296 lines
18 KiB
Go
296 lines
18 KiB
Go
package store
|
||
|
||
import (
|
||
"context"
|
||
"fmt"
|
||
)
|
||
|
||
// migrations are applied in order; schema_version records the highest applied
|
||
// version so re-runs are no-ops. Every step is also idempotent (CREATE TABLE
|
||
// IF NOT EXISTS) so a half-applied database still converges. Append-only:
|
||
// never edit an earlier migration (дисциплина vojo).
|
||
var migrations = []string{
|
||
// v1: the Phase-0 operational schema.
|
||
`
|
||
-- Snapshot контекста джобы (Р6, implementation-notes §3.2): материализованная
|
||
-- запись; snapshot_id входит в request-hash, так что волатильность контекста
|
||
-- заморожена на джобу. payload — JSON (версии промптов per-role, модели,
|
||
-- версия чанкера, style sheet, резюме на момент старта).
|
||
CREATE TABLE IF NOT EXISTS snapshots (
|
||
snapshot_id TEXT PRIMARY KEY,
|
||
brief_hash TEXT NOT NULL,
|
||
payload TEXT NOT NULL,
|
||
created_at TEXT NOT NULL DEFAULT (datetime('now'))
|
||
);
|
||
|
||
-- Durable jobs: джоба = глава×стадия (Р6). Гранулярность СОХРАННОСТИ — чанк
|
||
-- (checkpoints), джоба лишь группирует их и несёт snapshot_id.
|
||
CREATE TABLE IF NOT EXISTS jobs (
|
||
id INTEGER PRIMARY KEY,
|
||
book_id TEXT NOT NULL,
|
||
chapter INTEGER NOT NULL,
|
||
stage TEXT NOT NULL,
|
||
status TEXT NOT NULL DEFAULT 'pending', -- pending|running|done|failed
|
||
snapshot_id TEXT NOT NULL REFERENCES snapshots(snapshot_id),
|
||
created_at TEXT NOT NULL DEFAULT (datetime('now')),
|
||
updated_at TEXT NOT NULL DEFAULT (datetime('now')),
|
||
UNIQUE (book_id, chapter, stage)
|
||
);
|
||
|
||
-- Чанк-чекпоинты: сырой ответ LLM персистится атомарно вместе с settle
|
||
-- (одна транзакция — SettleWithCheckpoint), ключ — request_hash от
|
||
-- детерминированного рендера (§3.1). kill -9 теряет максимум один
|
||
-- in-flight вызов. Найденный чекпоинт на resume = вызов не повторяется и
|
||
-- не оплачивается второй раз.
|
||
CREATE TABLE IF NOT EXISTS checkpoints (
|
||
request_hash TEXT PRIMARY KEY,
|
||
job_id INTEGER NOT NULL REFERENCES jobs(id),
|
||
chunk_idx INTEGER NOT NULL,
|
||
attempt INTEGER NOT NULL DEFAULT 0, -- регенерации Фазы 1: attempt входит в request-hash
|
||
stage TEXT NOT NULL,
|
||
role TEXT NOT NULL,
|
||
model_requested TEXT NOT NULL,
|
||
model_actual TEXT NOT NULL,
|
||
response_text TEXT NOT NULL,
|
||
usage_json TEXT NOT NULL,
|
||
cost_usd REAL NOT NULL,
|
||
finish_reason TEXT NOT NULL DEFAULT '',
|
||
provider_request_id TEXT NOT NULL DEFAULT '',
|
||
created_at TEXT NOT NULL DEFAULT (datetime('now'))
|
||
);
|
||
CREATE INDEX IF NOT EXISTS checkpoints_job_idx ON checkpoints (job_id, chunk_idx);
|
||
|
||
-- Дневной/книжный ledger с резервированием (порт семантики vojo spend):
|
||
-- потолки считают committed + reserved на допуске, поэтому burst
|
||
-- конкурентных вызовов не проскакивает потолок (TOCTOU-дисциплина).
|
||
CREATE TABLE IF NOT EXISTS spend (
|
||
book_id TEXT NOT NULL,
|
||
date TEXT NOT NULL, -- UTC YYYY-MM-DD
|
||
committed_usd REAL NOT NULL DEFAULT 0,
|
||
reserved_usd REAL NOT NULL DEFAULT 0,
|
||
PRIMARY KEY (book_id, date)
|
||
);
|
||
|
||
-- request_log: одна строка на LLM-вызов (Р7: per-книга/глава/чанк/стадия/
|
||
-- роль/модель, $, latency, cache-поля). Телеметрия, не источник денег —
|
||
-- деньги живут в spend/checkpoints.
