agentson
f2ad270e8b
docs: 2026-02-21 요구사항 로그 업데이트 ( #187 )
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-21 00:34:16 +09:00
agentson
3952a5337b
docs: add requirements log entry for overseas limit order fix ( #149 )
CI / test (pull_request) Has been cancelled
2026-02-18 23:54:18 +09:00
agentson
f7289606fc
fix: use prompt_override in gemini_client.decide() for playbook generation
...
CI / test (pull_request) Has been cancelled
decide() ignored market_data["prompt_override"], always building a generic
trade-decision prompt. This caused pre_market_planner playbook generation
to fail with JSONDecodeError on every market, falling back to defensive
playbooks. Now prompt_override takes priority over both optimization and
standard prompt building.
Closes #143
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-18 02:02:13 +09:00
agentson
1288181e39
docs: add requirements log entry for overseas ranking API fix
...
CI / test (pull_request) Has been cancelled
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-18 01:04:42 +09:00
agentson
733e6b36e9
feat: unify domestic scanner and sizing; update docs
CI / test (pull_request) Has been cancelled
2026-02-17 06:29:36 +09:00
agentson
0659cc0aca
docs: reflect overseas ranking integration and volatility-first selection
2026-02-17 06:29:16 +09:00
agentson
d105a3ff5e
docs: v2 상태 반영 - 전체 문서 현행화 ( #131 )
...
CI / test (pull_request) Has been cancelled
- testing.md: 54 tests/4 files → 551 tests/25 files 반영, 전체 테스트 파일 설명
- architecture.md: v2 컴포넌트 추가 (Strategy, Context, Dashboard, Decision Logger 등),
Playbook Mode 데이터 플로우, DB 스키마 5개 테이블, v2 환경변수
- commands.md: Dashboard 실행, Telegram 명령어 9종 레퍼런스
- CLAUDE.md: Project Structure 확장, 테스트 수 업데이트, --dashboard 플래그
- skills.md: DB 파일명 trades.db로 통일, Dashboard 명령어 추가
- requirements-log.md: 2026-02-16 문서 v2 동기화 요구사항 기록
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-16 21:44:59 +09:00
agentson
9a8936ab34
docs: add plan-implementation consistency check to code review checklist ( #114 )
...
CI / test (pull_request) Has been cancelled
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 >
2026-02-10 04:15:51 +09:00
agentson
7725e7a8de
docs: update documentation for Smart Volatility Scanner
...
CI / test (pull_request) Has been cancelled
Update project documentation to reflect new Smart Volatility Scanner feature:
## CLAUDE.md
- Add Smart Volatility Scanner section with configuration guide
- Update project structure to include analysis/ module
- Update test count (273→343 tests)
## docs/architecture.md
- Add Analysis component (VolatilityAnalyzer + SmartVolatilityScanner)
- Add new KIS API methods (fetch_market_rankings, get_daily_prices)
- Update data flow diagram to show Python-first filtering pipeline
- Add selection_context to database schema documentation
- Add Smart Scanner configuration section
- Renumber components (Brain 2→3, Risk Manager 3→4, etc.)
## docs/requirements-log.md
- Document 2026-02-06 requirement for Smart Volatility Scanner
- Explain Python-First, AI-Last pipeline rationale
- Record implementation details and benefits
- Reference issue #76 and PR #77
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-06 07:35:25 +09:00
agentson
0057de4d12
feat: implement daily trading mode with batch decisions (issue #57 )
...
CI / test (pull_request) Has been cancelled
Add API-efficient daily trading mode for Gemini Free tier compatibility:
## Features
- **Batch Decisions**: GeminiClient.decide_batch() analyzes multiple stocks
in a single API call using compressed JSON format
- **Daily Trading Mode**: run_daily_session() executes N sessions per day
at configurable intervals (default: 4 sessions, 6 hours apart)
- **Mode Selection**: TRADE_MODE env var switches between daily (batch)
and realtime (per-stock) modes
- **Requirements Log**: docs/requirements-log.md tracks user feedback
chronologically for project evolution
## Configuration
- TRADE_MODE: "daily" (default) | "realtime"
- DAILY_SESSIONS: 1-10 (default: 4)
- SESSION_INTERVAL_HOURS: 1-24 (default: 6)
## API Efficiency
- 2 markets × 4 sessions = 8 API calls/day (within Free tier 20 calls)
- 3 markets × 4 sessions = 12 API calls/day (within Free tier 20 calls)
## Testing
- 9 new batch decision tests (all passing)
- All existing tests maintained (298 passed)
## Documentation
- docs/architecture.md: Trading Modes section with daily vs realtime
- CLAUDE.md: Requirements Management section
- docs/requirements-log.md: Initial entries for API efficiency needs
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-05 09:28:10 +09:00
