From 67d8d4871bb788f351e191f60641debd205b6147 Mon Sep 17 00:00:00 2001 From: Jarca Date: Sat, 27 Jun 2026 10:40:06 +0900 Subject: [PATCH] feat: add ledger backup safety workflow confirm dcy-002 and add REQ/BAT evidence add ledger backup/status metadata workflow document restore as runbook/script-only guarded operation add synthetic DB backup/restore smoke tests --- .../design.md | 42 ++++ .../implementation.md | 62 +++++ .../index.md | 33 +++ .../planning.md | 34 +++ .../verification.md | 111 +++++++++ docs/batches/index.md | 1 + docs/data-model.md | 21 +- ...-ux-e2e-categorization-refund-workflows.md | 2 +- ...nal-safety-backup-restore-validation-db.md | 228 ++++++++++++++++++ docs/discovery/index.md | 1 + docs/interface-contract.md | 12 +- docs/runbooks/ledger-backup-restore.md | 100 ++++++++ docs/runtime-flows.md | 13 +- ...nal-safety-backup-restore-validation-db.md | 45 ++++ docs/srs/index.md | 5 +- jarca_ledger_mcp/server.py | 20 ++ jarca_ledger_mcp/service.py | 162 ++++++++++++- scripts/ledger_restore_smoke.py | 71 ++++++ tests/test_backup_workflow.py | 80 ++++++ 19 files changed, 1035 insertions(+), 8 deletions(-) create mode 100644 docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/design.md create mode 100644 docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/implementation.md create mode 100644 docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/index.md create mode 100644 docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/planning.md create mode 100644 docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/verification.md create mode 100644 docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md create mode 100644 docs/runbooks/ledger-backup-restore.md create mode 100644 docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md create mode 100644 scripts/ledger_restore_smoke.py create mode 100644 tests/test_backup_workflow.py diff --git a/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/design.md b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/design.md new file mode 100644 index 0000000..ce24487 --- /dev/null +++ b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/design.md @@ -0,0 +1,42 @@ +# BAT-002 Design + +## Architecture Summary +BAT-002 adds a small operational-safety layer around the existing SQLite ledger without changing transaction schemas. The service layer produces metadata-only DB evidence, creates backups with SQLite's online backup API, lists backup files, and validates one backup file. MCP exposes only non-destructive backup/status operations. Restore remains a repo script/runbook workflow requiring explicit user approval before overwriting a target DB. + +## Changed Areas +- `jarca_ledger_mcp/service.py` + - New constants: default backup directory and restore policy. + - New helpers: sha256, file metadata, read-only SQLite status, safe table counts, aggregate totals. + - New public functions: `get_ledger_db_status`, `create_ledger_backup`, `list_ledger_backups`, `get_ledger_backup_status`. +- `jarca_ledger_mcp/server.py` + - New additive MCP tools for backup/status/list/hash only. + - No restore MCP tool. +- `scripts/ledger_restore_smoke.py` + - Script-only restore smoke helper with explicit overwrite approval token. +- Docs/tests + - Synthetic tests and operational runbook/baseline docs. + +## Key Decisions +1. Backup creation uses SQLite online backup API rather than raw copy so WAL-mode DBs are copied consistently. +2. Backup evidence returns metadata only: path, size, mtime, sha256, integrity result, table row counts, and aggregate totals by cashflow kind. +3. Retention policy implements "recent 30 days OR recent 20 files" by pruning only files that are both older than the retention window and outside the newest count. +4. Restore is deliberately excluded from MCP. The script exists for fixture/validation DB restore smoke and requires `RESTORE_APPROVED` for overwriting any existing target. +5. Existing success response shapes are preserved; all new response fields are additive under new tools/functions. + +## Edge Cases +- Missing source DB: backup/status returns `not_found` rather than initializing or mutating a new DB. +- Empty backup directory: list returns success with zero backups. +- Invalid/corrupt backup: backup status includes integrity error metadata and restore smoke fails before copying. +- Existing target restore path: restore smoke fails unless `--allow-overwrite --approval-token RESTORE_APPROVED` are supplied. +- Sensitive row data: metadata collection never selects merchant, counterparty, account number, raw_payload, or raw financial file content. + +## Architecture Impact +- runtime-flows: updated with backup/status and restore-restricted operational flow. +- data-model: updated with backup artifact and evidence policy notes. +- interface-contract: updated with new MCP tools and explicit no-restore-MCP rule. + +## Reference Doc Update Plan +- Update `docs/runtime-flows.md` with operational backup/validation/restore-smoke flow and high-risk flow constraints. +- Update `docs/data-model.md` with backup artifact/evidence persistence boundary. +- Update `docs/interface-contract.md` with additive backup/status tools and restore non-exposure. +- Add `docs/runbooks/ledger-backup-restore.md`. diff --git a/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/implementation.md b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/implementation.md new file mode 100644 index 0000000..19b8d65 --- /dev/null +++ b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/implementation.md @@ -0,0 +1,62 @@ +# BAT-002 Implementation + +## Plan Summary +Implemented REQ-002 as a staged additive operational-safety change. No transaction schema migration, operating DB restore, or broad data rewrite was performed. + +## Changed Files +- `jarca_ledger_mcp/service.py` + - Added metadata-only DB status helpers. + - Added SQLite online backup creation with retention enforcement. + - Added backup list/status/hash functions. + - Added explicit restore policy metadata (`mcp_restore_exposed: false`). +- `jarca_ledger_mcp/server.py` + - Added MCP tools: `get_ledger_db_status`, `create_ledger_backup`, `list_ledger_backups`, `get_ledger_backup_status`. + - Did not add any restore MCP tool. +- `scripts/ledger_restore_smoke.py` + - Added script-only restore smoke helper with overwrite approval token. +- `tests/test_backup_workflow.py` + - Added synthetic DB tests for metadata-only status, backup create/list/status/hash, retention pruning, and sensitive evidence exclusion. +- `docs/runbooks/ledger-backup-restore.md` + - Added operator runbook and QC checklist. +- `docs/runtime-flows.md` + - Added operational backup/validation/restore smoke runtime flow. +- `docs/data-model.md` + - Added `LedgerBackupArtifact` and metadata-only persistence notes. +- `docs/interface-contract.md` + - Added backup/status MCP contract and restore non-exposure rule. +- StagePilot docs + - `docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md` + - `docs/srs/index.md` + - `docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md` + - `docs/batches/index.md` + - `docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/*` + +## Execution Log +- RED test first: + - Command: `source .venv/bin/activate && pytest tests/test_backup_workflow.py -q` + - Initial result: failed with missing `service.get_ledger_db_status`, `create_ledger_backup`, `list_ledger_backups`, `get_ledger_backup_status` attributes. +- Implemented service/server/script/docs changes. +- Targeted test: + - Command: `source .venv/bin/activate && pytest tests/test_backup_workflow.py -q` + - Result: `3 passed`. +- Full syntax/test: + - Command: `source .venv/bin/activate && python -m py_compile jarca_ledger_mcp/*.py dashboard/app.py && pytest tests/test_backup_workflow.py -q && pytest -q` + - Result: backup tests passed, full suite passed with `...........ss.........ss [100%]`. +- Full pytest summary: + - Command: `source .venv/bin/activate && pytest -ra` + - Result: `20 passed, 4 skipped in 16.02s`; skips are sample KB/Toss PDF tests without sample files/passwords. +- Restore smoke: + - Command: created synthetic tmp DB, created backup via `service.create_ledger_backup`, then ran `python scripts/ledger_restore_smoke.py --backup --target `. + - Result: `success: true`, backup and restored target `integrity_check: ok`, table counts `{accounts: 1, transactions: 1, budgets: 0, import_batches: 0, category_rules: 0, ledger_categories: 0}`, health check `active_transactions: 1`. +- MCP surface check: + - Command: `source .venv/bin/activate && hermes mcp test jarca-ledger` + - Result: connected, `Tools discovered: 45`, including backup/status tools and no restore tool. + +## Validation +- Synthetic DB tests confirmed no operating DB is needed for backup/status/list/hash verification. +- Restore smoke used `/tmp/...