|
||
CREATE TABLE IF NOT EXISTS request_log (
|
||
id INTEGER PRIMARY KEY,
|
||
ts TEXT NOT NULL DEFAULT (datetime('now')),
|
||
trace_id TEXT NOT NULL DEFAULT '',
|
||
book_id TEXT NOT NULL,
|
||
chapter INTEGER NOT NULL DEFAULT 0,
|
||
chunk_idx INTEGER NOT NULL DEFAULT 0,
|
||
stage TEXT NOT NULL DEFAULT '',
|
||
role TEXT NOT NULL DEFAULT '',
|
||
model_requested TEXT NOT NULL DEFAULT '',
|
||
model_actual TEXT NOT NULL DEFAULT '',
|
||
request_hash TEXT NOT NULL DEFAULT '',
|
||
prompt_tokens INTEGER NOT NULL DEFAULT 0,
|
||
cached_tokens INTEGER NOT NULL DEFAULT 0,
|
||
cache_creation_tokens INTEGER NOT NULL DEFAULT 0,
|
||
completion_tokens INTEGER NOT NULL DEFAULT 0,
|
||
reasoning_tokens INTEGER NOT NULL DEFAULT 0,
|
||
cost_usd REAL NOT NULL DEFAULT 0,
|
||
latency_ms INTEGER NOT NULL DEFAULT 0,
|
||
finish_reason TEXT NOT NULL DEFAULT '',
|
||
tm_hit INTEGER NOT NULL DEFAULT 0, -- ответ взят из чекпоинта, вызова не было
|
||
degraded TEXT NOT NULL DEFAULT '',
|
||
err TEXT NOT NULL DEFAULT '',
|
||
ok INTEGER NOT NULL DEFAULT 1
|
||
);
|
||
CREATE INDEX IF NOT EXISTS request_log_ts_idx ON request_log (ts);
|
||
`,
|
||
// v2: per-chunk×stage disposition (Веха 2, D2). Резолв ПОВЕРХ append-only
|
||
// checkpoints (keyed by request_hash-с-attempt) — не колонка на checkpoints:
|
||
// на resume строка пересобирается из чекпоинтов, поэтому её потеря на kill -9
|
||
// самолечится (classify по тексту чекпоинта, без ре-биллинга). jobs.status
|
||
// контентом НЕ расширяется — failed остаётся инфра-сбоем; плохой чанк живёт
|
||
// здесь как disposition, а цикл продолжается.
|
||
`
|
||
CREATE TABLE IF NOT EXISTS chunk_status (
|
||
book_id TEXT NOT NULL,
|
||
chapter INTEGER NOT NULL,
|
||
chunk_idx INTEGER NOT NULL,
|
||
stage TEXT NOT NULL,
|
||
snapshot_id TEXT NOT NULL, -- под каким снапшотом резолвнут (stale после --resnapshot игнорируется)
|
||
content_hash TEXT NOT NULL DEFAULT '',-- сигнатура отрендеренных msgs (исходник НЕ в снапшоте): правка src делает позиционную строку недействительной, а не подаёт устаревший перевод
|
||
disposition TEXT NOT NULL, -- ok | flagged | skipped
|
||
flag_reason TEXT NOT NULL DEFAULT '', -- '' когда ok; Go-константа FlagReason
|
||
attempts INTEGER NOT NULL DEFAULT 0,
|
||
final_hash TEXT NOT NULL DEFAULT '', -- request_hash авторитетного чекпоинта (ok-путь подаёт его текст дальше)
|
||
cost_usd REAL NOT NULL DEFAULT 0, -- сумма по ВСЕМ попыткам (F3-честно: ретраи учтены)
|
||
detail TEXT NOT NULL DEFAULT '',
|
||
updated_at TEXT NOT NULL DEFAULT (datetime('now')),
|
||
PRIMARY KEY (book_id, chapter, chunk_idx, stage)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS chunk_status_book_idx ON chunk_status (book_id, disposition);
|
||
`,
|
||
// v3: escalation flag on checkpoints (Веха 2.5, D12 single-hop). The fallback
|
||
// draft (a deterministic content-failure routed to another model ONCE) is tagged
|
||
// so the book's escalation.budget_usd can be enforced by summing ONLY escalation
|
||
// spend, independent of the primary translation cost. On the checkpoint (written
|
||
// in the same tx as the settle), NOT request_log, so the sum is durable across
|
||
// resume / kill -9 (telemetry is fire-and-forget; money-path budgeting is not).
