From d5beefc8f4237552999380d8191b77dc59cd6476 Mon Sep 17 00:00:00 2001 From: "Claude (backend session)" Date: Sun, 12 Jul 2026 22:39:03 +0300 Subject: [PATCH] Land the readability infra-pack (D38): cosmetic-class strip-and-export for flagged chunks, a CJK-leak sanitizer class, and an opt-in post-reflow number/omission regression guard --- backend/cmd/tmctl/render.go | 13 +- backend/internal/config/pipeline.go | 19 +- backend/internal/pipeline/bookrun.go | 25 +- backend/internal/pipeline/cheapgates.go | 25 +- backend/internal/pipeline/cheapgates_test.go | 2 +- backend/internal/pipeline/chunkrun.go | 37 ++- backend/internal/pipeline/disposition.go | 24 +- backend/internal/pipeline/golden_test.go | 33 ++- backend/internal/pipeline/regressionguard.go | 159 +++++++++++ .../internal/pipeline/regressionguard_test.go | 82 ++++++ backend/internal/pipeline/resume.go | 20 ++ backend/internal/pipeline/sanitizer.go | 164 +++++++++++- backend/internal/pipeline/sanitizer_test.go | 94 +++++++ backend/internal/pipeline/stagerun.go | 46 +++- backend/internal/pipeline/status.go | 9 +- .../pipeline/testdata/golden/capture.golden | 246 +++++++++++------- .../pipeline/testdata/golden/source.txt | 8 + backend/internal/store/ledger.go | 27 ++ backend/internal/store/store_test.go | 35 +++ 19 files changed, 929 insertions(+), 139 deletions(-) create mode 100644 backend/internal/pipeline/regressionguard.go create mode 100644 backend/internal/pipeline/regressionguard_test.go diff --git a/backend/cmd/tmctl/render.go b/backend/cmd/tmctl/render.go index 97b405c..0ec6048 100644 --- a/backend/cmd/tmctl/render.go +++ b/backend/cmd/tmctl/render.go @@ -26,9 +26,16 @@ import ( func renderTranslate(w io.Writer, res *pipeline.BookResult, ledger func() (committed, reserved float64, err error)) error { for _, ch := range res.Chunks { fmt.Fprintf(w, "=== ГЛАВА %d ЧАНК %d — %s%s ===\n", ch.Chapter, ch.ChunkIdx, ch.Disposition, flagSuffix(ch.FlagReason)) - if ch.Disposition == pipeline.DispOK { + switch { + case ch.Disposition == pipeline.DispOK: fmt.Fprintln(w, ch.FinalText) - } else { + case ch.FinalText != "": + // Cosmetic sanitizer strip (D35.4a): the leak was removed and the remainder exported, + // but the chunk stays flagged for a human to verify the auto-clean — not lost to an + // empty placeholder (ch5/ch20 chapter openers used to drop whole for a leading «###»). + fmt.Fprintf(w, "[ФЛАГ %s — утечка вычищена, экспортирован очищенным, проверь] ↓\n", ch.FlagReason) + fmt.Fprintln(w, ch.FinalText) + default: fmt.Fprintf(w, "[ФЛАГ %s] чанк не переведён — черновик/редактура непригодны, помечен для человека\n", ch.FlagReason) } for _, st := range ch.Stages { @@ -159,7 +166,7 @@ func renderReport(w io.Writer, fmt.Fprintf(w, "%-4d %-6d %6d %s\n", rs.Chapter, rs.ChunkIdx, rs.NPostcheckMiss, rs.PostcheckDetail) } // Cheap style/number flaggers (observability, not gates): total + per-chunk detail. - fmt.Fprintf(w, "\n=== СТИЛЬ-ГЕЙТЫ (наблюдаемость: тире-диалоги, ё, транслит-междометия, разряды 万/億) — всего %d ===\n", style) + fmt.Fprintf(w, "\n=== СТИЛЬ-ГЕЙТЫ (наблюдаемость: тире-диалоги, ё, транслит-междометия, разряды 万/億, reflow-регрессия) — всего %d ===\n", style) stylePrinted := false for _, rs := range states { if rs.NStyleFlags == 0 { diff --git a/backend/internal/config/pipeline.go b/backend/internal/config/pipeline.go index aaf0a6a..adc21d5 100644 --- a/backend/internal/config/pipeline.go +++ b/backend/internal/config/pipeline.go @@ -86,9 +86,22 @@ type Stage struct { // Gates is the QA-gate config skeleton (пороги полигона; исполнение — Фаза 1). type Gates struct { - Coverage CoverageGate `yaml:"coverage"` - Glossary GlossaryGate `yaml:"glossary"` - Sanitizer SanitizerGate `yaml:"sanitizer"` + Coverage CoverageGate `yaml:"coverage"` + Glossary GlossaryGate `yaml:"glossary"` + Sanitizer SanitizerGate `yaml:"sanitizer"` + RegressionGuard RegressionGuardGate `yaml:"regression_guard"` +} + +// RegressionGuardGate controls the post-reflow regression guard (D38 infra-pack, +// research/18 §C#5): two deterministic OBSERVABILITY flaggers over the draft→final transform — +// a length collapse and a numeric drift — that surface a reflow that dropped content or drifted a +// number (四成四=44%→«четыре десятых»). Opt-in (default false), and by design NEVER a disposition +// change: the reflow editor legitimately restructures/merges, so a hard skip would false-flag a +// good edit — a hit is recorded in the cheap-gate observability channel (retrieval-state +// n_style_flags) and surfaced in the report, never dropping the chunk. Its thresholds are code +// consts (versioned with the cheap gates), so the gate carries only an on/off switch. +type RegressionGuardGate struct { + Enabled bool `yaml:"enabled"` } // SanitizerGate controls the output-sanitizer (D30.3): a deterministic verdict-axis diff --git a/backend/internal/pipeline/bookrun.go b/backend/internal/pipeline/bookrun.go index c2af1c9..c81bf7d 100644 --- a/backend/internal/pipeline/bookrun.go +++ b/backend/internal/pipeline/bookrun.go @@ -22,10 +22,16 @@ type StageResult struct { LatencyMS int FinishReason string Text string // the usable output (only on an ok disposition) - Disposition Disposition - FlagReason FlagReason // "" when ok - Detail string - Attempts int + // RecoveredText is the cosmetic-stripped export text (D35.4a): non-empty ONLY for a + // FlagSanitizerStripped final stage, where the sanitizer removed a leading markdown header / + // CJK-leak and committed the cleaned remainder. It carries the export forward on BOTH the + // fresh path (runStage) and resume (resumeFromChunkStatus reads the derived checkpoint), so + // translateChunk assembles the identical FinalText either way. "" for every other disposition. + RecoveredText string + Disposition Disposition + FlagReason FlagReason // "" when ok + Detail string + Attempts int // Escalated — a single-hop fallback draft was tried this stage (D12); when the // fallback passed the re-gate, Model above is the fallback (it answered). Escalated bool @@ -34,10 +40,13 @@ type StageResult struct { // ChunkOutcome is one chunk's result across the stage list. type ChunkOutcome struct { - Chapter int - ChunkIdx int - Stages []StageResult - FinalText string // the last stage's output; "" when the chunk is flagged + Chapter int + ChunkIdx int + Stages []StageResult + // FinalText is the exported text: the last stage's output on ok; the cosmetic-stripped + // remainder on a FlagSanitizerStripped flag (D35.4a — the chunk is exported flagged, not lost + // to an empty placeholder); "" on any other flag (the contaminated output never exports). + FinalText string Disposition Disposition // ok | flagged (a chunk has no "skipped" — that is a per-later-stage state) FlagReason FlagReason // the flagging stage's reason ("" when ok) CostUSD float64 // THIS run's spend on this chunk diff --git a/backend/internal/pipeline/cheapgates.go b/backend/internal/pipeline/cheapgates.go index a0428b8..3658c69 100644 --- a/backend/internal/pipeline/cheapgates.go +++ b/backend/internal/pipeline/cheapgates.go @@ -46,6 +46,10 @@ const cheapGateVersion = "cheapgate-v2" type cheapGateConfig struct { yoPolicy string // "auto" (inconsistency only) | "all-yo" | "all-e" allowlist map[string]bool // lower-cased surfaces exempt from the interjection blocklist + // regressionEnabled turns on the post-reflow regression guard (D38, regressionguard.go): an + // OPT-IN observability flagger (draft→final length collapse + number drift) folded into this + // result. Off → the two regression fields stay 0 and the output is byte-identical to before. + regressionEnabled bool } // cheapGateResult is the per-chunk outcome: a count per flagger plus human-readable detail lines @@ -55,15 +59,22 @@ type cheapGateResult struct { YoInconsistent int `json:"yo,omitempty"` TranslitInterj int `json:"translit_interj,omitempty"` NumberMagnitude int `json:"number_magnitude,omitempty"` - Detail []string `json:"detail,omitempty"` + // LengthCollapse / NumberDrift are the opt-in post-reflow regression guard (D38, + // regressionguard.go), folded into this observability result. They stay 0 unless + // cfg.regressionEnabled, so a book that does not enable the guard serialises identically. + LengthCollapse int `json:"length_collapse,omitempty"` + NumberDrift int `json:"number_drift,omitempty"` + Detail []string `json:"detail,omitempty"` } func (c cheapGateResult) total() int { - return c.DialogueDash + c.YoInconsistent + c.TranslitInterj + c.NumberMagnitude + return c.DialogueDash + c.YoInconsistent + c.TranslitInterj + c.NumberMagnitude + c.LengthCollapse + c.NumberDrift } -// runCheapGates runs all four flaggers over one chunk's source and FINAL translated text. -func runCheapGates(source, final string, cfg cheapGateConfig) cheapGateResult { +// runCheapGates runs the four always-on style flaggers over one chunk's source and FINAL text, plus +// (opt-in) the draft→final regression guard. `draft` is the first-stage translator output (== final +// when there is no distinct reflow stage, so the guard then trivially never fires). +func runCheapGates(source, draft, final string, cfg cheapGateConfig) cheapGateResult { var r cheapGateResult n, det := lintDialogueDash(final) r.DialogueDash, r.Detail = n, append(r.Detail, det...) @@ -76,6 +87,12 @@ func runCheapGates(source, final string, cfg cheapGateConfig) cheapGateResult { n, det = lintNumberMagnitude(source, final) r.NumberMagnitude = n r.Detail = append(r.Detail, det...) + if cfg.regressionEnabled { + rg := runRegressionGuard(draft, final) + r.LengthCollapse = rg.LengthCollapse + r.NumberDrift = rg.NumberDrift + r.Detail = append(r.Detail, rg.Detail...) + } return r } diff --git a/backend/internal/pipeline/cheapgates_test.go b/backend/internal/pipeline/cheapgates_test.go index 805f08a..15858af 100644 --- a/backend/internal/pipeline/cheapgates_test.go +++ b/backend/internal/pipeline/cheapgates_test.go @@ -168,7 +168,7 @@ func TestRunCheapGatesCombined(t *testing.T) { src := "他有三万石粮食。" final := "- Ара-ара, — у Пётр было три миллиона мешков. Потом Петр ушёл." cfg := cheapGateConfig{yoPolicy: "auto", allowlist: map[string]bool{}} - r := runCheapGates(src, final, cfg) + r := runCheapGates(src, final, final, cfg) if r.DialogueDash == 0 { t.Error("expected a dialogue-dash flag (hyphen-led line)") } diff --git a/backend/internal/pipeline/chunkrun.go b/backend/internal/pipeline/chunkrun.go index 23fbc94..795a231 100644 --- a/backend/internal/pipeline/chunkrun.go +++ b/backend/internal/pipeline/chunkrun.go @@ -6,6 +6,7 @@ import ( "fmt" "maps" "slices" + "strings" "textmachine/backend/internal/store" ) @@ -39,6 +40,17 @@ func (r *Runner) classifyOutput(role, source, output, finish string, isFinal boo // its rule version folds into the snapshot only when enabled (sanitizerSnapshot). if isFinal && r.Pipeline.Gates.Sanitizer.Enabled { if san := sanitizeOutput(output); san.total() > 0 { + // Cosmetic-only leak (leading markdown header and/or CJK-leak) → strip it and export + // the remainder flagged, not drop the whole chunk (D35.4a). The guard is load-bearing: + // we tag sanitizer_stripped ONLY when the strip yields a NON-EMPTY output that is now + // clean, so runStage/resume can trust that the derived export text is usable; anything + // else falls through to the substantive skip. Both are pure over `output`, so a resumed + // checkpoint re-derives the identical verdict. + if san.cosmeticOnly() { + if stripped := stripCosmetic(output); strings.TrimSpace(stripped) != "" && sanitizeOutput(stripped).total() == 0 { + return classification{FlagSanitizerStripped, san.summary()} + } + } return classification{FlagSanitizerDefect, san.summary()} } } @@ -73,6 +85,14 @@ func (r *Runner) translateChunk(ctx