Implementation Plan: LLM Table Translation Service

Branch: 028-llm-datasource-supeset (актуальная: 032-translate-requests-httpx) | Date: 2026-05-08 (актуализация: 2026-06-07) | Spec: spec.md Input: Feature specification from /specs/028-llm-datasource-supeset/spec.md (updated 2026-05-14 with multi-language & correction optimization)

Summary

Implement an LLM-powered table translation service as a new backend plugin (TranslationPlugin) with companion API routes, ORM models, Pydantic schemas, and Svelte frontend components. The service reads rows from a Superset datasource (translation column + context columns), auto-detects source language per row via LLM, sends batches to a configured LLM provider for ALL target languages simultaneously (multi-target in single structured JSON response), with optional per-batch filtered multilingual terminology dictionary context (language-pair-aware). Generates safe PostgreSQL INSERT/UPSERT SQL, submits to Superset via /api/v1/sqllab/execute/ with status polling. Supporting capabilities: multilingual terminology dictionaries (source_language + target_language per entry), configurable preview (1-100 rows), inline correction from any run result with dictionary submission, bulk find-and-replace, scheduled execution via APScheduler (new-key-only with baseline_expired fallback), structured event logging with per-language MetricSnapshot persistence, RBAC-gated access control, and 90-day retention with metric continuity.

Total implemented: ~153 files, ~36 091 LOC across backend (Python/FastAPI) and frontend (Svelte 5/SvelteKit).
Actual complexity distribution: 2× C5, 6× C4, 12× C3, 7× C2, 4× C1.
Plugins: 59 source files (decomposed) + 13 routes + 1 model + 1 schema + 27 frontend source + 47 test files.

Technical Context

Language/Version: Python 3.13+ (backend), JavaScript/TypeScript (frontend Svelte 5)
Primary Dependencies: FastAPI 0.115+, SQLAlchemy 2.0+, APScheduler 3.x, Pydantic v2 (backend); SvelteKit 2.x, Svelte 5.43+, Vite 7.x, Tailwind CSS 3.x (frontend)
Storage: PostgreSQL 16 (shared with existing ss-tools schema)
Testing: pytest 8.x + pytest-asyncio (backend); vitest 4.x + @testing-library/svelte 5.x (frontend)
Target Platform: Linux server (Docker Compose: backend + frontend + PostgreSQL)
Project Type: web application — FastAPI REST + WebSocket backend, SvelteKit SPA frontend
Performance Goals: Preview of 10 rows within 30s (LLM-dependent); INSERT generation <5s for 1000 rows; schedule trigger precision ±60s; event recording <10s after occurrence
Constraints: RBAC enforcement via access-control matrix; dictionary per-batch filtering (case-insensitive, word-boundary-aware); 90-day detailed data retention with MetricSnapshot persistence; plugin lifecycle compatible with PluginBase; dialect-aware SQL generation (PostgreSQL/Greenplum, ClickHouse supported for MVP); snapshot isolation for in-progress runs; structured JSON LLM output required
Scale/Scope: Tens of thousands of rows per run; dictionaries of any size; 50 concurrent users; 5–10 active translation jobs per deployment

Constitution Check

GATE: Must pass before Phase 0 research. Re-check after Phase 1 design.