` source/target only, not `/root/.local/share/jarca/ledger.sqlite3`. +- Evidence captured only path, size, mtime, sha256, integrity, row counts, aggregate totals, and health/test results. + +## Remaining Risks +- Real operating DB restore remains intentionally untested and requires separate explicit user approval. +- Browser/UI copy is not changed in this batch; operator safety guidance is runbook/MCP/script level only. diff --git a/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/index.md b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/index.md new file mode 100644 index 0000000..bf784f6 --- /dev/null +++ b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/index.md @@ -0,0 +1,33 @@ +# BAT-002: 운영 안전 백업·복구·검증 DB 워크플로우 + +## Metadata +- BAT ID: BAT-002 +- Profile: standard +- Status: release-candidate +- Source Discovery: dcy-002 +- Included REQ: REQ-002 +- Created At (KST): 2026-06-27 10:17 +- Owner: 렛저장인 + +## Scope +- Add metadata-only DB status, backup create/list/status helpers. +- Expose backup/status/list/hash as additive MCP tools. +- Keep restore execution out of MCP and document script/runbook approval path. +- Verify with synthetic DB tests and safe restore smoke. +- Update runtime, data-model, and interface baseline docs. + +## Out of Scope +- 실제 운영 DB restore 실행. +- 원본 운영 DB 직접 mutation. +- 파괴적 SQLite migration 또는 대량 data rewrite. +- 신규 금융기관 parser, CI/CD 구축, 배포 서비스화. + +## Documents +- [planning.md](planning.md) +- [design.md](design.md) +- [implementation.md](implementation.md) +- [verification.md](verification.md) + +## Notes +- Restore is intentionally script/runbook only; no `restore_*` MCP tool should be added. +- Evidence must remain metadata-only and exclude merchant/counterparty full dumps, raw_payload, account numbers, passwords, and source financial files. diff --git a/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/planning.md b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/planning.md new file mode 100644 index 0000000..ed2e1b6 --- /dev/null +++ b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/planning.md @@ -0,0 +1,34 @@ +# BAT-002 Planning + +## Included REQ +- REQ-002: 운영 안전 백업·복구·검증 DB 워크플로우 + +## Delivery Plan +1. Add service helpers for non-sensitive DB status evidence and SQLite online backup creation. +2. Add additive MCP tools for backup creation, backup list, backup status/hash, and DB status. +3. Add a non-MCP restore smoke script requiring explicit approval for overwriting an existing target DB. +4. Add synthetic DB tests for status evidence, backup/list/status/hash, retention, and restore smoke policy. +5. Update runtime/data/interface docs and add a runbook. +6. Run targeted/full verification and request jarcaledgerqc QC gate. + +## Dependencies +- Existing SQLite initialization and additive migration behavior in `jarca_ledger_mcp/db.py`. +- Existing service response convention: `{"success": True, ...}` and `fail(...)` error shape. +- Synthetic pytest tmp DBs for safe evidence. + +## Design Gate +Design required: yes. + +Reason: this batch changes the MCP interface surface and runtime/data safety baseline, and must explicitly preserve restore non-exposure and sensitive evidence restrictions. + +## Milestones +- M1: REQ-002 Approved and BAT-002 scaffolded. +- M2: Backup/status/list/hash helpers and MCP tools implemented. +- M3: Restore smoke script and runbook documented without MCP restore surface. +- M4: Synthetic tests and docs evidence complete. +- M5: QC gate PASS/PASS_WITH_NOTES, then REQ-002 Implemented. + +## Risks +- Accidentally exposing restore as MCP would violate dcy-002 policy. +- SQLite WAL copy must be consistent; implementation should use SQLite online backup API rather than raw file copy for backup creation. +- Evidence must not serialize sensitive row-level details. diff --git a/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/verification.md b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/verification.md new file mode 100644 index 0000000..99310ab --- /dev/null +++ b/docs/batches/bat-002_20260627_operational-safety-backup-restore-validation-db/verification.md @@ -0,0 +1,111 @@ +# BAT-002 Verification + +## Verification Status +- Status: approved +- Ready for Release: true +- Verified At (KST): 2026-06-27 10:33 +- Verified By: 렛저장인 + +## Acceptance Mapping + +### REQ-002 AC1 +Backup creation must write timestamped SQLite files under `/root/.local/share/jarca/backups/ledger/` by default and return source/backup path, size, mtime, sha256, integrity, and table counts. + +Evidence: +- `service.create_ledger_backup` uses default `DEFAULT_LEDGER_BACKUP_DIR = ~/.local/share/jarca/backups/ledger` and returns `source_db`, `backup`, `retention`, and `restore_policy`. +- `tests/test_backup_workflow.py::test_create_list_and_status_ledger_backup_with_retention` verifies backup file creation, sha256 presence, `integrity_check == "ok"`, and source/backup table count equality on synthetic DB. + +Result: pass. + +### REQ-002 AC2 +Retention keeps recent 30 days or newest 20 backup files and reports pruned paths. + +Evidence: +- `_apply_backup_retention` prunes only backups that are both outside newest count and older than day cutoff. +- `tests/test_backup_workflow.py::test_backup_retention_keeps_recent_count_and_prunes_older_extras` verifies retention with synthetic old backup files and checks `pruned_paths` length. + +Result: pass. + +### REQ-002 AC3 +Backup list/status/hash is additive service/MCP surface and existing response shapes are preserved. + +Evidence: +- New service functions: `list_ledger_backups`, `get_ledger_backup_status`, `get_ledger_db_status`. +- New MCP tools are additive in `server.py`. +- `hermes mcp test jarca-ledger` result: connected, `Tools discovered: 45`, including `get_ledger_db_status`, `create_ledger_backup`, `list_ledger_backups`, `get_ledger_backup_status`. + +Result: pass. + +### REQ-002 AC4 +Restore execution is not MCP-exposed and is script/runbook only with explicit approval for overwrite. + +Evidence: +- `server.py` contains no restore MCP tool. +- `hermes mcp test jarca-ledger` discovered backup/status tools and no restore tool. +- `scripts/ledger_restore_smoke.py` requires `--allow-overwrite --approval-token RESTORE_APPROVED` before overwriting an existing target. +- `docs/runbooks/ledger-backup-restore.md` documents restore as script-only and warns not to target the live operating DB without explicit user approval. + +Result: pass. + +### REQ-002 AC5 +Validation uses synthetic fixture DB first; operating DB copy evidence is metadata-only if used. + +Evidence: +- All tests use pytest `tmp_path` synthetic SQLite DBs. +- Restore smoke command used `/tmp/.../fixture.sqlite3`, `/tmp/.../backups/...sqlite3`, and `/tmp/.../restored.sqlite3`. +- No operating DB copy was needed. + +Result: pass. + +### REQ-002 AC6 +Baseline docs reflect backup/status/list/hash/restore restrictions and sensitive evidence policy. + +Evidence: +- `docs/runtime-flows.md` adds operational backup/validation/restore smoke flow and restore non-MCP constraint. +- `docs/data-model.md` adds `LedgerBackupArtifact` and metadata-only evidence notes. +- `docs/interface-contract.md` adds backup/status tools and restore non-exposure compatibility rule. +- `docs/runbooks/ledger-backup-restore.md` lists allowed/forbidden evidence and QC checklist. + +Result: pass. + +### REQ-002 AC7 +Synthetic tests verify backup/status/list/hash/retention/restore smoke or