context.Context, snapID string, ch Chunk, st 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 := "" // Hot path: select the glossary records for this chunk ONCE (deterministic, $0), and // serialize the translator injection block. Recomputed on every run (resumed chunks @@ -127,9 +147,13 @@ func (r *Runner) translateChunk(ctx context.Context, snapID string, ch Chunk, st 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 @@ -161,7 +185,7 @@ func (r *Runner) translateChunk(ctx context.Context, snapID string, ch Chunk, st // (the 万/億 magnitude gate compares source↔output). var cheap cheapGateResult if !flagged && prev != "" { - cheap = runCheapGates(ch.Text, prev, r.cheapGateConfig()) + 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(), @@ -183,7 +207,10 @@ func (r *Runner) translateChunk(ctx context.Context, snapID string, ch Chunk, st if flagged { out.Disposition = DispFlagged out.FlagReason = flagReason - out.FinalText = "" // garbage/refusal/glossary-miss never propagates to the next chunk or export + // A cosmetic sanitizer strip exports its cleaned remainder (recovered != ""); every other + // flag (garbage/refusal/glossary-miss/substantive-sanitizer) exports "" — the contaminated + // output never reaches TM/export (D2 / D35.4a). + out.FinalText = recovered } else { out.FinalText = prev } @@ -247,5 +274,9 @@ func (r *Runner) cheapGateConfig() cheapGateConfig { for _, s := range r.Book.StyleAllowlist { allow[s] = true } - return cheapGateConfig{yoPolicy: r.Book.YoPolicy, allowlist: allow} + return cheapGateConfig{ + yoPolicy: r.Book.YoPolicy, + allowlist: allow, + regressionEnabled: r.Pipeline.Gates.RegressionGuard.Enabled, + } } diff --git a/backend/internal/pipeline/disposition.go b/backend/internal/pipeline/disposition.go index 56c8fe6..b39ffcb 100644 --- a/backend/internal/pipeline/disposition.go +++ b/backend/internal/pipeline/disposition.go @@ -82,14 +82,24 @@ const ( // escalatable in v1 (the L3 targeted re-ask is a Phase-2 remedy, research/14 §9). FlagGlossaryMiss FlagReason = "glossary_miss" - // FlagSanitizerDefect is the output-sanitizer verdict (D30.3, sanitizer.go): the stage - // output carries an "instant unreadability" defect no other gate catches — a leaked - // service preamble, a trailing note/edit block, a markdown ### header, a Latin-script - // insertion, or a broken word form. Emitted ONLY when the opt-in Gates.Sanitizer is - // enabled; the contaminated output is flagged (D2 flag+skip) so it never commits to - // TM/export. NOT retryable (a same-model retry re-produces the artifact) and NOT - // escalatable in v1 (the editor is pinned; a redrive surfaces the defect to a human). + // FlagSanitizerDefect is the output-sanitizer verdict for a SUBSTANTIVE defect (D30.3, + // sanitizer.go): the stage output carries an "instant unreadability" defect with no reliable + // removable boundary — a leaked service preamble, a trailing note/edit block, a Latin-script + // insertion, or a broken word form. Emitted ONLY when the opt-in Gates.Sanitizer is enabled; + // the contaminated output is flagged AND skipped (D2 flag+skip) so it never commits to + // TM/export (FinalText stays ""). NOT retryable (a same-model retry re-produces the artifact) + // and NOT escalatable in v1 (the editor is pinned; a redrive surfaces the defect to a human). FlagSanitizerDefect FlagReason = "sanitizer_defect" + + // FlagSanitizerStripped is the output-sanitizer verdict for a COSMETIC-ONLY defect that was + // STRIPPED and the remainder EXPORTED (D38 infra-pack, D35.4a): a leading markdown «### Глава» + // header and/or a stray CJK-leak run, removed deterministically by stripCosmetic. Unlike + // FlagSanitizerDefect the chunk is NOT lost — the cleaned text is committed as the export + // (final_hash points at a derived sanitized checkpoint, so the standard + // final_hash→checkpoint.response_text export contract yields the cleaned text) — but it STAYS + // flagged so a human verifies the auto-clean ("не терять чанк ... флаг для человека"). NOT + // retryable / NOT escalatable (deterministic; a redrive would re-produce the same leak). + FlagSanitizerStripped FlagReason = "sanitizer_stripped" ) // classifierVersion versions the INTRINSIC classify() verdict logic — the refusal diff --git a/backend/internal/pipeline/golden_test.go b/backend/internal/pipeline/golden_test.go index 2f58b16..65a49c5 100644 --- a/backend/internal/pipeline/golden_test.go +++ b/backend/internal/pipeline/golden_test.go @@ -41,8 +41,15 @@ import ( // • 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: ch6 draft leaks a service preamble → the output-sanitizer gate (ON in the -// fixture pipeline) flags it FlagSanitizerDefect and the edit is skipped. +// • 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_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 +// = 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. // @@ -57,7 +64,9 @@ 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 + 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 @@ -85,6 +94,12 @@ func goldenRespond(body string) (text, finish string) { case strings.Contains(body, goldenUnionMarker) && !isEditBody(body): // ch5 draft carries a keying token («СТАРИК-СЦЕНА») the edit branch below keys on. return "ЧЕРНОВИК ПЕРЕВОДА " + tag + ". СТАРИК-СЦЕНА Судзуки увидел старика.", "stop" + case strings.Contains(body, goldenMarkdownMarker) && !isEditBody(body): + // ch7 draft carries a keying token («МАРКДАУН-СЦЕНА») the cosmetic edit branch keys on. + return "ЧЕРНОВИК ПЕРЕВОДА " + tag + ". МАРКДАУН-СЦЕНА Судзуки открыл седьмую дверь.", "stop" + case strings.Contains(body, goldenCJKMarker) && !isEditBody(body): + // ch8 draft carries a keying token («ИЕРОГЛИФ-СЦЕНА») the cosmetic edit branch keys on. + return "ЧЕРНОВИК ПЕРЕВОДА " + tag + ". ИЕРОГЛИФ-СЦЕНА Судзуки нашёл камень.", "stop" case strings.Contains(body, goldenEchoMarker) && !isEditBody(body): if req.Model == "fake-fallback" { // The escalation hop returns a clean translation → the re-gate passes it. @@ -100,6 +115,16 @@ func goldenRespond(body string) (text, finish string) { // ch5 edit — the FINAL text carries the NOMINATIVE «старик» (not an oblique decl // form of 老人→старик), exercising the base-dst∪decl union → postcheck_miss=0. return "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД " + tag + ". Судзуки увидел, как в тени ждал старик.", "stop" + case isEditBody(body) && strings.Contains(body, "МАРКДАУН-СЦЕНА"): + // ch7 edit leaks a leading markdown «### Глава» header — a COSMETIC class: the sanitizer + // STRIPS it and exports the remainder flagged sanitizer_stripped (D35.4a). This PINS the + // strip-and-export path: final_text = «Глава 7\n\n…» (no «### »), disposition=flagged. + return "### Глава 7\n\nСудзуки открыл седьмую дверь книгохранилища.", "stop" + case isEditBody(body) && strings.Contains(body, "ИЕРОГЛИФ-СЦЕНА"): + // ch8 edit leaks a sparse CJK run «特产» in otherwise-Russian prose (below the 15% echo + // threshold classify() catches) — a COSMETIC class: stripped + exported flagged. PINS the + // CJK-leak strip: «Судзуки нашёл 特产 древний камень.» → «Судзуки нашёл древний камень.» + return "Судзуки нашёл 特产 древний камень на каменном алтаре.", "stop" case isEditBody(body): return "ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД " + tag + ". Судзуки шёл по коридорам Академии магии.", "stop" default: @@ -171,7 +196,7 @@ func captureGolden(t *testing.T, label string, r *Runner, res *BookResult, wireB w(" stage=%s role=%s model=%s resume=%t disp=%s flag=%q attempts=%d escalated=%t esc_model=%q finish=%q cum_usd=%s detail=%q", st.Stage, st.Role, st.Model, st.FromResume, st.Disposition, st.FlagReason, st.Attempts, st.Escalated, st.EscalationModel, st.FinishReason, fl(st.CumCostUSD), st.Detail) - w(" stage_text=%q", st.Text) + w(" stage_text=%q recovered=%q", st.Text, st.RecoveredText) } } diff --git a/backend/internal/pipeline/regressionguard.go b/backend/internal/pipeline/regressionguard.go new file mode 100644 index 0000000..d5fe6f6 --- /dev/null +++ b/backend/internal/pipeline/regressionguard.go @@ -0,0 +1,159 @@ +package pipeline + +import ( + "fmt" + "sort" + "unicode" +) + +// regressionguard.go: the post-reflow regression guard (D38 infra-pack, research/18 §C#5) — two +// deterministic OBSERVABILITY flaggers over the DRAFT→FINAL transform, opt-in like a QA gate +// (Gates.RegressionGuard) but NEVER a disposition change. The reflow editor legitimately +// restructures and merges sentences, so a HARD skip would false-flag a correct edit; instead a hit +// is recorded in the cheap-gate observability channel (retrieval-state n_style_flags) and surfaced +// in the report for a human. Both flaggers are tuned PRECISION over recall. +// +// (a) length collapse — the final is drastically SHORTER than the draft (>regressionMaxShrinkPct +// of non-space chars), catching a reflow that dropped whole sentences/paragraphs (draft +// 5000 → final 600). Reflow SUMMARISES structure into paragraphs; it must not delete content. +// (b) number drift — a MULTI-DIGIT arabic number in the draft is ABSENT from the final, or a +// new one APPEARS: 四成四=44%→«четыре десятых» (the 44 vanished), or a hallucinated figure. +// Single digits are EXCLUDED (they are routinely spelled out — «5»→«пять» — a legit reflow), +// and grouped triples are stitched (10 000 ≡ 10000), so the signal is high precision. +// +// HONEST recall gap: a number rendered as WORDS on BOTH sides (черновик «сорок четыре» → финал +// «четыре десятых») is invisible here — offline word-number alignment is a Ф2 concern. And a +// legit reflow that converts a multi-digit figure to words («44%»→«сорок четыре процента») will +// show as a disappeared number: a FALSE observability flag, tolerable ONLY because this never +// drops the chunk (a human glance dismisses it). Precision over recall, observability over gating. + +const ( + // regressionMaxShrinkPct: a final shorter than the draft by MORE than this percent of non-space + // characters is a collapse signal. 