|
||
`ALTER TABLE checkpoints ADD COLUMN escalation INTEGER NOT NULL DEFAULT 0;`,
|
||
// v4: ruby/furigana readings captured on ingest (шаг 3a, 04-unhappy §4 / D9). A
|
||
// ja epub's <ruby>base<rt>reading</rt></ruby> carries the AUTHOR's reading of a
|
||
// name/term; epub-v1 drops inline markup (02-mvp:25), which would silently kill
|
||
// this layer, so ingest EXTRACTS the readings into this table instead. It is NOT
|
||
// injected into any prompt (that is memory v2 + determinism-load-bearing) — this
|
||
// step only CAPTURES + PERSISTS; memory v2 (шаг 4) consumes it into a glossary
|
||
// name-lock (base→dst via reading, first_chapter→since_ch — D7 schema). PK
|
||
// (book_id, base, reading): the same name may carry several readings across a
|
||
// book (variant yomi), each a distinct row. first_chapter = the MIN chapter the
|
||
// pair appears in (a glossary "since"); occurrences = the pair's full-book count
|
||
// (a memory-v2 confidence signal). The persist is idempotent AND a full replace:
|
||
// ingest aggregates each (base,reading) once over the WHOLE book, and persistRuby
|
||
// DELETEs the book's set before re-inserting (store.ReplaceRubyReadings), so
|
||
// re-ingesting the same source re-derives identical rows and a source edit
|
||
// converges every column — including DROPPING a pair the edit removed (never a
|
||
// lingering phantom, never a MIN-pin/increment that drifts on resume).
|
||
`
|
||
CREATE TABLE IF NOT EXISTS ruby_readings (
|
||
book_id TEXT NOT NULL,
|
||
base TEXT NOT NULL, -- the ruby BODY: the kanji/base surface form
|
||
reading TEXT NOT NULL, -- the <rt> reading (furigana) captured for it
|
||
first_chapter INTEGER NOT NULL,-- 1-based full-book MIN chapter the pair appears in (glossary "since"; idempotent REPLACE)
|
||
occurrences INTEGER NOT NULL DEFAULT 0, -- full-book count (idempotent REPLACE, not increment)
|
||
created_at TEXT NOT NULL DEFAULT (datetime('now')),
|
||
PRIMARY KEY (book_id, base, reading)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS ruby_readings_book_idx ON ruby_readings (book_id);
|
||
`,
|
||
// v5: the memory bank v2 glossary (шаг 4, registry architecture/06 §Гейты + D7).
|
||
// The DETERMINISTIC substrate the hot-path matcher, the injection surface and the
|
||
// post-check are built on. Rows are the frozen-at-job-start injectable pool whose
|
||
// approved subset the F1 memoryVersion() hashes into the snapshot. Like ruby_readings
|
||
// this is "dumb storage" (aggregation/classification live in the pipeline); the
|
||
// pipeline REPLACES a book's whole glossary from its deterministic inputs (seed file
|
||
// + classified ruby), so re-seeding is idempotent and a seed edit converges every
|
||
// column. No cross-table FK (mirrors the ruby/chunkstatus dumb-storage style): both
|
||
// child tables are scoped by book_id and replaced in the same transaction, term_id is
|
||
// a logical link (glossary.id is a fresh autoincrement each replace and is NEVER hashed
|
||
// into memoryVersion — only content columns are, ORDER BY-stable).