health/status check without operating DB mutation. + +Evidence: +- Command: `source .venv/bin/activate && pytest -ra` +- Result: `20 passed, 4 skipped in 16.02s`. +- Command: synthetic restore smoke with `scripts/ledger_restore_smoke.py`. +- Result: `success: true`, backup/target `integrity_check: ok`, matching table counts, `health_check.success: true`. + +Result: pass. + +### REQ-002 AC8 +QC gate must verify operating DB mutation absence, restore MCP non-exposure, sensitive evidence absence, smoke evidence, tests/docs. + +Evidence: +- This verification document and runbook include QC checklist. +- `jarcaledgerqc` QC gate returned `PASS`. +- QC summary confirmed no operating DB restore/direct mutation, backup/status/list/hash policy compliance, no restore MCP tool, synthetic restore smoke success, no real sensitive evidence exposure, and tests/docs evidence. + +Result: pass. + +## Evidence Summary +- Syntax: `python -m py_compile jarca_ledger_mcp/*.py dashboard/app.py` -> exit 0. +- Targeted tests: `pytest tests/test_backup_workflow.py -q` -> `3 passed`. +- Full tests: `pytest -ra` -> implementer `20 passed, 4 skipped in 16.02s`; QC rerun `20 passed, 4 skipped in 14.14s`. +- Restore smoke: synthetic tmp DB restore -> `success: true`, `integrity_check: ok`, table counts `{accounts: 1, transactions: 1, budgets: 0, import_batches: 0, category_rules: 0, ledger_categories: 0}`. +- MCP surface: `hermes mcp test jarca-ledger` -> connected, `Tools discovered: 45`, backup/status tools present, no restore tool listed. + +## Sensitive Evidence Review +- No transaction row dumps, merchant/counterparty full dumps, account numbers, `raw_payload`, source financial files, or passwords were written into docs/tests/logs. +- Synthetic test data contains placeholder sentinel labels only and asserts those labels are not serialized in status evidence. + +## QC Gate Result +- Verdict: PASS +- Reviewer: jarcaledgerqc +- Reviewed At (KST): 2026-06-27 10:33 +- Summary: 검수관은 원본 운영 DB restore/direct mutation 없음, backup/status/list/hash 정책 정합성, restore MCP 비노출, synthetic restore smoke 성공, 민감정보 비노출, tests/docs evidence를 확인했다. +- Notes: 실제 backup MCP 호출은 운영 DB mutation을 피하기 위해 수행하지 않았고, service-level synthetic DB 테스트와 smoke로 대체 검증했다. 이는 비차단 참고사항이다. + +## Blocking Issues +- None. diff --git a/docs/batches/index.md b/docs/batches/index.md index 4fe964c..eefd844 100644 --- a/docs/batches/index.md +++ b/docs/batches/index.md @@ -9,3 +9,4 @@ | BAT ID | Profile | Status | Included REQ | Discovery | Folder | | --- | --- | --- | --- | --- | --- | | BAT-001 | batch-lite | release-candidate | REQ-001 | dcy-001 | [bat-001_20260626_category-rule-ops](bat-001_20260626_category-rule-ops/) | +| BAT-002 | standard | release-candidate | REQ-002 | dcy-002 | [bat-002_20260627_operational-safety-backup-restore-validation-db](bat-002_20260627_operational-safety-backup-restore-validation-db/) | diff --git a/docs/data-model.md b/docs/data-model.md index 9f9cc18..bea43f8 100644 --- a/docs/data-model.md +++ b/docs/data-model.md @@ -4,7 +4,7 @@ - Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml` - Status: draft - Owner: Jarca / project maintainer -- Last Updated (KST): 2026-06-26 22:24 +- Last Updated (KST): 2026-06-27 10:17 - Source Discovery / Batch: bootstrap-baseline ## Project Summary @@ -118,6 +118,22 @@ - Relationships: - Compared against Transaction aggregates by report functions. +## Entity: LedgerBackupArtifact +- Source of Truth: filesystem under `/root/.local/share/jarca/backups/ledger/` by default +- Purpose: Timestamped SQLite backup artifact used for operational recovery and validation smoke checks. +- Lifecycle: created -> listed/status-checked -> retained/pruned by policy -> optionally restored by script/runbook after approval +- Key Evidence Fields: + - `path` :: text :: backup file path outside repository + - `size_bytes` :: integer :: file size metadata + - `mtime` :: text :: filesystem modification time + - `sha256` :: text :: file checksum + - `integrity_check` :: text :: SQLite integrity result + - `table_counts` / `aggregate_totals` :: metadata-only validation evidence +- State Rules: + - Keep backups from the most recent 30 days or newest 20 files. + - Backup artifacts and validation DB copies must not be committed to git. + - Restore execution is not a persisted MCP operation and requires script/runbook approval controls. + ## Consistency Rules - Actual cashflow reports include only categories whose `cashflow_kind` represents actual income or expense according to report semantics. - Account movement summaries should be separate from actual household income/expense summaries. @@ -128,6 +144,8 @@ ## Persistence Notes - Schema changes should be additive/idempotent unless a destructive migration is explicitly approved and backed up. +- Operational backup/status evidence may include only path, size, mtime, checksum, integrity, row counts, and aggregate totals. +- Validation DB copies should live outside the repository and should be selected explicitly via `JARCA_LEDGER_DB_PATH` when used. - Passwords for encrypted imports are runtime-only inputs and are not part of the persisted model. - Raw payloads may contain sensitive financial evidence and should not be committed to git. @@ -138,3 +156,4 @@ ## Change Log - 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation. +- 2026-06-27 10:17 KST: BAT-002/REQ-002 기준으로 LedgerBackupArtifact와 metadata-only evidence 정책 추가. diff --git a/docs/discovery/dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md b/docs/discovery/dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md index 533cc80..db4c7c3 100644 --- a/docs/discovery/dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md +++ b/docs/discovery/dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md @@ -7,7 +7,7 @@ - 작성 시각(KST): 2026-06-26 22:38 - 마지막 갱신 시각(KST): 2026-06-26 23:31 - 대체됨: 없음 -- 후속 Discovery 참조: 없음 +- 후속 Discovery 참조: docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md - 생성된 REQ 참조: REQ-001 ([docs/srs/Interface/req-001_category-rule-ops.md](../srs/Interface/req-001_category-rule-ops.md)) # 1. 계획 상태 요약 diff --git a/docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md b/docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md new file mode 100644 index 0000000..cee4d73 --- /dev/null +++ b/docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md @@ -0,0 +1,228 @@ +# 0. 문서 상태 +이 문서의 현재 상태와 식별 정보를 기록한다. 문서 추적과 승인 흐름에 필요한 최소 메타데이터를 적는다. + +- 상태: confirmed +- 문서 ID: dcy-002_20260627_operational-safety-backup-restore-validation-db +- 이슈명: Jarca Ledger 운영 안전장치 및 백업·복구·검증 DB 워크플로우 정립 +- 작성 시각(KST): 2026-06-27 00:06 +- 마지막 갱신 시각(KST): 2026-06-27 10:17 +- 대체됨: 없음 +- 후속 Discovery 참조: 없음 +- 생성된 REQ 참조: REQ-002 (`docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md`) + +# 1. 계획 상태 요약 +현재 Discovery가 어떤 배경에서 작성되고 있는지, 연계 문서가 있는지, 지금 시점의 해석이 무엇인지 짧게 요약한다. + +- 연계 문서 현황: + - 관련 점수 파일: 미생성 + - 관련 TODO/메모: 없음 +- 해석: + - dcy-001의 BAT-001은 분류 규칙 운영 액션을 작은 단위로 안정화했고, 검증 과정에서 synthetic DB와 기본 DB mtime 확인을 대체 smoke evidence로 사용했다. + - 이번 Discovery는 이후 import, rollback, categorization, reconciliation 같은 위험 작업을 원본 운영 DB 훼손 없이 진행하기 위한 백업·복구·검증 DB 표준 워크플로우를 정의한다. + +# 2. 요구사항 판정 결과 +이번 요청이 기존 요구사항과 비교해 신규인지, 유사한지, 중복인지 판단하고 그 근거를 남긴다. + +- 판정: 신규 +- 근거 + - dcy-001은 Streamlit 운영 UX/E2E와 분류·환급 workflow 안정화가 중심이고, 백업/복구/검증 DB 운용 체계 자체를 독립 성공 기준으로 다루지 않는다. + - `docs/runtime-flows.md`, `docs/data-model.md`에는 destructive migration 회피와 백업 승인 필요성이 gap/constraint로만 기록되어 있어 별도 Discovery로 운영 안전장치를 추적하는 것이 명확하다. + +# 3. 