40% — a reflow that keeps content while merging lines shrinks + // only slightly (Russian is ~fertility-neutral draft→final); losing ~half the characters is a + // strong omission signal, not a merge. Tuned precision-over-recall; a code const (a change is a + // loud cheapGateVersion bump), not config, so the gate carries only an on/off switch. + regressionMaxShrinkPct = 40 + // regressionMinChars: below this the draft is too short for a percentage ratio to be meaningful + // (a 3-word draft legitimately halving is noise), so the length flagger stays silent. + regressionMinChars = 200 +) + +// regressionGuardResult is the guard's per-chunk outcome (folded into the cheap-gate observability +// result). LengthCollapse/NumberDrift are 0/1 counts; Detail carries the human-readable lines. +type regressionGuardResult struct { + LengthCollapse int + NumberDrift int + Detail []string +} + +// runRegressionGuard compares the DRAFT (first-stage translator output) with the FINAL (last-stage +// reflow output). Pure and deterministic (sorted detail), so a resume re-derives identical counts. +func runRegressionGuard(draft, final string) regressionGuardResult { + var r regressionGuardResult + + // (a) length collapse — non-space chars, mirroring the coverage gate's length metric. + dn, fn := nonSpaceRuneCount(draft), nonSpaceRuneCount(final) + if dn >= regressionMinChars && fn*100 < dn*(100-regressionMaxShrinkPct) { + r.LengthCollapse = 1 + r.Detail = append(r.Detail, fmt.Sprintf( + "reflow-регрессия: коллапс длины черновик→финал %d→%d непробельных символов (−%d%%, порог −%d%%) — возможен пропуск", + dn, fn, 100-fn*100/dn, regressionMaxShrinkPct)) + } + + // (b) number drift — multi-digit arabic tokens present on one side only. + dNums, fNums := arabicNumberTokens(draft), arabicNumberTokens(final) + disappeared := numberSetDiff(dNums, fNums) + appeared := numberSetDiff(fNums, dNums) + if len(disappeared) > 0 || len(appeared) > 0 { + r.NumberDrift = len(disappeared) + len(appeared) + if len(disappeared) > 0 { + r.Detail = append(r.Detail, "reflow-регрессия: числа черновика отсутствуют в финале (возможен пропуск/дрейф разряда): "+joinPreview(disappeared)) + } + if len(appeared) > 0 { + r.Detail = append(r.Detail, "reflow-регрессия: в финале появились числа, которых не было в черновике (возможна добавка): "+joinPreview(appeared)) + } + } + return r +} + +// nonSpaceRuneCount counts non-whitespace runes — the length metric for the collapse flagger. +func nonSpaceRuneCount(s string) int { + n := 0 + for _, r := range s { + if !unicode.IsSpace(r) { + n++ + } + } + return n +} + +// arabicNumberTokens returns the MULTI-DIGIT (≥2) arabic integers in text, stitching grouping +// separators (space / NBSP / comma) between runs of exactly three digits so "10 000" reads as one +// "10000", not "10" and "000". Single-digit numbers are dropped (routinely spelled out in prose). +func arabicNumberTokens(text string) []string { + rs := []rune(text) + var out []string + for i := 0; i < len(rs); { + if !isASCIIDigit(rs[i]) { + i++ + continue + } + j := i + for j < len(rs) && isASCIIDigit(rs[j]) { + j++ + } + digits := string(rs[i:j]) + // Stitch " ddd" / " ddd" / ",ddd" grouped triples. + for j < len(rs) { + if rs[j] == ' ' || rs[j] == ' ' || rs[j] == ',' { + k := j + 1 + g := 0 + for k < len(rs) && isASCIIDigit(rs[k]) { + k++ + g++ + } + if g == 3 { + digits += string(rs[j+1 : k]) + j = k + continue + } + } + break + } + if len(digits) >= 2 { + out = append(out, digits) + } + i = j + } + return out +} + +// numberSetDiff returns the distinct members of a that do not appear in b, sorted. A SET diff (not +// a multiset): a number present on both sides is covered even if its multiplicity differs, keeping +// the precision-over-recall bias (a repeated number is not a drift signal on its own). +func numberSetDiff(a, b []string) []string { + inB := make(map[string]bool, len(b)) + for _, x := range b { + inB[x] = true + } + seen := map[string]bool{} + var out []string + for _, x := range a { + if !inB[x] && !seen[x] { + seen[x] = true + out = append(out, x) + } + } + sort.Strings(out) + return out +} + +// joinPreview renders a sorted number list compactly for the detail line (bounded). +func joinPreview(nums []string) string { + const max = 8 + if len(nums) > max { + return preview(fmt.Sprintf("%v …(+%d)", nums[:max], len(nums)-max)) + } + return fmt.Sprintf("%v", nums) +} diff --git a/backend/internal/pipeline/regressionguard_test.go b/backend/internal/pipeline/regressionguard_test.go new file mode 100644 index 0000000..bb76662 --- /dev/null +++ b/backend/internal/pipeline/regressionguard_test.go @@ -0,0 +1,82 @@ +package pipeline + +import ( + "strings" + "testing" +) + +// regressionguard_test.go — the post-reflow regression guard (D38). Precision over recall: each +// flagger asserts BOTH firing on a real regression AND non-firing on a legitimate reflow. + +func TestRegressionGuardLengthCollapse(t *testing.T) { + // A draft well over the min-chars floor, halved by the "reflow" → collapse fires. + draft := strings.Repeat("Судзуки медленно шёл по коридору академии магии. ", 12) // ~560 non-space chars + shortFinal := "Судзуки шёл." + if r := runRegressionGuard(draft, shortFinal); r.LengthCollapse == 0 { + t.Errorf("expected a length-collapse flag (draft≫final)") + } + // A legitimate reflow that merges lines keeps ~all the content → must NOT fire. + sameFinal := strings.Repeat("Судзуки медленно шёл по коридору академии магии. ", 11) + if r := runRegressionGuard(draft, sameFinal); r.LengthCollapse != 0 { + t.Errorf("length-collapse FALSE POSITIVE on a near-equal reflow: %v", r.Detail) + } + // A short draft below the floor must never fire (a % ratio is meaningless there). + if r := runRegressionGuard("Он ушёл.", "Он."); r.LengthCollapse != 0 { + t.Errorf("length-collapse fired below the min-chars floor: %v", r.Detail) + } +} + +func TestRegressionGuardNumberDrift(t *testing.T) { + // 四成四=44% rendered as «44» in the draft, drifted to a word form in the final → 44 disappears. + if r := runRegressionGuard("У него было 44 процента запаса.", "У него было четыре десятых запаса."); r.NumberDrift == 0 { + t.Errorf("expected a number-drift flag (44 vanished)") + } + // A number APPEARING in the final that was not in the draft (hallucinated figure). + if r := runRegressionGuard("Он собрал войско.", "Он собрал войско из 3000 солдат."); r.NumberDrift == 0 { + t.Errorf("expected a number-drift flag (3000 appeared)") + } + clean := []struct{ draft, final string }{ + // The multi-digit number is preserved across the reflow (44 on both sides). + {"У него было 44 процента.", "У него имелось 44 процента запаса."}, + // Grouped-triple vs joined form of the SAME number must not drift (10 000 ≡ 10000). + {"Армия в 10 000 воинов.", "Армия насчитывала 10000 воинов."}, + // SINGLE digits are excluded (routinely spelled out), so «5»→«пять» is not a drift. + {"У него было 5 мечей.", "У него было пять мечей."}, + // No numbers at all — never fires. + {"Судзуки шёл по коридору академии магии.", "Судзуки медленно шёл по длинному коридору."}, + } + for _, c := range clean { + if r := runRegressionGuard(c.draft, c.final); r.NumberDrift != 0 { + t.Errorf("number-drift FALSE POSITIVE on %q→%q: %v", c.draft, c.final, r.Detail) + } + } +} + +// TestRunCheapGatesRegressionOptIn pins that the guard is OFF by default and folds into the +// observability total only when enabled (a book that does not opt in serialises identically). +func TestRunCheapGatesRegressionOptIn(t *testing.T) { + draft := strings.Repeat("Судзуки медленно шёл по коридору академии магии. ", 12) + final := "Судзуки шёл." + off := runCheapGates("", draft, final, cheapGateConfig{yoPolicy: "auto", allowlist: map[string]bool{}}) + if off.LengthCollapse != 0 || off.NumberDrift != 0 { + t.Errorf("regression guard fired while disabled: %+v", off) + } + on := runCheapGates("", draft, final, cheapGateConfig{yoPolicy: "auto", allowlist: map[string]bool{}, regressionEnabled: true}) + if on.LengthCollapse == 0 { + t.Errorf("regression guard did not fire while enabled: %+v", on) + } + if on.total() <= off.total() { + t.Errorf("enabled guard must raise the observability total: off=%d on=%d", off.total(), on.total()) + } +} + +// TestRegressionGuardDeterministic — a pure function of (draft, final), resume-safe. +func TestRegressionGuardDeterministic(t *testing.T) { + d := strings.Repeat("текст с числом 44 и 128. ", 20) + f := "короткий финал без чисел" + a, b := runRegressionGuard(d, f), runRegressionGuard(d, f) + if a.LengthCollapse != b.LengthCollapse || a.NumberDrift != b.NumberDrift || + strings.Join(a.Detail, "|") != strings.Join(b.Detail, "|") { + t.Fatalf("runRegressionGuard not deterministic: %+v vs %+v", a, b) + } +} diff --git a/backend/internal/pipeline/resume.go b/backend/internal/pipeline/resume.go index 51e8c21..950f7b3 100644 --- a/backend/internal/pipeline/resume.go +++ b/backend/internal/pipeline/resume.go @@ -50,6 +50,26 @@ func (r *Runner) resumeFromChunkStatus(ctx context.Context, st config.Stage, ch sr.Model = cp.ModelActual sr.FinishReason = cp.FinishReason sr.Text = cp.ResponseText + } else if cs.FlagReason == string(FlagSanitizerStripped) && cs.FinalHash != "" { + // A cosmetic sanitizer strip (D35.4a): the cleaned export text lives in the derived + // checkpoint final_hash points at (written durably before this chunk_status row), so resume + // re-serves the identical FinalText WITHOUT re-stripping — deterministic and $0. A missing + // derived checkpoint is a torn store (final_hash is written after it), so fail loud like the + // ok branch rather than silently export empty. + cp, err := r.Store.GetCheckpoint(cs.FinalHash) + if err != nil { + return nil, fmt.Errorf("pipeline: read sanitized-export checkpoint %.12s for %s/ch%d/chunk%d/%s: %w", + cs.FinalHash, r.Book.BookID, ch.Chapter, ch.ChunkIdx, st.Name, err) + } + if cp == nil || cp.ResponseText == "" { + return nil, fmt.Errorf("pipeline: chunk_status sanitizer_stripped for %s/ch%d/chunk%d/%s references derived checkpoint %.12s which is missing/empty — inconsistent store", + r.Book.BookID, ch.Chapter, ch.ChunkIdx, st.Name, cs.FinalHash) + } + sr.RecoveredText = cp.ResponseText + // Mirror the ok branch: the resume request_log row's request_hash points at this derived + // checkpoint, so report ITS finish_reason ("sanitized_export") rather than a bare "" that + // contradicts the referenced row (adversarial review NIT; telemetry-only). + sr.FinishReason = cp.FinishReason } rl := r.baseRequestLog(st, ch, st.Model, cs.FinalHash) rl.ModelActual = sr.Model diff --git a/backend/internal/pipeline/sanitizer.go b/backend/internal/pipeline/sanitizer.go index 6987271..d45ad9c 100644 --- a/backend/internal/pipeline/sanitizer.go +++ b/backend/internal/pipeline/sanitizer.go @@ -18,7 +18,7 @@ import ( // (sanitizerVersion, mirroring coverageSnapshot), and moves to verdictSnapshotID once // content-addressed resume lands (D15.2). // -// Five classes, each tuned PRECISION over recall (fire only on a high-confidence signal; +// Six classes, each tuned PRECISION over recall (fire only on a high-confidence signal; // the ambiguous middle stays silent — a false flag turns a good chunk into an export // placeholder, worse than a missed defect for an opt-in readability gate): // @@ -27,6 +27,21 @@ import ( // 3. markdown ### header — «### Глава 1» (8/54 finals of stage A — D29 finding) // 4. Latin-script insertion — an untranslated Latin phrase/heavy Latin in the ru output // 5. broken word form — homoglyph-mixed token or an invalid Cyrillic sign bigram +// 6. CJK-leak in the final — a stray Han ideograph / kana / fullwidth glyph in the ru output +// («…охотники,却有 деньги!» arms/C/17.0 — D38.1; below the ≥15% +// echo threshold classify() already catches, so a sparse leak) +// +// DISPOSITION-BY-CLASS (D38 infra-pack): the classes split into two tiers so a chunk is not +// silently lost to an export placeholder when the leak is a REMOVABLE cosmetic span (D35.4a — +// ch5/ch20 chapter openers dropped whole for a leading «### Глава N»): +// - COSMETIC (strippable, exported + flagged for a human, cosmeticOnly()==true): the markdown +// header (3) and the CJK-leak (6). The leak sits in a bounded span stripCosmetic() removes +// deterministically, leaving readable prose; the chunk is flagged sanitizer_stripped (a +// "auto-cleaned, verify" signal), NOT dropped. +// - SUBSTANTIVE (dropped to a placeholder, current behaviour): the preamble (1), trailing +// note (2), Latin insertion (4) and broken word (5). Their contamination has no reliable +// removable boundary (a preamble may swallow real narration; a Latin clause / broken token is +// lost content), so the output is not trusted — flagged sanitizer_defect + skipped. // // HONEST recall gap (documented, precision over recall): the broken-word class catches only // the two ZERO-false-positive signatures (invalid Cyrillic sign bigrams, mixed Cyrillic/Latin @@ -43,7 +58,15 @@ import ( // v2 (D33.1/33.2): tail edit-summary «Основные правки для справки:» now flags; the // junction-duplication split detector was removed (false-flagged prose); markdown/heavy-Latin // narrowed. A verdict-axis change → loud --resnapshot + golden re-capture (invariant №8). -const sanitizerVersion = "sanitizer-v2" +// v3 (D38 infra-pack): added the CJK-leak class (Han/kana/fullwidth in the ru final) and the +// cosmetic-vs-substantive disposition split (the markdown header and CJK-leak