jihoson/The-Ouroboros
1
0
Fork 0
Code Issues Pull Requests Actions 14 Packages Projects Releases Wiki Activity
247 Commits 147 Branches 0 Tags
2e27000760248be53a27548c5180c820668660b2
Commit Graph

2 Commits

Author SHA1 Message Date
agentson
60a22d6cd4 feat: add position-aware conditions to StockCondition (#171)
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
- Add unrealized_pnl_pct_above/below and holding_days_above/below fields
  to StockCondition so AI can generate rules like 'P&L > 3% → SELL'
- Evaluate new fields in ScenarioEngine.evaluate_condition() with same
  AND-combining logic as existing technical indicator fields
- Include position fields in _build_match_details() for audit logging
- Parse new fields from AI JSON response in PreMarketPlanner._parse_scenario()
- Update prompt schema example to show new position-aware condition fields
- Add 13 tests covering all new condition combinations and edge cases

Closes #171

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-20 08:27:44 +09:00
agentson
7fd48c7764 feat: add strategy/playbook Pydantic models (issue #79)
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
Define data contracts for the proactive strategy system:
- StockCondition: AND-combined condition fields (RSI, volume, price)
- StockScenario: condition-action rules with stop loss/take profit
- StockPlaybook: per-stock scenario collection
- GlobalRule: portfolio-level rules (e.g. REDUCE_ALL on loss limit)
- DayPlaybook: complete daily playbook per market with validation
- CrossMarketContext: cross-market awareness (KR↔US)
- ScenarioAction, MarketOutlook, PlaybookStatus enums

33 tests covering validation, serialization, edge cases.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-08 02:06:16 +09:00