|
||
`
|
||
CREATE TABLE IF NOT EXISTS glossary (
|
||
id INTEGER PRIMARY KEY,
|
||
book_id TEXT NOT NULL,
|
||
src TEXT NOT NULL, -- source key (raw; normalized in Go for matching, §3.6)
|
||
dst TEXT NOT NULL DEFAULT '', -- approved Russian translation (LEMMA/base form); '' for a ruby candidate with no dst yet
|
||
type TEXT NOT NULL DEFAULT '', -- name|term|title|… alias-graph node type (B3)
|
||
sense TEXT NOT NULL DEFAULT '', -- A3 polysemy disambiguator (part of the uniqueness key)
|
||
gender TEXT NOT NULL DEFAULT '', -- male|female|hidden|'' (C2; hidden = gender-avoidant rendering until reveal)
|
||
speech TEXT NOT NULL DEFAULT '', -- ты/вы register note (series-bible-lite; the transition JOURNAL is deferred)
|
||
decl TEXT NOT NULL DEFAULT '', -- JSON {"invariant":bool,"forms":[...]}: the dst declension forms the post-check accepts (E1/E2 safety, decl = grammaticality mechanism, not a market feature)
|
||
translit_policy TEXT NOT NULL DEFAULT '', -- B5 western-name-via-katakana (field only in v1; validator = Phase 2)
|
||
first_person TEXT NOT NULL DEFAULT '', -- D7 first_person field (field only)
|
||
nickname_translation TEXT NOT NULL DEFAULT '', -- D7 (keep in v1: a column + a "translate once" lock)
|
||
since_ch INTEGER NOT NULL DEFAULT 0, -- spoiler window start; 0 = valid from the beginning (C1 hard reject-gate below since_ch)
|
||
until_ch INTEGER NOT NULL DEFAULT 0, -- spoiler window end; 0 = no end (valid forever)
|
||
status TEXT NOT NULL DEFAULT 'auto',-- auto|draft|approved (term status machine; only approved is CONFIRMED-injected)
|
||
allow_short INTEGER NOT NULL DEFAULT 0, -- rare escape hatch: permit a below-min_key_len key (A3 single-key ban override)
|
||
source TEXT NOT NULL DEFAULT '', -- provenance: seed|ruby|auto (who created the row)
|
||
ruby_reading TEXT NOT NULL DEFAULT '', -- ruby-seeded rows: the furigana reading (bridge to Polivanov dst validation, B6 Phase 2 — NOT a dst)
|
||
ruby_class TEXT NOT NULL DEFAULT '', -- name|gloss|ambiguous (ruby classifier §8: phonetic-name → name-lock candidate, unrelated reading → gloss/footnote, else flag)
|
||
confidence INTEGER NOT NULL DEFAULT 0, -- ruby occurrences count = confidence prior (NOT a direct promotion to approved)
|
||
note TEXT NOT NULL DEFAULT '',
|
||
-- B2: at most one row per (source key, sense, spoiler window). since_ch/until_ch are
|
||
-- NOT NULL with default 0, so the SQLite "NULLs are distinct in UNIQUE" gotcha cannot
|
||
-- silently admit a duplicate. A term whose approved rendering changes across a spoiler
|
||
-- boundary is two rows with different windows (legitimately distinct), not a collision.
|
||
UNIQUE (book_id, src, sense, since_ch, until_ch)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS glossary_book_idx ON glossary (book_id, status);
|
||
|
||
CREATE TABLE IF NOT EXISTS glossary_aliases (
|
||
id INTEGER PRIMARY KEY,
|
||
book_id TEXT NOT NULL,
|
||
term_id INTEGER NOT NULL, -- logical link to glossary.id within the SAME replace tx (no hard FK — dumb storage, scoped+replaced by book_id)
|
||
alias TEXT NOT NULL, -- an alternative source surface (raw; normalized in Go for matching)
|
||
alias_type TEXT NOT NULL DEFAULT '', -- имя|цзы|хао|прозвище|титул (B3 alias-graph node type)
|
||
UNIQUE (book_id, term_id, alias)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS glossary_aliases_term_idx ON glossary_aliases (term_id);
|
||
CREATE INDEX IF NOT EXISTS glossary_aliases_book_idx ON glossary_aliases (book_id);
|
||
|
||
-- B1 editorial-time axis, ORTHOGONAL to the spoiler window (since_ch/until_ch is the
|
||
-- STORY timeline; this is the EDITORIAL timeline). Append-only journal of approved-dst
|
||
-- changes so a stale first-translation-wins rendering is DETECTABLE (DelTA PNR generates
|
||
-- stale/drift; this is the substrate that catches it). Not injected → not in any hash;
|
||
-- datetime('now') here is fine (telemetry, like request_log), never feeds memoryVersion.
|
||
CREATE TABLE IF NOT EXISTS glossary_revisions (
|
||
id INTEGER PRIMARY KEY,
|
||
book_id TEXT NOT NULL,
|
||
src TEXT NOT NULL,
|
||
sense TEXT NOT NULL DEFAULT '',
|
||
old_dst TEXT NOT NULL DEFAULT '',
|
||
new_dst TEXT NOT NULL,
|
||
editorial_ts TEXT NOT NULL DEFAULT (datetime('now')),
|
||
reason TEXT NOT NULL DEFAULT ''
|
||
);
|
||
CREATE INDEX IF NOT EXISTS glossary_revisions_book_idx ON glossary_revisions (book_id, src);
|
||
|
||
-- Per-chunk retrieval-state (registry gate #4 / A1/F2/G2/E1): observability of memory
|
||
-- degradation FROM DAY ONE — the mechanism that converts silent degradation into loud.