are now STRIPPED +// and exported flagged, not dropped to an empty placeholder — D35.4a). Both shift the resolved +// disposition/export of a flagged chunk → a loud --resnapshot + golden re-capture (invariant №8). +// v4 (D38 infra-pack, adversarial review): stripCosmetic now FOLDS content-bearing fullwidth ASCII +// («１２３»→«123», not deleted) and ideographic comma/period, space-replaces dropped ideographs (no +// word-merge), removes an emptied bracket pair, and no longer reformats a legit «2 : 1» — all shift +// a stripped chunk's EXPORT text → a loud --resnapshot + golden re-capture (invariant №8). +const sanitizerVersion = "sanitizer-v4" // sanitizer tuning constants (versioned by sanitizerVersion). const ( @@ -72,11 +95,21 @@ type sanitizerResult struct { MarkdownHeader int `json:"markdown_header,omitempty"` LatinInsert int `json:"latin_insert,omitempty"` BrokenWord int `json:"broken_word,omitempty"` + CJKLeak int `json:"cjk_leak,omitempty"` Detail []string `json:"detail,omitempty"` } func (s sanitizerResult) total() int { - return s.Preamble + s.TrailingNote + s.MarkdownHeader + s.LatinInsert + s.BrokenWord + return s.Preamble + s.TrailingNote + s.MarkdownHeader + s.LatinInsert + s.BrokenWord + s.CJKLeak +} + +// cosmeticOnly reports whether the ONLY classes that fired are the STRIPPABLE cosmetic ones +// (markdown header and/or CJK-leak) — the strip-and-export tier (D35.4a). A single substantive +// class (preamble/trailing-note/latin/broken-word) pulls the whole chunk into the skip tier: its +// contamination has no reliable removable boundary, so the output is not trusted even if a +// cosmetic leak also happens to be present. False when nothing fired. +func (s sanitizerResult) cosmeticOnly() bool { + return s.total() > 0 && s.Preamble == 0 && s.TrailingNote == 0 && s.LatinInsert == 0 && s.BrokenWord == 0 } // summary is the human-readable disposition detail for a sanitizer flag (deterministic — @@ -91,7 +124,7 @@ func (s sanitizerResult) summary() string { return strings.Join(s.Detail, "; ") } -// sanitizeOutput runs all five classes over one chunk's FINAL translated text. +// sanitizeOutput runs all six classes over one chunk's FINAL translated text. func sanitizeOutput(text string) sanitizerResult { var r sanitizerResult if det := detectLeadingPreamble(text); det != "" { @@ -114,6 +147,10 @@ func sanitizeOutput(text string) sanitizerResult { r.BrokenWord = n r.Detail = append(r.Detail, det...) } + if n, det := detectCJKLeak(text); n > 0 { + r.CJKLeak = n + r.Detail = append(r.Detail, det...) + } sort.Strings(r.Detail) return r } @@ -316,6 +353,125 @@ func detectBrokenWords(text string) (int, []string) { return len(det), det } +// --- 6. CJK-leak in the final -------------------------------------------------- + +// isCJKLeakRune reports whether r is a stray CJK glyph that has NO place in a Russian final: a +// Han ideograph, kana, a fullwidth/halfwidth form (U+FF00–FFEF — «，（）！» etc.), or a CJK +// symbol/punctuation (U+3001–303F — «、。「」»). The ideographic SPACE U+3000 is deliberately +// EXCLUDED (it is an indent artifact, not a content leak — research/18 §C#4 "draft-21 includes a +// U+3000 indent → 9 real leaks"): stripCosmetic normalises it to a plain space, but it does not +// alone FIRE the class, so a legitimately-indented chunk is not flag-stormed. In clean Russian +// prose every one of these is count-0, so the class is high precision. The intrinsic classify() +// already flags a ≥15%-CJK output as an ECHO (cjk_artifact, substantive) BEFORE the sanitizer +// runs, so this class only ever sees a SPARSE leak in otherwise-Russian text. +func isCJKLeakRune(r rune) bool { + switch { + case unicode.Is(unicode.Han, r): + return true + case unicode.Is(unicode.Hiragana, r) || unicode.Is(unicode.Katakana, r): + return true + case r >= 0xFF00 && r <= 0xFFEF: // fullwidth & halfwidth forms + return true + case r >= 0x3001 && r <= 0x303F: // CJK symbols & punctuation, EXCLUDING U+3000 (ideographic space) + return true + } + return false +} + +// detectCJKLeak counts maximal runs of leak runes in the final text and returns a deduped detail +// per distinct run. A single run («却有») is enough to fire — the class is COSMETIC, so the whole +// chunk is not lost: stripCosmetic removes the run and the remainder exports (flagged for review). +func detectCJKLeak(text string) (int, []string) { + var det []string + seen := map[string]bool{} + n := 0 + rs := []rune(text) + for i := 0; i < len(rs); { + if !isCJKLeakRune(rs[i]) { + i++ + continue + } + j := i + for j < len(rs) && isCJKLeakRune(rs[j]) { + j++ + } + n++ + run := string(rs[i:j]) + if !seen[run] { + seen[run] = true + det = append(det, "CJK-утечка в ru-выходе: "+preview(run)) + } + i = j + } + return n, det +} + +// --- deterministic strip of the COSMETIC classes (D35.4a export fix) ------------- + +// leadingMarkdownStripRE matches the leading markdown ATX prefix on a line (optional indent, 1–6 +// hashes, blank(s)) directly before a header WORD/number — the same shape markdownHeaderRE fires +// on. It captures the first header rune so ReplaceAll keeps the heading text, dropping only the +// «### » artifact («### Глава 5» → «Глава 5»). A decorative «### ---» scene break (punctuation +// after the hashes) does NOT match, so it is left intact (and it never fired the class either). +var leadingMarkdownStripRE = regexp.MustCompile(`(?m)^[ \t]{0,3}#{1,6}[ \t]+([\p{L}\p{Nd}])`) + +// stripCosmetic deterministically removes the two STRIPPABLE cosmetic leak classes — leading +// markdown headers and CJK-leak runs — and tidies the whitespace the removal leaves, so the +// remainder is readable. It is a PURE function (resume re-derives the identical export), invoked +// ONLY on output the sanitizer classified as cosmeticOnly (classifyOutput guarantees the result +// is non-empty and clean — sanitizeOutput(stripCosmetic(x)).total()==0 — before tagging it +// sanitizer_stripped). It never crosses newlines when tidying, so paragraph structure is kept. +func stripCosmetic(text string) string { + // 1) markdown header prefixes → keep the heading text, drop the «#### » artifact. + out := leadingMarkdownStripRE.ReplaceAllString(text, "$1") + // 2) neutralise CJK-leak runes. CONTENT-BEARING glyphs are FOLDED, not dropped (adversarial + // review MAJOR): a fullwidth ASCII form is a wrong-glyph rendering of a plain char, so «１２３» + // folds to «123» (the number is kept, not deleted) and «，」→«,» — the same NFKC fold the + // memory normaliser uses. Only genuinely contentless runes (Han/kana/CJK brackets/symbols) are + // removed, and a removed run leaves a SINGLE SPACE so adjacent Russian words do not merge + // («нашёл特产древний» → «нашёл древний», not «нашёлдревний»). U+3000 → a plain space (indent). + var b strings.Builder + b.Grow(len(out)) + for _, r := range out { + switch { + case r == '　': // U+3000 ideographic space → plain space + b.WriteByte(' ') + case r >= 0xFF01 && r <= 0xFF5E: // fullwidth ASCII form → fold to plain ASCII (１→1, Ａ→A, ，→,) + b.WriteRune(r - 0xFEE0) + case r == '、': // ideographic comma → plain comma (keep the clause boundary) + b.WriteByte(',') + case r == '。': // ideographic full stop → plain period + b.WriteByte('.') + case isCJKLeakRune(r): // Han / kana / CJK brackets / other symbol → drop, leaving a space + b.WriteByte(' ') + default: + b.WriteRune(r) + } + } + out = b.String() + // 3) tidy the seams the removal created, per line (horizontal whitespace only — never a + // newline): collapse doubled spaces, drop a bracket/quote pair the strip emptied («(羅漢拳)» → + // «()» → removed), drop a space now sitting before closing punctuation or after an opening + // bracket/quote (never-correct Russian spacing), and trim trailing blanks. ':' is deliberately + // NOT in the closing-punct set: a space-before-colon is legitimate in a Russian ratio/score/time + // («счёт 2 : 1») and must not be reformatted (adversarial review — false positive). + out = multiSpaceRE.ReplaceAllString(out, " ") + out = emptyBracketRE.ReplaceAllString(out, "") + out = spaceBeforePunctRE.ReplaceAllString(out, "$1") + out = spaceAfterOpenRE.ReplaceAllString(out, "$1") + out = multiSpaceRE.ReplaceAllString(out, " ") // an emptied bracket may leave a doubled space + out = trailingHSpaceRE.ReplaceAllString(out, "") + return out +} + +var ( + multiSpaceRE = regexp.MustCompile(`[ \t]{2,}`) + emptyBracketRE = regexp.MustCompile(`\([ \t]*\)|«[ \t]*»|\[[ \t]*\]`) + spaceBeforePunctRE = regexp.MustCompile(`[ \t]+([,.!?;…»)\]])`) + spaceAfterOpenRE = regexp.MustCompile(`([«(\[])[ \t]+`) + trailingHSpaceRE = regexp.MustCompile(`(?m)[ \t]+$`) +) + type scriptToken struct { text string cyr bool // Cyrillic-only diff --git a/backend/internal/pipeline/sanitizer_test.go b/backend/internal/pipeline/sanitizer_test.go index 516ebb6..4f60dce 100644 --- a/backend/internal/pipeline/sanitizer_test.go +++ b/backend/internal/pipeline/sanitizer_test.go @@ -211,6 +211,100 @@ func TestSanitizerCleanNarrative(t *testing.T) { } } +// TestSanitizerCJKLeak — the D38.1 class: a stray Han/kana/fullwidth glyph in the ru final. +func TestSanitizerCJKLeak(t *testing.T) { + fire := []string{ + // The span the orchestrator verified (arms/C/17.0): a raw Han run mid-Russian-sentence. + "«…охотники,却有 на это лишние деньги!»", + "Судзуки нашёл 特产 древнего клана.", // single Han run + "Разряд资质乙等 остался неясен.", // Han glued to Cyrillic + "Он сказал: すごい, и замолчал.", // kana leak (ja book) + "Цена была １２３ золотых.", // fullwidth digits + "Он вошёл в дом、и дверь закрылась.", // ideographic comma (U+3001) + } + for _, s := range fire { + if got := sanitizeOutput(s); got.CJKLeak == 0 { + t.Errorf("CJK-leak not detected in %q: %+v", preview(s), got) + } + } + clean := []string{ + "Судзуки шёл по коридорам Академии магии, вспоминая вчерашнюю долгую лекцию.", + "— Сегодня я открою дверь книгохранилища, — прошептал он, сжимая ключ.", + "На гербе была латинская надпись, но он её не разобрал в темноте.", + "Цена была 123 золотых, и он расплатился не торгуясь.", // ASCII digits — not fullwidth + // U+3000 ideographic space alone is an INDENT artifact, NOT a content leak → must NOT fire + // (research/18 §C#4); stripCosmetic still normalises it, but it does not flag the chunk. + "　Судзуки медленно шёл по длинному коридору к башне.", + } + for _, s := range clean { + if got := sanitizeOutput(s); got.CJKLeak != 0 { + t.Errorf("CJK-leak FALSE POSITIVE in %q: %v", preview(s), got.Detail) + } + } +} + +// TestSanitizerCosmeticOnly pins the strip-vs-skip disposition matrix (D35.4a): only the markdown +// header and CJK-leak classes are strippable; any substantive class pulls the chunk into skip. +func TestSanitizerCosmeticOnly(t *testing.T) { + cosmetic := []string{ + "### Глава 7\n\nСудзуки открыл седьмую дверь и замер на пороге.", // markdown only + "Судзуки нашёл 特产 древнего клана в тёмном углу книгохранилища.", // cjk only + "### Пролог\n\nСудзуки увидел 却有 на алтаре забытого клана.", // BOTH cosmetic classes + } + for _, s := range cosmetic { + got := sanitizeOutput(s) + if got.total() == 0 || !got.cosmeticOnly() { + t.Errorf("expected cosmeticOnly for %q: %+v", preview(s), got) + } + } + substantive := []string{ + "Вот перевод фрагмента: Судзуки открыл дверь.", // preamble (substantive) + // a LEADING preamble co-occurring with a CJK leak → the substantive class wins (skip, not strip). + "Вот перевод фрагмента: Судзуки увидел 特产 на алтаре забытого клана.", + "Судзуки открыл дверь.