e3740be cost=0.00182 escalated=false esc_model="" detail="" -ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=685dbe9923e245ceef1f0237ee7fbc7558fcf93590a88aef1bef310f83aaa8c2 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=59e252c7d50d6e2e146ef3bbcb6910e98824dfa68b13dd564791a54f1506f426 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 edit snap_match=true content_hash=82b05e4c3f5ca8432d7eaa7d7d63c4a7766f47a08398953c9a9bc3dc8437039b disp=ok flag="" attempts=1 final_hash=2916b384d1b23b5e9439fb9d9baab299d16898bf1e1c2dbe25f52c434b2212c0 cost=0.00182 escalated=false esc_model="" detail="" -ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=4bccc97fdab953a881aea64c33305d529d6f54692fd7048d455db543ae0af5bb cost=0.00182 escalated=false esc_model="" detail="" +ch3/0 edit snap_match=true content_hash= disp=skipped flag="hard_refusal" attempts=0 final_hash= cost=0 escalated=false esc_model="" detail="skipped: a member draft chunk of this edit unit was flagged (hard_refusal)" +ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=ac14e02f697c4fc4963946365a118afb5e8ba974c0d3c6781aac17d403dec5fd cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=5db400bde72cc0e7991f5860a524a73db4b511c683ef918cad505ffba3a6e314 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=7a7a6a7c55f5dcd00a80d04e8da5b4bc0f4b9bca8a33baa24397b7dfa9424e20 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 edit snap_match=true content_hash=82b05e4c3f5ca8432d7eaa7d7d63c4a7766f47a08398953c9a9bc3dc8437039b disp=ok flag="" attempts=1 final_hash=3fdb393a5e9bcba9869c7e0125d89e07f8bf64bb33c0098d999a9dcf5f5285ae cost=0.00182 escalated=false esc_model="" detail="" +ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=a96545d035e16b72a6abce2274f2ea4664399da63b9aaf88e5dfb3a96af20e2d cost=0.00182 escalated=false esc_model="" detail="" ch6/0 edit snap_match=true content_hash=592353321cc8000e792e0897446e4dd4f88a0280b9368b62cbd5c82b0c433193 disp=flagged flag="sanitizer_defect" attempts=1 final_hash= cost=0.00182 escalated=false esc_model="" detail="ведущая служебная преамбула: Вот перевод фрагмента:" -ch7/0 draft snap_match=true content_hash=d90c335cba3d1547a22bb3f656443cb432f84c12a577d43509cfe472cf86a2ac disp=ok flag="" attempts=1 final_hash=64cc7c596cfb048cf48b2202d7dea01f07e7f3536884c93d2fc5cb5719abed9d cost=0.00182 escalated=false esc_model="" detail="" -ch7/0 edit snap_match=true content_hash=e12521b6eb6dbc2cd35758d664d4d31894c528f092083b5cfe0e79c51be2663e disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:2bef56171e2a1a6dd901a283e6d4f9f1f2aca106735e2a5ff638fbe366433c0a cost=0.00182 escalated=false esc_model="" detail="markdown-заголовок в выходе: ### Глава 7" -ch8/0 draft snap_match=true content_hash=fbd27af11da2275cd1d47a0224970a5f8d073c6164f614efb6522ea96fa1e021 disp=ok flag="" attempts=1 final_hash=bb2e0697351fc22258ff3f163d986a8ebff1bc6fff4ee5186b3cf3e579b222e6 cost=0.00182 escalated=false esc_model="" detail="" -ch8/0 edit snap_match=true content_hash=0c6030a943cb341390509e2ebed4bbfd52af328d36916ce2e341f43665cf9183 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:d699a1e04616de214bf266a3e610ce060c5afc1fd640a537d19e49e8ad69c139 cost=0.00182 escalated=false esc_model="" detail="CJK-утечка в ru-выходе: 特产" +ch7/0 draft snap_match=true content_hash=d90c335cba3d1547a22bb3f656443cb432f84c12a577d43509cfe472cf86a2ac disp=ok flag="" attempts=1 final_hash=9af233395ddde718f61b1bbb4709095a43ea3c4e146ca10990e821607b92bca5 cost=0.00182 escalated=false esc_model="" detail="" +ch7/0 edit snap_match=true content_hash=e12521b6eb6dbc2cd35758d664d4d31894c528f092083b5cfe0e79c51be2663e disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:6f0567f25e056974a065d6ea5aedc9b204eeaa7ae7648bd7f3bf34366348355e cost=0.00182 escalated=false esc_model="" detail="markdown-заголовок в выходе: ### Глава 7" +ch8/0 draft snap_match=true content_hash=fbd27af11da2275cd1d47a0224970a5f8d073c6164f614efb6522ea96fa1e021 disp=ok flag="" attempts=1 final_hash=f5da217f1c2a26da0f7b7d946dada785e03cb30dc13600272cf74b0c54704451 cost=0.00182 escalated=false esc_model="" detail="" +ch8/0 edit snap_match=true content_hash=0c6030a943cb341390509e2ebed4bbfd52af328d36916ce2e341f43665cf9183 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:e0ea15352185a07b28f7b8b2ca50567d1b8044c5d8ad54ad6fd9d3e45f761c51 cost=0.00182 escalated=false esc_model="" detail="CJK-утечка в ru-выходе: 特产" -- request_log (insertion order) -- -ch1/0 draft role=translator req=fake-model actual=fake-model hash=0dcdc0ec5804cb4724522fa5430c82e11e63fe268551831a525223e12d986773 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/0 edit role=editor req=fake-model actual=fake-model hash=6eade8f5698c8eb88f5d1262a94056be4cae227b6ec56e1dda601eace14ee6e5 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/1 draft role=translator req=fake-model actual=fake-model hash=73d8ca5c2b4686c7af6325355e39dfa97b1c08514920cad5300bc227c3e67f7e tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/1 edit role=editor req=fake-model actual=fake-model hash=0fb66113726b6614be47ce6c90a101cbc9bfce1d547479c27ecdabeab1ca8c02 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch2/0 draft role=translator req=fake-model actual=fake-model hash=62824a48a6143b1ee8d16aa167f45389050cae0b36488db3cf08dd5c75c44ced tm_hit=0 ok=0 finish="stop" degraded="cjk_artifact" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch2/0 draft role=translator req=fake-fallback actual=fake-fallback hash=75c33fde9dfdefa90047f6879603bafc2648a33023195937f3f716a58a3e0b4e tm_hit=0 ok=1 finish="stop" degraded="" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" -ch2/0 edit role=editor req=fake-model actual=fake-model hash=f21f5490bcba6e6eb8810b2fbce38a9e0c91be87705326c8a642aab7a1405a22 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch3/0 draft role=translator req=fake-model actual=fake-model hash=eecbe6ed41153e35103989ba5dade978d20d97613c3b858fa2b24e20e8042523 tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch3/0 draft role=translator req=fake-fallback actual=fake-fallback hash=46a90aa896830bcc1c308d109d365d7b95f570ab0f347b3fd5895eb22cf71fe4 tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" -ch4/0 draft role=translator req=fake-model actual=fake-model hash=368928e6b6ebc6422df723a726b99152b999e293dbcd2b38ae1a977d3e3740be tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch4/0 edit role=editor req=fake-model actual=fake-model hash=685dbe9923e245ceef1f0237ee7fbc7558fcf93590a88aef1bef310f83aaa8c2 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch5/0 draft role=translator req=fake-model actual=fake-model hash=59e252c7d50d6e2e146ef3bbcb6910e98824dfa68b13dd564791a54f1506f426 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch5/0 edit role=editor req=fake-model actual=fake-model hash=2916b384d1b23b5e9439fb9d9baab299d16898bf1e1c2dbe25f52c434b2212c0 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch6/0 draft role=translator req=fake-model actual=fake-model hash=4bccc97fdab953a881aea64c33305d529d6f54692fd7048d455db543ae0af5bb tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch6/0 edit role=editor req=fake-model actual=fake-model hash=0cb5a1c9a33dd9fe176d2b477f34de09681d8c191f6f8fb85f6fe4a2a60372bc tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch7/0 draft role=translator req=fake-model actual=fake-model hash=64cc7c596cfb048cf48b2202d7dea01f07e7f3536884c93d2fc5cb5719abed9d tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch7/0 edit role=editor req=fake-model actual=fake-model hash=c1f1f7432def336d03507bca7cc63d79dba7e792b08820b63977f3cfeb2d3540 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch8/0 draft role=translator req=fake-model actual=fake-model hash=bb2e0697351fc22258ff3f163d986a8ebff1bc6fff4ee5186b3cf3e579b222e6 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch8/0 edit role=editor req=fake-model actual=fake-model hash=012cf140c68edece8ad9819388854aef0002f34de9062746bda78c932353cf7f tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/0 draft role=translator req=fake-model actual=fake-model hash=96f55c8caeec48506a73141758fe8e819c9da32c9f6d969e02b83057cc2a7af3 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/1 draft role=translator req=fake-model actual=fake-model hash=c9b9807b0279cb186cfae7e1255b2ea6e608b994b3429df9e7cb48f40c21b520 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 draft role=translator req=fake-model actual=fake-model hash=2e498c5ae088fcd6701b94c2f2ad7761033b6f663a26a48554ae12ca2c2f2630 tm_hit=0 ok=0 finish="stop" degraded="cjk_artifact" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 draft role=translator req=fake-fallback actual=fake-fallback hash=999ab8cd87c3505efaade5cc30b7f2d38a4e3fc6183250f34906e5c2db84f078 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" +ch3/0 draft role=translator req=fake-model actual=fake-model hash=6b744aad02e6e2d255353035a3943a278bc407cf2b1f2abaac9503c0d21239da tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch3/0 draft role=translator req=fake-fallback actual=fake-fallback hash=c42d577ea9c432be30ea7716f15b779320113de3d1269559988fde390fe1589d tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" +ch4/0 draft role=translator req=fake-model actual=fake-model hash=ac14e02f697c4fc4963946365a118afb5e8ba974c0d3c6781aac17d403dec5fd tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch5/0 draft role=translator req=fake-model actual=fake-model hash=7a7a6a7c55f5dcd00a80d04e8da5b4bc0f4b9bca8a33baa24397b7dfa9424e20 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch6/0 draft role=translator req=fake-model actual=fake-model hash=a96545d035e16b72a6abce2274f2ea4664399da63b9aaf88e5dfb3a96af20e2d tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch7/0 draft role=translator req=fake-model actual=fake-model hash=9af233395ddde718f61b1bbb4709095a43ea3c4e146ca10990e821607b92bca5 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch8/0 draft role=translator req=fake-model actual=fake-model hash=f5da217f1c2a26da0f7b7d946dada785e03cb30dc13600272cf74b0c54704451 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/0 edit role=editor req=fake-model actual=fake-model hash=dd9978846ec37ddde3e4db428582661271fd51e8cccbce1374fd2200800e9614 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 edit role=editor req=fake-model actual=fake-model hash=894afeaecfc7bef655d937d01a1c69b920c9500d10e4de9d1095f4391a55adac tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch4/0 edit role=editor req=fake-model actual=fake-model hash=5db400bde72cc0e7991f5860a524a73db4b511c683ef918cad505ffba3a6e314 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch5/0 edit role=editor req=fake-model actual=fake-model hash=3fdb393a5e9bcba9869c7e0125d89e07f8bf64bb33c0098d999a9dcf5f5285ae tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch6/0 edit role=editor req=fake-model actual=fake-model hash=8db26b560abdf5e538830d6e60d6552225140163668ee698936990ceba379189 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch7/0 edit role=editor req=fake-model actual=fake-model hash=9ba86bea5f00ed45d089fea42c4353ed4321ade3980514765e26cf891aedd319 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch8/0 edit role=editor req=fake-model actual=fake-model hash=943591a7303b83478ab8f24af256c4e663b7b01f9fed670a704ae10a330798f8 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" -- retrieval_state -- ch1/0 snap_match=true exact=3 sticky=0 ambiguous=0 spoiler=1 evicted=0 postcheck_miss=1 style_flags=0 trust_gated=0 injected_ids=["紋章\u001f\u001f0\u001f0","鈴木\u001f\u001f0\u001f0","魔法学院\u001f\u001f0\u001f0"] postcheck_detail=[{"src":"紋章","dst":"герб","disp":"confirmed"}] style_detail= trust_gate_detail= @@ -110,41 +108,40 @@ ch8/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= trust_gate_detail= -- wire bodies (call order) -- [0] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n紋章 → герб\n鈴木 → Судзуки\n魔法学院 → Академия магии"},{"role":"user","content":"第一章　図書館の秘密\n\n一番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ一層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。鈴木の指先に刻まれた印は、書庫に近づくたびに淡く光った。司書たちはその光を恐れ、誰も彼に声をかけなかった。\n\n二番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ二層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。回廊の壁には歴代の院長の肖像が並び、その視線は生きているかのように彼の背中を追った。埃の匂いが記憶を刺激した。\n\n三番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ三層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。鈴木の指先に刻まれた印は、書庫に近づくたびに淡く光った。司書たちはその光を恐れ、誰も彼に声をかけなかった。\n\n四番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ四層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。回廊の壁には歴代の院長の肖像が並び、その視線は生きているかのように彼の背中を追った。埃の匂いが記憶を刺激した。\n\n五番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ五層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。鈴木の指先に刻まれた印は、書庫に近づくたびに淡く光った。司書たちはその光を恐れ、誰も彼に声をかけなかった。\n\n六番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ六層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。回廊の壁には歴代の院長の肖像が並び、その視線は生きているかのように彼の背中を追った。埃の匂いが記憶を刺激した。扉の奥で彼が見たものは、台座に置かれた竜の紋章だった。それは禁じられた歴史の最後の欠片だと、後に彼は知ることになる。\n\n七番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ七層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。鈴木の指先に刻まれた印は、書庫に近づくたびに淡く光った。司書たちはその光を恐れ、誰も彼に声をかけなかった。"}],"model":"fake-model","stream":false,"temperature":0.3} -[1] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 紋章 → «герб»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)\n- 魔法学院 → «Академия магии»"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА a62fff0a94c2. Судзуки шёл по коридорам Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} -[2] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки\n魔法学院 → Академия магии\n紋章 → герб"},{"role":"user","content":"八番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ八層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。回廊の壁には歴代の院長の肖像が並び、その視線は生きているかのように彼の背中を追った。埃の匂いが記憶を刺激した。"}],"model":"fake-model","stream":false,"temperature":0.3} -[3] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)\n- 魔法学院 → «Академия магии»\n- 紋章 → «герб»"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА f543c12a3d62. Судзуки шёл по коридорам Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} -[4] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n竜の紋章 → Драконья печать\n鈴木 → Судзуки\n魔法学院 → Академия магии"},{"role":"user","content":"第二章　響動計画\n\n夜明け前、鈴木は再び書庫に戻り、竜の紋章を布に包んで持ち出した。魔法学院の鐘が三度鳴り、計画の始まりを告げた。\n\n「響動計画は今夜動き出す」と老司書が言った。その声は震えていたが、目は確かな決意に満ちていた。"}],"model":"fake-model","stream":false,"temperature":0.3} -[5] {"max_tokens":6000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n竜の紋章 → Драконья печать\n鈴木 → Судзуки\n魔法学院 → Академия магии"},{"role":"user","content":"第二章　響動計画\n\n夜明け前、鈴木は再び書庫に戻り、竜の紋章を布に包んで持ち出した。魔法学院の鐘が三度鳴り、計画の始まりを告げた。\n\n「響動計画は今夜動き出す」と老司書が言った。その声は震えていたが、目は確かな決意に満ちていた。"}],"model":"fake-fallback","stream":false,"temperature":0.3} -[6] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 竜の紋章 → «Драконья печать»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)\n- 魔法学院 → «Академия магии»"},{"role":"user","content":"Черновик перевода для редактуры: ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} -[7] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第三章　拒絶計画\n\nその手紙には拒絶計画という言葉だけが記されていた。鈴木は封を閉じ、暖炉の火にかざした。\n\n炎は紙を包み、言葉は灰になった。しかし灰の中で、何かが微かに光り続けていた。"}],"model":"fake-model","stream":false,"temperature":0.3} -[8] {"max_tokens":6000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第三章　拒絶計画\n\nその手紙には拒絶計画という言葉だけが記されていた。