|
||
-- Recomputed deterministically each run (the matcher is $0), so it self-heals on resume;
|
||
-- NOT wire-load-bearing (it records what the injection did, it does not change the request).
|
||
CREATE TABLE IF NOT EXISTS retrieval_state (
|
||
book_id TEXT NOT NULL,
|
||
chapter INTEGER NOT NULL,
|
||
chunk_idx INTEGER NOT NULL,
|
||
snapshot_id TEXT NOT NULL,
|
||
n_exact_hits INTEGER NOT NULL DEFAULT 0, -- entries matched by an exact key/alias in this chunk
|
||
n_sticky INTEGER NOT NULL DEFAULT 0, -- entries carried by scene-inertia (A5), not re-matched here
|
||
n_ambiguous_flagged INTEGER NOT NULL DEFAULT 0, -- injected AMBIGUOUS (auto/draft) → "unverified" + forced post-check (A2)
|
||
n_spoiler_blocked INTEGER NOT NULL DEFAULT 0, -- matched but hard-rejected by the since_ch/until_ch window (C1)
|
||
n_evicted INTEGER NOT NULL DEFAULT 0, -- dropped by the token budget (F2 — logged, never silent)
|
||
embedding_tier_used INTEGER NOT NULL DEFAULT 0, -- always 0 in v1 (no embeddings on the hot path, Р3)
|
||
n_postcheck_miss INTEGER NOT NULL DEFAULT 0, -- E1 flags: a confirmed src matched but no accepted dst form is in the output
|
||
postcheck_detail TEXT NOT NULL DEFAULT '', -- JSON [{src,dst}] of the misses, for the report / human
|
||
injected_ids TEXT NOT NULL DEFAULT '', -- JSON of exact-matched entity keys (audit + sticky reconstruction)
|
||
updated_at TEXT NOT NULL DEFAULT (datetime('now')),
|
||
PRIMARY KEY (book_id, chapter, chunk_idx)
|
||
);
|
||
`,
|
||
// v6: surface single-hop escalation on the chunk_status RESOLVE (D15.3 status/redrive).
|
||
// The fallback fact lived only on the checkpoint (escalation flag, v3); folding it into
|
||
// chunk_status lets `tmctl status` project escalation-on-flagged-resume WITHOUT re-reading
|
||
// checkpoints (the deferred Milestone-2.5 finding #6 — the escalation column the status
|
||
// read-model needs). Derivable from checkpoints, so a lost/rebuilt row self-heals on the
|
||
// next resolve. escalation_model is the fallback that answered (empty when not escalated).
|
||
`
|
||
ALTER TABLE chunk_status ADD COLUMN escalated INTEGER NOT NULL DEFAULT 0;
|
||
ALTER TABLE chunk_status ADD COLUMN escalation_model TEXT NOT NULL DEFAULT '';
|
||
`,
|
||
}
|
||
|
||
// migrate runs all pending migrations on the write pool, one transaction per
|
||
// step, recording each in schema_version.
|
||
func (s *Store) migrate(ctx context.Context) error {
|
||
if _, err := s.w.ExecContext(ctx, `CREATE TABLE IF NOT EXISTS schema_version (version INTEGER PRIMARY KEY)`); err != nil {
|
||
return fmt.Errorf("store: schema_version: %w", err)
|
||
}
|
||
var current int
|
||
if err := s.w.QueryRowContext(ctx, `SELECT COALESCE(MAX(version), 0) FROM schema_version`).Scan(¤t); err != nil {
|
||
return fmt.Errorf("store: read version: %w", err)
|
||
}
|
||
for v := current; v < len(migrations); v++ {
|
||
tx, err := s.w.BeginTx(ctx, nil)
|
||
if err != nil {
|
||
return fmt.Errorf("store: begin migration %d: %w", v+1, err)
|
||
}
|
||
if _, err := tx.ExecContext(ctx, migrations[v]); err != nil {
|
||
_ = tx.Rollback()
|
||
return fmt.Errorf("store: apply migration %d: %w", v+1, err)
|
||
}
|
||
if _, err := tx.ExecContext(ctx, `INSERT INTO schema_version (version) VALUES (?)`, v+1); err != nil {
|
||
_ = tx.Rollback()
|
||
return fmt.Errorf("store: record migration %d: %w", v+1, err)
|
||
}
|
||
if err := tx.Commit(); err != nil {
|
||
return fmt.Errorf("store: commit migration %d: %w", v+1, err)
|
||
}
|
||
}
|
||
return nil
|
||
}
|