\n\nПримечание: имя героя оставлено как есть.", // trailing note + "Он прочитал: the quick brown fox jumps over lazy dog today.", // latin phrase + } + for _, s := range substantive { + if got := sanitizeOutput(s); got.total() == 0 || got.cosmeticOnly() { + t.Errorf("expected NOT cosmeticOnly (substantive) for %q: %+v", preview(s), got) + } + } +} + +// TestStripCosmetic pins the exact deterministic strip output — the "экспортит текст БЕЗ ведущего +// ###" contract — and that the result is itself clean (the classifyOutput guarantee). +func TestStripCosmetic(t *testing.T) { + cases := []struct{ in, want string }{ + // markdown header prefix removed, heading text kept. + {"### Глава 7\n\nСудзуки открыл дверь.", "Глава 7\n\nСудзуки открыл дверь."}, + {"# Пролог\nТекст главы.", "Пролог\nТекст главы."}, + // Han run removed; the seam is tidied (no double space, no space-before-comma), no word-merge. + {"«…охотники,却有 на это лишние деньги!»", "«…охотники, на это лишние деньги!»"}, + {"Судзуки нашёл 特产 древнего клана.", "Судзуки нашёл древнего клана."}, + {"нашёл特产древний", "нашёл древний"}, // no spaces in source → strip leaves a space, not a merge + // CONTENT-BEARING fullwidth ASCII is FOLDED, not deleted (adversarial review MAJOR): the number survives. + {"Цена была １２３ золотых.", "Цена была 123 золотых."}, + {"Индекс ＡＢＣ найден.", "Индекс ABC найден."}, + // ideographic comma/period fold to plain — the clause boundary is kept. + {"Он вошёл в дом、и дверь закрылась。", "Он вошёл в дом,и дверь закрылась."}, + // a parenthetical Han gloss is stripped and the emptied «()» removed (adversarial review). + {"Кулак Ло Хань (羅漢拳) был силён.", "Кулак Ло Хань был силён."}, + // a legit ratio «2 : 1» is NOT reformatted (colon dropped from the tidy set). + {"### Итог\n\nСчёт был 2 : 1 却有 в пользу гостей.", "Итог\n\nСчёт был 2 : 1 в пользу гостей."}, + // U+3000 ideographic space normalised to a plain space (the indent artifact). + {"　Судзуки шёл.", " Судзуки шёл."}, + } + for _, c := range cases { + got := stripCosmetic(c.in) + if got != c.want { + t.Errorf("stripCosmetic(%q) = %q, want %q", c.in, got, c.want) + } + if san := sanitizeOutput(got); san.total() != 0 { + t.Errorf("stripCosmetic(%q) is not clean: %+v", c.in, san.Detail) + } + } +} + // TestSanitizerDeterministic asserts the verdict is a pure function of the text (resume-safe). func TestSanitizerDeterministic(t *testing.T) { s := "### Заголовок\nВот отредактированный перевод: текст. Стольь странно.\nПримечание: правка." diff --git a/backend/internal/pipeline/stagerun.go b/backend/internal/pipeline/stagerun.go index 3489919..62156ae 100644 --- a/backend/internal/pipeline/stagerun.go +++ b/backend/internal/pipeline/stagerun.go @@ -2,6 +2,8 @@ package pipeline import ( "context" + "crypto/sha256" + "encoding/hex" "encoding/json" "errors" "fmt" @@ -149,8 +151,12 @@ func (r *Runner) runStage(ctx context.Context, st config.Stage, stageIdx int, sn runCost += esc.fb.runCost anyFresh = anyFresh || esc.fb.freshCall escalated, escModel = true, st.EscalateTo - if esc.fb.cls.ok() { - last = esc.fb // the fallback draft passed the re-gate → it is authoritative + if esc.fb.cls.ok() || esc.fb.cls.Reason == FlagSanitizerStripped { + // The fallback is authoritative when it passed the re-gate OR when it is a cosmetic + // sanitizer strip on a FINAL escalatable stage (adversarial review): a stripped fallback + // is a usable-but-flagged export, so it must be recovered (final_hash → its cleaned text) + // rather than discarded to an empty placeholder — mirroring the non-escalated path. + last = esc.fb } // else: the fallback also failed → keep the primary flag (last unchanged); // the fallback call is billed and counted, the chunk stays flagged (1 hop). @@ -158,12 +164,27 @@ func (r *Runner) runStage(ctx context.Context, st config.Stage, stageIdx int, sn disposition := last.cls.Reason.disposition() finalHash := "" + recovered := "" if disposition == DispOK { finalHash = last.reqHash + } else if last.cls.Reason == FlagSanitizerStripped { + // Cosmetic leak (D35.4a): strip it and COMMIT the cleaned remainder as a $0 derived export + // checkpoint, then point final_hash at it — so the standard final_hash→checkpoint.response_text + // export (records.json / exp12_extract) yields the cleaned text instead of empty, while the + // chunk stays flagged for a human. classifyOutput guaranteed the strip is non-empty and clean. + // The derived checkpoint is durably written BEFORE chunk_status references it (the ok path's + // checkpoint-before-pointer discipline), so a resume never dangles final_hash at a missing row. + recovered = stripCosmetic(last.text) + dh, err := r.commitSanitizedExport(st, ch, job, last, attemptsMade-1, recovered) + if err != nil { + return nil, err + } + finalHash = dh } // chunk_status is a RESOLVE over the checkpoints: cost_usd sums every attempt // (F3-honest — retries are counted), final_hash points at the authoritative - // checkpoint the ok path serves on resume. + // checkpoint the ok path serves on resume (or the derived sanitized-export checkpoint for + // a FlagSanitizerStripped chunk, so its cleaned text still exports). if err := r.Store.UpsertChunkStatus(store.ChunkStatus{ BookID: r.Book.BookID, Chapter: ch.Chapter, ChunkIdx: ch.ChunkIdx, Stage: st.Name, SnapshotID: snapID, ContentHash: contentHash, Disposition: string(disposition), FlagReason: string(last.cls.Reason), @@ -181,6 +202,7 @@ func (r *Runner) runStage(ctx context.Context, st config.Stage, stageIdx int, sn CumCostUSD: cumCost, LatencyMS: last.latency, FinishReason: last.finish, + RecoveredText: recovered, Disposition: disposition, FlagReason: last.cls.Reason, Detail: last.cls.Detail, @@ -198,6 +220,24 @@ func (r *Runner) runStage(ctx context.Context, st config.Stage, stageIdx int, sn return sr, nil } +// commitSanitizedExport persists the cosmetic-stripped export text as a $0 derived checkpoint and +// returns its request_hash (→ chunk_status.final_hash). The hash is CONTENT-ADDRESSED and +// namespaced ("tm-sanitized-v1:") so it can never collide with a real attempt's hex request_hash +// and a resume/re-run re-derives the identical id for free. Called ONLY for a FlagSanitizerStripped +// final stage (D35.4a); `att` is the flagged completion the strip ran over. +func (r *Runner) commitSanitizedExport(st config.Stage, ch Chunk, job *store.Job, att stageAttempt, attempt int, stripped string) (string, error) { + sum := sha256.Sum256([]byte("tm-sanitized-v1\x00" + att.reqHash + "\x00" + stripped)) + derivedHash := "tm-sanitized-v1:" + hex.EncodeToString(sum[:]) + if err := r.Store.PutDerivedCheckpoint(store.Checkpoint{ + RequestHash: derivedHash, JobID: job.ID, ChunkIdx: ch.ChunkIdx, Attempt: attempt, + Stage: st.Name, Role: st.Role, ModelRequested: att.modelActual, ModelActual: att.modelActual, + ResponseText: stripped, UsageJSON: "{}", FinishReason: "sanitized_export", + }); err != nil { + return "", fmt.Errorf("pipeline: commit sanitized export ch%d/chunk%d/%s: %w", ch.Chapter, ch.ChunkIdx, st.Name, err) + } + return derivedHash, nil +} + // stageAttempt is the result of one attempt (a checkpoint hit or a fresh call). type stageAttempt struct { reqHash string diff --git a/backend/internal/pipeline/status.go b/backend/internal/pipeline/status.go index a1bb25c..d3d5d54 100644 --- a/backend/internal/pipeline/status.go +++ b/backend/internal/pipeline/status.go @@ -104,7 +104,7 @@ func flagReasonSeverity(reason string) int { case FlagCJKArtifact, FlagExcisionSuspect, FlagCoverageFail: return 1 case FlagSanitizerDefect: - // A contaminated output (leaked preamble / notes / ###) is unreadable-as-shipped — + // A contaminated output (leaked preamble / notes) that was DROPPED is unreadable-as-shipped — // ranked with the deterministic content failures, above a mere budget symptom. return 2 case FlagLoopDegenerate: @@ -113,10 +113,15 @@ func flagReasonSeverity(reason string) int { return 4 case FlagGlossaryMiss: return 5 + case FlagSanitizerStripped: + // A cosmetic leak the sanitizer STRIPPED and exported (D35.4a): the chunk shipped cleaned, + // so it is the least alarming flag — an "auto-cleaned, glance to verify" signal, ranked below + // a budget symptom (the chunk is not lost; a human need only spot-check the auto-clean). + return 7 case FlagLength, FlagEmpty: return 6 } - return 7 + return 8 } // bookChunks re-derives the book's chunk manifest — Ingest + SplitChunks — for the honest N/M diff --git a/backend/internal/pipeline/testdata/golden/capture.golden b/backend/internal/pipeline/testdata/golden/capture.golden index f394d85..90fdb83 100644 --- a/backend/internal/pipeline/testdata/golden/capture.golden +++ b/backend/internal/pipeline/testdata/golden/capture.golden @@ -1,76 +1,94 @@ ==== run 1 (fresh) ==== -snapshot_id: 22bf92a04ce8d7b3045f0d752998ce818a24f2532a0bc97beeb73e32361bf3d9 -snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v4-utf8-quotedepth","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,"stm_depth":0,"overlap_tokens":0,"cache_ttl":""},"memory_version":"cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v2","sanitizer":{"enabled":true,"version":"sanitizer-v2"},"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_id: 1ffbc9534a39a98d8abeb61fae993c32c0c51240b3515177a4395b581cce8cb0 +snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v4-utf8-quotedepth","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,"stm_depth":0,"overlap_tokens":0,"cache_ttl":""},"memory_version":"cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v2","sanitizer":{"enabled":true,"version":"sanitizer-v4"},"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}}]} brief_hash: c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df memory_version: cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9 -- book result -- -chunks=7 flagged=2 exit=2 total_usd=0.03458 +chunks=9 flagged=4 exit=2 total_usd=0.041859999999999994 chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД cf9f848abc2b. 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 a62fff0a94c2. Судзуки шёл по коридорам Академии магии." + 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 cf9f848abc2b. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД cf9f848abc2b. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch1/1 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД d672ee6a6f49. 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." + 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 d672ee6a6f49. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД d672ee6a6f49. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 138fd5c384e3. 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." + stage_text="ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из 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 138fd5c384e3. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 138fd5c384e3. Судзуки шёл по коридорам Академии магии." recovered="" 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="" + 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_text="" + 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="" - stage_text="ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. Судзуки шёл по коридорам Академии магии." + stage_text="ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. 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 035dad4c3958. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 035dad4c3958. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch5/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 26a647c94a75. Судзуки увидел, как в тени ждал старик." 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 bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика." + stage_text="ЧЕРНОВИК ПЕРЕВОДА bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика." 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 26a647c94a75. Судзуки увидел, как в тени ждал старик." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 26a647c94a75. Судзуки увидел, как в тени ждал старик." recovered="" chunk ch6/0 disposition=flagged flag="sanitizer_defect" final_text="" 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="Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь." + stage_text="Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь." recovered="" stage=edit role=editor model=fake-model resume=false disp=flagged flag="sanitizer_defect" attempts=1 escalated=false esc_model="" finish="stop" cum_usd=0.00182 detail="ведущая служебная преамбула: Вот перевод фрагмента:" - stage_text="" + stage_text="" recovered="" +chunk ch7/0 disposition=flagged flag="sanitizer_stripped" final_text="Глава 7\n\nСудзуки открыл седьмую дверь книгохранилища." 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 ec12f3d7a1df. МАРКДАУН-СЦЕНА Судзуки открыл седьмую дверь." recovered="" + 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="markdown-заголовок в выходе: ### Глава 7" + stage_text="" recovered="Глава 7\n\nСудзуки открыл седьмую дверь книгохранилища." +chunk ch8/0 disposition=flagged flag="sanitizer_stripped" final_text="Судзуки нашёл древний камень на каменном алтаре." 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 0bc6a4817acb. ИЕРОГЛИФ-СЦЕНА Судзуки нашёл камень." recovered="" + 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=7bda1d23e4828d0f05f167f0980d6dcb31e6d7808175c3e934e512f25ec4d03f cost=0.00182 escalated=false esc_model="" detail="" -ch1/0 edit snap_match=true content_hash=a559165b4d1fc3f9e75472ca654f4d039ae1e0cad1541c043e7aa68fbea5415a disp=ok flag="" attempts=1 final_hash=1d2aad2175e4e34c894709417460a3a4a395fc977e603f339327b1d302befcf5 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=96d877d33a55d992fa1a4d36fa13a0d97eb61324dda80296cce432f279991b96 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 edit snap_match=true content_hash=b11a1740e5af98af20e207672555da8d411311e6c1e26595b456b656e8de59ef disp=ok flag="" attempts=1 final_hash=15ca0e09a901d97cc9f4665196e60aa10ef1ece4a5abb8ac2ccf65355ee4af04 cost=0.00182 escalated=false esc_model="" detail="" -ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=91bc556b12b7ee88771b870dcc872172a7edfa75b4cd0286fc6f9c9b1e030b50 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" -ch2/0 edit snap_match=true content_hash=b467337f05775296985a6d79454b518302812edb57d398001b8852d0663c5bbb disp=ok flag="" attempts=1 final_hash=4cb824da88d824dee2548f25c99a07af19d8e7a960dc12eb8a2dcfbfea565dfe cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=fb1549b81d5a6aa0a2b041b6410bb56390caf1253916cb4153178f67d88c5a91 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 edit snap_match=true content_hash=a559165b4d1fc3f9e75472ca654f4d039ae1e0cad1541c043e7aa68fbea5415a disp=ok flag="" attempts=1 final_hash=4dd7ec790e3550feeec4e2958ad6a28b0e22c667766771b053493020c5377ce2 cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=50cc19ab0ebe06a432a93d7c0912ec8ac75ee357291268f22ee3400c97530b8d cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 edit snap_match=true content_hash=b11a1740e5af98af20e207672555da8d411311e6c1e26595b456b656e8de59ef disp=ok flag="" attempts=1 final_hash=884f043f9054b38443a58fbfa2a66ff306478b81869e02454abe0c33d7a2ce47 cost=0.00182 escalated=false esc_model="" detail="" +ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=a2c7cfdfe4df917201626c685901ad06cd0eef3a00901ca469d8c913838ec996 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" +ch2/0 edit snap_match=true content_hash=b467337f05775296985a6d79454b518302812edb57d398001b8852d0663c5bbb disp=ok flag="" attempts=1 final_hash=f36dbfa0f76ab0866e33792bc664b00505cdc231daca83dce90d40e6276c292e 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=887c72449d515b208d1473df5bfa91b0e0f5e2eec3850b967d2888413189bbc4 cost=0.00182 escalated=false esc_model="" detail="" -ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=88be9923f7e6e6781b8eb9e02ffeea614003dc504b676e0cb54fe21ee1b239ba cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=e723f314c5cd17a0f000c0bbac25812b42f414ae9d395d59ceb186ea65caed90 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 edit snap_match=true content_hash=99ebb10d754a2f3ae3a00d62734ad1c39160f083350217eda5bda6e91373f4de disp=ok flag="" attempts=1 final_hash=b8d6e3f357b740ad065e37c46eeb9b31dc170849db8bd8f8d468040ad2b47701 cost=0.00182 escalated=false esc_model="" detail="" -ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=7b0dd4e5b9a7648c65e7c04b6dd928ff8e6d7dc74b3f4baf469058e8dbdf628f cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=78f8769dd85cf50aeffdc3be1a3ea8c40291af736598834449508be15424fe3b cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=713a76508a2ebac88c6f4baab807fef35ac3926e0fa8b5ea90dfdf8b5462c451 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=c0b8686d58549f284727bd02a8799a7eb02dbb1cb44ec0c1d4508f33a1c6fdd8 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 edit snap_match=true content_hash=99ebb10d754a2f3ae3a00d62734ad1c39160f083350217eda5bda6e91373f4de disp=ok flag="" attempts=1 final_hash=0107bb59088ea63d56ca05075998350b6e953bd95c7aca6fdf77b57988193881 cost=0.00182 escalated=false esc_model="" detail="" +ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=80bf6ede255b88fbcf0ed7b34c5f9b3d7ae0414666355a408fe5b5a36988c3b4 cost=0.00182 escalated=false esc_model="" detail="" ch6/0 edit snap_match=true content_hash=f9a70ce8a43db4a89eda5e53a6f29ba5f0c2a35559a9d35b73f771220bb262ee 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=c3df59650641637d598d01f4e2beba4c08408fbdf72ad99b4b0d4c6d471961ae cost=0.00182 escalated=false esc_model="" detail="" +ch7/0 edit snap_match=true content_hash=f003d8ad25546238e63b98d28a08f942c8e3cf57251df694de81bea293a6dd26 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:fc3e0c22addbbd1367e9712d82deec0905762d3ac94d40c0b64fc01c5885b132 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=90f4b85790e9cb4057b7d35c31ede2497db38ec98988635662b7375f888f4c7b cost=0.00182 escalated=false esc_model="" detail="" +ch8/0 edit snap_match=true content_hash=40c2dd5b7b713800e8453930779bf2c88e2a296056f594bc1a4f5c495956915a disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:5a543ddaa7f464a1c0bd08d83fed383ba3a2f2bb3223ebc158c70fe1d4ac1750 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=7bda1d23e4828d0f05f167f0980d6dcb31e6d7808175c3e934e512f25ec4d03f 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=1d2aad2175e4e34c894709417460a3a4a395fc977e603f339327b1d302befcf5 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=96d877d33a55d992fa1a4d36fa13a0d97eb61324dda80296cce432f279991b96 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=15ca0e09a901d97cc9f4665196e60aa10ef1ece4a5abb8ac2ccf65355ee4af04 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=1f46b5678d6507f1bbd445c35ca21105df5a902c67c631e1c64fb044e7d4c818 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=91bc556b12b7ee88771b870dcc872172a7edfa75b4cd0286fc6f9c9b1e030b50 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=4cb824da88d824dee2548f25c99a07af19d8e7a960dc12eb8a2dcfbfea565dfe 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=bc8732c7c5039acef1d37e3d3cc9c3d86f4cfaece50d8c2985c0a405b24f583d 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=832508029b158e9b8533740283f1cccdedf1597d6e8bb98f797587b7c461566c 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=887c72449d515b208d1473df5bfa91b0e0f5e2eec3850b967d2888413189bbc4 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=88be9923f7e6e6781b8eb9e02ffeea614003dc504b676e0cb54fe21ee1b239ba 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=e723f314c5cd17a0f000c0bbac25812b42f414ae9d395d59ceb186ea65caed90 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=b8d6e3f357b740ad065e37c46eeb9b31dc170849db8bd8f8d468040ad2b47701 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=7b0dd4e5b9a7648c65e7c04b6dd928ff8e6d7dc74b3f4baf469058e8dbdf628f 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=190b651aa53eb1991b5d2a3b75440190d3a5d9ef4b5226cd0bedfb938179de73 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" +ch1/0 draft role=translator req=fake-model actual=fake-model hash=fb1549b81d5a6aa0a2b041b6410bb56390caf1253916cb4153178f67d88c5a91 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=4dd7ec790e3550feeec4e2958ad6a28b0e22c667766771b053493020c5377ce2 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=50cc19ab0ebe06a432a93d7c0912ec8ac75ee357291268f22ee3400c97530b8d 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=884f043f9054b38443a58fbfa2a66ff306478b81869e02454abe0c33d7a2ce47 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=c8449d0453646f7d74262278d13698eaed0b321f58b44aceee0bd38eafe81ff5 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=a2c7cfdfe4df917201626c685901ad06cd0eef3a00901ca469d8c913838ec996 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=f36dbfa0f76ab0866e33792bc664b00505cdc231daca83dce90d40e6276c292e 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=9c3617bd273d8af97c274007bb76dcca7b66c2833f2e1ee88c0c81c955bbc7d3 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=4bcdc93f17408c43c777ce6ae42fc66012b89a7d6cf8356e8725e4b2c678a0af 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=78f8769dd85cf50aeffdc3be1a3ea8c40291af736598834449508be15424fe3b 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=713a76508a2ebac88c6f4baab807fef35ac3926e0fa8b5ea90dfdf8b5462c451 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=c0b8686d58549f284727bd02a8799a7eb02dbb1cb44ec0c1d4508f33a1c6fdd8 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=0107bb59088ea63d56ca05075998350b6e953bd95c7aca6fdf77b57988193881 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=80bf6ede255b88fbcf0ed7b34c5f9b3d7ae0414666355a408fe5b5a36988c3b4 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=19dd3aee47df5ffdf4c9b54200736558cedfbbf93b4de04a09736e115f509fd5 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=c3df59650641637d598d01f4e2beba4c08408fbdf72ad99b4b0d4c6d471961ae 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=8fb19111ef328216f23a189007f381203ae6d67efc688c22a4f0d1ca4a378ced 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=90f4b85790e9cb4057b7d35c31ede2497db38ec98988635662b7375f888f4c7b 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=dbaf45791e58372dc3c244db97911c0178e6faf39e2d4df70eb7c8f6b10230d1 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 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= @@ -86,6 +104,10 @@ ch5/0 snap_match=true exact=2 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck injected_ids=["老人\u001f\u001f0\u001f0","鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= ch6/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= +ch7/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 + injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= +ch8/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 + injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_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 эти сущности должны быть переданы ИМЕННО этими формами — приводи к ним любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- «герб»\n- «Судзуки»\n- «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} @@ -102,92 +124,118 @@ ch6/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck [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 эти сущности должны быть переданы ИМЕННО этими формами — приводи к ним любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- «старик»\n- «Судзуки»"},{"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 эти сущности должны быть переданы ИМЕННО этими формами — приводи к ним любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- «Судзуки»"},{"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} +[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 