This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryAdded a rule‑based L3 strategy adjustment system with SQLite storage, CRUD APIs, and generation logic.
Full changelog
L3 Strategy Adjustments — Rule-based strategy tuning from L2 patterns
Added
strategy_adjustmentstable in SQLite with proposed/approved/applied/rejected lifecycle- 5 deterministic rules: strategy_disable, strategy_prefer, session_reduce, session_increase, direction_restrict
generate_l3_adjustments()in ReflectionEngine — reads L2 patterns, outputs proposed adjustments- 3 CRUD methods in Database:
insert_adjustment,query_adjustments,update_adjustment_status - 3 REST API endpoints:
POST /reflect/generate_adjustments,GET /adjustments/query,POST /adjustments/update_status demo.pyStep 6: production L1→L2→L3 pipeline- 21 new tests — total 181 tests passing
- CI auto-publish to PyPI on release
Details
- No LLM needed — all rules are deterministic with confidence thresholds
- Adjustment lifecycle: proposed → approved → applied (or rejected)
- Rules only fire when pattern confidence ≥ 0.7 (requires n ≥ 50 trades)
Full Changelog: https://github.com/mnemox-ai/tradememory-protocol/compare/v0.2.0...v0.3.0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About mnemox-ai/tradememory-protocol
Structured 3-layer memory system (trades → patterns → strategy) for AI trading agents. Supports MT5, Binance, and Alpaca.
Related context
Beta — feedback welcome: [email protected]