diff --git a/.kiro/steering/development-process.md b/.kiro/steering/development-process.md
index 394d048..f098273 100644
--- a/.kiro/steering/development-process.md
+++ b/.kiro/steering/development-process.md
@@ -22,7 +22,9 @@
 - Frontend: Vitest + MSW (Mock Service Worker) for deterministic API mocking, tests in `frontend/src/test/`
 - Run Python tests: `python -m pytest tests/ -x --tb=short -q`
 - Run frontend tests: `cd frontend && npx vitest --run`
-- Lint Python: `nix-shell -p ruff --run "ruff check services/"`
+- Lint Python: `nix-shell -p ruff --run "ruff check services/"` (or `.venv/bin/ruff check services/`)
+- Ruff is pinned to `ruff==0.15.10` in `requirements.txt` — CI uses the same version
+- Ruff config: `ruff.toml` with `known-first-party = ["services"]` for consistent import sorting
 - Pre-existing test failures (not regressions): `test_extractor_prompts.py`, `test_extractor_schemas.py`, `test_filings_adapter.py`, `test_ollama_client.py`
 
 ## CI/CD — GitHub Actions
diff --git a/.kiro/steering/project-context.md b/.kiro/steering/project-context.md
index b55c7fc..3a593ea 100644
--- a/.kiro/steering/project-context.md
+++ b/.kiro/steering/project-context.md
@@ -25,6 +25,7 @@ Three-layer signal aggregation engine:
 - Dashboard: `https://stonks.celestium.life`
 - Query API: `https://stonks-api.celestium.life`
 - Symbol Registry: `https://stonks-registry.celestium.life`
+- Trading Engine: `https://stonks-trading.celestium.life`
 - Superset: `https://stonks-dash.celestium.life`
 - Trino: `https://stonks-trino.celestium.life`
 
@@ -72,12 +73,15 @@ When a full reset is needed:
 - Ollama: `ollama.ollama-service.svc.cluster.local:11434` (cluster-internal), also at `http://10.1.1.12:2701` (external), GPU: 4070 Ti Super 16GB
 
 ## Database Migrations
-- Located in `infra/migrations/001_*.sql` through `017_*.sql`
+- Located in `infra/migrations/001_*.sql` through `027_*.sql`
 - Applied automatically by `runmefirst.sh` in sorted order
-- Next migration number: **018**
+- Next migration number: **028**
 - Key migrations:
   - 016: Global news interpolation (global_events, macro_impact_records, exposure_profiles, trend_projections)
   - 017: Competitive intelligence (competitor_relationships, competitive_signal_records)
+  - 024: Trend history time-series table
+  - 026: AI agents management (ai_agents, agent_performance_log)
+  - 027: Agent variants (agent_variants table for A/B testing)
 
 ## Key Conventions
 - All services use `services/shared/config.py` for configuration via env vars
diff --git a/README.md b/README.md
index 953b412..9e622bf 100644
--- a/README.md
+++ b/README.md
@@ -77,6 +77,9 @@ Seed data: `python -m services.symbol_registry.seed`
 ### Autonomous Trading Engine
 Continuous decision loop that polls for actionable recommendations and executes paper trades without manual intervention. Includes confidence-based position sizing (with sample-size-dampened agreement scoring to prevent thin-evidence inflation), dynamic stop-loss/take-profit (ATR-based), circuit breakers (daily loss cap, single-position loss, volatility detection), reserve pool management (auto-siphon from profits), risk tier auto-adjustment (conservative/moderate/aggressive based on trailing performance), portfolio rebalancing (sector and concentration limits), gradual entry (multi-tranche orders), correlation-aware diversification, earnings calendar awareness, portfolio heat management, tax-lot tracking with wash sale detection, performance tracking (Sharpe, drawdown, win rate, profit factor), and backtesting against historical data.
 
+### AI Agent Management
+Configurable AI agents (document extractor, event classifier, thesis rewriter) with database-driven model/prompt resolution. 60-second TTL cache for hot-swapping models without restarts. Agent performance logging with variant attribution for future A/B testing support.
+
 ### Global News Interpolation
 Macro/geopolitical event ingestion from dedicated sources. Ollama-based classification by impact type, severity, affected regions, and sectors. Company exposure profiles (geographic revenue mix, supply chain regions, commodity dependencies, market position tier) map events to per-company macro impact scores with resilience modifiers. Forward-looking trend projections combine company momentum with macro trajectories.
 
@@ -105,7 +108,8 @@ Historical pattern mining on the platform's own data — how similar catalyst ty
 
 ### Paper Trading
 - Alpaca paper trading integration (3 accounts max per Alpaca owner)
-- Full reset: liquidates broker positions, cancels orders, syncs capital from broker balance
+- Full reset: liquidates broker positions, cancels orders, clears local DB, syncs capital from broker's actual account balance
+- No manual capital controls — engine capital always derived from broker state on reset
 - Moderate risk tier default, auto-adjustable
 - Full execution audit trail from signal to broker response
 - Operator approval workflow available for live mode