鈴木は封を閉じ、暖炉の火にかざした。\n\n炎は紙を包み、言葉は灰になった。しかし灰の中で、何かが微かに光り続けていた。"}],"model":"fake-fallback","stream":false,"temperature":0.3} -[9] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"user","content":"第四章　静かな終わり\n\n夜が明けると、街は霧に包まれていた。人々は何も知らないまま、いつもの朝を迎えた。\n\n遠くの丘の上で、旅人がひとり、東の空を眺めていた。風は冷たく、道はまだ長い。"}],"model":"fake-model","stream":false,"temperature":0.3} -[10] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. Судзуки шёл по коридорам Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} -[11] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n老人 → старик\n鈴木 → Судзуки"},{"role":"user","content":"第五章　老人の秘密\n\n鈴木は書庫の奥で老人に会った。老人は静かに古い巻物を差し出した。"}],"model":"fake-model","stream":false,"temperature":0.3} -[12] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 老人 → «старик»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика."}],"model":"fake-model","stream":false,"temperature":0.4} -[13] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第六章　序文漏洩\n\n鈴木は最後の扉の前に立ち、深く息を吸い込んだ。その先に何があるのか、誰も知らなかった。"}],"model":"fake-model","stream":false,"temperature":0.3} -[14] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь."}],"model":"fake-model","stream":false,"temperature":0.4} -[15] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第七章　見出漏洩\n\n七層目の朝、鈴木は最後の書庫の扉を開けた。扉の奥には見出しだけが刻まれた石板が静かに待っていた。誰もその文字を読めなかった。"}],"model":"fake-model","stream":false,"temperature":0.3} +[1] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки\n魔法学院 → Академия магии\n紋章 → герб"},{"role":"user","content":"八番目の朝、鈴木は魔法学院の長い廊下をゆっくりと歩きながら、昨夜の講義の内容を思い返していた。窓の外では銀色の雨が降り続き、石畳の中庭に小さな川を作っていた。図書館の塔は霧に包まれ、その頂は見えなかった。「今日こそ八層書庫の扉を開ける」と彼はつぶやき、胸元の古い鍵を握りしめた。鍵は冷たく、微かに震えているようだった。回廊の壁には歴代の院長の肖像が並び、その視線は生きているかのように彼の背中を追った。埃の匂いが記憶を刺激した。"}],"model":"fake-model","stream":false,"temperature":0.3} +[2] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n竜の紋章 → Драконья печать\n鈴木 → Судзуки\n魔法学院 → Академия магии"},{"role":"user","content":"第二章　響動計画\n\n夜明け前、鈴木は再び書庫に戻り、竜の紋章を布に包んで持ち出した。魔法学院の鐘が三度鳴り、計画の始まりを告げた。\n\n「響動計画は今夜動き出す」と老司書が言った。その声は震えていたが、目は確かな決意に満ちていた。"}],"model":"fake-model","stream":false,"temperature":0.3} +[3] {"max_tokens":6000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n竜の紋章 → Драконья печать\n鈴木 → Судзуки\n魔法学院 → Академия магии"},{"role":"user","content":"第二章　響動計画\n\n夜明け前、鈴木は再び書庫に戻り、竜の紋章を布に包んで持ち出した。魔法学院の鐘が三度鳴り、計画の始まりを告げた。\n\n「響動計画は今夜動き出す」と老司書が言った。その声は震えていたが、目は確かな決意に満ちていた。"}],"model":"fake-fallback","stream":false,"temperature":0.3} +[4] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第三章　拒絶計画\n\nその手紙には拒絶計画という言葉だけが記されていた。鈴木は封を閉じ、暖炉の火にかざした。\n\n炎は紙を包み、言葉は灰になった。しかし灰の中で、何かが微かに光り続けていた。"}],"model":"fake-model","stream":false,"temperature":0.3} +[5] {"max_tokens":6000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第三章　拒絶計画\n\nその手紙には拒絶計画という言葉だけが記されていた。鈴木は封を閉じ、暖炉の火にかざした。\n\n炎は紙を包み、言葉は灰になった。しかし灰の中で、何かが微かに光り続けていた。"}],"model":"fake-fallback","stream":false,"temperature":0.3} +[6] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"user","content":"第四章　静かな終わり\n\n夜が明けると、街は霧に包まれていた。人々は何も知らないまま、いつもの朝を迎えた。\n\n遠くの丘の上で、旅人がひとり、東の空を眺めていた。風は冷たく、道はまだ長い。"}],"model":"fake-model","stream":false,"temperature":0.3} +[7] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n老人 → старик\n鈴木 → Судзуки"},{"role":"user","content":"第五章　老人の秘密\n\n鈴木は書庫の奥で老人に会った。老人は静かに古い巻物を差し出した。"}],"model":"fake-model","stream":false,"temperature":0.3} +[8] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第六章　序文漏洩\n\n鈴木は最後の扉の前に立ち、深く息を吸い込んだ。その先に何があるのか、誰も知らなかった。"}],"model":"fake-model","stream":false,"temperature":0.3} +[9] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第七章　見出漏洩\n\n七層目の朝、鈴木は最後の書庫の扉を開けた。扉の奥には見出しだけが刻まれた石板が静かに待っていた。誰もその文字を読めなかった。"}],"model":"fake-model","stream":false,"temperature":0.3} +[10] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第八章　漢字漏洩\n\n鈴木は石板の文字をなぞり、古い漢字の意味を思い出そうとした。だが記憶は霧のように薄れ、指先だけが淡く光っていた。"}],"model":"fake-model","stream":false,"temperature":0.3} +[11] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 紋章 → «герб»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)\n- 魔法学院 → «Академия магии»"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА a62fff0a94c2. Судзуки шёл по коридорам Академии магии.\n\nЧЕРНОВИК ПЕРЕВОДА f543c12a3d62. Судзуки шёл по коридорам Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} +[12] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 竜の紋章 → «Драконья печать»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)\n- 魔法学院 → «Академия магии»"},{"role":"user","content":"Черновик перевода для редактуры: ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} +[13] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. Судзуки шёл по коридорам Академии магии."}],"model":"fake-model","stream":false,"temperature":0.4} +[14] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 老人 → «старик»\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика."}],"model":"fake-model","stream":false,"temperature":0.4} +[15] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь."}],"model":"fake-model","stream":false,"temperature":0.4} [16] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА ec12f3d7a1df. МАРКДАУН-СЦЕНА Судзуки открыл седьмую дверь."}],"model":"fake-model","stream":false,"temperature":0.4} -[17] {"max_tokens":4000,"messages":[{"role":"system","content":"Переводи художественный текст с ja на ru. Жанр: ранобэ. Аудитория: взрослые. Баланс Венути: 0.50. Хонорифики: keep. Транскрипция: polivanov."},{"role":"system","content":"ГЛОССАРИЙ (используй эти утверждённые переводы имён и терминов последовательно; строки с пометкой ⟨проверить⟩ — неподтверждённые кандидаты):\n鈴木 → Судзуки"},{"role":"user","content":"第八章　漢字漏洩\n\n鈴木は石板の文字をなぞり、古い漢字の意味を思い出そうとした。だが記憶は霧のように薄れ、指先だけが淡く光っていた。"}],"model":"fake-model","stream":false,"temperature":0.3} -[18] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА 0bc6a4817acb. ИЕРОГЛИФ-СЦЕНА Судзуки нашёл камень."}],"model":"fake-model","stream":false,"temperature":0.4} +[17] {"max_tokens":4000,"messages":[{"role":"system","content":"Ты — монолингвальный редактор русского текста. Правь стиль, не меняя смысла. Книга: Золотая книга."},{"role":"system","content":"КАНОНИЧЕСКИЕ ПЕРЕВОДЫ имён и терминов (в черновике термин исходника слева ДОЛЖЕН быть передан именно указанной формой справа — приводи к ней любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- 鈴木 → «Судзуки» (муж. — мужские родовые формы)"},{"role":"user","content":"Черновик перевода для редактуры: ЧЕРНОВИК ПЕРЕВОДА 0bc6a4817acb. ИЕРОГЛИФ-СЦЕНА Судзуки нашёл камень."}],"model":"fake-model","stream":false,"temperature":0.4} ==== run 2 (resume) ==== -snapshot_id: 263b1c4baad731258ef34bcfee11c12de767737c3f282ec2561f66b8ce90f669 -snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit","estimator_version":"estimator-v0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"636d2a6993285e433ce25bad2f5da01c1bcc19a4682dc9fe1efb15e5feb92f53","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"draft","role":"translator","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"26d0245a56d180eafd200ebe5311aab2488142c4a98dcddee21ea457814aa21a","temperature":0.3,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000},"escalate_to":"fake-fallback","escalate_capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":6000}},{"name":"edit","role":"editor","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"6a8e7f71139d6bc09a95159d1cb895e05b56d2f2f7417c5e20a7073c517c79f6","temperature":0.4,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000}}]} +snapshot_draft: 914c9434d646ec173dbafbac5f2355d9bd4920bf9e3499f237a97c046d82c84d +snapshot_draft_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit+u15.0.0","estimator_version":"estimator-v0+u15.0.0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop+u15.0.0","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"173e87fc011e832c108711097eeffc05db95ab56eafe2ef913b43829505cdfdd","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers+u15.0.0","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"draft","role":"translator","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"26d0245a56d180eafd200ebe5311aab2488142c4a98dcddee21ea457814aa21a","temperature":0.3,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000},"escalate_to":"fake-fallback","escalate_capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":6000}}]} +snapshot_edit: 6fe7e9463b2bb3a93c602468201d650ffcc489c02042099351ac8e66be6f17ed +snapshot_edit_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v5-output-budget-editunit+u15.0.0","estimator_version":"estimator-v0+u15.0.0","max_tokens_policy":"maxtok-v1-double-per-attempt","classifier_version":"classify-v1-refusal+echo015+loop+u15.0.0","pipeline_core":"C1","max_output_ratio":2,"min_max_tokens":512,"context_assembly":{"glossary_injection":"selective","glossary_token_budget":800,"cache_ttl":""},"segmentation":{"draft_budget_out":1797,"edit_ceiling_out":3200,"fertility_cjk":1.1978,"fertility_other":0.3852},"render_format_version":"renderfmt-v2-editor-src2dst+dc3-gender","memory_version":"740aefe880a34396172775751d41d0e9ef136d053f3200a4f94391fa72aee7e4","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v3-dc-checkers+u15.0.0","sanitizer":{"enabled":true,"version":"sanitizer-v6"},"stages":[{"name":"edit","role":"editor","model":"fake-model","prompt_version":"v-golden","prompt_sha256":"6a8e7f71139d6bc09a95159d1cb895e05b56d2f2f7417c5e20a7073c517c79f6","temperature":0.4,"reasoning":"off","capability":{"Budget":"max_tokens","Temp":"send","TempValue":0,"Reasoning":{"Control":"none","OffEffort":"","OffExtraBody":null,"OnExtraBody":null},"MinMaxTokens":4000}}]} brief_hash: c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df -memory_version: 636d2a6993285e433ce25bad2f5da01c1bcc19a4682dc9fe1efb15e5feb92f53 +memory_version: 740aefe880a34396172775751d41d0e9ef136d053f3200a4f94391fa72aee7e4 +base_memory_version: 173e87fc011e832c108711097eeffc05db95ab56eafe2ef913b43829505cdfdd -- book result -- -chunks=9 flagged=4 exit=2 total_usd=0 -chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 2de18cd1c124. Судзуки шёл по коридорам Академии магии." cost=0 +chunks=8 flagged=4 exit=2 total_usd=0 +chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 22c30f20dea6. Судзуки шёл по коридорам Академии магии." cost=0 stage=draft role=translator model=fake-model resume=true disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" stage_text="ЧЕРНОВИК ПЕРЕВОДА a62fff0a94c2. Судзуки шёл по коридорам Академии магии." recovered="" - stage=edit role=editor model=fake-model resume=true disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" - stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 2de18cd1c124. Судзуки шёл по коридорам Академии магии." recovered="" -chunk ch1/1 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 838537705d66. Судзуки шёл по коридорам Академии магии." cost=0 stage=draft role=translator model=fake-model resume=true disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" stage_text="ЧЕРНОВИК ПЕРЕВОДА f543c12a3d62. Судзуки шёл по коридорам Академии магии." recovered="" stage=edit role=editor model=fake-model resume=true disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" - stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 838537705d66. Судзуки шёл по коридорам Академии магии." recovered="" + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 22c30f20dea6. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 5abc35ddfb65. Судзуки шёл по коридорам Академии магии." cost=0 stage=draft role=translator model=fake-fallback resume=true disp=ok flag="" attempts=1 escalated=true esc_model="fake-fallback" finish="stop" cum_usd=0.00728 detail="" stage_text="ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из Академии магии." recovered="" @@ -153,7 +150,7 @@ chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫ chunk ch3/0 disposition=flagged flag="hard_refusal" final_text="" cost=0 stage=draft role=translator model=fake-model resume=true disp=flagged flag="hard_refusal" attempts=1 escalated=true esc_model="fake-fallback" finish="" cum_usd=0.00728 detail="provider finish_reason=refusal" stage_text="" recovered="" - stage=edit role=editor model=fake-model resume=false disp=skipped flag="hard_refusal" attempts=0 escalated=false esc_model="" finish="" cum_usd=0 detail="skipped: an upstream stage was flagged (hard_refusal)" + stage=edit role=editor model=fake-model resume=false disp=skipped flag="hard_refusal" attempts=0 escalated=false esc_model="" finish="" cum_usd=0 detail="skipped: a member draft chunk of this edit unit was flagged (hard_refusal)" stage_text="" recovered="" chunk ch4/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 035dad4c3958. Судзуки шёл по коридорам Академии магии." cost=0 stage=draft role=translator model=fake-model resume=true disp=ok flag="" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="" @@ -181,61 +178,58 @@ chunk ch8/0 disposition=flagged flag="sanitizer_stripped" final_text="Судзу stage=edit role=editor model=fake-model resume=true disp=flagged flag="sanitizer_stripped" attempts=1 escalated=false esc_model="" finish="sanitized_export" cum_usd=0.00182 detail="CJK-утечка в ru-выходе: 特产" stage_text="" recovered="Судзуки нашёл древний камень на каменном алтаре." -- chunk_status -- -ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=0dcdc0ec5804cb4724522fa5430c82e11e63fe268551831a525223e12d986773 cost=0.00182 escalated=false esc_model="" detail="" -ch1/0 edit snap_match=true content_hash=3c8d82d49806a85aee173bbbf0fb2136c73238056cab87df0127fdc7650a999c disp=ok flag="" attempts=1 final_hash=6eade8f5698c8eb88f5d1262a94056be4cae227b6ec56e1dda601eace14ee6e5 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=73d8ca5c2b4686c7af6325355e39dfa97b1c08514920cad5300bc227c3e67f7e cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 edit snap_match=true content_hash=d80847cc32e983dd19a71c2972a58e1b31a87363adcec42fdccc14a21d0ac9dc disp=ok flag="" attempts=1 final_hash=0fb66113726b6614be47ce6c90a101cbc9bfce1d547479c27ecdabeab1ca8c02 cost=0.00182 escalated=false esc_model="" detail="" -ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=75c33fde9dfdefa90047f6879603bafc2648a33023195937f3f716a58a3e0b4e cost=0.00728 escalated=true esc_model="fake-fallback" detail="" -ch2/0 edit snap_match=true content_hash=5a5397d41bcfa9326b5fe67c70aca8d9ef14ef89af2dbe1a758e25d364226fc5 disp=ok flag="" attempts=1 final_hash=f21f5490bcba6e6eb8810b2fbce38a9e0c91be87705326c8a642aab7a1405a22 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=96f55c8caeec48506a73141758fe8e819c9da32c9f6d969e02b83057cc2a7af3 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 edit snap_match=true content_hash=8a4e763f79c94ad20a1bac0231a8c1376ccd4f5a71c53cdfcb4de146c0b48b42 disp=ok flag="" attempts=1 final_hash=dd9978846ec37ddde3e4db428582661271fd51e8cccbce1374fd2200800e9614 cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=c9b9807b0279cb186cfae7e1255b2ea6e608b994b3429df9e7cb48f40c21b520 cost=0.00182 escalated=false esc_model="" detail="" +ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=999ab8cd87c3505efaade5cc30b7f2d38a4e3fc6183250f34906e5c2db84f078 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" +ch2/0 edit snap_match=true content_hash=5a5397d41bcfa9326b5fe67c70aca8d9ef14ef89af2dbe1a758e25d364226fc5 disp=ok flag="" attempts=1 final_hash=894afeaecfc7bef655d937d01a1c69b920c9500d10e4de9d1095f4391a55adac cost=0.00182 