эти сущности должны быть переданы ИМЕННО этими формами — приводи к ним любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- «Судзуки»"},{"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 эти сущности должны быть переданы ИМЕННО этими формами — приводи к ним любые расхождения, склоняя по контексту; не вводи иных вариантов и не меняй ничего другого):\n- «Судзуки»"},{"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: 22bf92a04ce8d7b3045f0d752998ce818a24f2532a0bc97beeb73e32361bf3d9 -snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v4-utf8-quotedepth","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,"stm_depth":0,"overlap_tokens":0,"cache_ttl":""},"memory_version":"cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v2","sanitizer":{"enabled":true,"version":"sanitizer-v2"},"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_id: 1ffbc9534a39a98d8abeb61fae993c32c0c51240b3515177a4395b581cce8cb0 +snapshot_payload: {"brief_hash":"c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df","chunker_version":"chunker-v4-utf8-quotedepth","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,"stm_depth":0,"overlap_tokens":0,"cache_ttl":""},"memory_version":"cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9","postcheck_gate":false,"coverage":{"enabled":false},"style_check_version":"cheapgate-v2","sanitizer":{"enabled":true,"version":"sanitizer-v4"},"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}}]} brief_hash: c2021b1b5e6c20f6084e425b9a70bdc5f682801be347a57eb1c591deb8cab0df memory_version: cee708b1c530789a0d07f88902051fe0a9af49ad3b0706b230dbe6d503fc3cd9 -- book result -- -chunks=7 flagged=2 exit=2 total_usd=0 +chunks=9 flagged=4 exit=2 total_usd=0 chunk ch1/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД cf9f848abc2b. 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." + 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 cf9f848abc2b. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД cf9f848abc2b. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch1/1 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД d672ee6a6f49. 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." + 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 d672ee6a6f49. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД d672ee6a6f49. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch2/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 138fd5c384e3. 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." + stage_text="ЭСКАЛАЦИОННЫЙ ПЕРЕВОД 0ab6e1368c17. Судзуки вынес Драконью печать из 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 138fd5c384e3. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 138fd5c384e3. Судзуки шёл по коридорам Академии магии." recovered="" 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="" + 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_text="" + 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="" - stage_text="ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. Судзуки шёл по коридорам Академии магии." + stage_text="ЧЕРНОВИК ПЕРЕВОДА 2eee3ef795d7. 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 035dad4c3958. Судзуки шёл по коридорам Академии магии." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 035dad4c3958. Судзуки шёл по коридорам Академии магии." recovered="" chunk ch5/0 disposition=ok flag="" final_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 26a647c94a75. Судзуки увидел, как в тени ждал старик." 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 bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика." + stage_text="ЧЕРНОВИК ПЕРЕВОДА bb921e6e678b. СТАРИК-СЦЕНА Судзуки увидел старика." 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 26a647c94a75. Судзуки увидел, как в тени ждал старик." + stage_text="ОТРЕДАКТИРОВАННЫЙ ПЕРЕВОД 26a647c94a75. Судзуки увидел, как в тени ждал старик." recovered="" chunk ch6/0 disposition=flagged flag="sanitizer_defect" final_text="" 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="Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь." + stage_text="Вот перевод фрагмента: ПРЕАМБУЛА-СЦЕНА Судзуки открыл дверь." recovered="" stage=edit role=editor model=fake-model resume=true disp=flagged flag="sanitizer_defect" attempts=1 escalated=false esc_model="" finish="" cum_usd=0.00182 detail="ведущая служебная преамбула: Вот перевод фрагмента:" - stage_text="" + stage_text="" recovered="" +chunk ch7/0 disposition=flagged flag="sanitizer_stripped" final_text="Глава 7\n\nСудзуки открыл седьмую дверь книгохранилища." 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 ec12f3d7a1df. МАРКДАУН-СЦЕНА Судзуки открыл седьмую дверь." recovered="" + 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="markdown-заголовок в выходе: ### Глава 7" + stage_text="" recovered="Глава 7\n\nСудзуки открыл седьмую дверь книгохранилища." +chunk ch8/0 disposition=flagged flag="sanitizer_stripped" final_text="Судзуки нашёл древний камень на каменном алтаре." 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 0bc6a4817acb. ИЕРОГЛИФ-СЦЕНА Судзуки нашёл камень." recovered="" + 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=7bda1d23e4828d0f05f167f0980d6dcb31e6d7808175c3e934e512f25ec4d03f cost=0.00182 escalated=false esc_model="" detail="" -ch1/0 edit snap_match=true content_hash=a559165b4d1fc3f9e75472ca654f4d039ae1e0cad1541c043e7aa68fbea5415a disp=ok flag="" attempts=1 final_hash=1d2aad2175e4e34c894709417460a3a4a395fc977e603f339327b1d302befcf5 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=96d877d33a55d992fa1a4d36fa13a0d97eb61324dda80296cce432f279991b96 cost=0.00182 escalated=false esc_model="" detail="" -ch1/1 edit snap_match=true content_hash=b11a1740e5af98af20e207672555da8d411311e6c1e26595b456b656e8de59ef disp=ok flag="" attempts=1 final_hash=15ca0e09a901d97cc9f4665196e60aa10ef1ece4a5abb8ac2ccf65355ee4af04 cost=0.00182 escalated=false esc_model="" detail="" -ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=91bc556b12b7ee88771b870dcc872172a7edfa75b4cd0286fc6f9c9b1e030b50 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" -ch2/0 edit snap_match=true content_hash=b467337f05775296985a6d79454b518302812edb57d398001b8852d0663c5bbb disp=ok flag="" attempts=1 final_hash=4cb824da88d824dee2548f25c99a07af19d8e7a960dc12eb8a2dcfbfea565dfe cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 draft snap_match=true content_hash=331c6f32c7f3ed15447e2639a2621d24a180e561a2aee92115324f492db5de3e disp=ok flag="" attempts=1 final_hash=fb1549b81d5a6aa0a2b041b6410bb56390caf1253916cb4153178f67d88c5a91 cost=0.00182 escalated=false esc_model="" detail="" +ch1/0 edit snap_match=true content_hash=a559165b4d1fc3f9e75472ca654f4d039ae1e0cad1541c043e7aa68fbea5415a disp=ok flag="" attempts=1 final_hash=4dd7ec790e3550feeec4e2958ad6a28b0e22c667766771b053493020c5377ce2 cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 draft snap_match=true content_hash=12fe3ccdf062f43e011363a33ff85c9b6842a8f23d790991fe9afab51a8becc8 disp=ok flag="" attempts=1 final_hash=50cc19ab0ebe06a432a93d7c0912ec8ac75ee357291268f22ee3400c97530b8d cost=0.00182 escalated=false esc_model="" detail="" +ch1/1 edit snap_match=true content_hash=b11a1740e5af98af20e207672555da8d411311e6c1e26595b456b656e8de59ef disp=ok flag="" attempts=1 final_hash=884f043f9054b38443a58fbfa2a66ff306478b81869e02454abe0c33d7a2ce47 cost=0.00182 escalated=false esc_model="" detail="" +ch2/0 draft snap_match=true content_hash=2693325bc747687acf090bc263fe8c17783726b949c6d8a2d072da3401be6827 disp=ok flag="" attempts=1 final_hash=a2c7cfdfe4df917201626c685901ad06cd0eef3a00901ca469d8c913838ec996 cost=0.00728 escalated=true esc_model="fake-fallback" detail="" +ch2/0 edit snap_match=true content_hash=b467337f05775296985a6d79454b518302812edb57d398001b8852d0663c5bbb disp=ok flag="" attempts=1 final_hash=f36dbfa0f76ab0866e33792bc664b00505cdc231daca83dce90d40e6276c292e 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=887c72449d515b208d1473df5bfa91b0e0f5e2eec3850b967d2888413189bbc4 cost=0.00182 escalated=false esc_model="" detail="" -ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=88be9923f7e6e6781b8eb9e02ffeea614003dc504b676e0cb54fe21ee1b239ba cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=e723f314c5cd17a0f000c0bbac25812b42f414ae9d395d59ceb186ea65caed90 cost=0.00182 escalated=false esc_model="" detail="" -ch5/0 edit snap_match=true content_hash=99ebb10d754a2f3ae3a00d62734ad1c39160f083350217eda5bda6e91373f4de disp=ok flag="" attempts=1 final_hash=b8d6e3f357b740ad065e37c46eeb9b31dc170849db8bd8f8d468040ad2b47701 cost=0.00182 escalated=false esc_model="" detail="" -ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=7b0dd4e5b9a7648c65e7c04b6dd928ff8e6d7dc74b3f4baf469058e8dbdf628f cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 draft snap_match=true content_hash=7aabdcb89dea365c95363b2662144ca1a10b307d377f47a8e7cc19b5b872d287 disp=ok flag="" attempts=1 final_hash=78f8769dd85cf50aeffdc3be1a3ea8c40291af736598834449508be15424fe3b cost=0.00182 escalated=false esc_model="" detail="" +ch4/0 edit snap_match=true content_hash=2854dfe1648b0cf0cbb683cb7ce94c5eedc9223b2ce20c99dc008c7add6317ef disp=ok flag="" attempts=1 final_hash=713a76508a2ebac88c6f4baab807fef35ac3926e0fa8b5ea90dfdf8b5462c451 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 draft snap_match=true content_hash=d8aba42cabb41853a81875ebc725bb516dc2412e29de3a03bc1a68e90f8cf157 disp=ok flag="" attempts=1 final_hash=c0b8686d58549f284727bd02a8799a7eb02dbb1cb44ec0c1d4508f33a1c6fdd8 cost=0.00182 escalated=false esc_model="" detail="" +ch5/0 edit snap_match=true content_hash=99ebb10d754a2f3ae3a00d62734ad1c39160f083350217eda5bda6e91373f4de disp=ok flag="" attempts=1 final_hash=0107bb59088ea63d56ca05075998350b6e953bd95c7aca6fdf77b57988193881 cost=0.00182 escalated=false esc_model="" detail="" +ch6/0 draft snap_match=true content_hash=9375b05780724cc354eba15a595da9a5f964219c0887042484256eed11fb566f disp=ok flag="" attempts=1 final_hash=80bf6ede255b88fbcf0ed7b34c5f9b3d7ae0414666355a408fe5b5a36988c3b4 cost=0.00182 escalated=false esc_model="" detail="" ch6/0 edit snap_match=true content_hash=f9a70ce8a43db4a89eda5e53a6f29ba5f0c2a35559a9d35b73f771220bb262ee 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=c3df59650641637d598d01f4e2beba4c08408fbdf72ad99b4b0d4c6d471961ae cost=0.00182 escalated=false esc_model="" detail="" +ch7/0 edit snap_match=true content_hash=f003d8ad25546238e63b98d28a08f942c8e3cf57251df694de81bea293a6dd26 disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:fc3e0c22addbbd1367e9712d82deec0905762d3ac94d40c0b64fc01c5885b132 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=90f4b85790e9cb4057b7d35c31ede2497db38ec98988635662b7375f888f4c7b cost=0.00182 escalated=false esc_model="" detail="" +ch8/0 edit snap_match=true content_hash=40c2dd5b7b713800e8453930779bf2c88e2a296056f594bc1a4f5c495956915a disp=flagged flag="sanitizer_stripped" attempts=1 final_hash=tm-sanitized-v1:5a543ddaa7f464a1c0bd08d83fed383ba3a2f2bb3223ebc158c70fe1d4ac1750 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=7bda1d23e4828d0f05f167f0980d6dcb31e6d7808175c3e934e512f25ec4d03f 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=1d2aad2175e4e34c894709417460a3a4a395fc977e603f339327b1d302befcf5 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=96d877d33a55d992fa1a4d36fa13a0d97eb61324dda80296cce432f279991b96 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=15ca0e09a901d97cc9f4665196e60aa10ef1ece4a5abb8ac2ccf65355ee4af04 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=1f46b5678d6507f1bbd445c35ca21105df5a902c67c631e1c64fb044e7d4c818 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=91bc556b12b7ee88771b870dcc872172a7edfa75b4cd0286fc6f9c9b1e030b50 