Principle	Status	Evidence
I. Plugin Architecture	✅ PASS	Feature implemented as a new plugin inheriting from `PluginBase` (`backend/src/plugins/translate/`), consistent with existing `llm_analysis`, `git`, `storage` plugin pattern.
II. API-First Design	✅ PASS	All operations exposed via REST endpoints under `/api/translate/` (jobs, dictionaries, runs, schedules, history) and WebSocket for run progress. Follows existing FastAPI route conventions.
III. Test-First	✅ PASS	Acceptance criteria per user story defined in spec; test strategy in research.md covers unit (pytest), integration (API + DB), and component (vitest + Svelte Testing Library) layers.
IV. RBAC & Security	✅ PASS	Granular permissions (`translate.job.`, `translate.dictionary.`, `translate.schedule.manage`, `translate.history.view`) via existing RBAC model. API keys encrypted via `EncryptionManager`. PII masking for LLM-facing context per existing patterns.
V. Observability & Retention	✅ PASS	Structured Translation Events (FR-046), per-job metrics (FR-047), notification integration (FR-048), 90-day retention with pruning (FR-049). C4+ flows instrumented with `belief_scope`/`reason`/`reflect`/`explore` markers.
Semantic Protocol Compliance	✅ PASS	All planned modules assigned `@COMPLEXITY` 1–5 with appropriate tag density per GRACE complexity scale (C1: anchor only, C2: +BRIEF, C3: +RELATION, C4: +PRE/POST/SIDE_EFFECT, C5: +DATA_CONTRACT/INVARIANT/RATIONALE/REJECTED). `@RATIONALE`/`@REJECTED` reserved for C5 contracts only. Canonical `@RELATION PREDICATE -> TARGET_ID` syntax. Anchor format: `#region`/`#endregion` for Python, `<!-- #region -->`/`<!-- #endregion -->` for Svelte markup.
Fractal Limit (INV_7)	✅ PASS	Planned modules kept under 400 lines each. No planned contract exceeds 150 lines or CC>10. Decomposition strategy documented in contracts/modules.md.

Gate Result: ✅ ALL PASS — no blocking constitutional or semantic conflicts.

Project Structure

Documentation (this feature)

specs/028-llm-datasource-supeset/
├── plan.md              # This file
├── research.md          # Phase 0 output
├── data-model.md        # Phase 1 output
├── quickstart.md        # Phase 1 output
├── contracts/           # Phase 1 output
│   └── modules.md       # Semantic contract design
├── spec.md              # Feature specification
├── ux_reference.md      # Interaction reference
└── checklists/
    └── requirements.md  # Quality validation

Source Code (repository root — ACTUAL as implemented)

backend/
├── src/
│   ├── api/routes/
│   │   └── translate/             # [ACTUAL] Пакет из 13 файлов (2 296 строк)
│   │       ├── __init__.py        # Инициализация, re-export router
│   │       ├── _router.py         # APIRouter(prefix="/api/translate")
│   │       ├── _job_routes.py     # Job CRUD (285 строк)
│   │       ├── _run_routes.py     # Run execution, cancel, inline edit (205 строк)
│   │       ├── _run_edit_routes.py # Run edit endpoints (200 строк) [NEW]
│   │       ├── _run_list_routes.py # Run list, detail, CSV (359 строк)
│   │       ├── _run_history_routes.py # Run history (133 строки) [NEW]
│   │       ├── _preview_routes.py  # Preview CRUD (194 строки)
│   │       ├── _dictionary_routes.py # Dictionary CRUD + import (391 строка)
│   │       ├── _correction_routes.py # Correction submission (100 строк)
│   │       ├── _schedule_routes.py   # Schedule CRUD (239 строк)
│   │       ├── _metrics_routes.py    # Metrics endpoints (65 строк)
│   │       └── _helpers.py           # Response helpers (70 строк)
│   ├── core/
│   │   ├── scheduler.py           # [REUSE] APScheduler
│   │   └── superset_client/       # [REUSE] Superset API client
│   ├── models/
│   │   └── translate.py           # [NEW] 15 ORM models (401 строка)
│   ├── plugins/
│   │   └── translate/             # [NEW] TranslationPlugin (59 файлов, декомпозирован)
│   │       ├── __init__.py        # Package (2 строки)
│   │       ├── plugin.py          # Plugin skeleton C2 (61 строка)
│   │       ├── orchestrator*.py   # Orchestrator C5 (14 файлов, 1 631 строка) ⭐
│   │       ├── executor*.py       # Executor/Batch/LLM C4 (9 файлов, 2 196 строк) ⭐
│   │       ├── preview*.py        # Preview engine C4 (11 файлов, 1 291 строка) ⭐
│   │       ├── dictionary*.py     # Dictionary CRUD C4 (7 файлов, 921 строка) ⭐
│   │       ├── service*.py        # Service layer C4 (6 файлов, 1 281 строка) ⭐
│   │       ├── scheduler.py       # Schedule management C4 (443 строки)
│   │       ├── sql_generator.py   # Dialect-aware SQL C3 (402 строки)
│   │       ├── superset_executor.py # Superset SQL Lab API C3 (439 строк)
│   │       ├── events.py          # Event log C5 (274 строки)
│   │       ├── metrics.py         # Metrics C3 (192 строки)
│   │       ├── prompt_builder.py  # Context-aware prompt C3 (153 строки)
│   │       ├── _token_budget.py   # Token estimation C2 (395 строк)
│   │       ├── _lang_detect.py    # Language detection C2 (207 строк) [NEW]
│   │       ├── _text_cleaner.py   # Text sanitization C1 (63 строки) [NEW]
│   │       └── _utils.py          # Utilities C1 (225 строк) [UPDATED]
│   │       └── __tests__/         # Plugin-level unit tests (27 файлов, 9 090 строк)
│   ├── schemas/
│   │   └── translate.py           # [NEW] 35+ Pydantic schemas (712 строк)
│   └── services/
│       ├── llm_provider.py        # [REUSE] LLM provider management
│       └── llm_prompt_templates.py # [REUSE] Prompt rendering
└── tests/                         # Integration tests (7 файлов, 2 458 строк)