escalated=false esc_model="" detail="" ch3/0 draft snap_match=true content_hash=733fc6a89215efe112cfadd1d1fb361bb8a7ab1013994248a49da0dbd137548e disp=flagged flag="hard_refusal" attempts=1 final_hash= cost=0.00728 escalated=true esc_model="fake-fallback" detail="provider finish_reason=refusal" -ch3/0 edit snap_match=true content_hash= disp=skipped flag="hard_refusal" attempts=0 final_hash= cost=0 escalated=false esc_model="" detail="skipped: an upstream stage was flagged (hard_refusal)" -ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=368928e6b6ebc6422df723a726b99152b999e293dbcd2b38ae1a977d3e3740be cost=0.00182 escalated=false esc_model="" detail="" -ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=685dbe9923e245ceef1f0237ee7fbc7558fcf93590a88aef1bef310f83aaa8c2 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=59e252c7d50d6e2e146ef3bbcb6910e98824dfa68b13dd564791a54f1506f426 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 edit snap_match=true content_hash=82b05e4c3f5ca8432d7eaa7d7d63c4a7766f47a08398953c9a9bc3dc8437039b disp=ok flag="" attempts=1 final_hash=2916b384d1b23b5e9439fb9d9baab299d16898bf1e1c2dbe25f52c434b2212c0 cost=0.00182 escalated=false esc_model="" detail="" -ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=4bccc97fdab953a881aea64c33305d529d6f54692fd7048d455db543ae0af5bb cost=0.00182 escalated=false esc_model="" detail="" +ch3/0 edit snap_match=true content_hash= disp=skipped flag="hard_refusal" attempts=0 final_hash= cost=0 escalated=false esc_model="" detail="skipped: a member draft chunk of this edit unit was flagged (hard_refusal)" +ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=ac14e02f697c4fc4963946365a118afb5e8ba974c0d3c6781aac17d403dec5fd cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=5db400bde72cc0e7991f5860a524a73db4b511c683ef918cad505ffba3a6e314 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=7a7a6a7c55f5dcd00a80d04e8da5b4bc0f4b9bca8a33baa24397b7dfa9424e20 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 edit snap_match=true content_hash=82b05e4c3f5ca8432d7eaa7d7d63c4a7766f47a08398953c9a9bc3dc8437039b disp=ok flag="" attempts=1 final_hash=3fdb393a5e9bcba9869c7e0125d89e07f8bf64bb33c0098d999a9dcf5f5285ae cost=0.00182 escalated=false esc_model="" detail="" +ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=a96545d035e16b72a6abce2274f2ea4664399da63b9aaf88e5dfb3a96af20e2d cost=0.00182 escalated=false esc_model="" detail="" ch6/0 edit snap_match=true content_hash=592353321cc8000e792e0897446e4dd4f88a0280b9368b62cbd5c82b0c433193 disp=flagged flag="sanitizer_defect" attempts=1 final_hash= cost=0.00182 escalated=false esc_model="" detail="ведущая служебная преамбула: Вот перевод фрагмента:" -ch7/0 draft snap_match=true content_hash=d90c335cba3d1547a22bb3f656443cb432f84c12a577d43509cfe472cf86a2ac disp=ok flag="" attempts=1 final_hash=64cc7c596cfb048cf48b2202d7dea01f07e7f3536884c93d2fc5cb5719abed9d cost=0.00182 escalated=false esc_model="" detail="" -ch7/0 edit snap_match=true content_hash=e12521b6eb6dbc2cd35758d664d4d31894c528f092083b5cfe0e79c51be2663e disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:2bef56171e2a1a6dd901a283e6d4f9f1f2aca106735e2a5ff638fbe366433c0a cost=0.00182 escalated=false esc_model="" detail="markdown-заголовок в выходе: ### Глава 7" -ch8/0 draft snap_match=true content_hash=fbd27af11da2275cd1d47a0224970a5f8d073c6164f614efb6522ea96fa1e021 disp=ok flag="" attempts=1 final_hash=bb2e0697351fc22258ff3f163d986a8ebff1bc6fff4ee5186b3cf3e579b222e6 cost=0.00182 escalated=false esc_model="" detail="" -ch8/0 edit snap_match=true content_hash=0c6030a943cb341390509e2ebed4bbfd52af328d36916ce2e341f43665cf9183 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:d699a1e04616de214bf266a3e610ce060c5afc1fd640a537d19e49e8ad69c139 cost=0.00182 escalated=false esc_model="" detail="CJK-утечка в ru-выходе: 特产" +ch7/0 draft snap_match=true content_hash=d90c335cba3d1547a22bb3f656443cb432f84c12a577d43509cfe472cf86a2ac disp=ok flag="" attempts=1 final_hash=9af233395ddde718f61b1bbb4709095a43ea3c4e146ca10990e821607b92bca5 cost=0.00182 escalated=false esc_model="" detail="" +ch7/0 edit snap_match=true content_hash=e12521b6eb6dbc2cd35758d664d4d31894c528f092083b5cfe0e79c51be2663e disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:6f0567f25e056974a065d6ea5aedc9b204eeaa7ae7648bd7f3bf34366348355e cost=0.00182 escalated=false esc_model="" detail="markdown-заголовок в выходе: ### Глава 7" +ch8/0 draft snap_match=true content_hash=fbd27af11da2275cd1d47a0224970a5f8d073c6164f614efb6522ea96fa1e021 disp=ok flag="" attempts=1 final_hash=f5da217f1c2a26da0f7b7d946dada785e03cb30dc13600272cf74b0c54704451 cost=0.00182 escalated=false esc_model="" detail="" +ch8/0 edit snap_match=true content_hash=0c6030a943cb341390509e2ebed4bbfd52af328d36916ce2e341f43665cf9183 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:e0ea15352185a07b28f7b8b2ca50567d1b8044c5d8ad54ad6fd9d3e45f761c51 cost=0.00182 escalated=false esc_model="" detail="CJK-утечка в ru-выходе: 特产" -- request_log (insertion order) -- -ch1/0 draft role=translator req=fake-model actual=fake-model hash=0dcdc0ec5804cb4724522fa5430c82e11e63fe268551831a525223e12d986773 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/0 edit role=editor req=fake-model actual=fake-model hash=6eade8f5698c8eb88f5d1262a94056be4cae227b6ec56e1dda601eace14ee6e5 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/1 draft role=translator req=fake-model actual=fake-model hash=73d8ca5c2b4686c7af6325355e39dfa97b1c08514920cad5300bc227c3e67f7e tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/1 edit role=editor req=fake-model actual=fake-model hash=0fb66113726b6614be47ce6c90a101cbc9bfce1d547479c27ecdabeab1ca8c02 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch2/0 draft role=translator req=fake-model actual=fake-model hash=62824a48a6143b1ee8d16aa167f45389050cae0b36488db3cf08dd5c75c44ced tm_hit=0 ok=0 finish="stop" degraded="cjk_artifact" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch2/0 draft role=translator req=fake-fallback actual=fake-fallback hash=75c33fde9dfdefa90047f6879603bafc2648a33023195937f3f716a58a3e0b4e tm_hit=0 ok=1 finish="stop" degraded="" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" -ch2/0 edit role=editor req=fake-model actual=fake-model hash=f21f5490bcba6e6eb8810b2fbce38a9e0c91be87705326c8a642aab7a1405a22 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch3/0 draft role=translator req=fake-model actual=fake-model hash=eecbe6ed41153e35103989ba5dade978d20d97613c3b858fa2b24e20e8042523 tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch3/0 draft role=translator req=fake-fallback actual=fake-fallback hash=46a90aa896830bcc1c308d109d365d7b95f570ab0f347b3fd5895eb22cf71fe4 tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" -ch4/0 draft role=translator req=fake-model actual=fake-model hash=368928e6b6ebc6422df723a726b99152b999e293dbcd2b38ae1a977d3e3740be tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch4/0 edit role=editor req=fake-model actual=fake-model hash=685dbe9923e245ceef1f0237ee7fbc7558fcf93590a88aef1bef310f83aaa8c2 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch5/0 draft role=translator req=fake-model actual=fake-model hash=59e252c7d50d6e2e146ef3bbcb6910e98824dfa68b13dd564791a54f1506f426 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch5/0 edit role=editor req=fake-model actual=fake-model hash=2916b384d1b23b5e9439fb9d9baab299d16898bf1e1c2dbe25f52c434b2212c0 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch6/0 draft role=translator req=fake-model actual=fake-model hash=4bccc97fdab953a881aea64c33305d529d6f54692fd7048d455db543ae0af5bb tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch6/0 edit role=editor req=fake-model actual=fake-model hash=0cb5a1c9a33dd9fe176d2b477f34de09681d8c191f6f8fb85f6fe4a2a60372bc tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch7/0 draft role=translator req=fake-model actual=fake-model hash=64cc7c596cfb048cf48b2202d7dea01f07e7f3536884c93d2fc5cb5719abed9d tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch7/0 edit role=editor req=fake-model actual=fake-model hash=c1f1f7432def336d03507bca7cc63d79dba7e792b08820b63977f3cfeb2d3540 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch8/0 draft role=translator req=fake-model actual=fake-model hash=bb2e0697351fc22258ff3f163d986a8ebff1bc6fff4ee5186b3cf3e579b222e6 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch8/0 edit role=editor req=fake-model actual=fake-model hash=012cf140c68edece8ad9819388854aef0002f34de9062746bda78c932353cf7f tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/0 draft role=translator req=fake-model actual=fake-model hash=0dcdc0ec5804cb4724522fa5430c82e11e63fe268551831a525223e12d986773 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch1/0 edit role=editor req=fake-model actual=fake-model hash=6eade8f5698c8eb88f5d1262a94056be4cae227b6ec56e1dda601eace14ee6e5 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch1/1 draft role=translator req=fake-model actual=fake-model hash=73d8ca5c2b4686c7af6325355e39dfa97b1c08514920cad5300bc227c3e67f7e tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch1/1 edit role=editor req=fake-model actual=fake-model hash=0fb66113726b6614be47ce6c90a101cbc9bfce1d547479c27ecdabeab1ca8c02 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch2/0 draft role=translator req=fake-model actual=fake-fallback hash=75c33fde9dfdefa90047f6879603bafc2648a33023195937f3f716a58a3e0b4e tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch2/0 edit role=editor req=fake-model actual=fake-model hash=f21f5490bcba6e6eb8810b2fbce38a9e0c91be87705326c8a642aab7a1405a22 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch1/0 draft role=translator req=fake-model actual=fake-model hash=96f55c8caeec48506a73141758fe8e819c9da32c9f6d969e02b83057cc2a7af3 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/1 draft role=translator req=fake-model actual=fake-model hash=c9b9807b0279cb186cfae7e1255b2ea6e608b994b3429df9e7cb48f40c21b520 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 draft role=translator req=fake-model actual=fake-model hash=2e498c5ae088fcd6701b94c2f2ad7761033b6f663a26a48554ae12ca2c2f2630 tm_hit=0 ok=0 finish="stop" degraded="cjk_artifact" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 draft role=translator req=fake-fallback actual=fake-fallback hash=999ab8cd87c3505efaade5cc30b7f2d38a4e3fc6183250f34906e5c2db84f078 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" +ch3/0 draft role=translator req=fake-model actual=fake-model hash=6b744aad02e6e2d255353035a3943a278bc407cf2b1f2abaac9503c0d21239da tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch3/0 draft role=translator req=fake-fallback actual=fake-fallback hash=c42d577ea9c432be30ea7716f15b779320113de3d1269559988fde390fe1589d tm_hit=0 ok=0 finish="refusal" degraded="hard_refusal" cost=0.0054600000000000004 tokens=1000/200/0/500/0 err="" +ch4/0 draft role=translator req=fake-model actual=fake-model hash=ac14e02f697c4fc4963946365a118afb5e8ba974c0d3c6781aac17d403dec5fd tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch5/0 draft role=translator req=fake-model actual=fake-model hash=7a7a6a7c55f5dcd00a80d04e8da5b4bc0f4b9bca8a33baa24397b7dfa9424e20 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch6/0 draft role=translator req=fake-model actual=fake-model hash=a96545d035e16b72a6abce2274f2ea4664399da63b9aaf88e5dfb3a96af20e2d tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch7/0 draft role=translator req=fake-model actual=fake-model hash=9af233395ddde718f61b1bbb4709095a43ea3c4e146ca10990e821607b92bca5 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch8/0 draft role=translator req=fake-model actual=fake-model hash=f5da217f1c2a26da0f7b7d946dada785e03cb30dc13600272cf74b0c54704451 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/0 edit role=editor req=fake-model actual=fake-model hash=dd9978846ec37ddde3e4db428582661271fd51e8cccbce1374fd2200800e9614 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch2/0 edit role=editor req=fake-model actual=fake-model hash=894afeaecfc7bef655d937d01a1c69b920c9500d10e4de9d1095f4391a55adac tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch4/0 edit role=editor req=fake-model actual=fake-model hash=5db400bde72cc0e7991f5860a524a73db4b511c683ef918cad505ffba3a6e314 tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch5/0 edit role=editor req=fake-model actual=fake-model hash=3fdb393a5e9bcba9869c7e0125d89e07f8bf64bb33c0098d999a9dcf5f5285ae tm_hit=0 ok=1 finish="stop" degraded="" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch6/0 edit role=editor req=fake-model actual=fake-model hash=8db26b560abdf5e538830d6e60d6552225140163668ee698936990ceba379189 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch7/0 edit role=editor req=fake-model actual=fake-model hash=9ba86bea5f00ed45d089fea42c4353ed4321ade3980514765e26cf891aedd319 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch8/0 edit role=editor req=fake-model actual=fake-model hash=943591a7303b83478ab8f24af256c4e663b7b01f9fed670a704ae10a330798f8 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_stripped" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/0 draft role=translator req=fake-model actual=fake-model hash=96f55c8caeec48506a73141758fe8e819c9da32c9f6d969e02b83057cc2a7af3 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch1/1 draft role=translator req=fake-model actual=fake-model hash=c9b9807b0279cb186cfae7e1255b2ea6e608b994b3429df9e7cb48f40c21b520 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch2/0 draft role=translator req=fake-model actual=fake-fallback hash=999ab8cd87c3505efaade5cc30b7f2d38a4e3fc6183250f34906e5c2db84f078 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" ch3/0 draft role=translator req=fake-model actual=fake-model hash= tm_hit=1 ok=0 finish="" degraded="hard_refusal" cost=0 tokens=0/0/0/0/0 err="" -ch4/0 draft role=translator req=fake-model actual=fake-model hash=368928e6b6ebc6422df723a726b99152b999e293dbcd2b38ae1a977d3e3740be tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch4/0 edit role=editor req=fake-model actual=fake-model hash=685dbe9923e245ceef1f0237ee7fbc7558fcf93590a88aef1bef310f83aaa8c2 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch5/0 draft role=translator req=fake-model actual=fake-model hash=59e252c7d50d6e2e146ef3bbcb6910e98824dfa68b13dd564791a54f1506f426 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch5/0 edit role=editor req=fake-model actual=fake-model hash=2916b384d1b23b5e9439fb9d9baab299d16898bf1e1c2dbe25f52c434b2212c0 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch6/0 draft role=translator req=fake-model actual=fake-model hash=4bccc97fdab953a881aea64c33305d529d6f54692fd7048d455db543ae0af5bb tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch4/0 draft role=translator req=fake-model actual=fake-model hash=ac14e02f697c4fc4963946365a118afb5e8ba974c0d3c6781aac17d403dec5fd tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch5/0 draft role=translator req=fake-model actual=fake-model hash=7a7a6a7c55f5dcd00a80d04e8da5b4bc0f4b9bca8a33baa24397b7dfa9424e20 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch6/0 draft role=translator req=fake-model actual=fake-model hash=a96545d035e16b72a6abce2274f2ea4664399da63b9aaf88e5dfb3a96af20e2d tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch7/0 draft role=translator