jihoson/The-Ouroboros
1
0
Fork 0
Code Issues 2 Pull Requests Actions 10 Packages Projects Releases Wiki Activity
157 Commits 145 Branches 0 Tags
d0bbdb5dc1031bdf2896bb9a5fa416abb5a7efb4
Commit Graph

5 Commits

Author SHA1 Message Date
agentson
6b3960a3a4 feat: inject self-market scorecard into planner prompt (issue #94)
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
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>
 2026-02-14 23:27:01 +09:00
agentson
86c94cff62 feat: cross-market date fix and strategic context selector (issue #88)
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
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>
 2026-02-14 23:20:24 +09:00
agentson
be695a5d7c fix: address PR review — inject today param, remove unused imports, fix lint
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
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>
 2026-02-08 21:57:39 +09:00
agentson
6471e66d89 fix: correct Settings field name in planner tests (KIS_ACCOUNT_NO)
Some checks failed
CI / test (pull_request) Has been cancelled
Details 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-08 21:36:42 +09:00
agentson
149039a904 feat: implement pre-market planner with Gemini integration (issue #83) 
PreMarketPlanner generates DayPlaybook via single Gemini API call per market:
- Structured JSON prompt with scan candidates + strategic context
- Cross-market context (KR reads US scorecard, US reads KR scorecard)
- Robust JSON parser with markdown fence stripping
- Unknown stock filtering (only scanner candidates allowed)
- MAX_SCENARIOS_PER_STOCK enforcement
- Defensive playbook on failure (HOLD + stop-loss)
- Empty playbook when no candidates (safe, no trades)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-08 21:35:57 +09:00