LegacyHUB/AGENTS.md

AGENTS — LegacyHUB

Operating instructions for AI agents working inside this repository.

What this project is

LegacyHUB ingests legacy PDF archives at scale (~70k docs), runs OCR (OCRmyPDF/Tesseract), extracts structured content with Docling, indexes chunks into PostgreSQL + OpenSearch (BM25) + Qdrant (BGE-M3 dense), and serves a hybrid lexical + semantic search API (FastAPI) reranked by BGE.

It is one module of the TeamHUB Suite.

TeamHUB Platform standards (source of truth)

For correcting existing code and for all future development, treat the TeamHUB platform standards in C:\Users\manag\TeamHUB\TeamHUB-Platform as the target source of truth.

Before behavior-changing work, read the current working-tree version of these documents:

• docs/ARCHITECTURE.md
• docs/CONVENTIONS.md
• docs/INTER_MODULE_CONTRACT.md
• docs/submodules/README.md
• docs/submodules/02_MODULE_CONTRACT.md
• docs/submodules/03_INTEGRATION_STANDARDS.md
• docs/submodules/08_DECISIONS.md
• docs/submodules/09_ROLLOUT_AND_SSO.md
• docs/submodules/10_ASSET_AND_DOCUMENT_STANDARD.md
• docs/submodules/18_REPO_LAYOUT_STANDARD.md
• docs/submodules/plans/LegacyHUB.md

If local code, README, or runbook content conflicts with those platform standards, do not resolve the conflict silently. Surface the contradiction, then move LegacyHUB toward the platform standard with small verified changes. Current local behavior remains evidence; platform docs define the intended contract.

Immediate platform implications for this repo:

• LegacyHUB is the TeamHUB pattern-B reference service.
• New TeamHUB document integrations use POST /api/v1/knowledge-ingest with an approved AssetManifest; POST /api/v1/ingest/folder is only compatibility for local workflows.
• LegacyHUB builds projections/indexes. It must not become the owner of source files owned by other modules.
• Inter-module events go through dispatch as a participant; Celery+Redis remain internal processing only.
• User-facing access targets gateway/SSO trusted X-TeamHub-* headers, with API-key checks as service/defense-in-depth auth.
• OCR/Markdown/Search reuse should converge on a stateless shared core rather than duplicating or hard-coding LegacyHUB-specific names into other modules.
• File-structure work follows docs/structure-map.md: current app/, ingestion/, indexing and storage layers are mature compatibility shapes and should not be renamed without a scoped migration and focused checks.

Stack (canonical)

Layer	Tech
API	FastAPI, Pydantic v2, SQLAlchemy 2, Alembic
Workers	Celery + Redis
OCR	OCRmyPDF + Tesseract (rus+eng)
Extract	Docling
Store	PostgreSQL 16, MinIO, OpenSearch 2.x, Qdrant
ML	BAAI/bge-m3 (dense, 1024), bge-reranker-v2-m3
Frontend	React 18, TS 5, Vite 5, Tailwind, shadcn, TanStack Query, Zustand, Framer Motion, Recharts
Tests	pytest
CI	GitHub Actions

Entry points

• Backend API — app/main.py (uvicorn app.main:app)
• Celery worker — celery -A app.workers.celery_app worker
• CLI scripts — scripts/init_db.py, scripts/init_opensearch.py, scripts/init_qdrant.py, scripts/ingest_folder.py, scripts/reindex_document.py, scripts/smoke_test.py
• Frontend dev — cd frontend && npm run dev (port 5273)
• Docker — docker compose up -d --build (dev), docker compose -f docker-compose.yml -f docker-compose.prod.yml ... (prod)

Inventory

legacy-knowledge-indexer/
  app/
    api/             routers + Pydantic schemas
    db/              SQLAlchemy models + Alembic migrations
    indexing/        OpenSearch + Qdrant clients, embeddings, reranker, hybrid
    ingestion/       scanner, OCR, Docling, chunker, table/figure processors,
                     quality, pipeline
    storage/         MinIO client + key conventions + ensure_artifact helper
    utils/           hashing, text cleaning, language detection, pdf helpers
    workers/         Celery app + tasks
  scripts/           init / ingest / reindex / smoke CLIs
  tests/             pytest suite
  docker/Dockerfile  API + worker image (OCRmyPDF + tesseract-rus+eng)
  docker-compose.yml dev orchestration
  docker-compose.prod.yml  production overlay
  frontend/          React app — see frontend/README.md
  .github/workflows  CI gate (ruff + pytest + tsc + vite build + compose config)

Code discovery order

Bounded discovery order for this repo. Use the first available that returns a usable answer; mark the rest "not available" for the task.