req=fake-model actual=fake-model hash=9af233395ddde718f61b1bbb4709095a43ea3c4e146ca10990e821607b92bca5 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch8/0 draft role=translator req=fake-model actual=fake-model hash=f5da217f1c2a26da0f7b7d946dada785e03cb30dc13600272cf74b0c54704451 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch1/0 edit role=editor req=fake-model actual=fake-model hash=dd9978846ec37ddde3e4db428582661271fd51e8cccbce1374fd2200800e9614 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch2/0 edit role=editor req=fake-model actual=fake-model hash=894afeaecfc7bef655d937d01a1c69b920c9500d10e4de9d1095f4391a55adac tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch4/0 edit role=editor req=fake-model actual=fake-model hash=5db400bde72cc0e7991f5860a524a73db4b511c683ef918cad505ffba3a6e314 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" +ch5/0 edit role=editor req=fake-model actual=fake-model hash=3fdb393a5e9bcba9869c7e0125d89e07f8bf64bb33c0098d999a9dcf5f5285ae tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" ch6/0 edit role=editor req=fake-model actual=fake-model hash= tm_hit=1 ok=0 finish="" degraded="sanitizer_defect" cost=0 tokens=0/0/0/0/0 err="" -ch7/0 draft role=translator req=fake-model actual=fake-model hash=64cc7c596cfb048cf48b2202d7dea01f07e7f3536884c93d2fc5cb5719abed9d tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch7/0 edit role=editor req=fake-model actual=fake-model hash=tm-sanitized-v1:2bef56171e2a1a6dd901a283e6d4f9f1f2aca106735e2a5ff638fbe366433c0a tm_hit=1 ok=0 finish="sanitized_export" degraded="sanitizer_stripped" cost=0 tokens=0/0/0/0/0 err="" -ch8/0 draft role=translator req=fake-model actual=fake-model hash=bb2e0697351fc22258ff3f163d986a8ebff1bc6fff4ee5186b3cf3e579b222e6 tm_hit=1 ok=1 finish="stop" degraded="" cost=0 tokens=0/0/0/0/0 err="" -ch8/0 edit role=editor req=fake-model actual=fake-model hash=tm-sanitized-v1:d699a1e04616de214bf266a3e610ce060c5afc1fd640a537d19e49e8ad69c139 tm_hit=1 ok=0 finish="sanitized_export" degraded="sanitizer_stripped" cost=0 tokens=0/0/0/0/0 err="" +ch7/0 edit role=editor req=fake-model actual=fake-model hash=tm-sanitized-v1:6f0567f25e056974a065d6ea5aedc9b204eeaa7ae7648bd7f3bf34366348355e tm_hit=1 ok=0 finish="sanitized_export" degraded="sanitizer_stripped" cost=0 tokens=0/0/0/0/0 err="" +ch8/0 edit role=editor req=fake-model actual=fake-model hash=tm-sanitized-v1:e0ea15352185a07b28f7b8b2ca50567d1b8044c5d8ad54ad6fd9d3e45f761c51 tm_hit=1 ok=0 finish="sanitized_export" degraded="sanitizer_stripped" cost=0 tokens=0/0/0/0/0 err="" -- retrieval_state -- ch1/0 snap_match=true exact=3 sticky=0 ambiguous=0 spoiler=1 evicted=0 postcheck_miss=1 style_flags=0 trust_gated=0 injected_ids=["紋章\u001f\u001f0\u001f0","鈴木\u001f\u001f0\u001f0","魔法学院\u001f\u001f0\u001f0"] postcheck_detail=[{"src":"紋章","dst":"герб","disp":"confirmed"}] style_detail= trust_gate_detail= diff --git a/backend/internal/pipeline/wave.go b/backend/internal/pipeline/wave.go index 3d5a0b4..fec014e 100644 --- a/backend/internal/pipeline/wave.go +++ b/backend/internal/pipeline/wave.go @@ -1,10 +1,60 @@ package pipeline -// wave.go: the W0 (deterministic, $0) pre-compute of the wave runner (WS1 §1б). This is the FIRST piece +import "strings" + +// unitJoinSeparator joins a the edit wave edit-unit's member draft chunks into the editor's input draft AND (in +// export --pairs) their source chunks into the unit's source column. It MUST be identical on both sides so +// the exported src↔dst pair aligns byte-for-byte (export map §4). "\n\n" mirrors the chunker's own paragraph +// separator (chunkDraftChunks joins paragraphs with "\n\n"), so a re-joined unit reads as clean prose. +const unitJoinSeparator = "\n\n" + +// editUnit is one the edit wave unit of edit work (WS2 decoupling: draft = small chunk, edit = coarse unit). It groups +// the WHOLE draft chunks sharing a Chunk.EditUnitID (assignEditUnits stamps them per chapter), so the unit's +// source/draft is exactly the concatenation of its members — no straddle, lossless reconstruction. It is +// addressed by (Chapter, FirstChunkIdx): FirstChunkIdx is the lowest ChunkIdx among the members, the +// LEADER chunk whose (chapter, chunk_idx, "edit") key carries the unit's single edit chunk_status row. +type editUnit struct { + EditUnitID int + Chapter int + FirstChunkIdx int + Members []Chunk // in ChunkIdx order (append order from SplitChunks is already sorted) +} + +// sourceText is the unit's source: the members' source joined with unitJoinSeparator (the editor's +// bilingual {{text}} and the fresh the edit wave memory.Select both run over this whole-unit source). +func (u editUnit) sourceText() string { + parts := make([]string, len(u.Members)) + for i, m := range u.Members { + parts[i] = m.Text + } + return strings.Join(parts, unitJoinSeparator) +} + +// buildEditUnits groups the ordered draft chunks into edit units by EditUnitID (WS2). SplitChunks emits +// chunks in (chapter, chunk_idx) order and stamps a monotone book-global EditUnitID, so a single ordered +// pass yields units in book order with members in ChunkIdx order. Pure and deterministic. +func buildEditUnits(chunks []Chunk) []editUnit { + var units []editUnit + byID := map[int]int{} // EditUnitID → index into units + for _, ch := range chunks { + if idx, ok := byID[ch.EditUnitID]; ok { + units[idx].Members = append(units[idx].Members, ch) + continue + } + byID[ch.EditUnitID] = len(units) + units = append(units, editUnit{ + EditUnitID: ch.EditUnitID, Chapter: ch.Chapter, FirstChunkIdx: ch.ChunkIdx, + Members: []Chunk{ch}, + }) + } + return units +} + +// wave.go: the the precompute pass (deterministic, $0) pre-compute of the wave runner (WS1 §1б). This is the FIRST piece // of the wave executor built ahead of the driver switch (R1 residual): the sticky-chain memory selection // is a CROSS-CHUNK sequential dependency (a chunk's sticky_prev is the union of the prior chunks' exact // matches in the same chapter), so the parallel waves cannot recompute it per-chunk — it must be -// precomputed once in W0. precomputeSticky replicates EXACTLY the sequential driver's inline computation +// precomputed once in the precompute pass. precomputeSticky replicates EXACTLY the sequential driver's inline computation // (bookrun.go's per-chapter reset + memory.Select + sticky advance), and the sequential driver now // CONSUMES it — so it is byte-identical by construction, and the golden test proves the injection bytes // did not move. When the driver switches to waves (residual), the waves consume this same precompute. @@ -13,7 +63,7 @@ package pipeline // model output, so precomputing it reproduces byte-for-byte the injection the sequential runner rendered // (parallelism does not change the bytes — the order is fixed and the input carries no model state). -// precomputeSticky computes the per-chunk memory selection for EVERY chunk in one ordered W0 pass +// precomputeSticky computes the per-chunk memory selection for EVERY chunk in one ordered the precompute pass pass // (WS1 §1б): the sticky window is reset at each chapter boundary (a new chapter is a scene change) and // advanced by each chunk's exact matches, exactly as the sequential loop did inline. Returns a slice // aligned index-for-index with `chunks`. A nil bank (report path / no glossary) yields zero-valued diff --git a/backend/internal/pipeline/waverun.go b/backend/internal/pipeline/waverun.go new file mode 100644 index 0000000..1f4122a --- /dev/null +++ b/backend/internal/pipeline/waverun.go @@ -0,0 +1,535 @@ +package pipeline + +import ( + "context" + "encoding/json" + "fmt" + "strings" + "sync" + + "textmachine/backend/internal/config" + "textmachine/backend/internal/store" +) + +// waverun.go: the R1 WAVE EXECUTOR — the driver switch from the sequential per-chunk-all-stages loop +// (bookrun.go/chunkrun.go, retired) to the precompute pass ($0) → the draft wave (draft stage ∥ over draft CHUNKS) → +// the bank-mining stop → the edit wave (edit stage ∥ over edit UNITS). The load-bearing decoupling (plan §1/§2): +// the DRAFT is the fine per-chunk unit (COGS/coverage/alignment), the EDIT is the coarse per-unit unit +// (a chapter-scale grouping of whole draft chunks — cross-chunk cohesion, D39 п.4). the edit wave reads a unit's draft +// as the concatenation of its members' draft-wave outputs and does a FRESH memory.Select over the whole-unit source; +// it NEVER re-renders the draft stage (the несущий invariant — a re-render over the enriched bank would move +// the draft request_hash and re-bill the draft wave). Money stays single-writer-safe (Reserve/Settle serialize); the +// waves add only read-only shared state (clients/templates/memory/rate-guards built in the precompute pass). Per-wave +// snapshots (draft-wave snapshot base-bank, edit-wave snapshot enriched) keep «переоплата ОДНА»: a the bank-mining stop enrichment moves +// only edit-wave snapshot, so draft-wave checkpoints stay valid. + +// wavedStage carries a wave stage with its GLOBAL index in Pipeline.Stages — runStage needs the global +// index for isFinal (the LAST stage is the shipping stage the sanitizer runs on) and for the >0 sizing +// path (a later stage sizes max_tokens from its input draft, not the source, D2.5). +type wavedStage struct { + st config.Stage + idx int +} + +// waveStagesIndexed partitions Pipeline.Stages by role for a wave, carrying each stage's global index +// (mirrors waveStages but retains the index runStage needs). the draft wave = translator (draft) stages; the edit wave = every +// non-translator (editor/other) stage. Order preserved. +func (r *Runner) waveStagesIndexed(w wave) []wavedStage { + var out []wavedStage + for i, st := range r.Pipeline.Stages { + isDraft := st.Role == roleTranslator + if (w == waveDraft) == isDraft { + out = append(out, wavedStage{st: st, idx: i}) + } + } + return out +} + +// stageNameSet is the set of a wave's stage names — used by the read-models to classify a stored +// chunk_status row by wave (its snapshot belongs to that wave's per-wave snapshot). +func stageNameSet(staged []wavedStage) map[string]bool { + m := make(map[string]bool, len(staged)) + for _, ws := range staged { + m[ws.st.Name] = true + } + return m +} + +// outputUnits is the SHIPPING granularity the read-models (export/status) project — matching the per-unit +// BookResult: edit units (member draft chunks grouped) for an edit pipeline, or one singleton unit per +// draft chunk for a draft-only pipeline (the draft itself ships). One helper so export and status agree. +func (r *Runner) outputUnits(chunks []Chunk) []editUnit { + if r.finalStageWave() == waveEdit { + return buildEditUnits(chunks) + } + out := make([]editUnit, len(chunks)) + for i, ch := range chunks { + out[i] = editUnit{EditUnitID: ch.EditUnitID, Chapter: ch.Chapter, FirstChunkIdx: ch.ChunkIdx, Members: []Chunk{ch}} + } + return out +} + +// WaveSignatureStop is the typed sentinel the CLI surfaces when bank-mining proposes a non-empty seed-delta: +// the run completes the draft wave, writes the owner signature map, and STOPS before the edit wave (plan §1(в) default — an explicit +// stop boundary, not a mid-run append). The owner reviews the signature map, curates the mined-delta file +// (promoting terms to approved with a dst), and re-runs: the draft wave resumes at $0, the bank-mining stop re-mines (the now-seeded +// terms are excluded → the delta empties → auto-continue), and the edit wave runs under edit-wave snapshot. NOT an infra +// failure — a deliberate human-in-the-loop pause, carried up like CompletedWithFlags. +type WaveSignatureStop struct { + Terms int + SignaturePath string +} + +func (e *WaveSignatureStop) Error() string { + return fmt.Sprintf("bank-mining proposed %d new term(s) — review + sign %s, then resume (the edit wave)", e.Terms, e.SignaturePath) +} + +// translateBookWaves is the wave driver (R1). It runs the draft wave (draft ∥), the bank-mining stop, the edit wave (edit ∥) and +// assembles the BookResult. chunks + stickySel come from the precompute pass (SplitChunks + precomputeSticky), computed by +// the caller (TranslateBook) after ingest/seed/eager-build. Returns a *WaveSignatureStop when the bank-mining stop stops. +func (r *Runner) translateBookWaves(ctx context.Context, chunks []Chunk, stickySel []memorySelection) (*BookResult, error) { + draftStages := r.waveStagesIndexed(waveDraft) + editStages := r.waveStagesIndexed(waveEdit) + workers := r.Pipeline.Waves.Workers + editWave := len(editStages) > 0 // a real editor wave exists; else the draft IS the shipping output (draft-only) + + // --- the draft wave: draft stage(s) ∥ over draft chunks under draft-wave snapshot (base-bank version) --- + draftSnapshot, draftPayload, err := r.snapshotIDForWave(waveDraft) + if err != nil { + return nil, err + } + if err := r.Store.UpsertSnapshot(draftSnapshot, r.Book.BriefHash(), draftPayload); err != nil { + return nil, fmt.Errorf("pipeline: upsert draft-wave snapshot %.12s: %w", draftSnapshot, err) + } + r.Log.InfoContext(ctx, "draft wave started", "snapshot", draftSnapshot[:12], + "chunks", len(chunks), "workers", workers, "draft_stages", len(draftStages)) + draftResults := make([]stageSeqResult, len(chunks)) + if err := r.runWave(ctx, workers, len(chunks), func(ctx context.Context, i int) error { + d, err := r.runDraftChunk(ctx, draftSnapshot, chunks[i], stickySel[i], draftStages, !editWave) + if err != nil { + return err + } + draftResults[i] = d + return nil + }); err != nil { + return nil, err + } + + // --- the bank-mining stop: bank-mining stop boundary (auto-continues when mining is not configured) --- + if stopped, err := r.runBankMiningStop(ctx, chunks); err != nil { + return nil, err + } else if stopped { + return nil, &WaveSignatureStop{Terms: r.lastMinedCount, SignaturePath: r.signatureMapPath()} + } + + res := &BookResult{BookID: r.Book.BookID} + + // --- Draft-only pipeline: the draft IS the shipping output; assemble per draft chunk (no edit units) --- + if !editWave { + for i, ch := range chunks { + oc := draftOnlyOutcome(ch, draftResults[i]) + res.Chunks = append(res.Chunks, oc) + res.TotalUSD += oc.CostUSD + if oc.Disposition == DispFlagged { + res.Flagged++ + } + } + r.Log.InfoContext(ctx, "book run finished (draft-only)", "book", r.Book.BookID, + "chunks", len(res.Chunks), "flagged", res.Flagged, "run_usd", fmt.Sprintf("%.6f", res.TotalUSD)) + return res, nil + } + + // --- the edit wave: edit stage(s) ∥ over edit units under edit-wave snapshot (enriched-bank version) --- + editSnapshot, editPayload, err := r.snapshotIDForWave(waveEdit) + if err != nil { + return nil, err + } + if err := r.Store.UpsertSnapshot(editSnapshot, r.Book.BriefHash(), editPayload); err != nil { + return nil, fmt.Errorf("pipeline: upsert edit-wave snapshot %.12s: %w", editSnapshot, err) + } + units := buildEditUnits(chunks) + draftByKey := make(map[chunkKey]stageSeqResult, len(chunks)) + for i, ch := range chunks { + draftByKey[chunkKey{ch.Chapter, ch.ChunkIdx}] = draftResults[i] + } + r.Log.InfoContext(ctx, "edit wave started", "snapshot", editSnapshot[:12], + "units", len(units), "workers", workers, "edit_stages", len(editStages)) + unitOutcomes := make([]*ChunkOutcome, len(units)) + if err := r.runWave(ctx, workers, len(units), func(ctx context.Context, i int) error { + oc, err := r.runEditUnit(ctx, editSnapshot, units[i], draftByKey, editStages) + if err != nil { + return err + } + unitOutcomes[i] = oc + return nil + }); err != nil { + return nil, err + } + for _, oc := range unitOutcomes { + res.Chunks = append(res.Chunks, *oc) + res.TotalUSD += oc.CostUSD + if oc.Disposition == DispFlagged { + res.Flagged++ + } + } + r.Log.InfoContext(ctx, "book run finished", "book", r.Book.BookID, + "units", len(res.Chunks), "flagged", res.Flagged, "run_usd", fmt.Sprintf("%.6f", res.TotalUSD)) + return res, nil +} + +// runWave fans `n` items out over `workers` goroutines, calling work(ctx, i) for each index. The first +// error cancels the rest (via a derived context) and is returned; work items are independent (a wave has no +// shared mutable input), and money/store writes serialize through the single-writer pool, so this is +// race-clean. Results are written by the callback into a caller-owned slice indexed by i, so the result +// ORDER is deterministic (item index) regardless of completion order — the golden capture sorts the wire/log +// side-effects separately. workers ≤ 0 is treated as 1 (LoadPipeline already clamps). +func (r *Runner) runWave(parent context.Context, workers, n int, work func(ctx context.Context, i int) error) error { + if workers < 1 { + workers = 1 + } + if n == 0 { + return nil + } + ctx, cancel := context.WithCancel(parent) + defer cancel() + idxCh := make(chan int) + var wg sync.WaitGroup + var mu sync.Mutex + var firstErr error + fail := func(err error) { + mu.Lock() + if firstErr == nil { + firstErr = err + cancel() + } + mu.Unlock() + } + for w := 0; w < workers; w++ { + wg.Add(1) + go func() { + defer wg.Done() + for i := range idxCh { + if err := work(ctx, i); err != nil { + fail(err) + return + } + } + }() + } + for i := 0; i < n; i++ { + select { + case idxCh <- i: + case <-ctx.Done(): + } + } + close(idxCh) + wg.Wait() + return firstErr +} + +// stageSeqResult is the outcome of running one chunk/unit through an ORDERED list of stages (one wave): +// the per-stage results, the final OK stage's text, and the terminal flag state. +type stageSeqResult struct { + stages []StageResult + finalText string // the last OK stage's Text (empty until a stage runs; unused when flagged) + flagged bool + flagReason FlagReason + recovered string // sanitizer-stripped export text from the flagging stage (D35.4a) + cost float64 // THIS run's spend across the sequence + bankTelem bankFlags // the translator-role stage's banknote telemetry (WS4 point 10) +} + +// runStageSequence runs `staged` in order over one chunk/unit, feeding each stage's output to the next as +// `prev` (starting from startPrev), stopping the sequence at the FIRST flagged stage (later stages are +// recorded `skipped` — no paid edit over a garbage draft, D2). It is the generalized inner loop of the +// retired translateChunk, reused by BOTH waves (draft over a chunk, the edit-wave editor over a unit). injectionByRole +// maps a stage role to its already-rendered memory-injection message (the translator's src→dst glossary in +// the draft wave, the editor's CONFIRMED-dst constraint block in the edit wave). Deterministic; content-verified resume via runStage. +func (r *Runner) runStageSequence(ctx context.Context, staged []wavedStage, snapID string, ch Chunk, startPrev string, injectionByRole map[string]string) (stageSeqResult, error) { + var res stageSeqResult + prev := startPrev + flagged := false + var flagReason FlagReason + recovered := "" + for _, ws := range staged { + st := ws.st + if flagged { + detail := fmt.Sprintf("skipped: an upstream stage was flagged (%s)", flagReason) + if err := r.Store.UpsertChunkStatus(store.ChunkStatus{ + BookID: r.Book.BookID, Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Stage: st.Name, + SnapshotID: snapID, Disposition: string(DispSkipped), FlagReason: string(flagReason), Detail: detail, + }); err != nil { + return res, fmt.Errorf("pipeline: record skipped chunk_status: %w", err) + } + res.stages = append(res.stages, StageResult{ + Stage: st.Name, Role: st.Role, Model: st.Model, + Disposition: DispSkipped, FlagReason: flagReason, Detail: detail, + }) + continue + } + sr, err := r.runStage(ctx, st, ws.idx, snapID, ch, prev, injectionByRole[st.Role]) + if err != nil { + return res, err + } + res.stages = append(res.stages, *sr) + res.cost += sr.CostUSD + if st.Role == roleTranslator { + res.bankTelem = sr.BankFlags + // FL-2: the resume fast-path serves the banknote-cleaned final_hash and leaves BankFlags zero; + // restore the telemetry the fresh run persisted so persistRetrievalState does not zero the three + // banknote columns on every resume of a ready chunk (guarded on an empty BankFlags so the + // attempt-loop path — which re-derives telemetry from the raw checkpoint — is never overwritten). + if res.bankTelem == (bankFlags{}) && sr.FromResume && r.Pipeline.Gates.Banknote.Enabled { + if prevRS, err := r.Store.GetRetrievalState(r.Book.BookID, ch.Chapter, ch.ChunkIdx); err == nil && prevRS != nil { + res.bankTelem = bankFlags{ + NLines: prevRS.NBanknoteLines, ParseFail: prevRS.BanknoteParseFail != 0, Truncated: prevRS.BanknoteTruncated != 0, + } + } + } + } + if sr.Disposition == DispFlagged { + flagged = true + flagReason = sr.FlagReason + recovered = sr.RecoveredText + continue + } + prev = sr.Text + } + res.finalText = prev + res.flagged = flagged + res.flagReason = flagReason + res.recovered = recovered + return res, nil +} + +// runDraftChunk runs the draft stage(s) over one chunk under the draft-wave snapshot (plan §1). It renders +// the translator's src→dst glossary injection from the precomputed per-chunk selection over the BASE bank +// (baseMemory — mined-excluded, so the injection is stable across a bank-mining enrichment), runs the +// sequence, and persists the draft retrieval_state (injection counts + banknote telemetry). When this is the +// FINAL wave (a draft-only pipeline with no editor), the draft IS the shipping text, so the post-check + +// cheap gates run here over the draft; otherwise they belong to the edit wave (the edit unit's final output). +func (r *Runner) runDraftChunk(ctx context.Context, draftSnapshot string, ch Chunk, memSel memorySelection, draftStages []wavedStage, isFinalWave bool) (stageSeqResult, error) { + injectionByRole := map[string]string{} + if r.baseMemory != nil { + // Serialize the per-role injection blocks via the role→renderer registry (D39 слой 7) from the + // precomputed base-bank selection: the translator gets its src→dst glossary block; any other + // role's block is rendered too but consumed only if a stage of that role runs in this wave. + for role, render := range roleInjectionRenderers { + injectionByRole[role] = render(memSel.injected) // pure → map-order-independent + } + if len(memSel.trustGated) > 0 { + r.Log.WarnContext(ctx, "memory: lower-trust longer key refused from suppressing a higher-trust nested key (approved term preserved; reconcile the seed)", + "chapter", ch.Chapter, "chunk", ch.ChunkIdx, "trust_gated", len(memSel.trustGated), + "first", memSel.trustGated[0].Suppressor+"⊃"+memSel.trustGated[0].Protected) + } + } + seq, err := r.runStageSequence(ctx, draftStages, draftSnapshot, ch, "", injectionByRole) + if err != nil { + return seq, err + } + + var postMisses []postcheckMiss + outputChecked := false + var cheap cheapGateResult + if isFinalWave && r.baseMemory != nil && !seq.flagged && seq.finalText != "" { + // Draft-only pipeline: the draft is the shipping output → run the FINAL-output checks here, over the + // SAME base bank whose terms the draft was injected with (post-check parity with the injection). + outputChecked = true + postMisses = r.baseMemory.postcheck(memSel.injected, seq.finalText) + if r.Pipeline.Gates.Glossary.PostcheckGate && countConfirmedMisses(postMisses) > 0 { + seq.flagged = true + seq.flagReason = FlagGlossaryMiss + r.Log.WarnContext(ctx, "glossary post-check gate flagged the chunk", + "chapter", ch.Chapter, "chunk", ch.ChunkIdx, "confirmed_misses", countConfirmedMisses(postMisses)) + } + } + if isFinalWave && !seq.flagged && seq.finalText != "" && isRuTarget(r.Book.TargetLang) { + cheap = runCheapGates(ch.Text, seq.finalText, seq.finalText, r.cheapGateConfig()) + } + if r.baseMemory != nil { + if err := r.persistRetrievalState(draftSnapshot, ch, memSel, postMisses, outputChecked, cheap, seq.bankTelem); err != nil { + return seq, err + } + } + return seq, nil +} + +// runEditUnit runs the editor stage(s) over one edit unit under the edit-wave snapshot (plan §1/§2). It reads +// the unit's draft as the concatenation of its member chunks' draft outputs (NEVER re-rendering the draft +// stage — the несущий invariant), does a FRESH memory.Select over the WHOLE-unit source over the ENRICHED +// bank (sticky degenerate at unit scope → nil), and runs the editor over (unit source, unit draft). A unit whose +// ANY member draft flagged is flagged (skip edit — no paid edit over a partial draft, D2 flag+skip); the +// good members' draft-wave spend stays honestly committed. Post-check + cheap gates run over the edit output at +// unit granularity, merged into the LEADER chunk's retrieval_state row. +func (r *Runner) runEditUnit(ctx context.Context, editSnapshot string, unit editUnit, draftByKey map[chunkKey]stageSeqResult, editStages []wavedStage) (*ChunkOutcome, error) { + leader := Chunk{Chapter: unit.Chapter, ChunkIdx: unit.FirstChunkIdx, Text: unit.sourceText()} + out := &ChunkOutcome{Chapter: unit.Chapter, ChunkIdx: unit.FirstChunkIdx, Disposition: DispOK} + + var draftStages []StageResult + var draftCost float64 + var draftParts []string + memberFlagged := false + var memberFlagReason FlagReason + memberRecovered := "" + for _, m := range unit.Members { + d, ok := draftByKey[chunkKey{m.Chapter, m.ChunkIdx}] + if !ok { + return nil, fmt.Errorf("pipeline: edit unit ch%d chunk%d: missing draft result (wave sequencing bug)", m.Chapter, m.ChunkIdx) + } + draftStages = append(draftStages, d.stages...) + draftCost += d.cost + if d.flagged { + if !memberFlagged { + memberFlagged = true + memberFlagReason = d.flagReason + memberRecovered = d.recovered + } + continue + } + draftParts = append(draftParts, d.finalText) + } + out.CostUSD = draftCost + + if memberFlagged { + // A member draft flagged → the unit's edit is skipped (no paid edit over a partial draft). Record a + // skipped edit chunk_status at the leader and export the recovered draft (or "" for a dropped flag). + skipped, err := r.recordSkippedStages(ctx, editStages, editSnapshot, leader, memberFlagReason) + if err != nil { + return nil, err + } + out.Stages = append(draftStages, skipped...) + out.Disposition = DispFlagged + out.FlagReason = memberFlagReason + out.FinalText = exportNormalize(memberRecovered) + return out, nil + } + + unitDraft := strings.Join(draftParts, unitJoinSeparator) + var editSel memorySelection + injectionByRole := map[string]string{} + if r.memory != nil { + // FRESH Select over the WHOLE-unit source over the ENRICHED bank (§1(б)/F3): NOT the the precompute pass per-chunk + // memSel (that was over the base bank). Sticky is degenerate at unit scope (a unit == a chapter or a + // sub-chapter split, so the intra-chapter sticky window does not apply) → nil sticky_prev. + editSel = r.memory.Select(leader.Text, unit.Chapter, nil, r.Pipeline.Context.GlossaryTokenBudget) + // Render the per-role injection from the ENRICHED unit selection via the registry (D39 слой 7): the + // editor gets its CONFIRMED-dst constraint block; other roles' blocks are rendered but consumed + // only if a stage of that role runs in the edit wave. + for role, render := range roleInjectionRenderers { + injectionByRole[role] = render(editSel.injected) + } + } + seq, err := r.runStageSequence(ctx, editStages, editSnapshot, leader, unitDraft, injectionByRole) + if err != nil { + return nil, err + } + out.Stages = append(draftStages, seq.stages...) + out.CostUSD += seq.cost + + finalText, flagged, flagReason, recovered := seq.finalText, seq.flagged, seq.flagReason, seq.recovered + var postMisses []postcheckMiss + outputChecked := false + if r.memory != nil && !flagged && finalText != "" { + outputChecked = true + postMisses = r.memory.postcheck(editSel.injected, finalText) + if r.Pipeline.Gates.Glossary.PostcheckGate && countConfirmedMisses(postMisses) > 0 { + flagged = true + flagReason = FlagGlossaryMiss + r.Log.WarnContext(ctx, "glossary post-check gate flagged the edit unit", + "chapter", unit.Chapter, "leader_chunk", unit.FirstChunkIdx, "confirmed_misses", countConfirmedMisses(postMisses)) + } + } + var cheap cheapGateResult + if !flagged && finalText != "" && isRuTarget(r.Book.TargetLang) { + cheap = runCheapGates(leader.Text, unitDraft, finalText, r.cheapGateConfig()) + if cheap.total() > 0 { + r.Log.InfoContext(ctx, "cheap style gates flagged the edit unit (observability, not a gate)", + "chapter", unit.Chapter, "leader_chunk", unit.FirstChunkIdx, "style_flags", cheap.total()) + } + } + if r.memory != nil { + if err := r.mergeUnitRetrievalState(unit.Chapter, unit.FirstChunkIdx, postMisses, outputChecked, cheap); err != nil { + return nil, err + } + } + + if flagged { + out.Disposition = DispFlagged + out.FlagReason = flagReason + out.FinalText = exportNormalize(recovered) + } else { + out.FinalText = exportNormalize(finalText) + } + return out, nil +} + +// recordSkippedStages writes a `skipped` chunk_status row (+ a skipped StageResult) for each stage in a +// wave, at chunk `ch` under `snapID` — used when a unit's member draft flagged, so the unit's edit is +// skipped (mirrors runStageSequence's flagged-skip path but for a pre-decided skip). +func (r *Runner) recordSkippedStages(ctx context.Context, staged []wavedStage, snapID string, ch Chunk, flagReason FlagReason) ([]StageResult, error) { + detail := fmt.Sprintf("skipped: a member draft chunk of this edit unit was flagged (%s)", flagReason) + var out []StageResult + for _, ws := range staged { + st := ws.st + if err := r.Store.UpsertChunkStatus(store.ChunkStatus{ + BookID: r.Book.BookID, Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Stage: st.Name, + SnapshotID: snapID, Disposition: string(DispSkipped), FlagReason: string(flagReason), Detail: detail, + }); err != nil { + return nil, fmt.Errorf("pipeline: record skipped edit chunk_status: %w", err) + } + out = append(out, StageResult{ + Stage: st.Name, Role: st.Role, Model: st.Model, + Disposition: DispSkipped, FlagReason: flagReason, Detail: detail, + }) + } + return out, nil +} + +// mergeUnitRetrievalState folds a edit unit's post-check + cheap-gate observability into the LEADER chunk's +// retrieval_state row — the row the draft wave already wrote with the leader chunk's draft-injection counts + banknote +// telemetry. A read-modify-write (single-writer safe; each unit owns a distinct leader chunk_idx) preserves +// the draft fields and adds the unit-level post-check/style fields, so the read-models aggregate injection +// per draft chunk and post-check/style per unit. A missing row (r.memory nil path) is a no-op. +func (r *Runner) mergeUnitRetrievalState(chapter, firstChunkIdx int, misses []postcheckMiss, outputChecked bool, cheap cheapGateResult) error { + rs, err := r.Store.GetRetrievalState(r.Book.BookID, chapter, firstChunkIdx) + if err != nil { + return fmt.Errorf("pipeline: read leader