문제점의 요약 +문제의 현재 상태, 기대 상태, 관련 이해관계자, 제약사항을 정리한다. Discovery의 핵심 맥락을 가장 먼저 이해할 수 있어야 한다. + +- 현재 상태 + - 기본 SQLite DB는 `~/.local/share/jarca/ledger.sqlite3`이며 `JARCA_LEDGER_DB_PATH`로 대체 가능하다. `db.py`는 DB path resolution과 schema initialization을 담당하지만, 운영 DB 백업/복구 workflow는 아직 명시적 기능이나 runbook으로 정리되어 있지 않다. + - Streamlit Import 화면에는 import batch rollback UI가 있고, service/server에는 import rollback 도구가 있지만, rollback 전후 백업 생성, 검증용 DB copy, 원본 DB 미변경 증거, restore smoke check가 일관된 acceptance criteria로 묶여 있지 않다. +- 기대 상태 + - 운영자는 import, rollback, 대량 categorization, reconciliation, schema 변경 전후에 표준화된 백업·검증 DB 절차를 따라 원본 운영 DB 훼손 위험을 낮출 수 있다. + - 렛저장인과 검수관은 REQ/BAT 수행 시 어떤 DB를 사용했는지, 원본 DB를 직접 건드리지 않았는지, 복구 가능한 백업이 있는지, smoke check가 통과했는지를 동일한 evidence 형식으로 검증할 수 있다. +- 이해관계자 + - Jarca Ledger 운영자: 실제 가계부 운영 DB를 안전하게 유지해야 하는 사용자 + - Jarca/Hermes Agent: DB 변경 작업과 검증을 보조하고 승인/중단 기준을 판단하는 자동화 주체 + - 렛저장인/검수관: 구현과 verification gate를 분담하는 profile subagents + - 프로젝트 유지보수자: SQLite schema, service layer, Streamlit UI, 운영 문서를 유지하는 개발 주체 +- 제약사항 + - 실제 금융 DB, 원본 PDF/XLS/XLSX/CSV, 비밀번호, 전체 계좌식별정보는 테스트·문서·커밋에 노출하지 않는다. + - 파괴적 SQLite migration, 원본 운영 DB 직접 mutation, 대량 data rewrite는 사용자 명시 승인 없이는 진행하지 않는다. + +## 주요 사용자 시나리오 +사용자 또는 운영자가 실제로 어떤 상황에서 이 변경을 필요로 하는지 대표 시나리오를 적는다. + +- 운영자가 새 KB/Toss/SeoulPay 자료를 import하기 전에 운영 DB 백업을 만들고, 검증 DB copy에서 preview/import/rollback smoke를 먼저 실행한다. +- 운영자가 분류 규칙 apply나 확인필요 큐 정리처럼 여러 거래를 바꿀 수 있는 작업을 하기 전에 원본 DB hash/mtime/row count를 기록하고, 변경 후 보고서와 DB 상태를 비교한다. +- 렛저장인이 batch 구현을 완료하면 검수관이 backup 존재 여부, 검증 DB 사용 여부, 원본 DB 미변경 증거, restore/health check 결과를 확인한 뒤 PASS/BLOCKED를 판단한다. + +# 4. 이번에 정의할 변경 +이번 Discovery에서 다루는 핵심 변경 항목을 목록으로 적는다. 기능, 구조, 규칙 변경을 함께 포함해도 된다. + +- 운영 DB 변경 전 백업 생성, 검증 DB copy 생성, 복구 절차, smoke check를 하나의 표준 workflow로 정의한다. +- import, rollback, categorization, reconciliation, migration 같은 위험 작업의 사전/사후 체크리스트와 검수관 evidence 기준을 정의한다. +- `docs/runtime-flows.md`, `docs/data-model.md`, 필요 시 별도 runbook 또는 utility script를 갱신해 운영자가 재현 가능한 명령 단위 절차를 갖도록 한다. + +## 영향 범위 +변경이 미칠 코드/문서/운영 범위를 명시해 REQ 정제와 batch planning에서 추정 누락을 줄인다. + +- 코드 영향: + - `jarca_ledger_mcp/db.py`: 필요 시 백업/복사/검증 DB 경로 helper 또는 안전 검사 helper 추가 후보. + - `jarca_ledger_mcp/service.py` / `server.py`: 필요 시 백업/health/smoke 관련 additive tool 또는 service function 추가 후보. + - `dashboard/app.py`: 필요 시 운영 DB 위험 작업 전 안내, 검증 DB 사용 안내, import/rollback 전 안전 상태 표시 추가 후보. + - `scripts/` 또는 `tests/`: 백업/복구/검증 DB smoke를 재현하는 utility와 regression 추가 후보. +- 문서 영향: + - `docs/runtime-flows.md`: 운영 DB 백업·복구·검증 DB workflow와 위험 작업 flow constraint 갱신. + - `docs/data-model.md`: SQLite persistence/backup/restore policy와 destructive migration 승인 조건 갱신. + - `docs/interface-contract.md`: 새 MCP tool 또는 dashboard action이 생길 경우 additive interface contract 갱신. + - 후속 REQ/BAT 문서: backup, DB copy, restore smoke, QC evidence acceptance criteria 기록. +- 운영 영향: + - 실제 운영 DB를 대상으로 하는 작업은 백업 또는 검증 DB copy 확인 후 진행한다. + - 검수관은 batch verification에서 원본 DB 직접 mutation 여부와 복구 가능성을 evidence로 확인한다. + +# 5. 요구사항 목록 +실제로 구현과 검증으로 이어질 요구사항을 기능/비기능으로 나누어 정리하고, 범위 경계를 명확히 적는다. + +## 기능 요구사항 +- FR-1: 운영 DB 변경 전 timestamped backup을 생성하고, 생성 경로·파일 크기·hash 또는 mtime 같은 식별 정보를 evidence로 남길 수 있어야 한다. +- FR-2: 검증용 DB copy 또는 synthetic fixture DB를 생성/선택하는 절차가 있어야 하며, Streamlit/MCP/pytest 검증이 해당 DB를 사용했음을 확인할 수 있어야 한다. +- FR-3: backup에서 restore하는 절차와 restore 후 `ledger_health_check` 또는 동등한 smoke check를 정의해야 한다. +- FR-4: import, rollback, categorization apply, reconciliation, migration 전후에 사용할 안전 체크리스트와 검수관 gate evidence 형식을 정의해야 한다. +- FR-5: 이번 Discovery가 확정하는 운영 flow는 `docs/runtime-flows.md`와 필요 시 `docs/data-model.md`에 반영되어야 한다. + +## 비기능 요구사항 +성능, 운영성, 일관성, 자동화 안정성 등 기능 외 요구사항을 적는다. + +- NFR-1: 원본 운영 DB 직접 mutation은 기본 금지이며, 불가피한 경우 사용자 명시 승인과 백업 evidence가 필요하다. +- NFR-2: 백업/검증/복구 절차는 민감정보를 노출하지 않는 방식으로 문서화되어야 하며, 원본 금융 파일·비밀번호·전체 계좌식별정보를 커밋하지 않는다. +- NFR-3: 기존 MCP tool 성공 응답 shape와 `cashflow_kind` 의미론은 보존하고, 새 도구나 응답 필드는 additive 방식으로 설계한다. +- NFR-4: 절차는 렛저장인과 검수관이 자동화 또는 반자동으로 반복 실행할 수 있을 만큼 명령어 단위로 재현 가능해야 한다. + +## 범위 경계 +이번 반복에서 반드시 포함할 범위와 명시적으로 제외할 범위를 구분한다. + +- In Scope + - 운영 DB 백업 생성 정책, 검증 DB copy/synthetic fixture 정책, restore smoke check 정의. + - 위험 작업 전후 체크리스트와 검수관 QC evidence 기준 정의. + - 필요한 경우 작은 additive helper/script/tool 및 문서 갱신. + - dcy-001 후속 batch에서 사용할 수 있는 DB safety verification pattern 정립. +- Out of Scope + - 신규 금융기관 parser 추가. + - 파괴적 SQLite schema migration 또는 대량 데이터 rewrite 실행. + - CI/CD 전체 구축과 배포 서비스화. + - 원본 금융 파일 보관 정책 전체와 장기 암호화 저장소 설계. + - 운영 DB의 실제 복구 실행. 실제 복구는 별도 사용자 승인 후 수행한다. + +# 6. 리스크/가정 목록 +불확실성과 전제 조건을 분리해서 적는다. 리스크는 영향과 완화 방안을, 가정은 현재 판단의 전제를 기록한다. + +## 리스크 +- R-1 (High): 백업/복구 절차 자체가 잘못 설계되면 운영 DB 손상 시 복구할 수 없거나 잘못된 DB를 복구할 수 있다. + - 완화 방안: synthetic fixture 또는 운영 DB copy에서 먼저 backup/restore smoke를 검증하고, 원본 DB restore는 사용자 승인 전까지 실행하지 않는다. +- R-2 (High): 검증 과정에서 실수로 기본 운영 DB를 대상으로 import, rollback, apply 작업을 실행할 수 있다. + - 완화 방안: `JARCA_LEDGER_DB_PATH` 명시, DB path evidence, 원본 DB mtime/hash/row count 확인, 검수관 gate를 acceptance criteria에 포함한다. +- R-3 (Medium): 백업 파일이나 검증 DB copy에 민감 금융정보가 포함되어 커밋 또는 로그에 노출될 수 있다. + - 완화 방안: 백업/DB copy는 git ignored 경로에 두고, 보고서에는 파일 경로·크기·hash 등 최소 메타데이터만 남긴다. + +## 가정 +아직 확정되지 않았지만 현재 문서 작성의 기반이 되는 전제를 적는다. + +- A-1: Jarca Ledger는 현재 로컬 SQLite 중심 운영이며, 기본 운영 DB는 `/root/.local/share/jarca/ledger.sqlite3`이다. +- A-2: 운영 안전장치는 먼저 문서/스크립트/작은 additive helper 중심으로 구현하며, 파괴적 migration framework는 이번 범위에서 제외한다. +- A-3: 검수관은 실제 browser evidence가 불가능할 때도 AppTest, HTTP 200, service/DB smoke, hash/mtime evidence 같은 대체 증거를 평가할 수 있다. + +## 오픈 질문 +답을 아직 모르는 항목을 적는다. 추정으로 덮지 말고 REQ 초안 작성 이전에 확인할 질문으로 남긴다. + +- OQ-1: 운영 DB backup 파일의 기본 보관 위치와 보관 기간을 어디로 둘지 결정해야 한다. + - 상태: Answered + - 처리 방안: 기본 백업 위치는 `/root/.local/share/jarca/backups/ledger/`, 보관 정책은 최근 30일 또는 최근 20개 백업 유지로 확정한다. + - 종료 조건: REQ acceptance criteria 또는 runbook에 해당 위치와 retention 정책을 반영한다. +- OQ-2: 백업/복구 기능을 MCP tool로 노출할지, 로컬 script/runbook으로만 둘지 결정해야 한다. + - 상태: Answered + - 처리 방안: 혼합 방식으로 확정한다. Backup 생성과 backup 목록/status/hash 확인은 MCP tool 또는 script를 허용하되, restore 실행은 MCP tool로 노출하지 않고 script/runbook과 사용자 명시 승인으로 제한한다. + - 종료 조건: 후속 REQ 범위에 backup/status 노출과 restore 비노출 원칙을 명시한다. +- OQ-3: 운영 DB copy를 사용하는 검증에서 어떤 수준의 masking 또는 hash-only 보고를 요구할지 결정해야 한다. + - 상태: Answered + - 처리 방안: 검증 보고에는 DB 파일 경로, 파일 크기, mtime, sha256/checksum, 주요 table row count, category/report aggregate total, 테스트/health check 결과만 허용한다. 거래 원문, merchant/counterparty 전체 dump, 계좌번호, raw_payload, 원본 금융 파일 내용은 금지한다. + - 종료 조건: 후속 REQ 또는 verification template에 hash/mtime/row count/aggregate 중심 evidence 정책을 반영한다. + +### 오픈 질문 처리 기준 +- `Open`: 아직 답이 없고 다음 단계 진행에 영향이 있는 상태다. 문서에 유지한다. +- `Answered`: 답이 확정된 상태다. 관련 본문/요구사항에 반영한 뒤 오픈 질문 목록에서는 제거하거나 resolved 기록으로 이동한다. +- `Deferred`: 지금 단계에서 결정하지 않고 다음 단계 또는 후속 이슈로 넘기는 상태다. 넘길 대상과 이유를 반드시 적는다. +- `Dropped`: 더 이상 유효하지 않은 질문이다. 삭제 사유를 짧게 남기고 목록에서 제거한다. +- 처리 원칙 1: 질문만 남기지 말고 반드시 `상태`, `처리 방안`, `종료 조건`을 함께 적는다. +- 처리 원칙 2: 답이 나온 질문은 본문 반영 없이 단순 삭제하지 않는다. 반영 위치를 먼저 갱신한다. +- 처리 원칙 3: High 영향 질문은 `Deferred` 처리 후 처리 방안에 REQ 인계 추적 방식을 명시한다. + +# 7. 초기 성공 기준 +이 변경이 성공했다고 판단할 기준을 측정 가능하게 정의한다. 가능하면 데이터 출처까지 연결한다. + +- S-1: 운영 DB 백업 생성과 검증 DB copy 생성 절차가 명령어 또는 함수 단위로 재현 가능하고, 원본 DB를 직접 변경하지 않았다는 evidence를 남길 수 있다. +- S-2: backup restore 절차와 restore 후 health/smoke check가 synthetic fixture 또는 DB copy에서 성공한다. +- S-3: import, rollback, categorization apply, reconciliation, migration에 대한 위험 작업 체크리스트가 후속 REQ/BAT와 검수관 gate에서 사용할 수 있는 형식으로 정리된다. +- S-4: `docs/runtime-flows.md`와 필요 시 `docs/data-model.md`가 운영 안전장치 flow를 반영한다. + +## 측정 방식 및 데이터 출처 +각 성공 기준을 어떻게 측정할지와 어떤 데이터나 문서를 근거로 쓸지 적는다. + +- S-1 측정 방식: backup/copy command 실행 결과, 파일 존재·크기·hash/mtime, 원본 DB mtime/hash 비교 / 데이터 출처: synthetic fixture DB 또는 운영 DB copy metadata +- S-2 측정 방식: restore 후 `ledger_health_check`, sqlite integrity check, pytest 또는 service smoke 결과 확인 / 데이터 출처: 복구된 검증 DB와 command output +- S-3 측정 방식: 후속 REQ acceptance criteria와 BAT verification checklist에 위험 작업 evidence 항목 존재 여부 확인 / 데이터 출처: `docs/srs/`, `docs/batches/`, 검수관 gate report +- S-4 측정 방식: baseline 문서 diff와 change log 확인 / 데이터 출처: `docs/runtime-flows.md`, `docs/data-model.md`, 필요 시 `docs/interface-contract.md` + +# 8. REQ로 넘기기 전 확인 체크 +REQ 초안 작성 단계로 넘기기 전에 무엇이 확정되어야 하는지 확인한다. 미완료 항목은 후속 결정이 필요함을 뜻한다. + +- [x] 범위(In Scope/Out of Scope) 확정 + - 기준: 운영 안전장치/백업/복구/검증 DB에 집중하고 신규 parser, CI/CD, 배포 서비스화, 파괴적 migration은 제외하는지 확인한다. +- [x] 성공 지표의 측정 방식/데이터 출처 확정 + - 기준: synthetic fixture 또는 DB copy 기반의 backup/copy/restore/smoke evidence 방식이 충분한지 확인한다. +- [x] High 영향 리스크 우선순위 및 해소 책임자 지정 + - 기준: 원본 운영 DB mutation과 잘못된 restore 리스크에 대해 자르카/렛저장인/검수관의 책임 경계를 지정한다. +- [x] 모든 오픈 질문(OQ) `Open` 상태 없음 확인 + - 기준: OQ 목록에 `Open` 상태 항목이 0개이거나, 잔여 항목 전부 `Deferred` 처리 완료 +- [x] Freeze 확정 담당자(CONFIRMED_BY) 지정 + - 기준: 사용자가 Discovery 내용을 확인하고 REQ draft 진행 가능 여부를 명시한다. + +# 9. 파일 처리 결과 +이 Discovery 문서 생성/갱신 결과와 참조 문서를 기록한다. 