frontend/
├── src/
│   ├── routes/
│   │   └── translate/             # [NEW] SvelteKit routes
│   │       ├── +page.svelte       # Job list (288 строк)
│   │       ├── [id]/
│   │       │   └── +page.svelte   # Job config + preview + run (269 строк)
│   │       ├── dictionaries/
│   │       │   ├── +page.svelte   # Dictionary list (247 строк)
│   │       │   └── [id]/
│   │       │       └── +page.svelte # Dictionary editor (202 строки)
│   │       └── history/
│   │           └── +page.svelte   # Run history (231 строка)
│   └── lib/
│       ├── components/
│       │   └── translate/         # [NEW] Translation components (14 файлов, 5 017 строк)
│       │       ├── TranslationPreview.svelte       # C4 (564 строки)
│       │       ├── TranslationRunResult.svelte     # C4 (618 строк)
│       │       ├── ConfigTabForm.svelte            # C3 (539 строк) [NEW]
│       │       ├── BulkReplaceModal.svelte         # C3 (438 строк)
│       │       ├── CorrectionCell.svelte           # C3 (343 строки)
│       │       ├── RunTabContent.svelte            # C3 (342 строки) [NEW]
│       │       ├── TermCorrectionPopup.svelte      # C3 (345 строк)
│       │       ├── TargetSchemaHint.svelte         # C2 (316 строк) [NEW]
│       │       ├── ScheduleConfig.svelte           # C3 (300 строк)
│       │       ├── BulkCorrectionSidebar.svelte    # C3 (288 строк)
│       │       ├── TranslationRunProgress.svelte   # C4 (277 строк)
│       │       ├── TargetTabForm.svelte            # C3 (224 строки) [NEW]
│       │       ├── TranslationRunGlobalIndicator.svelte # C2 (237 строк)
│       │       └── TranslationMetricsDashboard.svelte   # C2 (186 строк)
│       ├── stores/
│       │   └── translationRun.svelte.ts  # [NEW] rune store (370 строк)
│       └── api/
│           └── translate/              # [NEW] API client (8 файлов, 987 строк)
└── e2e/
    └── tests/
        └── translation.e2e.js     # [NEW] E2E тесты (142 строки)

Semantic Contract Guidance

All planned contracts follow GRACE-Poly v2.6 protocol with #region/#endregion anchors (or [DEF:...]/[/DEF:...] for backward compatibility in docs).
Python backend uses # #region/# #endregion comment-anchor syntax.
Svelte components use / in markup and // #region/// #endregion in script blocks.
Complexity assignments follow strict tag density per GRACE complexity scale (detailed in contracts/modules.md).
C4+ Python modules instrumented with belief_scope() + reason()/reflect()/explore() markers.
C5 contracts carry @RATIONALE and @REJECTED decision memory (C1-C4 MUST NOT have these tags).
@RELATION targets reference existing contracts where applicable (e.g., [LLMProviderService:Module], [SchedulerService:Class], [SupersetClient:Module], [NotificationService:Module]).