1. Zoekt / code-index — primary local indexed search for broad source-code discovery, symbols, filenames, and routes. Run a bounded smoke check before relying on results.
2. ast-grep / sg — syntax-aware structural search.
3. Serena / LSP — semantic navigation and references when available.
4. rg / rg --files — reliable fallback for strings, configs, docs, scripts, route paths, hashes, generated files, or after recording an indexed-tool blocker.
5. Docling / extracted Markdown in MinIO — for content questions about ingested documents, not source code.

Index check and refresh:

codex-session-start -RepoRoot .
repo-index-build -RepoRoot . -Rebuild

If any indexer times out or returns stale results, capture the error and fall through. Do not retry the same failing indexer.

Module contracts (high level)

• app/ingestion/pipeline.py::process_document_id(document_id, run_id) — single document end-to-end. Idempotent. Returns {status, chunks, error?}.
• app/indexing/hybrid_search.py::run_search(SearchRequest) -> SearchResponse — the only public search entry. Lexical + semantic + reranker.
• app/storage/artifacts.py::ensure_artifact(...) — single source of truth for document_artifacts upsert. Used by scanner, pipeline, table_processor, figure_processor.
• app/storage/minio_client.py::MinioStorage — bucket bootstrap + retryable put/get. Never bypass for object IO.
• app/indexing/opensearch_client.py::ensure_index() / index_chunks() — chunk index lifecycle.
• app/indexing/qdrant_client.py::ensure_collection() / upsert_chunks() — vector index lifecycle.

Runtime vs legacy scope

Everything under app/ is runtime. scripts/ are operational tools. tests/ are non-runtime. There is no archived/legacy code yet.

Baseline checks

# Backend
python -m pip check
python -m compileall -q app scripts tests
python -m pytest tests/ -q
python scripts/report_module_sizes.py   # report-only size guardrail

# Frontend
cd frontend
npx tsc --noEmit
npm run lint
npm run build

# Docker
docker compose config --quiet

Operating rules for agents

• Inspect before changing. git status first.
• Small reviewable commits. One ownership boundary per commit.
• Do not delete files, routes, migrations, or env vars without evidence (see software-project-delivery-governance skill).
• Do not invent secret values. Use .env.example placeholders.
• Use ensure_artifact instead of re-implementing artifact upsert.
• Use existing UI primitives in frontend/src/components/ui/* before adding new ones.
• Never commit node_modules/, dist/, .env, data/input/*, data/work/*.
• Failures must be logged via processing_events (backend) or sonner toast (frontend) — not silenced.

Ownership

• Backend, ingestion, search — Vadim Malanov.
• Frontend, design system — Vadim Malanov.

Where to update what

• New behavior — update README.md.
• New repeated agent rule — update this file.
• New deployment / recovery step — update RUNBOOK.md.
• Cleanup findings — docs/cleanup-report.md (create on demand).

Внешняя связь (агенты)

• Nextcloud Talk: ~/.usms/talk-send.ps1 -File <utf8-файл> (room q4toq6w4).
• Telegram: ~/.usms/tg-send.ps1 -File <utf8-файл> [-Channel it] — общий движок teamhub-telegram-bridge (TeamHUB\Engines); env с токеном/chat id — ~/.usms-codex/telegram-<channel>-bot.env; значения секретов не печатать.
• Каждое внешнее сообщение подписывать: — AI-агент TeamHUB (Claude).
• Созвоны и встречи от имени агента не предлагать: агент в них не участвует.