retrieval_state ch%d/chunk%d: %w", chapter, firstChunkIdx, err) + } + if rs == nil { + return nil // no draft row (no memory / no draft) → nothing to merge onto + } + rs.NStyleFlags = cheap.total() + rs.StyleDetail = "" + if cheap.total() > 0 { + if b, err := json.Marshal(cheap); err == nil { + rs.StyleDetail = string(b) + } + } + rs.NPostcheckMiss = 0 + rs.PostcheckDetail = "" + if outputChecked { + rs.NPostcheckMiss = countConfirmedMisses(misses) + if len(misses) > 0 { + if b, err := json.Marshal(misses); err == nil { + rs.PostcheckDetail = string(b) + } + } + } + return r.Store.UpsertRetrievalState(*rs) +} + +// draftOnlyOutcome assembles a ChunkOutcome for a draft-only pipeline (no editor): the draft is the shipping +// output, so the per-chunk draft result maps straight to the outcome (post-check/cheap already ran in +// runDraftChunk as the final wave). Mirrors the export contract: a cosmetic strip exports its recovered +// text; every other flag exports "". +func draftOnlyOutcome(ch Chunk, d stageSeqResult) ChunkOutcome { + oc := ChunkOutcome{Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Stages: d.stages, CostUSD: d.cost, Disposition: DispOK} + if d.flagged { + oc.Disposition = DispFlagged + oc.FlagReason = d.flagReason + oc.FinalText = exportNormalize(d.recovered) + } else { + oc.FinalText = exportNormalize(d.finalText) + } + return oc +} diff --git a/backend/internal/pipeline/waverun_test.go b/backend/internal/pipeline/waverun_test.go new file mode 100644 index 0000000..392f827 --- /dev/null +++ b/backend/internal/pipeline/waverun_test.go @@ -0,0 +1,368 @@ +package pipeline + +import ( + "context" + "errors" + "math" + "os" + "path/filepath" + "strings" + "testing" + + "textmachine/backend/internal/obs" +) + +// waverun_test.go: the R1 wave-driver behaviours the 1-chunk-per-chapter fixtures cannot exercise — a +// MULTI-CHUNK edit unit (the editor collapses several draft chunks into one edit call over their +// concatenation, addressed by the leader), parallel-worker money conservation, a flagged member draft +// skipping the unit's edit, and the bank-mining stop gate. + +// cjkSource builds a single-chapter ja source of `paras` paragraphs, each `hanPerPara` Han chars + a full +// stop, separated by a blank line — enough to make the chunker split it into several draft chunks. +func cjkSource(paras, hanPerPara int) string { + p := make([]string, paras) + for i := range p { + p[i] = strings.Repeat("文", hanPerPara) + "。" + } + return strings.Join(p, "\n\n") +} + +// TestWaveMultiChunkEditUnit is the load-bearing R1 pin: a chapter that splits into TWO draft chunks but +// groups into ONE edit unit. The editor must run ONCE over the concatenation of the two members' drafts +// (never re-rendering either draft), the unit's outcome is a single ChunkOutcome at the leader, and export +// projects one row — not two "pending" chunks. +func TestWaveMultiChunkEditUnit(t *testing.T) { + rec := &reqRec{} + srv := newJSONProvider(rec, draftEdit) + defer srv.Close() + // para1 est_out ≈ 1677 (≤ draft budget 1797 → its own chunk); para2 est_out ≈ 1318 forces a second + // chunk; together ≈ 2995 ≤ edit ceiling 3200 → ONE edit unit with both members. + bookPath := setupProjectOpts(t, srv.URL, projectOpts{source: cjkSource(1, 1400) + "\n\n" + strings.Repeat("字", 1100) + "。", regenerate: 0}) + ctx := obs.WithReqInfo(context.Background(), obs.ReqInfo{TraceID: obs.NewTraceID()}) + + // Confirm the fixture actually produces the 2-chunk / 1-unit shape the test targets. + r0 := newRunner(t, bookPath) + manifest, err := r0.bookChunks() + r0.Close() + if err != nil { + t.Fatal(err) + } + units := buildEditUnits(manifest) + if len(manifest) != 2 || len(units) != 1 || len(units[0].Members) != 2 { + t.Fatalf("fixture must be 2 draft chunks in 1 edit unit, got %d chunks / %d units", len(manifest), len(units)) + } + + r1 := newRunner(t, bookPath) + res, err := r1.TranslateBook(ctx) + if err != nil { + t.Fatal(err) + } + r1.Close() + + // One outcome PER UNIT, at the leader chunk, carrying both member drafts + the single edit stage. + if len(res.Chunks) != 1 { + t.Fatalf("a 2-chunk unit must yield ONE unit outcome, got %d", len(res.Chunks)) + } + oc := res.Chunks[0] + if oc.ChunkIdx != 0 { + t.Fatalf("the unit outcome must address the leader chunk (0), got %d", oc.ChunkIdx) + } + if len(oc.Stages) != 3 { + t.Fatalf("the unit outcome must carry 2 member drafts + 1 edit, got %d stages", len(oc.Stages)) + } + if oc.Stages[0].Role != roleTranslator || oc.Stages[1].Role != roleTranslator || oc.Stages[2].Role != roleEditor { + t.Fatalf("stages must be [draft, draft, edit], got %s/%s/%s", oc.Stages[0].Role, oc.Stages[1].Role, oc.Stages[2].Role) + } + if oc.FinalText != "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД" { + t.Fatalf("the unit's final text is the single edit output, got %q", oc.FinalText) + } + // EXACTLY 3 provider calls: 2 drafts + 1 edit — the editor did NOT re-render either draft. + if rec.count() != 3 { + t.Fatalf("multi-chunk unit must be 2 draft + 1 edit calls, got %d", rec.count()) + } + // The editor's request carried the CONCATENATION of both members' drafts (joined by the unit separator). + var editBody string + for _, b := range rec.all() { + if isEditBody(b) { + editBody = b + } + } + // Both members' drafts appear in the editor's input (the body JSON-escapes the join, so count the + // draft marker rather than match the raw separator). + if n := strings.Count(editBody, "ЧЕРНОВИК ПЕРЕВОДА"); n != 2 { + t.Fatalf("the editor must read BOTH member drafts concatenated, found %d in the edit body", n) + } + + // Export projects ONE unit row (not 2, and not a phantom "pending" for the non-leader member). + r2 := newRunner(t, bookPath) + exp, err := r2.Export(true) + if err != nil { + t.Fatal(err) + } + if exp.TotalChunks != 1 || exp.PendingChunks != 0 || len(exp.Chunks) != 1 { + t.Fatalf("export must be 1 unit / 0 pending, got total=%d pending=%d rows=%d", exp.TotalChunks, exp.PendingChunks, len(exp.Chunks)) + } + if exp.Chunks[0].FinalText != "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД" { + t.Fatalf("export unit text mismatch: %q", exp.Chunks[0].FinalText) + } + // --pairs source is the members' joined source (the src↔target pair aligns to the editor's input). + if !strings.Contains(exp.Chunks[0].Source, unitJoinSeparator) { + t.Fatalf("export --pairs source must be the joined unit source, got %q", exp.Chunks[0].Source[:min(40, len(exp.Chunks[0].Source))]) + } + + // Status counts the unit as ONE done chunk (not two). + st, err := r2.Status(ctx) + if err != nil { + t.Fatal(err) + } + if st.TotalChunks != 1 || st.Done != 1 { + t.Fatalf("status must be 1 unit done, got total=%d done=%d", st.TotalChunks, st.Done) + } + r2.Close() + + // Resume is $0 (all checkpoints hit; the editor re-derives its content-addressed id for free). + r3 := newRunner(t, bookPath) + defer r3.Close() + before := rec.count() + res2, err := r3.TranslateBook(ctx) + if err != nil { + t.Fatal(err) + } + if rec.count() != before || res2.TotalUSD != 0 { + t.Fatalf("resume must be $0 with no new calls: calls=%d usd=%v", rec.count()-before, res2.TotalUSD) + } +} + +// TestWaveParallelWorkersMoneyConserved runs the wave driver with several parallel workers over a book of +// many chunks and asserts the money invariant survives concurrency: committed spend == the sum of the +// settled checkpoints (the single-writer store serializes Reserve/Settle), and the per-unit result is +// complete + deterministic. Run under `-race` this also proves the waves share only read-only state. +func TestWaveParallelWorkersMoneyConserved(t *testing.T) { + rec := &reqRec{} + srv := newJSONProvider(rec, draftEdit) + defer srv.Close() + // 5 paragraphs of ~1400 Han each → 5 draft chunks, and since any two exceed the 3200 edit ceiling, + // 5 edit units → 10 wave work items fanned over 4 workers. + bookPath := setupProjectOpts(t, srv.URL, projectOpts{source: cjkSource(5, 1400), regenerate: 0, waveWorkers: 4, bookUSD: 100}) + ctx := obs.WithReqInfo(context.Background(), obs.ReqInfo{TraceID: obs.NewTraceID()}) + + r1 := newRunner(t, bookPath) + res, err := r1.TranslateBook(ctx) + if err != nil { + t.Fatal(err) + } + if len(res.Chunks) != 5 { + t.Fatalf("5 chapters-worth of single-chunk units expected, got %d", len(res.Chunks)) + } + for _, oc := range res.Chunks { + if oc.Disposition != DispOK || oc.FinalText != "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД" { + t.Fatalf("every parallel unit must be ok+edited, got %s / %q", oc.Disposition, oc.FinalText) + } + } + // Money invariant under parallelism: the ledger's committed spend matches the run's own aggregate and + // no reservation leaked — the single-writer store serialized every Reserve/Settle despite N workers + // (the store-level atomicity + kill-9 durability is separately pinned by store/kill9_test.go). + committed, reserved, err := r1.Store.SpentUSD("test-book") + if err != nil { + t.Fatal(err) + } + r1.Close() + if reserved != 0 { + t.Fatalf("no reservation may leak after a clean parallel run, reserved=%v", reserved) + } + if math.Abs(res.TotalUSD-committed) > 1e-9 { + t.Fatalf("run total %v != ledger committed %v under parallel workers — a settle raced/leaked", res.TotalUSD, committed) + } +} + +// TestWaveEditUnitFlaggedMemberDraft: when ONE member draft of a multi-chunk unit flags, the whole unit is +// flagged and its edit is SKIPPED (no paid edit over a partial draft), while the good member's draft money +// stays committed. There is exactly ONE edit call fewer than a clean run. +func TestWaveEditUnitFlaggedMemberDraft(t *testing.T) { + rec := &reqRec{} + // The second paragraph carries a marker; the mock returns an untranslated CJK echo for it → cjk_artifact. + const echoMarker = "禁" + respond := func(body string) (string, string) { + if isEditBody(body) { + return "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД", "stop" + } + if strings.Contains(body, echoMarker) { + return "这是完全没有翻译的中文内容。", "stop" // fully-CJK → classify flags cjk_artifact + } + return "ЧЕРНОВИК ПЕРЕВОДА", "stop" + } + srv := newJSONProvider(rec, respond) + defer srv.Close() + src := strings.Repeat("文", 1400) + "。\n\n" + strings.Repeat(echoMarker, 1100) + "。" + bookPath := setupProjectOpts(t, srv.URL, projectOpts{source: src, regenerate: 0}) + ctx := obs.WithReqInfo(context.Background(), obs.ReqInfo{TraceID: obs.NewTraceID()}) + + r := newRunner(t, bookPath) + defer r.Close() + res, err := r.TranslateBook(ctx) + if err != nil { + t.Fatal(err) + } + if len(res.Chunks) != 1 { + t.Fatalf("still one unit outcome, got %d", len(res.Chunks)) + } + oc := res.Chunks[0] + if oc.Disposition != DispFlagged || oc.FlagReason != FlagCJKArtifact { + t.Fatalf("a flagged member draft must flag the unit (cjk_artifact), got %s/%s", oc.Disposition, oc.FlagReason) + } + if oc.FinalText != "" { + t.Fatalf("a flagged unit exports nothing, got %q", oc.FinalText) + } + // 2 draft calls (one ok, one echo), ZERO edit calls — the unit's edit was skipped over the partial draft. + if rec.count() != 2 { + t.Fatalf("a partial-draft unit runs 2 drafts + 0 edit, got %d calls", rec.count()) + } +} + +// TestWaveEscalationBudgetSerializedUnderParallelism pins the escMu: two draft chunks escalate +// CONCURRENTLY under a budget that admits only ONE hop. The escalation soft-cap is a non-atomic +// read-then-act over EscalationSpentUSD, so without escMu both parallel workers could read spent 1e-12 || diff < -1e-12 { + t.Fatalf("escMu must serialize escalation admission under parallel workers: want exactly one hop (%.6f), got %.6f", fakeCallUSD, esc) + } + // Exactly one unit escalated-OK and one stayed flagged (WHICH one wins the single hop is + // scheduling-dependent, so assert the totals, not the identity). + escalatedOK, flagged := 0, 0 + for _, oc := range res.Chunks { + if oc.Disposition == DispOK && len(oc.Stages) > 0 && oc.Stages[0].Escalated { + escalatedOK++ + } + if oc.Disposition == DispFlagged { + flagged++ + } + } + if escalatedOK != 1 || flagged != 1 { + t.Fatalf("exactly one unit escalates-OK and one stays flagged, got ok=%d flagged=%d", escalatedOK, flagged) + } +} + +// TestWaveMinedSignDoesNotRebillDraft is the «переоплата ОДНА» pin AT THE INJECTION LEVEL (the checkpoint- +// review found the split was implemented only at the version-hash level): signing a mined term and re-running +// must move ONLY the edit wave, leaving the draft wave's checkpoints byte-stable. The draft selects over the +// BASE bank (mined-excluded), so a mined addition does NOT change the draft's injected wire → its content_hash +// / final_hash / snapshot are unchanged → the draft resumes at $0. The editor selects over the ENRICHED bank, +// so the mined term DOES move the edit-wave snapshot (the single, --resnapshot-gated overpay). Reverting the +// fix (draft over the enriched bank) makes the draft content_hash change here → the test fails. +func TestWaveMinedSignDoesNotRebillDraft(t *testing.T) { + rec := &reqRec{} + srv := newJSONProvider(rec, draftEdit) + defer srv.Close() + // Source carries a BASE seed term (魔法学院) and a to-be-mined term (方源); both are ≥2-char Han keys. + src := "方源走进了魔法学院的图书馆。" + seed := "terms:\n - src: 魔法学院\n dst: Академия магии\n status: approved\n" + bookPath := setupProjectOpts(t, srv.URL, projectOpts{source: src, glossarySeed: seed, regenerate: 0}) + ctx := obs.WithReqInfo(context.Background(), obs.ReqInfo{TraceID: obs.NewTraceID()}) + + r1 := newRunner(t, bookPath) + if _, err := r1.TranslateBook(ctx); err != nil { + t.Fatal(err) + } + draftBefore, err := r1.Store.GetChunkStatus("test-book", 1, 0, "draft") + if err != nil || draftBefore == nil { + t.Fatalf("draft chunk_status after run 1: %v / %v", draftBefore, err) + } + editBefore, err := r1.Store.GetChunkStatus("test-book", 1, 0, "edit") + if err != nil || editBefore == nil { + t.Fatalf("edit chunk_status after run 1: %v / %v", editBefore, err) + } + r1.Close() + + // Owner signs 方源 → Фан Юань (approved) into a mined-delta file (loaded as Source:mined) and re-runs + // with --resnapshot (the edit wave's enriched snapshot legitimately moves; the draft's must not). + dir := filepath.Dir(bookPath) + writeFile(t, filepath.Join(dir, "mined-delta.yaml"), "terms:\n - src: 方源\n dst: Фан Юань\n status: approved\n") + rawBook, err := os.ReadFile(bookPath) + if err != nil { + t.Fatal(err) + } + writeFile(t, bookPath, strings.Replace(string(rawBook), "pipeline: pipeline.yaml", "pipeline: pipeline.yaml\nmined_delta: mined-delta.yaml", 1)) + + r2 := newRunner(t, bookPath) + defer r2.Close() + r2.Resnapshot = true + if _, err := r2.TranslateBook(ctx); err != nil { + t.Fatal(err) + } + draftAfter, err := r2.Store.GetChunkStatus("test-book", 1, 0, "draft") + if err != nil || draftAfter == nil { + t.Fatalf("draft chunk_status after run 2: %v / %v", draftAfter, err) + } + editAfter, err := r2.Store.GetChunkStatus("test-book", 1, 0, "edit") + if err != nil || editAfter == nil { + t.Fatalf("edit chunk_status after run 2: %v / %v", editAfter, err) + } + + // «переоплата ОДНА»: the DRAFT wave is byte-stable across the mined sign — same snapshot, same rendered + // content, same authoritative checkpoint → it resumed at $0 (a mined term never entered the draft wire). + if draftAfter.SnapshotID != draftBefore.SnapshotID { + t.Fatalf("draft-wave snapshot moved on a mined