Complexity Tracking

No constitutional violations detected. UPDATED 2026-05-17: Complexity скорректирована по факту реализации.

Contract	Plan (C?)	Actual (C?)	Файл	Примечание
`TranslatePlugin:Module`	C3	C2	`plugin.py`	Только регистрация; execute() — NotImplementedError
`TranslationOrchestrator`	C5	C5 ✅	`orchestrator.py`	Stateful lifecycle, PRE/POST, multi-step coordination
`TranslationEventLog`	C5	C5 ✅	`events.py`	Immutable event log + retention + MetricSnapshot
`TranslationExecutor`	C4	C4 ✅	`executor.py`	Batch LLM, caching, parsing, retry
`TranslationPreview`	C4	C4 ✅	`preview.py`	Quality gate, approve/edit/reject
`DictionaryManager`	C4	C4 ✅	`dictionary.py`	CRUD + import + per-batch filtering
`TranslationScheduler`	C4	C4 ✅	`scheduler.py`	APScheduler integration
`TranslateJobService`	—	C4 [NEW]	`service.py`	Job CRUD + InlineCorrection + BulkReplace
`TranslateRoutes`	C3	C4 🔴	`translate/`	Пакет с 13 подмодулями
`SQLGenerator`	C4	C3 🟢	`sql_generator.py`	Pure function, нет I/O
`SupersetSqlLabExecutor`	—	C3 [NEW]	`superset_executor.py`	Superset SQL Lab API клиент
`ContextAwarePromptBuilder`	—	C3 [NEW]	`prompt_builder.py`	Jaccard similarity, priority
`InlineCorrectionService`	C4	C3 🟢	`service.py`	Context capture, origin tracking
`BulkFindReplaceService`	C4	C3 🟢	`service.py`	Regex, preview, atomic apply
`TranslationMetrics`	C3	C3 ✅	`metrics.py`	Metrics aggregation
`TranslationModels`	C2	C2 ✅	`models/translate.py`	15 ORM models
`TranslateSchemas`	C2	C2 ✅	`schemas/translate.py`	35+ Pydantic schemas (712 строк)
`TranslateApiClient`	C2	C2 ✅	`api/translate/` (пакет)	8-модульный API client
`translateStore`	C3	C3 ✅	`translationRun.svelte.ts`	Svelte 5 rune store (370 строк)
`TranslationLanguage`	C1	C1 ✅	`models/translate.py`	DTO
`TranslationRunLanguageStats`	C1	C1 ✅	`models/translate.py`	DTO
`CorrectionCell` (Svelte)	—	C3 [NEW]	`CorrectionCell.svelte`	Inline edit + submit
`BulkReplaceModal` (Svelte)	—	C3 [NEW]	`BulkReplaceModal.svelte`	Find & replace modal
`ConfigTabForm` (Svelte)	—	C3 [NEW]	`ConfigTabForm.svelte`	Config form
`RunTabContent` (Svelte)	—	C3 [NEW]	`RunTabContent.svelte`	Run tab
`TargetTabForm` (Svelte)	—	C3 [NEW]	`TargetTabForm.svelte`	Target tab
`TargetSchemaHint` (Svelte)	—	C2 [NEW]	`TargetSchemaHint.svelte`	Schema hint
Other Svelte components	C3	C3 ✅	—	Все 14 компонентов

16 KiB Raw Blame History Unescape Escape