- MARKET_SHORTHAND + expand_market_codes()로 config "US" → schedule "US_NASDAQ/NYSE/AMEX" 자동 확장
- /report, /scenarios, /review, /dashboard 텔레그램 명령 추가
- price_change_pct를 trading_cycle과 run_daily_session에 주입
- HOLD시 get_open_position 기반 손절 모니터링 및 자동 SELL 오버라이드
- 대시보드 /api/status 동적 market 조회로 변경
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add --dashboard CLI flag and DASHBOARD_ENABLED env var to start
FastAPI dashboard in a daemon thread alongside the trading loop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add observability dashboard: status, playbook, scorecard, performance,
context browser, decisions, and active scenarios endpoints.
SQLite read-only on separate connections from trading loop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wrap evolution notification in try/except so telegram failures don't
crash the evolution loop. Add integration tests for market close flow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Run EvolutionOptimizer.evolve() at US market close, skip for other
markets, and notify via Telegram when a strategy PR is generated.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wire up periodic context rollups (weekly/monthly/quarterly/annual/legacy)
in both daily and realtime trading loops with dedup-safe scheduling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add build_self_market_scorecard() to read previous day's own market
performance, and include it in the Gemini planning prompt alongside
cross-market context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
KR planner now reads US scorecard from previous day (timezone-aware),
and generate_playbook uses STRATEGIC context selection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract _handle_market_close() helper that runs EOD aggregation,
generates scorecard with optional AI lessons, and sends Telegram summary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Generate per-market daily scorecards from decision_logs and trades,
optional Gemini-powered lessons, and store results in L6 context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add decision_id column to trades table, capture log_decision() return
value, and update original BUY decision outcome on SELL execution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ContextScheduler with run_if_due() for periodic rollups
- Weekly (Sunday), monthly (last day), quarterly, annual, legacy schedules
- Daily cleanup of expired contexts via ContextStore
- Dedup guard: each task runs at most once per day
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add market parameter to aggregate_daily_from_trades() for per-market L6 aggregation
- Store market-scoped keys (total_pnl_KR, win_rate_US, etc.) in L6/L5/L4 layers
- Hook aggregate_daily_from_trades() into market close detection in run()
- Update tests for market-scoped context keys
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add L7_REALTIME writes in trading_cycle() for volatility, price, rsi, volume_ratio
- Normalize key format to {metric}_{market}_{stock_code} across scanner and main
- Fix existing key mismatch between scanner writes and main reads
- Remove unused MarketScanner dead code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
리뷰 시 플랜과 구현의 일치 여부를 필수로 확인하는 규칙 추가.
- workflow.md에 Code Review Checklist 섹션 신설
- requirements-log.md에 사용자 요구사항 기록
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
run_all_aggregations() previously used datetime.now(UTC) for weekly
through annual layers while using the trade date only for daily,
causing data misalignment on backfill. Now all layers consistently
use the latest trade timestamp. Also adds "Z" suffix handling for
fromisoformat() compatibility and strengthens test assertions to
verify L4-L2 layer values end-to-end.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address PR #110 review findings:
1. High — Realtime mode now loads playbook from DB before calling Gemini,
preventing duplicate API calls on process restart (4/day budget).
2. Medium — Pass market-local date (via market.timezone) to
generate_playbook() and _empty_playbook() instead of date.today().
3. Medium — scan_candidates restructured from {stock_code: candidate}
to {market_code: {stock_code: candidate}} to prevent KR/US symbol
collision.
New test: test_scan_candidates_market_scoped verifies cross-market
isolation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove unused imports (sys, ScenarioMatch, asyncio, StockPlaybook),
fix import ordering, and split long lines for ruff compliance.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace brain.decide() with scenario_engine.evaluate() in trading_cycle
and brain.decide_batch() with per-stock scenario evaluation in
run_daily_session. Initialize PreMarketPlanner, ScenarioEngine, and
PlaybookStore in run(). Add pre-market playbook generation on market
open (1 Gemini call per market per day), market_data enrichment from
scanner metrics (rsi, volume_ratio), portfolio_data for global rules,
scenario match notifications, and playbook lifecycle management.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Review findings addressed:
- Finding 1 (ImportError): false positive — ContextLayer is re-exported from
src.context.store, import works correctly at runtime
- Finding 2 (timezone): generate_playbook() and build_cross_market_context()
now accept optional today parameter for market-local date injection
- Finding 3 (lint): removed unused imports (UTC, datetime, PlaybookStatus),
fixed line-too-long in prompt template
- Tests simplified: replaced date patching with direct today= parameter
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add playbooks table to src/db.py with UNIQUE(date, market) constraint
- PlaybookStore: save/load/delete, status management, match_count tracking,
list_recent with market filter, stats without full deserialization
- DayPlaybook JSON serialization via Pydantic model_dump_json/model_validate_json
- 23 tests, 100% coverage on playbook_store.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Addresses second round of PR #102 review:
- _warn_missing_key(): logs each missing key only once per engine instance
to prevent log spam in high-frequency trading loops
- _build_match_details(): uses _safe_float() normalized values instead of
raw market_data to ensure consistent float types in logging/analysis
- Test: verify warning fires exactly once across repeated calls
- Test: verify match_details contains normalized float values
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