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=4cb824da88d824dee2548f25c99a07af19d8e7a960dc12eb8a2dcfbfea565dfe 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=bc8732c7c5039acef1d37e3d3cc9c3d86f4cfaece50d8c2985c0a405b24f583d 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=832508029b158e9b8533740283f1cccdedf1597d6e8bb98f797587b7c461566c 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=887c72449d515b208d1473df5bfa91b0e0f5e2eec3850b967d2888413189bbc4 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=88be9923f7e6e6781b8eb9e02ffeea614003dc504b676e0cb54fe21ee1b239ba 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=e723f314c5cd17a0f000c0bbac25812b42f414ae9d395d59ceb186ea65caed90 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=b8d6e3f357b740ad065e37c46eeb9b31dc170849db8bd8f8d468040ad2b47701 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=7b0dd4e5b9a7648c65e7c04b6dd928ff8e6d7dc74b3f4baf469058e8dbdf628f 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=190b651aa53eb1991b5d2a3b75440190d3a5d9ef4b5226cd0bedfb938179de73 tm_hit=0 ok=0 finish="stop" degraded="sanitizer_defect" cost=0.00182 tokens=1000/200/0/500/0 err="" -ch1/0 draft role=translator req=fake-model actual=fake-model hash=7bda1d23e4828d0f05f167f0980d6dcb31e6d7808175c3e934e512f25ec4d03f 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=1d2aad2175e4e34c894709417460a3a4a395fc977e603f339327b1d302befcf5 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=96d877d33a55d992fa1a4d36fa13a0d97eb61324dda80296cce432f279991b96 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=15ca0e09a901d97cc9f4665196e60aa10ef1ece4a5abb8ac2ccf65355ee4af04 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=91bc556b12b7ee88771b870dcc872172a7edfa75b4cd0286fc6f9c9b1e030b50 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=4cb824da88d824dee2548f25c99a07af19d8e7a960dc12eb8a2dcfbfea565dfe 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=fb1549b81d5a6aa0a2b041b6410bb56390caf1253916cb4153178f67d88c5a91 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=4dd7ec790e3550feeec4e2958ad6a28b0e22c667766771b053493020c5377ce2 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=50cc19ab0ebe06a432a93d7c0912ec8ac75ee357291268f22ee3400c97530b8d 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=884f043f9054b38443a58fbfa2a66ff306478b81869e02454abe0c33d7a2ce47 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=c8449d0453646f7d74262278d13698eaed0b321f58b44aceee0bd38eafe81ff5 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=a2c7cfdfe4df917201626c685901ad06cd0eef3a00901ca469d8c913838ec996 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=f36dbfa0f76ab0866e33792bc664b00505cdc231daca83dce90d40e6276c292e 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=9c3617bd273d8af97c274007bb76dcca7b66c2833f2e1ee88c0c81c955bbc7d3 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=4bcdc93f17408c43c777ce6ae42fc66012b89a7d6cf8356e8725e4b2c678a0af 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=78f8769dd85cf50aeffdc3be1a3ea8c40291af736598834449508be15424fe3b 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=713a76508a2ebac88c6f4baab807fef35ac3926e0fa8b5ea90dfdf8b5462c451 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=c0b8686d58549f284727bd02a8799a7eb02dbb1cb44ec0c1d4508f33a1c6fdd8 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=0107bb59088ea63d56ca05075998350b6e953bd95c7aca6fdf77b57988193881 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=80bf6ede255b88fbcf0ed7b34c5f9b3d7ae0414666355a408fe5b5a36988c3b4 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=19dd3aee47df5ffdf4c9b54200736558cedfbbf93b4de04a09736e115f509fd5 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=c3df59650641637d598d01f4e2beba4c08408fbdf72ad99b4b0d4c6d471961ae 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=8fb19111ef328216f23a189007f381203ae6d67efc688c22a4f0d1ca4a378ced 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=90f4b85790e9cb4057b7d35c31ede2497db38ec98988635662b7375f888f4c7b 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=dbaf45791e58372dc3c244db97911c0178e6faf39e2d4df70eb7c8f6b10230d1 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=fb1549b81d5a6aa0a2b041b6410bb56390caf1253916cb4153178f67d88c5a91 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=4dd7ec790e3550feeec4e2958ad6a28b0e22c667766771b053493020c5377ce2 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=50cc19ab0ebe06a432a93d7c0912ec8ac75ee357291268f22ee3400c97530b8d 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=884f043f9054b38443a58fbfa2a66ff306478b81869e02454abe0c33d7a2ce47 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=a2c7cfdfe4df917201626c685901ad06cd0eef3a00901ca469d8c913838ec996 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=f36dbfa0f76ab0866e33792bc664b00505cdc231daca83dce90d40e6276c292e 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=887c72449d515b208d1473df5bfa91b0e0f5e2eec3850b967d2888413189bbc4 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=88be9923f7e6e6781b8eb9e02ffeea614003dc504b676e0cb54fe21ee1b239ba 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=e723f314c5cd17a0f000c0bbac25812b42f414ae9d395d59ceb186ea65caed90 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=b8d6e3f357b740ad065e37c46eeb9b31dc170849db8bd8f8d468040ad2b47701 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=7b0dd4e5b9a7648c65e7c04b6dd928ff8e6d7dc74b3f4baf469058e8dbdf628f 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=78f8769dd85cf50aeffdc3be1a3ea8c40291af736598834449508be15424fe3b 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=713a76508a2ebac88c6f4baab807fef35ac3926e0fa8b5ea90dfdf8b5462c451 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=c0b8686d58549f284727bd02a8799a7eb02dbb1cb44ec0c1d4508f33a1c6fdd8 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=0107bb59088ea63d56ca05075998350b6e953bd95c7aca6fdf77b57988193881 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=80bf6ede255b88fbcf0ed7b34c5f9b3d7ae0414666355a408fe5b5a36988c3b4 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=c3df59650641637d598d01f4e2beba4c08408fbdf72ad99b4b0d4c6d471961ae 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:fc3e0c22addbbd1367e9712d82deec0905762d3ac94d40c0b64fc01c5885b132 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=90f4b85790e9cb4057b7d35c31ede2497db38ec98988635662b7375f888f4c7b 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-v1:5a543ddaa7f464a1c0bd08d83fed383ba3a2f2bb3223ebc158c70fe1d4ac1750 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 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= @@ -203,4 +251,8 @@ ch5/0 snap_match=true exact=2 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck injected_ids=["老人\u001f\u001f0\u001f0","鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= ch6/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= +ch7/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 + injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= +ch8/0 snap_match=true exact=1 sticky=0 ambiguous=0 spoiler=0 evicted=0 postcheck_miss=0 style_flags=0 + injected_ids=["鈴木\u001f\u001f0\u001f0"] postcheck_detail= style_detail= -- wire bodies (call order) -- diff --git a/backend/internal/pipeline/testdata/golden/source.txt b/backend/internal/pipeline/testdata/golden/source.txt index 9b5fa4d..a8617c4 100644 --- a/backend/internal/pipeline/testdata/golden/source.txt +++ b/backend/internal/pipeline/testdata/golden/source.txt @@ -41,3 +41,11 @@ 第六章　序文漏洩 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。 + +第七章　見出漏洩 + +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。 + +第八章　漢字漏洩 + +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。 diff --git a/backend/internal/store/ledger.go b/backend/internal/store/ledger.go index 0789c2c..de202a3 100644 --- a/backend/internal/store/ledger.go +++ b/backend/internal/store/ledger.go @@ -170,6 +170,33 @@ func (s *Store) SettleWithCheckpoint(res Reservation, cost float64, cp Checkpoin return tx.Commit() } +// PutDerivedCheckpoint persists a $0 DERIVED checkpoint — a deterministic post-processing +// artifact, NOT a billed provider response (D38 infra-pack): the output-sanitizer's cosmetic +// strip commits the cleaned final text here so the standard final_hash→checkpoint.response_text +// export contract (records.json / exp12_extract) yields the cleaned text for a flagged chunk that +// would otherwise export empty (D35.4a). It touches NO spend/reservation (cost must be 0), keyed +// by its own derived request_hash (namespaced, collision-free with real attempt hashes), and is +// idempotent (ON CONFLICT DO NOTHING) so a re-run re-derives the identical row for free. Escalation +// is deliberately false so it never counts toward escalation.budget_usd. It is deleted with its +// stage's real checkpoints on `redrive` (ResetChunkStages joins by job/chunk/stage), never orphaned. +func (s *Store) PutDerivedCheckpoint(cp Checkpoint) error { + ctx, cancel := opContext() + defer cancel() + _, err := s.w.ExecContext(ctx, ` + INSERT INTO checkpoints ( + request_hash, job_id, chunk_idx, attempt, stage, role, + model_requested, model_actual, response_text, usage_json, + cost_usd, finish_reason, provider_request_id, escalation + ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 0, ?, '', 0) + ON CONFLICT (request_hash) DO NOTHING`, + cp.RequestHash, cp.JobID, cp.ChunkIdx, cp.Attempt, cp.Stage, cp.Role, + cp.ModelRequested, cp.ModelActual, cp.ResponseText, cp.UsageJSON, cp.FinishReason) + if err != nil { + return fmt.Errorf("store: derived checkpoint insert: %w", err) + } + return nil +} + // GetCheckpoint returns the persisted response for a request hash, if any — // the resume path: a hit means the call is NOT repeated or re-billed. func (s *Store) GetCheckpoint(requestHash string) (*Checkpoint, error) { diff --git a/backend/internal/store/store_test.go b/backend/internal/store/store_test.go index 7e022ed..50dd111 100644 --- a/backend/internal/store/store_test.go +++ b/backend/internal/store/store_test.go @@ -73,6 +73,41 @@ func TestReserveSettleLifecycle(t *testing.T) { } } +// TestPutDerivedCheckpoint pins the $0 sanitized-export checkpoint (D38 infra-pack): it persists a +// retrievable response, books NO spend, and is idempotent (re-derive on resume is free). +func TestPutDerivedCheckpoint(t *testing.T) { + s, _ := openTemp(t) + job := mustSnapshotAndJob(t, s) + + cp := Checkpoint{RequestHash: "tm-sanitized-v1:abc", JobID: job.ID, ChunkIdx: 0, Stage: "edit", + Role: "editor", ModelRequested: "m", ModelActual: "m", ResponseText: "очищенный текст", + UsageJSON: "{}", FinishReason: "sanitized_export"} + if err := s.PutDerivedCheckpoint(cp); err != nil { + t.Fatal(err) + } + // Retrievable via the standard checkpoint read (the final_hash→checkpoint export contract). + got, err := s.GetCheckpoint("tm-sanitized-v1:abc") + if err != nil || got == nil || got.ResponseText != "очищенный текст" { + t.Fatalf("derived checkpoint: %+v err=%v", got, err) + } + if got.CostUSD != 0 { + t.Fatalf("derived checkpoint must be $0, got %v", got.CostUSD) + } + // No spend booked (it is a post-processing artifact, not a provider call). + committed, reserved, _ := s.SpentUSD("book") + if committed != 0 || reserved != 0 { + t.Fatalf("derived checkpoint booked spend: committed=%v reserved=%v", committed, reserved) + } + // Idempotent: a resume re-derives the identical row for free (ON CONFLICT DO NOTHING). + if err := s.PutDerivedCheckpoint(cp); err != nil { + t.Fatalf("re-put must be idempotent: %v", err) + } + committed, _, _ = s.SpentUSD("book") + if committed != 0 { + t.Fatalf("idempotent re-put booked spend: committed=%v", committed) + } +} + func TestCeilingsDeny(t *testing.T) { s, _ := openTemp(t) mustSnapshotAndJob(t, s)