이후 추적과 리뷰 시 근거로 사용한다. + +- 처리 결과: 생성 +- 생성 경로: docs/discovery/dcy-002_20260627_operational-safety-backup-restore-validation-db.md +- 참조 문서: + - docs/discovery/dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md + - docs/runtime-flows.md + - docs/data-model.md + - docs/interface-contract.md + - docs/batches/bat-001_20260626_category-rule-ops/verification.md + +# 10. 사용자 결정 필요 항목 요약 +사용자나 승인자가 결정해야 하는 항목만 모아 정리한다. 결정, 확인, 데이터 요청을 구분해서 적는다. + +## DECIDE +- 운영 DB backup 기본 저장 위치는 `/root/.local/share/jarca/backups/ledger/`, 보관 정책은 최근 30일 또는 최근 20개 백업 유지로 확정한다. +- 백업/복구 인터페이스는 혼합 방식으로 확정한다. Backup 생성과 목록/status/hash 확인은 MCP tool 또는 script를 허용하고, restore 실행은 MCP tool로 노출하지 않으며 script/runbook과 사용자 명시 승인으로 제한한다. +- 운영 DB copy 검증 보고에는 파일 경로, 크기, mtime, checksum, 주요 table row count, category/report aggregate, 테스트/health check 결과만 허용하고 거래 상세·계좌번호·raw_payload·원본 금융 파일 내용은 금지한다. + +## CONFIRM +- 이번 Discovery는 운영 안전장치·백업·복구·검증 DB workflow로 한정하고 신규 parser, CI/CD, 배포 서비스화, 파괴적 migration은 제외하는 것으로 확정한다. +- 사용자 승인에 따라 REQ draft로 넘긴다. + +## DATA +- 1차 검증은 synthetic fixture DB를 우선 사용하고, 필요 시 운영 DB copy를 repo 밖 임시/백업 디렉터리에 생성해 사용한다. 운영 DB copy evidence는 hash, mtime, row count, aggregate만 기록한다. + +# 11. Discovery Freeze +REQ 초안 작성 인계 시점의 확정 플래그와 섹션 참조만 기록한다. 내용 재작성 없이 원본 섹션을 링크로 대신한다. + +## 섹션 참조 +- 범위: [# 5. 요구사항 목록 > 범위 경계](#5-요구사항-목록) +- 리스크/오픈 질문: [# 6. 리스크/가정 목록](#6-리스크가정-목록) +- 성공 기준: [# 7. 초기 성공 기준](#7-초기-성공-기준) +- 인계 전 확인: [# 8. REQ로 넘기기 전 확인 체크](#8-req로-넘기기-전-확인-체크) +- 사용자 결정 필요: [# 10. 사용자 결정 필요 항목 요약](#10-사용자-결정-필요-항목-요약) + +## Freeze 플래그 +- Handoff Decision: 승인 +- Handoff Rationale: 사용자 승인으로 백업 위치/보관 기간, 백업·복구 인터페이스 수준, 검증 DB evidence 수준, 범위 경계가 확정되었으므로 REQ 초안 작성으로 넘긴다. +- Ready for REQ Drafting: true +- Confirmed By: 사용자 + Jarca +- Confirmed At (KST): 2026-06-27 10:12 diff --git a/docs/discovery/index.md b/docs/discovery/index.md index b7c390e..afc3ee1 100644 --- a/docs/discovery/index.md +++ b/docs/discovery/index.md @@ -7,3 +7,4 @@ | ID | 날짜 | 이슈명 | 문서 | 상태 | |---|---|---|---|---| | dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows | 20260626 | Streamlit 운영 UX/E2E 검증 및 분류·환급 워크플로우 안정화 | [Discovery](./dcy-001_20260626_streamlit-ux-e2e-categorization-refund-workflows.md) | approved | +| dcy-002_20260627_operational-safety-backup-restore-validation-db | 20260627 | Jarca Ledger 운영 안전장치 및 백업·복구·검증 DB 워크플로우 정립 | [Discovery](./dcy-002_20260627_operational-safety-backup-restore-validation-db.md) | confirmed | diff --git a/docs/interface-contract.md b/docs/interface-contract.md index 7b5f41b..9809ee6 100644 --- a/docs/interface-contract.md +++ b/docs/interface-contract.md @@ -4,7 +4,7 @@ - Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml` - Status: draft - Owner: Jarca / project maintainer -- Last Updated (KST): 2026-06-26 22:24 +- Last Updated (KST): 2026-06-27 10:17 - Source Discovery / Batch: bootstrap-baseline ## Project Summary @@ -21,7 +21,8 @@ - Stability: internal but should preserve existing success response shapes for compatibility. ### Representative Tool Groups -- Health: `ledger_health_check` +- Health: `ledger_health_check`, `get_ledger_db_status` +- Operational backup: `create_ledger_backup`, `list_ledger_backups`, `get_ledger_backup_status` (restore is intentionally not exposed as MCP) - Accounts: `create_ledger_account`, `list_ledger_accounts` - Transactions: `create_ledger_transaction`, `list_ledger_transactions`, `update_ledger_transaction`, `delete_ledger_transaction` - Budgets/reports: `create_ledger_budget`, `list_ledger_budgets`, monthly/category/fixed/budget/investable reports @@ -36,6 +37,7 @@ ### Outputs - Python dictionary payloads containing success data, counts, records, previews, reports, or error details. +- Backup/status tools return metadata-only DB evidence: path, size, mtime, sha256, integrity check, table row counts, and aggregate totals. - Existing success shape compatibility is preferred; new fields should be additive where possible. ### Errors @@ -46,7 +48,8 @@ ### Compatibility Rules - Preserve existing success response shapes unless a migration/REQ explicitly approves a breaking change. -- Do not write secrets or raw passwords into persistent output, skill files, or committed documentation. +- Additive backup/status/list/hash tools are allowed; restore execution must not be added as an MCP tool. +- Do not write secrets, raw passwords, raw_payload, full merchant/counterparty dumps, or full account identifiers into persistent output, skill files, or committed documentation. - Source evidence should remain auditable through raw fields and import batch records. ## Interface: Streamlit Dashboard @@ -90,6 +93,8 @@ - All import flows should support preview before mutation where implemented. - Dedupe should use deterministic source/external IDs or same-account/date/type/amount/merchant evidence. - Import batch metadata should support rollback and audit. +- Broad mutation workflows should capture metadata-only DB status and backup evidence before/after risky operations. +- Restore execution is limited to script/runbook workflows and explicit approval, not MCP tools. - Financial data and passwords are sensitive runtime inputs and should not be committed. ## Current Gaps / Planned Changes @@ -99,3 +104,4 @@ ## Change Log - 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation. +- 2026-06-27 10:17 KST: BAT-002/REQ-002 기준으로 backup/status/list/hash MCP contract와 restore 비노출 정책 추가. diff --git a/docs/runbooks/ledger-backup-restore.md b/docs/runbooks/ledger-backup-restore.md new file mode 100644 index 0000000..bcfa9c2 --- /dev/null +++ b/docs/runbooks/ledger-backup-restore.md @@ -0,0 +1,100 @@ +# Ledger Backup / Restore / Validation DB Runbook + +## Purpose +This runbook defines the approved operational safety workflow from dcy-002 / REQ-002. It is designed for Jarca Ledger local SQLite operation and for Hermes agents working under `jarcaledgerdev`/QC profiles. + +## Policy Summary +- Default backup directory: `/root/.local/share/jarca/backups/ledger/` +- Retention: keep backups from the most recent 30 days OR the newest 20 backup files. +- Backup creation/list/status/hash may be exposed as additive MCP tools or scripts. +- Restore execution must not be exposed as an MCP tool. +- Restore execution requires script/runbook use and explicit user approval before touching a real operating DB. +- Preferred validation DB: synthetic fixture DB. If an operating DB copy is needed, keep it outside the repository and report only metadata evidence. + +## Allowed Evidence +- DB path +- File size +- mtime +- sha256/checksum +- SQLite `PRAGMA integrity_check` result +- Major table row counts +- Category/report aggregate totals +- Test, health check, or smoke command result + +## Forbidden Evidence +- Full transaction row dumps +- Full merchant/counterparty dumps +- Full account identifiers/account numbers +- `raw_payload` +- Original financial file content +- Passwords or encrypted file secrets + +## Create Backup +From Python/service: + +```bash +cd /root/projects/jarca-ledger-mcp +source .venv/bin/activate +python - <<'PY' +from jarca_ledger_mcp import service +print(service.create_ledger_backup()) +PY +``` + +MCP tool equivalent is allowed: +- `create_ledger_backup` +- `list_ledger_backups` +- `get_ledger_backup_status` +- `get_ledger_db_status` + +## Validation DB Smoke +Prefer synthetic DB: + +```bash +cd /root/projects/jarca-ledger-mcp +source .venv/bin/activate +pytest tests/test_backup_workflow.py +``` + +For a repo-external validation DB copy, set `JARCA_LEDGER_DB_PATH` to the copy path before running smoke tests or service checks. Do not commit that DB. + +## Restore Smoke Script +Restore is script-only and not an MCP operation. + +```bash +cd /root/projects/jarca-ledger-mcp +source .venv/bin/activate +python scripts/ledger_restore_smoke.py \ + --backup /root/.local/share/jarca/backups/ledger/.sqlite3 \ + --target /tmp/jarca-ledger-restore-smoke.sqlite3 +``` + +If the target already exists, overwriting requires explicit approval controls: + +```bash +python scripts/ledger_restore_smoke.py \ + --backup /root/.local/share/jarca/backups/ledger/.sqlite3 \ + --target /tmp/jarca-ledger-restore-smoke.sqlite3 \ + --allow-overwrite \ + --approval-token RESTORE_APPROVED +``` + +Do not point `--target` at `/root/.local/share/jarca/ledger.sqlite3` unless the user has explicitly approved a real operating DB restore in the current task. + +## High-Risk Work Checklist +Before import, rollback, categorization apply, reconciliation apply, migration, or any broad DB mutation: +1. Capture `get_ledger_db_status` for the selected DB. +2. Create a backup or confirm an acceptable recent backup. +3. Prefer running the risky operation against a synthetic fixture or repo-external validation copy first. +4. Capture post-operation status/report aggregates. +5. Record only allowed metadata evidence. +6. Ask QC to confirm no direct operating DB mutation occurred unless explicitly approved. + +## QC Gate Checklist +QC should verify: +- No source operating DB direct mutation without approval. +- Backup/status/list/hash tools exist and restore MCP tool does not exist. +- Restore path is script/runbook only and approval-gated for overwrite. +- Synthetic fixture or repo-external DB copy smoke evidence exists. +- Docs/tests/logs do not expose forbidden sensitive data. +- Tests and baseline docs are updated. diff --git a/docs/runtime-flows.md b/docs/runtime-flows.md index 1e01600..5f792e6 100644 --- a/docs/runtime-flows.md +++ b/docs/runtime-flows.md @@ -4,7 +4,7 @@ - Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml` - Status: draft - Owner: Jarca / project maintainer -- Last Updated (KST): 2026-06-26 22:24 +- Last Updated (KST): 2026-06-27 10:17 - Source Discovery / Batch: bootstrap-baseline - Primary Runtime: mixed @@ -63,11 +63,21 @@ 3. Matched self-transfers become `이체 / 본인계좌이동`; investment movements become `이체 / 투자이동`; ambiguous rows remain `확인필요`. 4. Cancel/refund rows can be linked to original expense rows; memo tags preserve manual link evidence. +## Flow: `Operational backup, validation DB, and restore smoke` +1. Operator captures non-sensitive DB status evidence with `get_ledger_db_status`: path, size, mtime, sha256, integrity check, major table row counts, and aggregate totals. +2. Operator creates a timestamped backup in `/root/.local/share/jarca/backups/ledger/` with `create_ledger_backup`; retention keeps the most recent 30 days or newest 20 files. +3. Risky import, rollback, categorization apply, reconciliation, or migration work is tested first against a synthetic fixture DB or repo-external validation DB copy selected through `JARCA_LEDGER_DB_PATH`. +4. Backup list/status/hash checks use `list_ledger_backups` and `get_ledger_backup_status`. +5. Restore execution is not an MCP flow. Restore smoke uses `scripts/ledger_restore_smoke.py` or the runbook and requires explicit approval before overwriting an existing target DB. +6. Verification evidence must not include full transaction dumps, full merchant/counterparty dumps, account identifiers, raw_payload, original financial file contents, or passwords. + ## Flow Constraints - Preview before broad import or categorization mutation where supported. - Do not include `transfer`, `investment`, `exclude`, or unresolved rows in actual household spending totals unless a report explicitly asks for account movement. - Preserve raw import evidence for audit and future reclassification. - Avoid destructive migrations without a backup/approval plan. +- Before broad DB mutation, capture DB status evidence and create or confirm a recent backup. +- Restore execution is script/runbook only and must not be exposed as an MCP tool. - Sensitive passwords are runtime inputs and must not be committed. ## Current Gaps / Planned Changes @@ -82,3 +92,4 @@ ## Change Log - 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation. +- 2026-06-27 10:17 KST: BAT-002/REQ-002 기준으로 운영 backup/status/list/hash 및 restore 제한 flow 추가. diff --git a/docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md b/docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md new file mode 100644 index 0000000..846f0c3 --- /dev/null +++ b/docs/srs/Non-Functional/req-002_operational-safety-backup-restore-validation-db.md @@ -0,0 +1,45 @@ +# REQ-002: 운영 안전 백업·복구·검증 DB 워크플로우 + +## Metadata +- ID: REQ-002 +- Type: Non-Functional +- Status: Implemented +- Priority: High +- Owner: 렛저장인 +- Source Discovery: dcy-002_20260627_operational-safety-backup-restore-validation-db +- Created At (KST): 2026-06-27 10:17 +- Approved At (KST): 2026-06-27 10:17 + +## Intent +원본 Jarca Ledger 운영 DB를 직접 훼손하지 않고 import, rollback, categorization, reconciliation, migration 검증을 반복할 수 있도록 백업 생성, 검증 DB 선택, 복구 smoke, QC evidence 기준을 표준화한다. + +## Requirement +시스템은 운영 DB의 timestamped backup을 생성·조회·상태 확인할 수 있는 additive service/MCP 인터페이스와, restore를 MCP로 노출하지 않는 script/runbook 기반 절차를 제공해야 한다. 모든 검증 evidence는 DB 파일 경로, 크기, mtime, sha256/checksum, 주요 table row count, aggregate total, health/test 결과처럼 민감정보가 없는 메타데이터로 제한해야 한다. + +## Acceptance Criteria +1. Backup 생성은 기본 위치 `/root/.local/share/jarca/backups/ledger/`에 timestamped SQLite 파일을 만들고, source DB와 backup DB의 path, size, mtime, sha256, integrity_check, 주요 table row count를 반환한다. +2. Backup 보관 정책은 최근 30일 또는 최근 20개 backup 유지이며, retention 실행 결과로 pruned path 목록을 메타데이터로 확인할 수 있다. +3. Backup 목록/status/hash 확인은 additive service/MCP tool로 제공되며 기존 MCP success response shape를 깨지 않는다. +4. Restore 실행은 MCP tool로 노출하지 않고 `scripts/ledger_restore_smoke.py`와 runbook으로만 제공하며, 기존 target overwrite에는 명시 승인 token이 필요하다. +5. 검증은 synthetic fixture DB를 우선 사용하고, 운영 DB copy가 필요한 경우 repo 밖 경로에서 hash/mtime/row count/aggregate만 evidence로 남긴다. +6. `docs/runtime-flows.md`, `docs/data-model.md`, `docs/interface-contract.md`는 backup/status/list/hash/restore 제한 정책과 민감정보 금지 evidence 기준을 반영한다. +7. 테스트는 synthetic DB에서 backup 생성, list, status/hash, retention, restore smoke 또는 health/status check를 검증하고 원본 운영 DB mutation 없이 통과한다. +8. 검수관 QC gate는 원본 운영 DB 직접 mutation 여부, restore MCP 노출 금지, 민감정보 노출 금지, synthetic fixture 또는 DB copy 기반 smoke evidence를 확인해 PASS/PASS_WITH_NOTES/BLOCKED 판정을 기록한다. + +## Impacted Area +- `jarca_ledger_mcp/service.py`: DB status, backup 생성, backup 목록/status helper 추가. +- `jarca_ledger_mcp/server.py`: restore 제외, backup/status/list/hash additive MCP tool 추가. +- `scripts/ledger_restore_smoke.py`: 사용자 승인 기반 restore smoke helper. +- `tests/test_backup_workflow.py`: synthetic DB 기반 regression. +- `docs/runtime-flows.md`, `docs/data-model.md`, `docs/interface-contract.md`, `docs/runbooks/ledger-backup-restore.md`: 운영 안전 flow와 interface 계약 갱신. + +## Notes +- 원본 운영 DB 직접 mutation, 실제 운영 DB restore, 파괴적 migration, 대량 data rewrite는 사용자 명시 승인 전까지 금지한다. +- Restore는 intentionally non-MCP surface다. 자동화가 필요해도 MCP tool로 추가하지 않는다. +- 거래 원문, merchant/counterparty 전체 dump, 계좌번호, raw_payload, 원본 금융 파일 내용은 docs/tests/logs evidence에 포함하지 않는다. +- 사용자 기본안이 승인되었으므로 REQ 상태는 Proposed 생성 직후 자르카 대리 승인 원칙에 따라 Approved로 전환했다. + +## Change Log +- 2026-06-27 10:17 KST: dcy-002에서 REQ-002 초안 생성. +- 2026-06-27 10:17 KST: 사용자 승인 기본안에 따라 REQ-002를 Approved로 전환. +- 2026-06-27 10:33 KST: BAT-002 verification 및 jarcaledgerqc PASS 근거로 REQ-002를 Implemented로 전환. diff --git a/docs/srs/index.md b/docs/srs/index.md index db1ecb7..d0ad83e 100644 --- a/docs/srs/index.md +++ b/docs/srs/index.md @@ -33,7 +33,7 @@ ## Next Requirement ID -- Current: `REQ-002` +- Current: `REQ-003` - Rule: `Requirement Register`에 있는 가장 큰 REQ 번호보다 정확히 1 커야 한다. ## Requirement Register @@ -41,8 +41,11 @@ | ID | Title | Type | Status | Priority | Owner | Link | | --- | --- | --- | --- | --- | --- | --- | | REQ-001 | 분류 규칙 운영 액션의 DB 경로 일관성 및 삭제 노출 | Interface | Implemented | High | 렛저장인 | [req-001_category-rule-ops.md](Interface/req-001_category-rule-ops.md) | +| REQ-002 | 운영 안전 백업·복구·검증 DB 워크플로우 | Non-Functional | Implemented | High | 렛저장인 | [req-002_operational-safety-backup-restore-validation-db.md](Non-Functional/req-002_operational-safety-backup-restore-validation-db.md) | ## Recent Change Log Summary - 2026-06-26 23:31 KST: dcy-001 후속 첫 구현 범위로 REQ-001을 Approved 상태로 등록. - 2026-06-26 23:41 KST: BAT-001 검증 및 검수관 PASS_WITH_NOTES 근거로 REQ-001을 Implemented 상태로 전환. +- 2026-06-27 10:17 KST: dcy-002 후속 운영 안전장치 범위로 REQ-002를 생성하고 사용자 승인 기본안에 따라 Approved 상태로 등록. +- 2026-06-27 10:33 KST: BAT-002 verification 및 