sign (%.12s → %.12s) — base bank not excluding mined", draftBefore.SnapshotID, draftAfter.SnapshotID) + } + if draftAfter.ContentHash != draftBefore.ContentHash { + t.Fatalf("draft injection CHANGED on a mined sign — the draft selects over the ENRICHED bank (regression): «переоплата ОДНА» broken, the whole draft wave re-bills") + } + if draftAfter.FinalHash != draftBefore.FinalHash { + t.Fatalf("draft checkpoint re-created on a mined sign (%.12s → %.12s) — the draft was re-billed", draftBefore.FinalHash, draftAfter.FinalHash) + } + // The single, gated overpay DID land on the edit wave: the enriched snapshot moved. + if editAfter.SnapshotID == editBefore.SnapshotID { + t.Fatalf("edit-wave snapshot did NOT move on a mined sign — the enriched bank is not folding the mined term") + } +} + +// TestWaveMiningUnconfiguredAutoContinues: with no langpack / no contrast (every existing fixture), the +// bank-mining stop is a no-op — the driver runs straight through to the edit wave and writes no signature +// map. Guards that the mining wiring never perturbs a normal $0 run. +func TestWaveMiningUnconfiguredAutoContinues(t *testing.T) { + rec := &reqRec{} + srv := newJSONProvider(rec, draftEdit) + defer srv.Close() + bookPath := setupProjectOpts(t, srv.URL, projectOpts{regenerate: 0}) + ctx := obs.WithReqInfo(context.Background(), obs.ReqInfo{TraceID: obs.NewTraceID()}) + + r := newRunner(t, bookPath) + defer r.Close() + if r.pack != nil { + t.Fatal("no langpack_root → pack must be nil") + } + stopped, err := r.runBankMiningStop(ctx, nil) + if err != nil || stopped { + t.Fatalf("unconfigured mining must auto-continue, got stopped=%v err=%v", stopped, err) + } + if _, err := r.TranslateBook(ctx); err != nil { + t.Fatal(err) + } + if _, err := os.Stat(r.signatureMapPath()); !errors.Is(err, os.ErrNotExist) { + t.Fatalf("no signature map may be written when mining is unconfigured (err=%v)", err) + } +} diff --git a/docs/PROGRESS.md b/docs/PROGRESS.md index cc0aef5..d2f6051 100644 --- a/docs/PROGRESS.md +++ b/docs/PROGRESS.md @@ -9,6 +9,10 @@ > - **Ждём от владельца:** тачпойнты exp16 (карта подписи/пол · мини-голд алиасов · precision@30, `books/gu-zhenren/exp16/`, ~30–40 мин — для сид-дельты к пере-прогону) · развилки плана §10 (W1.5-UX · DC5-стих-политика · Edit-ceiling · и др.) · реплика ja→ru (тест общности §B5) · **ре-чек прайса DeepSeek у катовера слагов 24.07** (до него платных deepseek-прогонов нет) · чтение пере-прогона (после R1+resnapshot) · старые висящие: планка запуска (лучше-фана/гибрид/издательский) · билингв-якорь пилота (D25.9-Q1) · контаминация пилот-корпуса (D27.4) · publishable/waiver (D25.1) · FN-bound L3 (D25.4) · юр-пакет · провенанс 12-*-доков. > - Архивы хроники: `archive/PROGRESS-2026-07-04-10.md` (D31) · `archive/PROGRESS-2026-07-10-13.md` (D39.6-гигиена). Записи ниже — живая эра D39. +## Оркестратор №7 — R1 драйвер-свитч ПРИНЯТ и залендён (D39.17), ПАК-11 ЗАВЕРШЁН, 19.07 + +Бэкенд-сессия сдала волновой исполнитель (`waverun.go`/`mining.go` нов): precompute→черновик∥→банк-майнинг-стоп→редактура∥; редактор читает concat-черновик по final_hash, НИКОГДА не пере-рендерит draft; `translateChunk` удалён. + wiring майнера (langpack fail-loud/nil + pack.Version-фолд + mined-write) + Ш-2 (unicode.Version) + Ш-1 (masked-diff) + golden-рерайт (8 глав→8 единиц) + read-модели per-unit + именование без W0-W2. **Приёмка: прямая (build/race сам, 8 волновых пинов вкл. кусачий регресс-пин переоплаты-ОДНА, golden байт-стабилен, построчное чтение waverun=план §1/research19 §B3-бис) + ПОЛНЫЙ рубеж-2** (5 линз вкл. явную синк-с-ресёрчем — владелец просил; refute-by-default, $0): **4 находки / 1 refuted / 3 выжили — ВСЕ MINOR/NOTE, 0 CRIT/MAJOR; все несущие линзы (деньги/секвенирование/детерминизм/СИНК/снапшот) ПУСТЫ.** Сессия сама поймала MAJOR (инъекция черновика над enriched вместо base → тихий re-bill при mined-подписи; фикс r.baseMemory + регресс-пин). **Фикс-лист (3, стенд-only mining / трипваер — не блокируют, ГЕЙТ до живого mining пере-прогона):** R1-FL-A (CLI не даёт WaveSignatureStop distinct exit-код → exit 1; коммент/отчёт оверклейм) · R1-FL-B (mining-стоп очищается только при пустой дельте, reject-механизма нет → отклонённый терм livelock'ит стоп; связано с W1.5-UX §10-1) · R1-FL-C (NOTE: x/text/norm своя Unicode-редакция не фолдится — расширить Ш-2). Девиации приняты (сургичный per-wave resnapshot, escMu-сериализация эскалаций). **ПАК-11 ЗАВЕРШЁН** (Block A+continuation+арх-проход+R1); `BACKEND_PLAN11` отработан→архив. **Очередь:** пере-прогон-преп (R1-FL-A/B/C + единый resnapshot D30.9 §8) → пере-прогон 3–10 глав (армы + live mining с подписью) → чтение (планка 2 претензии). + ## Оркестратор №7 — подпись карты exp16 + находка «Бай Нинбин = предел DC-3», 19.07 Владелец подписал карту exp16 (`books/gu-zhenren/exp16/signature_map.md`, вне git): **dst-канон принят** (banknote-dst + сидовый dst для Палладий-канон-записей; мусорные co-occ «справочно» — игнор, это доказанный провал WHAT §3.3). Правки владельца: 南疆→«Южные земли» (не транслит), 青丝蛊→«Шёлковый гу», 长生 без изм. (=«бессмертие», авто-dst был брак). Пол: остальные персонажи — male по evidence (ожидает финального «ок» владельца), **白凝冰 (Бай Нинбин) = `hidden`**. **НАХОДКА (предел дефект-класса gender-enforce D39.8):** Бай Нинбин ЛОМАЕТ статическое поле пола — пол МЕНЯЕТСЯ по книге (безгендерный→мужчина→магически женщина) И расщеплён по перспективе (внешне ж / сам себя мыслит мужчиной). Ни `gender`, ни окно `since_ch/until_ch` этого не выражают → **детерминированный DC-3 НЕ трогает (правильно, `hidden`→Ф2/редактор); местоимения рендерит редактор ПО СЦЕНЕ.** Следствия: (1) валидирует D39.16-решение отложить hidden-чекер в Ф2; (2) **требование к Ф2/editor-контексту: нужна НАРРАТИВНАЯ гендер-аннотация (since_ch-смены + перспектива), не булево поле** — вход дизайна Ф2-аннотатора; (3) **ожидание пере-прогона (честно владельцу): его претензия «мечтал/мечтала» по Бай Нинбину — редакторская-на-понимание, детерминированным фиксом НЕ закрывается; зависит от того, поймёт ли редактор сцену (может частично на прямых фазах, не гарантировано на расщеплённых).** Гарантированные детерм-фиксы пере-прогона — чистые male-персонажи + 时辰-юниты + числа + регистр. diff --git a/docs/README.md b/docs/README.md index 9710cd7..be6608a 100644 --- a/docs/README.md +++ b/docs/README.md @@ -16,7 +16,7 @@ - `experiments/` — эмпирика «Полигона»: `00-provider-quirks` (читать перед любым вызовом провайдера), `01-token-calibration`, `02-refusal-benchmark`, `03-local-stand`, `04-editor-quality`, `06-local-extraction`, `07-coverage-precision`, `08-cost-model-v2` (актуальная денежная модель), `09-pilot-protocol` (пилот Ф2.5 + поправки D13), `10-explicit-benchmark` (18+ violence-рука канала B), `11-erotica-benchmark` (erotica по трём парам/регистрам — закрытие D14.4, D22). - `research/` — фактура исследований 04–05.07: `01–10` базовые, `11-gap-*` добор критиком, `12-*` режимы отказа/отзывы/таксономии (+ два внешних материала с провенанс-шапками), `13` валидация памяти, `14` адаптивная память, `15` голос и состояние (принят, D21), **`16` ридер-IDE (принят с ревью-шапкой, D29)**, **`17` внешняя критика GPT-5.6 (принят с ревью-шапкой, D25)** — у 16/17 читать шапку прежде тела. **`18` рычаги качества (два отчёта, D36)** · **`19` нарезка+когезия+контракт t/e (D39.1)** · **`20` банк-майнинг W1.5 (D39.6)** — у всех ревью-шапки. ⚠ Часть под superseded-баннерами (01/02/03/04/05/09 и gap-1/2/5) — **читай баннер прежде содержимого**. - `PROGRESS.md` — **журнал** (CURRENT-STATE сверху, ниже хронология; НЕ источник решений). -- **Активные хендофф-промты (пост-D39.16, 19.07):** [`BACKEND_PLAN11_SESSION_PROMPT.md`](BACKEND_PLAN11_SESSION_PROMPT.md) (**СТАРТОВЫЙ — R1-продолжение [драйвер-свитч + FL-фиксы + фолд `pack.Version()`/загрузка langpack при wiring майнера] по плану [`11-implementation-plan.md`](architecture/11-implementation-plan.md); D39.12/14/16**) · [`ORCHESTRATOR_SESSION_PROMPT.md`](ORCHESTRATOR_SESSION_PROMPT.md) (хендофф №5 оркестратора) · [`POLYGON_PACKAGE4_SESSION_PROMPT.md`](POLYGON_PACKAGE4_SESSION_PROMPT.md) (residual пилот/18+/echo). Закрытые — в `archive/prompts/` (свежие: арх-cleanup→D39.16, дизайн-синтез→D39.12, exp16→D39.10, Q4a→D39.9, exp15→D39.7). +- **Активные хендофф-промты (пост-D39.17, 19.07):** [`ORCHESTRATOR_SESSION_PROMPT.md`](ORCHESTRATOR_SESSION_PROMPT.md) (хендофф №5 оркестратора; статус-баннер — пост-D39.17) · [`POLYGON_PACKAGE4_SESSION_PROMPT.md`](POLYGON_PACKAGE4_SESSION_PROMPT.md) (residual пилот/18+/echo). **ПАК-11 ЗАВЕРШЁН** — след. шаг = пере-прогон-преп (3 mining-wiring-фикса R1-FL-A/B/C + единый resnapshot; промт пишет оркестратор). Закрытые — в `archive/prompts/` (свежие: пак-11/R1→D39.17, арх-cleanup→D39.16, дизайн-синтез→D39.12). - `archive/` — закрытые сессионные промты (только история, инструкции оттуда не исполнять). ## Статус (2026-07-19, пост-D39.16 — стройка пере-прогонного стека) diff --git a/docs/architecture/05-decisions-log.md b/docs/architecture/05-decisions-log.md index 615e381..c7dd12c 100644 --- a/docs/architecture/05-decisions-log.md +++ b/docs/architecture/05-decisions-log.md @@ -3,7 +3,7 @@ > **⟶ КАРТА АКТУАЛЬНОСТИ (ревизия D31, продлена до D38.2 [12.07]; исторические записи ниже НЕ переписываются — дисциплина D23.3).** Читая контракт целиком, держи под рукой, что чем перекрыто: > - **Полностью superseded:** **D1 (моно-редактор) → D17 → D30.1 (редактор БИЛИНГВ)** · D9 (ja-приёмка) → D18 (蛊真人 zh→ru; ja — второй прогон) · D17 → D30.1 · скобка D19.4 «ключ без data-sharing» и D20.3 «чистый ключ = блокер пилота» → **D27** (единый ключ С data-sharing, отключение перед продом) · exp04-дефолт «editor grok-4.3» (D3) → D30.1 (grok reasoning-off из редакторских ролей СНЯТ — no-op; кандидат glm-5-билингв; gemini — премиум-эскалация только за санитайзером D30.3). > - **Частично амендировано:** D3 (канал B → D14.1/D19.1 + оговорки D22.5/D22.6; апекс-слаг `-preview` — D22.4; draft под вопросом exp13 — D30.6) · D6 («off/minimal для draft/edit» эродирован: draft thinking-ON принудительно, editor-off снят D30.1; живы per-роль принцип и D6.2-буфер) · D10 (+D24.2 alias-слепое пятно, истинная консистентность ≈99.5%) · D11-числа → exp08 → **D30.4** (флип D1 = +15–25%, ~$0.85/ранобэ; «$1.5–2» = неподписанная опция Б) · D12 (+D24.3 флоры max_tokens; +D29.1в rollup — амендмент вердикт-правила) · D13.1-арм из решающего → ПОДТВЕРЖДАЮЩИЙ (D30.1); +D25.3 prefix-анализ судьи · D14.2 закрыт D19.1/D22.4; D14.4 закрыт D22.1 · D15.3 исполнен; спека D15.2: v2→v3→v3.1 (D22.2), реализация = текущий пакет (D30.9) · D24.4 +D28.1 (precision/recall-трейдофф; hard-gate требует пере-замера) · порядок D24.5 отложен D26.1 (этап B — после читаемых 25 глав). -> - **Живое ядро без изменений:** D2 (+новый гейт-класс D30.3), D4, D5, D7, D8, D10-механизм, D12-таксономия отказов, D16, D18, D19.1–19.2, D21 (Ф2-механизмы voice/address/reveal), D22.5–22.7, D23 (golden = инвариант №8), D24–D39.16 — действующая голова контракта (**D39.16 = арх-проход ЗАЛЕНДЕН: майнер-данные (百家姓/Палладий/частицы/суффиксы) вынесены в `internal/lang`+`configs/langpacks/` [граница компиль-enforced, байт-точно — парити EXACT, golden байт-идентичен]; FL-1/2/3+тест-путь; РАТИФИЦИРОВАНЫ 3 дивергенции: language.Tag ОТВЕРГНУТ [CLDR-инстабильность в вердиктах], DC-чекеры+снапшот-фолд DEFER [майнер offline/нейтральность]; общность структурно доказана; промт отработан→архив**; **D39.15 = директива владельца: изоляция языковых данных из `pipeline/` [движок общий · `internal/lang/`+`configs/langpacks/` данными-файлами · `x/text/language.Tag` вместо `isRuTarget` · снапшот-folded как промпты · алгоритмы не трогать]; архитектурный проход ПЕРЕД R1 [ре-секвенс]; поведенчески нейтрально zh→ru [golden байт-стабилен]; не минор-хант/не rewrite-ради-rewrite; промт `BACKEND_ARCH_CLEANUP_SESSION_PROMPT.md` 5-фазный [ресёрч→синтез→фикс-лист→исполнение→ревью]; ja→ru = тест общности §B5 позже**; **D39.14 = пак-11 continuation ПРИНЯТ и залендён [R2 майнер паритет-EXACT · R3 банкнота 12-точек · R4 DC-чекеры+export--pairs · R5 арм-конфиги · R1-аддитив; рубеж-2 D39.13-долга погашен: 3 MINOR/PARTIAL-находки [FL-1 bankTokenBudget-фолд · FL-2 banknote-телеметрия-резюм · FL-3 emission-top-N-кап], все латентны → R1-продолжение; R1 драйвер-свитч резидуал; clean bill по деньгам/wire/порту]**; **D39.13 = пак-11 Block A ПРИНЯТ и залендён [WS2 целиком (вкл. src→dst-блок редактора = закрытие D30.1) + WS1a/b/c-инфра + WS4-ядро; 2 девиации ратифицированы; резидуал R1–R5 в PACK11_REPORT; промт остаётся активным; рубеж-2 приёмки — долг]**; **D39.12 = план `architecture/11-implementation-plan.md` РАТИФИЦИРОВАН [три рубежа: ревью-2 F1–F11 → 7-агентный адверсариал → подтверждающий пас; пер-волновой снапшот + инвариант секвенирования = «переоплата ОДНА»; EditCeilingOut=3200; лемматизатор дефолт B; 4 гейтнутых арма]; бэкенд-пак ЕДИНОЙ сессией — `BACKEND_PLAN11_SESSION_PROMPT.md`**; **D39.11 = директива владельца: стройка ТОЛЬКО после дизайн-синтез сессии с верифицированными алгоритмами; хендофф №5**; **D39.10 = exp16: WHICH подтверждена [V-C recall 0.97, $0] / WHAT→банкнота+Палладий [canon-recovery <70%], 9B-споттер не нужен, Z1→облако, ре-аудит exp14b чист [errata не требуется]; исследовательская программа ЗАВЕРШЕНА → бэкенд-пак слоёв 1+4**; **D39.9 = Q4a: верность НЕ на translate-стадии [flash уже верен, pro ×3.67 не ратифицирован], смысл ломает glm-РЕДАКТОР [свап-арм приоритетен], DET-пол 0.261; exp14b-правила дефектны → $0-ре-аудит в exp16**; **D39.8 = слепое чтение: планка не пройдена никем, дефекты распределены [читатель подтвердил floor-null], битва качества → дефект-классы [时辰-юниты, числа, gender-enforce, стих, регистр]**; **D39.7 = exp15 залендён REV.2: «граница вредит» отозван [артефакт окна судьи], все когезия-эффекты под floor 0.126, «sequential нигде не лучше» LOO-stable [не ратифицированный зелёный свет], фертильность 1.20/0.39, $12.79/$15; гейт = слепое чтение владельца**; **D39.6 = research/20 банк-майнинг залендён [детектор-лестница V-A/B/C, алиас-ярусы, banknote-v1 с 12 гейт-точками, §B5 плагины P1–P6, §D-пре-рег]; полигон-стадия после exp15**; **D39.5 = пак-1.5+F1–F9 залендены [tmctl export с manifest/drift-гардами · fold-first санитайзер · bounded глосс · пример zh-ru]; экстракция полигона впредь через tmctl export**; **D39.4 = адверсариал-долг ПОГАШЕН [8 осей: 0 CRIT/1 HIGH/6 MED], пак-1.5 придержан под фикс-лист F1–F9 в §T4**; **D39.3 = пакет банк-майнинга W1.5 [диспозиция H15/V4-п4] ратифицирован, research/20-промт с HOLD до фриза exp15**; **D39.2 = трек-A пак-1 залендён `d3f6b34`: trust-gated suppressor [терм-дрейф закрыт в КОДЕ] + export-contract нормализация + pair-сеам + реестры + quality-report; адверсариал-долг за 529**; **D39.1 = research/19 залендён: конфликт exp14↔research/18 разрешён [эмиссия≠окно≠связность], Go-спека чанкера+когезии, волновая архитектура W0–W3 [вводная владельца: параллелизм], пре-рег эмпирики Q0–Q5; оркестратор-ревью снято владельцем**; **D39 = АРХ-РЕСЕТ: синк-аудит сломанного телефона [65 находок, 0 refuted, `08-sync-audit-ledger.md`] + целевая 7-слойная архитектура [`09-target-architecture.md`] + фазовый план [трек A build-now ∥ трек B ресёрч, пере-прогон после]; формализует фантомный «D35.7» как цель слоя 1; терм-дрейф код-корень жив [сид-воркэраунд]; редактор 4-мандата-full-regen = причина инверсий**; D35 = пивот качество-первым; D36 = приёмка research/18; D37 = приёмка exp14: претензия-1=промпт-рычаг; D38 = приёмка exp14b: «только gpt-5.4» ОПРОВЕРГНУТО [mistral/deepseek-pro чинят], фронтир в дефолт НЕ нужен, корень терм-дрейфа = статус-draft сида; **D38.1 = слепой h2h P1a↔F-disc залендён [ChatGPT «фронтир сильнее» / Claude «near-parity» расходятся, СХОДЯТСЯ: дефекты = инфра] → РАЗВОРОТ «мерить→строить», выдан BACKEND_INFRA_PACK; D38.2 = консолидация/док-гигиена: спент exp-скрипты в `eval/exp12|13|14|14b/`, статус-доки+.puml актуализированы; D38.3 = инфра-пак читаемости залендён (санитайзер-классы strip+export + число/omission-гард), верифицирован исполнением [build/vet/test зелёные, 3 span-дефекта запинены]; D38.4 = аудит полноты exp14/14b: чэнъюй-рычаг забыт near-term→дописан в дискурс-промпт; inversion-гард D37 §2г не строился (число/omission ≠ полярность)→editor-swap = защита от инверсий (приоритет↑); нарезка = re-run-арм; гард-тумблер вкл. при resnapshot; D38.5 = компоненты resnapshot залендены+верифицированы [reseed-сид eb409f2 · дискурс+чэнъюй editor v3 0ac5f7a с few_shot-тумблером] → следующий шаг единый resnapshot + пере-прогон**). +> - **Живое ядро без изменений:** D2 (+новый гейт-класс D30.3), D4, D5, D7, D8, D10-механизм, D12-таксономия отказов, D16, D18, D19.1–19.2, D21 (Ф2-механизмы voice/address/reveal), D22.5–22.7, D23 (golden = инвариант №8), D24–D39.17 — действующая голова контракта (**D39.17 = R1 драйвер-свитч ЗАЛЕНДЕН [волновой исполнитель черновик∥→банк-майнинг-стоп→редактура∥; редактор не пере-рендерит draft; Ш-1/Ш-2; golden-рерайт; read-модели per-unit]; полный рубеж-2 [5 линз вкл. синк-с-ресёрчем] = clean bill по несущим осям, 3 MINOR/NOTE-фикса (R1-FL-A CLI-exit-код · R1-FL-B mining-стоп-reject · R1-FL-C x/text-версия) в стенд-only mining-пути → пере-прогон-преп; ПАК-11 ЗАВЕРШЁН**; **D39.16 = арх-проход ЗАЛЕНДЕН: майнер-данные (百家姓/Палладий/частицы/суффиксы) вынесены в `internal/lang`+`configs/langpacks/` [граница компиль-enforced, байт-точно — парити EXACT, golden байт-идентичен]; FL-1/2/3+тест-путь; РАТИФИЦИРОВАНЫ 3 дивергенции: language.Tag ОТВЕРГНУТ [CLDR-инстабильность в вердиктах], DC-чекеры+снапшот-фолд DEFER [майнер offline/нейтральность]; общность структурно доказана; промт отработан→архив**; **D39.15 = директива владельца: изоляция языковых данных из `pipeline/` [движок общий · `internal/lang/`+`configs/langpacks/` данными-файлами · `x/text/language.Tag` вместо `isRuTarget` · снапшот-folded как промпты · алгоритмы не трогать]; архитектурный проход ПЕРЕД R1 [ре-секвенс]; поведенчески нейтрально zh→ru [golden байт-стабилен]; не минор-хант/не rewrite-ради-rewrite; промт `BACKEND_ARCH_CLEANUP_SESSION_PROMPT.md` 5-фазный [ресёрч→синтез→фикс-лист→исполнение→ревью]; ja→ru = тест общности §B5 позже**; **D39.14 = пак-11 continuation ПРИНЯТ и залендён [R2 майнер паритет-EXACT · R3 банкнота 12-точек · R4 DC-чекеры+export--pairs · R5 арм-конфиги · R1-аддитив; рубеж-2 D39.13-долга погашен: 3 MINOR/PARTIAL-находки [FL-1 bankTokenBudget-фолд · FL-2 banknote-телеметрия-резюм · FL-3 emission-top-N-кап], все латентны → R1-продолжение; R1 драйвер-свитч резидуал; clean bill по деньгам/wire/порту]**; **D39.13 = пак-11 Block A ПРИНЯТ и залендён [WS2 целиком (вкл. src→dst-блок редактора = закрытие D30.1) + WS1a/b/c-инфра + WS4-ядро; 2 девиации ратифицированы; резидуал R1–R5 в PACK11_REPORT; промт остаётся активным; рубеж-2 приёмки — долг]**; **D39.12 = план `architecture/11-implementation-plan.md` РАТИФИЦИРОВАН [три рубежа: ревью-2 F1–F11 → 7-агентный адверсариал → подтверждающий пас; пер-волновой снапшот + инвариант секвенирования = «переоплата ОДНА»; EditCeilingOut=3200; лемматизатор дефолт B; 4 гейтнутых арма]; бэкенд-пак ЕДИНОЙ сессией — `BACKEND_PLAN11_SESSION_PROMPT.md`**; **D39.11 = директива владельца: стройка ТОЛЬКО после дизайн-синтез сессии с верифицированными алгоритмами; хендофф №5**; **D39.10 = exp16: WHICH подтверждена [V-C recall 0.97, $0] / WHAT→банкнота+Палладий [canon-recovery <70%], 9B-споттер не нужен, Z1→облако, ре-аудит exp14b чист [errata не требуется]; исследовательская программа ЗАВЕРШЕНА → бэкенд-пак слоёв 1+4**; **D39.9 = Q4a: верность НЕ на translate-стадии [flash уже верен, pro ×3.67 не ратифицирован], смысл ломает glm-РЕДАКТОР [свап-арм приоритетен], DET-пол 0.261; exp14b-правила дефектны → $0-ре-аудит в exp16**; **D39.8 = слепое чтение: планка не пройдена никем, дефекты распределены [читатель подтвердил floor-null], битва качества → дефект-классы [时辰-юниты, числа, gender-enforce, стих, регистр]**; **D39.7 = exp15 залендён REV.2: «граница вредит» отозван [артефакт окна судьи], все когезия-эффекты под floor 0.126, «sequential нигде не лучше» LOO-stable [не ратифицированный зелёный свет], фертильность 1.20/0.39, $12.79/$15; гейт = слепое чтение владельца**; **D39.6 = research/20 банк-майнинг залендён [детектор-лестница V-A/B/C, алиас-ярусы, banknote-v1 с 12 гейт-точками, §B5 плагины P1–P6, §D-пре-рег]; полигон-стадия после exp15**; **D39.5 = пак-1.5+F1–F9 залендены [tmctl export с manifest/drift-гардами · fold-first санитайзер · bounded глосс · пример zh-ru]; экстракция полигона впредь через tmctl export**; **D39.4 = адверсариал-долг ПОГАШЕН [8 осей: 0 CRIT/1 HIGH/6 MED], пак-1.5 придержан под фикс-лист F1–F9 в §T4**; **D39.3 = пакет банк-майнинга W1.5 [диспозиция H15/V4-п4] ратифицирован, research/20-промт с HOLD до фриза exp15**; **D39.2 = трек-A пак-1 залендён `d3f6b34`: trust-gated suppressor [терм-дрейф закрыт в КОДЕ] + export-contract нормализация + pair-сеам + реестры + quality-report; адверсариал-долг за 529**; **D39.1 = research/19 залендён: конфликт exp14↔research/18 разрешён [эмиссия≠окно≠связность], Go-спека чанкера+когезии, волновая архитектура W0–W3 [вводная владельца: параллелизм], пре-рег эмпирики Q0–Q5; оркестратор-ревью снято владельцем**; **D39 = АРХ-РЕСЕТ: синк-аудит сломанного телефона [65 находок, 0 refuted, `08-sync-audit-ledger.md`] + целевая 7-слойная архитектура [`09-target-architecture.md`] + фазовый план [трек A build-now ∥ трек B ресёрч, пере-прогон после]; формализует фантомный «D35.7» как цель слоя 1; терм-дрейф код-корень жив [сид-воркэраунд]; редактор 4-мандата-full-regen = причина инверсий**; D35 = пивот качество-первым; D36 = приёмка research/18; D37 = приёмка exp14: претензия-1=промпт-рычаг; D38 = приёмка exp14b: «только gpt-5.4» ОПРОВЕРГНУТО [mistral/deepseek-pro чинят], фронтир в дефолт НЕ нужен, корень терм-дрейфа = статус-draft сида; **D38.1 = слепой h2h P1a↔F-disc залендён [ChatGPT «фронтир сильнее» / Claude «near-parity» расходятся, СХОДЯТСЯ: дефекты = инфра] → РАЗВОРОТ «мерить→строить», выдан BACKEND_INFRA_PACK; D38.2 = консолидация/док-гигиена: спент exp-скрипты в `eval/exp12|13|14|14b/`, статус-доки+.puml актуализированы; D38.3 = инфра-пак читаемости залендён (санитайзер-классы strip+export + число/omission-гард), верифицирован исполнением [build/vet/test зелёные, 3 span-дефекта запинены]; D38.4 = аудит полноты exp14/14b: чэнъюй-рычаг забыт near-term→дописан в дискурс-промпт; inversion-гард D37 §2г не строился (число/omission ≠ полярность)→editor-swap = защита от инверсий (приоритет↑); нарезка = re-run-арм; гард-тумблер вкл. при resnapshot; D38.5 = компоненты resnapshot залендены+верифицированы [reseed-сид eb409f2 · дискурс+чэнъюй editor v3 0ac5f7a с few_shot-тумблером] → следующий шаг единый resnapshot + пере-прогон**). Ответ на вопросы бэкенд-сессии (PROGRESS §«Вопросы от бэкенда», §«[НУЖНО РЕШЕНИЕ] перед Фазой 1» — с ревизии D31 в `archive/PROGRESS-2026-07-04-10.md`) и полигона (think-режим). Каждое решение прошло адверсариальную панель из 3 критиков (research / экономика / исполнимость в коде Фазы 0); ни одно не отклонено, все уточнены. Это **контракт Фазы 1** — бэкенд исполняет отсюда; при конфликте с буквой 01-decisions/02-mvp-plan — источник истины здесь (потом сольём в основные доки). @@ -550,6 +550,19 @@ exp14b (D37-мандат) прогнал батарею DET-смысл-трап **ИТОГ: все 3 компонента resnapshot ГОТОВЫ** — дискурс+чэнъюй editor (v3) · reseed-сид · инфра-пак (D38.3). **Следующий шаг = единый resnapshot** (D30.9, одна переоплата книги) + пере-прогон 3–10 глав: конфиг = glm=P1a-few-shot (дефолт) + армы {mistral few-shot · deepseek-pro `few_shot:false` = инверсия-защита D38.4 · крупная edit-единица = нарезка-арм D38.4} + `RegressionGuard` ON (D38.4). ПАРНО с чтением владельца (интерим-планка 2 претензии, D35). Крупная edit-единица — НЕ реализована (нарезка-арм, не промпт-порт). **[⟶ ПРИОСТАНОВЛЕНО D39: владелец остановил раунд для арх-ресета; пере-прогон гейтится треком B, см. D39.]** +## D39.17 — Приёмка R1 драйвер-свитч ЗАЛЕНДЕНА: волновой исполнитель (черновик∥→банк-майнинг-стоп→редактура∥); полный рубеж-2 — clean bill по несущим осям, 3 MINOR/NOTE-фикса в mining-wiring → пере-прогон-преп (19.07, оркестратор №7). ✅ + +Бэкенд-сессия сдала последний резидуал пака-11 — **волновой исполнитель** (`BACKEND_PLAN11` §R1; отчёт `docs/archive/reports/R1_DRIVER_SWITCH_REPORT_2026-07-19.md`, мой новый процесс соблюдён — не в `backend/`). **Залендено:** `translateBookWaves` заменил последовательный цикл — precompute($0)→**черновик-волна(∥ по чанкам, `snapshot_draft`=base-банк)**→**банк-майнинг-стоп**(подпись владельца или авто-continue)→**редактура-волна(∥ по edit-ЕДИНИЦАМ, `snapshot_edit`=enriched)**; редактор читает черновик как конкатенацию member-final по `final_hash`, **НИКОГДА не пере-рендерит draft** (несущий инвариант); `translateChunk` удалён. + wiring майнера в живой стоп (`loadLangPack` fail-loud/nil-and-run, `pack.Version()`-фолд omitempty, mined-write `Source:mined`) + **Ш-2** (`unicode.Version` в memnorm/classifier/style + chunker/estimator) + **Ш-1** (`goldenMaskedDiff`) + структурный golden-рерайт (8 глав→8 единиц, 19→18 вызовов) + read-модели per-unit + именование (директива: без W0/W1/W1.5/W2 в коде/логах → waveDraft/waveEdit/runBankMiningStop). + +**Приёмка — ПРЯМАЯ верификация исполнением + ПОЛНЫЙ рубеж-2** (R1 = ре-архитектура исполнения, тяжёлый адверсариал оправдан; владелец явно просил сверку волновых алгоритмов против ресёрчей). Прямая: `build/vet/test -race` зелёные (сам, `pipeline` ~31с); **8 волновых пинов** вербозно вкл. **кусачий регресс-пин `TestWaveMinedSignDoesNotRebillDraft`** (подписывает mined-терм, ре-прогон с `--resnapshot`, ассертит draft-волна байт-стабильна [SnapshotID+ContentHash+FinalHash] / edit-снапшот двинулся — падает без фикса); **golden байт-стабилен** независимо; построчное чтение `waverun.go` (алгоритм = план §1 / research/19 §B3-бис) + `mining.go` + `seeding.go` (base/enriched: `hasMined=false`→`baseMemory==memory`, golden цел). **Рубеж-2 (5-агентный × 5 линз, вкл. явную линзу СВЕРКИ с research/19 §B3-бис + research/20 §C + план §1/§2, refute-by-default, $0): 4 находки, 1 refuted, 3 выжили — ВСЕ MINOR/NOTE, 0 CRITICAL/MAJOR. Все несущие линзы (деньги/durability/параллелизм · секвенирование · детерминизм · СИНК-С-РЕСЁРЧЕМ · снапшот/golden) — ПУСТЫ; синк-линза расхождений от ратифицированного волнового дизайна НЕ нашла.** Сессия сама поймала MAJOR в своём чекпойнте (инъекция черновика считалась над ENRICHED-банком, снапшот пинился к base → тихий re-bill при подписи mined; фикс `r.baseMemory` base-scoped + регресс-пин). + +**Фикс-лист рубежа-2 (3, все в стенд-only mining-пути / трипваер — лендинг R1 НЕ блокируют; ГЕЙТ: закрыть до живого mining-раунда пере-прогона):** +- **R1-FL-A (MINOR, F1):** CLI не обрабатывает `WaveSignatureStop` → mining-стоп даёт exit 1 (генерик-крэш) вместо distinct exit-2 (как `CompletedWithFlags`); коммент/отчёт («CLI-сентинел», «carried up like CompletedWithFlags») ПЕРЕ-заявили несуществующую проводку. Человек-mitigated (stderr печатается), но exit-код-автоматику вводит в заблуждение. Фикс: distinct exit-код + рендер Terms/SignaturePath; поправить оверклейм-коммент. +- **R1-FL-B (MINOR, F2):** банк-майнинг-стоп очищается ТОЛЬКО при пустой дельте (`mining.go:56`); reject-механизма нет → терм, который владелец ОТКЛОНИЛ (опустил), ре-предлагается каждый ре-прогон → стоп фаерит вечно, edit-волна недостижима. escape (добавить как `status:auto`) не задокументирован в stop-сообщении. Связано с W1.5-UX (§10-1). Фикс: документировать escape / reject-механизм / clear-on-reviewed. +- **R1-FL-C (NOTE, F3):** `x/text/norm` несёт свою Unicode-редакцию независимо от stdlib `unicode.Version` (сессия сама пометила `memnorm.go:48`) → standalone `go get -u golang.org/x/text` мог бы тихо сдвинуть NFKC/NFC → пере-вердикт post-check без сдвига `memoryNormVersion`. Расширить Ш-2: фолдить x/text-версию / трипваер «не бампать x/text без resnapshot». + +**Ратифицированные девиации/флаги (приняты):** пер-волновой `--resnapshot` СУРГИЧЕН (не all-or-nothing — прямое следствие пер-волнового снапшота §1(в); `TestRunnerSnapshotPinning` 4→3) · `escMu` сериализует эскалации через LLM-вызов (осознанный трейд: точность soft-cap > параллелизм редких эскалаций) · Ш-2 расширен на chunker/estimator (тот же silent-drift класс). **Пак-11 ЗАВЕРШЁН** (Block A + continuation + арх-проход + R1); промт `BACKEND_PLAN11` отработан → архив. **Очередь:** пере-прогон-преп (R1-FL-A/B/C mining-wiring + единый resnapshot §8 D30.9) → пере-прогон 3–10 глав (армы glm/mistral/deepseek-pro; live mining-раунд с подписью) → чтение владельца (планка 2 претензии). + ## D39.16 — Приёмка арх-прохода D39.15 ЗАЛЕНДЕНА: язык-данные майнера вынесены в `internal/lang`+`configs/langpacks`, байт-точно (парити EXACT); три дивергенции от предложения оркестратора ратифицированы (19.07, оркестратор №7). ✅ Бэкенд-сессия исполнила `BACKEND_ARCH_CLEANUP_SESSION_PROMPT` (5 фаз-воркфлоу: ресёрч 2×3 → синтез → фикс-лист do/defer/don't → исполнение → ревью). **Залендено:** zh/Палладий-данные майнера (百家姓 single/compound, титул/топо/rank-инвентари, частицы `aliasParticle`, таблица Палладия) вынесены из Go-констант `internal/pipeline/` в **`configs/langpacks/zh|zh-ru/` (10 файлов)**, грузятся новым leaf-пакетом **`internal/lang`** (данные+загрузчик+`Version()` content-hash; **НЕ импортит pipeline → граница компиль-enforced**); движок читает резолвнутый `*lang.Pack` через DI (как `contrast`). Плюс риды-along: **FL-1** (`bankTokenBudget`→`banknoteSnap.TokenBudget`), **FL-2** (банкнота-телеметрия репопулируется на резюме из `prev.NBanknote*`, guard `FromResume && Enabled`), **FL-3** (`emitRankCap=200` перед emission-фильтрами, зеркало `a3[:200]`), тест-путь (env-override `TM_MINER_PARITY_{CONTRAST,RECORDS,SEED}`, skip-if-absent). diff --git a/docs/BACKEND_PLAN11_SESSION_PROMPT.md b/docs/archive/prompts/BACKEND_PLAN11_SESSION_PROMPT_2026-07-19.md similarity index 98% rename from docs/BACKEND_PLAN11_SESSION_PROMPT.md rename to docs/archive/prompts/BACKEND_PLAN11_SESSION_PROMPT_2026-07-19.md index 34d547c..a32ccc9 100644 --- a/docs/BACKEND_PLAN11_SESSION_PROMPT.md +++ b/docs/archive/prompts/BACKEND_PLAN11_SESSION_PROMPT_2026-07-19.md @@ -1,3 +1,5 @@ +> **⟶ ОТРАБОТАН ПОЛНОСТЬЮ → пак-11 ЗАВЕРШЁН (Block A D39.13 · continuation D39.14 · арх-проход D39.16 · R1 драйвер-свитч D39.17). Волновой исполнитель залендён, рубеж-2 clean bill. Остаток — 3 MINOR/NOTE mining-wiring-фикса (R1-FL-A/B/C) → пере-прогон-преп. Архивная копия.** + > **⚠ АКТУАЛИЗИРОВАН ПОД R1-ПРОДОЛЖЕНИЕ (19.07, пост-D39.14; предыдущие версии — в git-истории).** Сессия №1 > сдала Block A (`85f5b9e`, D39.13); сессия №2 сдала R2–R5 + R1-аддитив (D39.14). **Осталось: R1 драйвер-свитч + > 3-пунктовый фикс-лист рубежа-2 (ниже).** Дизайны — `docs/archive/reports/PACK11_CONT_REPORT_2026-07-19.md §R1` + `docs/archive/reports/PACK11_REPORT_2026-07-19.md §Резидуал`