jarcaledgerqc PASS 근거로 REQ-002를 Implemented 상태로 전환. diff --git a/jarca_ledger_mcp/server.py b/jarca_ledger_mcp/server.py index a4e4b44..438aeeb 100644 --- a/jarca_ledger_mcp/server.py +++ b/jarca_ledger_mcp/server.py @@ -14,6 +14,26 @@ def ledger_health_check() -> dict: """Verify the Jarca Ledger MCP server and SQLite database are reachable.""" return service.health_check() +@mcp.tool() +def get_ledger_db_status(include_hash: bool = True, include_integrity: bool = True) -> dict: + """Return non-sensitive DB status evidence: path, size, mtime, checksum, table row counts, and aggregate totals.""" + return service.get_ledger_db_status(include_hash=include_hash, include_integrity=include_integrity) + +@mcp.tool() +def create_ledger_backup(backup_dir: str = "", retention_days: int = 30, retention_count: int = 20) -> dict: + """Create a timestamped ledger DB backup. Restore is intentionally not exposed as an MCP tool.""" + return service.create_ledger_backup(backup_dir=backup_dir or None, retention_days=retention_days, retention_count=retention_count) + +@mcp.tool() +def list_ledger_backups(backup_dir: str = "", include_hash: bool = False, limit: int = 50) -> dict: + """List ledger DB backups with metadata-only evidence.""" + return service.list_ledger_backups(backup_dir=backup_dir or None, include_hash=include_hash, limit=limit) + +@mcp.tool() +def get_ledger_backup_status(file_path: str, include_hash: bool = True, include_integrity: bool = True) -> dict: + """Return metadata-only status and integrity evidence for one backup file.""" + return service.get_ledger_backup_status(file_path, include_hash=include_hash, include_integrity=include_integrity) + @mcp.tool() def create_ledger_account(name: str, type: str = "bank", institution: str = "", currency: str = "KRW", active: bool = True, memo: str = "", account_number_masked: str = "", holder_name: str = "", last_balance: int | None = None, last_synced_at: str = "") -> dict: """Create an account/card/cash/investment/loan ledger account.""" diff --git a/jarca_ledger_mcp/service.py b/jarca_ledger_mcp/service.py index a56d8e2..a3c934c 100644 --- a/jarca_ledger_mcp/service.py +++ b/jarca_ledger_mcp/service.py @@ -4,7 +4,8 @@ import csv import hashlib import json import re -from datetime import date, datetime +import sqlite3 +from datetime import date, datetime, timedelta from pathlib import Path from typing import Any from uuid import uuid4 @@ -31,6 +32,12 @@ END)""" CROSS_TRANSFER_MATCH_TAG = "cross_transfer_match:" CROSS_TRANSFER_REVIEW_TAG = "cross_transfer_review:" +DEFAULT_LEDGER_BACKUP_DIR = Path.home() / ".local" / "share" / "jarca" / "backups" / "ledger" +BACKUP_RESTORE_POLICY = { + "mcp_restore_exposed": False, + "restore_requires_explicit_user_approval": True, + "restore_entrypoint": "scripts/ledger_restore_smoke.py 또는 docs/runbooks/ledger-backup-restore.md", +} def _normalize_counterparty_for_match(value: str) -> str: @@ -134,6 +141,159 @@ def health_check(db_path: str | None = None) -> dict[str, Any]: tx_count = conn.execute("SELECT COUNT(*) FROM transactions WHERE status='active'").fetchone()[0] return ok(server="jarca-ledger-mcp", db_path=path, schema_version=schema_version, active_transactions=tx_count) + +def _sha256_file(path: Path) -> str: + digest = hashlib.sha256() + with path.open("rb") as f: + for chunk in iter(lambda: f.read(1024 * 1024), b""): + digest.update(chunk) + return digest.hexdigest() + + +def _file_metadata(path: Path, include_hash: bool = True) -> dict[str, Any]: + stat = path.stat() + metadata: dict[str, Any] = { + "path": str(path.resolve()), + "size_bytes": stat.st_size, + "mtime": datetime.fromtimestamp(stat.st_mtime).replace(microsecond=0).isoformat(), + } + if include_hash: + metadata["sha256"] = _sha256_file(path) + return metadata + + +def _readonly_sqlite_connection(path: Path) -> sqlite3.Connection: + conn = sqlite3.connect(f"file:{path}?mode=ro", uri=True) + conn.row_factory = sqlite3.Row + return conn + + +def _safe_table_counts(conn: sqlite3.Connection) -> dict[str, int]: + counts: dict[str, int] = {} + for table in ("accounts", "transactions", "budgets", "import_batches", "category_rules", "ledger_categories"): + exists = conn.execute("SELECT 1 FROM sqlite_master WHERE type='table' AND name=?", (table,)).fetchone() + if exists: + counts[table] = int(conn.execute(f"SELECT COUNT(*) FROM {table}").fetchone()[0]) + return counts + + +def _safe_monthly_aggregates(conn: sqlite3.Connection) -> dict[str, Any]: + current_month = date.today().strftime("%Y-%m") + start, next_month = _month_range(current_month) + rows = conn.execute( + f"""SELECT {CASHFLOW_KIND_SQL} AS cashflow_kind, SUM(t.amount) AS total, COUNT(*) AS count + FROM transactions t + LEFT JOIN ledger_categories lc ON lc.active=1 AND t.category=lc.category AND t.subcategory=lc.subcategory + WHERE t.status='active' AND t.transaction_date>=? AND t.transaction_date dict[str, Any]: + status: dict[str, Any] = {"db_path": str(path.resolve()), "exists": path.exists()} + if not path.exists(): + return status + status.update(_file_metadata(path, include_hash=include_hash)) + try: + with _readonly_sqlite_connection(path) as conn: + if include_integrity: + status["integrity_check"] = str(conn.execute("PRAGMA integrity_check").fetchone()[0]) + status["table_counts"] = _safe_table_counts(conn) + status["aggregate_totals"] = _safe_monthly_aggregates(conn) + except Exception as e: + status["integrity_check"] = "error" + status["error"] = str(e) + return status + + +def get_ledger_db_status(db_path: str | None = None, include_hash: bool = True, include_integrity: bool = True) -> dict[str, Any]: + """Return non-sensitive metadata evidence for the selected ledger DB.""" + path = resolve_db_path(db_path) + if not path.exists(): + return fail("not_found", f"ledger DB not found: {path}", db_path=str(path), exists=False) + return ok(**_ledger_db_status_for_path(path, include_hash=include_hash, include_integrity=include_integrity)) + + +def _resolve_backup_dir(backup_dir: str | None = None) -> Path: + return Path(backup_dir).expanduser().resolve() if backup_dir else DEFAULT_LEDGER_BACKUP_DIR.resolve() + + +def _backup_file_metadata(path: Path, include_hash: bool = False) -> dict[str, Any]: + metadata = _file_metadata(path, include_hash=include_hash) + metadata["name"] = path.name + metadata["restore_policy"] = BACKUP_RESTORE_POLICY + return metadata + + +def _apply_backup_retention(backup_dir: Path, retention_days: int = 30, retention_count: int = 20) -> list[str]: + backups = sorted(backup_dir.glob("*.sqlite3"), key=lambda p: p.stat().st_mtime, reverse=True) + keep_count = max(1, int(retention_count)) + cutoff = datetime.now() - timedelta(days=max(0, int(retention_days))) + pruned: list[str] = [] + for idx, path in enumerate(backups): + mtime = datetime.fromtimestamp(path.stat().st_mtime) + should_keep = idx < keep_count or mtime >= cutoff + if should_keep: + continue + path.unlink() + pruned.append(str(path.resolve())) + return pruned + + +def create_ledger_backup(db_path: str | None = None, backup_dir: str | None = None, retention_days: int = 30, retention_count: int = 20) -> dict[str, Any]: + """Create a timestamped SQLite backup and return metadata-only evidence.""" + source_path = resolve_db_path(db_path) + if not source_path.exists(): + return fail("not_found", f"ledger DB not found: {source_path}", db_path=str(source_path), exists=False) + backup_root = _resolve_backup_dir(backup_dir) + backup_root.mkdir(parents=True, exist_ok=True) + timestamp = datetime.now().strftime("%Y%m%d%H%M%S%f") + backup_path = backup_root / f"ledger_{timestamp}.sqlite3" + try: + # Use SQLite's online backup API so WAL-mode databases are copied consistently. + with sqlite3.connect(f"file:{source_path}?mode=ro", uri=True) as source_conn: + with sqlite3.connect(backup_path) as backup_conn: + source_conn.backup(backup_conn) + except Exception: + if backup_path.exists(): + backup_path.unlink() + raise + source_status = _ledger_db_status_for_path(source_path, include_hash=True, include_integrity=True) + backup_status = _ledger_db_status_for_path(backup_path, include_hash=True, include_integrity=True) + pruned_paths = _apply_backup_retention(backup_root, retention_days=retention_days, retention_count=retention_count) + return ok( + source_db=source_status, + backup=backup_status, + backup_dir=str(backup_root), + retention={"retention_days": int(retention_days), "retention_count": int(retention_count), "pruned_paths": pruned_paths}, + restore_policy=BACKUP_RESTORE_POLICY, + ) + + +def list_ledger_backups(backup_dir: str | None = None, include_hash: bool = False, limit: int = 50) -> dict[str, Any]: + backup_root = _resolve_backup_dir(backup_dir) + if not backup_root.exists(): + return ok(backup_dir=str(backup_root), backups=[], count=0, restore_policy=BACKUP_RESTORE_POLICY) + max_items = max(1, min(int(limit), 500)) + files = sorted(backup_root.glob("*.sqlite3"), key=lambda p: p.stat().st_mtime, reverse=True)[:max_items] + backups = [_backup_file_metadata(path, include_hash=include_hash) for path in files] + return ok(backup_dir=str(backup_root), backups=backups, count=len(backups), restore_policy=BACKUP_RESTORE_POLICY) + + +def get_ledger_backup_status(file_path: str, include_hash: bool = True, include_integrity: bool = True) -> dict[str, Any]: + path = Path(file_path).expanduser().resolve() + if not path.exists(): + return fail("not_found", f"backup file not found: {path}", path=str(path), exists=False) + return ok(backup=_ledger_db_status_for_path(path, include_hash=include_hash, include_integrity=include_integrity), restore_policy=BACKUP_RESTORE_POLICY) + def create_ledger_account(name: str, type: str = "bank", institution: str = "", currency: str = "KRW", active: bool = True, memo: str = "", account_number_masked: str = "", holder_name: str = "", last_balance: int | None = None, last_synced_at: str = "", db_path: str | None = None) -> dict[str, Any]: if not name.strip(): return fail("validation_error", "account name is required") diff --git a/scripts/ledger_restore_smoke.py b/scripts/ledger_restore_smoke.py new file mode 100644 index 0000000..9ffa8b3 --- /dev/null +++ b/scripts/ledger_restore_smoke.py @@ -0,0 +1,71 @@ +#!/usr/bin/env python3 +"""Restore/smoke helper for Jarca Ledger backups. + +This script is intentionally not exposed as an MCP tool. It restores a backup file +into an explicitly provided target DB path, then runs SQLite integrity and Jarca +ledger health/status checks. Use a synthetic fixture or repo-external validation +DB first. Do not point --target at the live operating DB unless the user has +explicitly approved the restore. +""" +from __future__ import annotations + +import argparse +import json +import shutil +import sys +from pathlib import Path + +from jarca_ledger_mcp import service + +APPROVAL_TEXT = "RESTORE_APPROVED" + + +def parse_args() -> argparse.Namespace: + parser = argparse.ArgumentParser(description="Restore a ledger backup into a target DB and run smoke checks.") + parser.add_argument("--backup", required=True, help="Backup sqlite3 file to restore from") + parser.add_argument("--target", required=True, help="Target sqlite3 path to create/replace") + parser.add_argument( + "--approval-token", + default="", + help=f"Required token for overwrite/live restore. Must be {APPROVAL_TEXT!r}.", + ) + parser.add_argument("--allow-overwrite", action="store_true", help="Allow replacing an existing target DB") + return parser.parse_args() + + +def main() -> int: + args = parse_args() + backup = Path(args.backup).expanduser().resolve() + target = Path(args.target).expanduser().resolve() + if not backup.exists(): + print(json.dumps({"success": False, "error_code": "not_found", "error": f"backup not found: {backup}"}, ensure_ascii=False)) + return 1 + if target.exists() and not args.allow_overwrite: + print(json.dumps({"success": False, "error_code": "target_exists", "error": f"target exists: {target}"}, ensure_ascii=False)) + return 2 + if target.exists() and args.approval_token != APPROVAL_TEXT: + print(json.dumps({"success": False, "error_code": "approval_required", "error": f"overwrite requires --approval-token {APPROVAL_TEXT}"}, ensure_ascii=False)) + return 3 + + before = service.get_ledger_backup_status(str(backup)) + if not before.get("success") or before.get("backup", {}).get("integrity_check") != "ok": + print(json.dumps({"success": False, "error_code": "invalid_backup", "backup_status": before}, ensure_ascii=False)) + return 4 + + target.parent.mkdir(parents=True, exist_ok=True) + shutil.copy2(backup, target) + health = service.health_check(str(target)) + status = service.get_ledger_db_status(str(target)) + result = { + "success": bool(health.get("success") and status.get("success") and status.get("integrity_check") == "ok"), + "backup": before.get("backup", {}), + "target": status, + "health_check": health, + "restore_policy": service.BACKUP_RESTORE_POLICY, + } + print(json.dumps(result, ensure_ascii=False, indent=2)) + return 0 if result["success"] else 5 + + +if __name__ == "__main__": + sys.exit(main()) diff --git a/tests/test_backup_workflow.py b/tests/test_backup_workflow.py new file mode 100644 index 0000000..8ab4a7f --- /dev/null +++ b/tests/test_backup_workflow.py @@ -0,0 +1,80 @@ +from __future__ import annotations + +from pathlib import Path + +from jarca_ledger_mcp import service + + +def test_db_status_reports_metadata_without_sensitive_rows(tmp_path): + db_path = str(tmp_path / "ledger.sqlite3") + service.create_ledger_transaction( + "2026-06-01", + "expense", + 12_000, + category="식비", + subcategory="카페", + merchant="SENTINEL_MERCHANT", + counterparty="SENTINEL_COUNTERPARTY", + raw_payload="SENTINEL_RAW_PAYLOAD", + db_path=db_path, + ) + + status = service.get_ledger_db_status(db_path=db_path) + + assert status["success"] is True + assert status["db_path"] == str(Path(db_path).resolve()) + assert status["exists"] is True + assert status["sha256"] + assert status["integrity_check"] == "ok" + assert status["table_counts"]["transactions"] == 1 + dumped = repr(status) + assert "SENTINEL_MERCHANT" not in dumped + assert "SENTINEL_COUNTERPARTY" not in dumped + assert "SENTINEL_RAW_PAYLOAD" not in dumped + + +def test_create_list_and_status_ledger_backup_with_retention(tmp_path): + db_path = str(tmp_path / "ledger.sqlite3") + backup_dir = str(tmp_path / "backups") + service.create_ledger_account("테스트 계좌", db_path=db_path) + before = service.get_ledger_db_status(db_path=db_path) + + created = service.create_ledger_backup(db_path=db_path, backup_dir=backup_dir, retention_days=30, retention_count=20) + + assert created["success"] is True + assert created["source_db"]["sha256"] == before["sha256"] + assert created["backup"]["path"].startswith(str(Path(backup_dir).resolve())) + assert Path(created["backup"]["path"]).exists() + assert created["backup"]["sha256"] + assert created["backup"]["integrity_check"] == "ok" + assert created["backup"]["table_counts"] == created["source_db"]["table_counts"] + assert created["restore_policy"]["mcp_restore_exposed"] is False + + listed = service.list_ledger_backups(backup_dir=backup_dir, include_hash=True) + assert listed["success"] is True + assert listed["count"] == 1 + assert listed["backups"][0]["sha256"] == created["backup"]["sha256"] + + backup_status = service.get_ledger_backup_status(created["backup"]["path"]) + assert backup_status["success"] is True + assert backup_status["backup"]["integrity_check"] == "ok" + assert backup_status["backup"]["table_counts"]["accounts"] == 1 + + +def test_backup_retention_keeps_recent_count_and_prunes_older_extras(tmp_path): + db_path = str(tmp_path / "ledger.sqlite3") + backup_dir = tmp_path / "backups" + service.create_ledger_transaction("2026-06-01", "income", 1000, category="수입", db_path=db_path) + + for i in range(3): + old = backup_dir / f"ledger_20200101000{i}000000.sqlite3" + old.parent.mkdir(parents=True, exist_ok=True) + old.write_text("old", encoding="utf-8") + + created = service.create_ledger_backup(db_path=db_path, backup_dir=str(backup_dir), retention_days=0, retention_count=2) + + assert created["success"] is True + remaining = sorted(p.name for p in backup_dir.glob("*.sqlite3")) + assert len(remaining) == 2 + assert Path(created["backup"]["path"]).name in remaining + assert len(created["retention"]["pruned_paths"]) == 2