jgrusewski 0689884f8b fix(factory): constrain LlmAnalyst to backtestable kinds (no hallucinated kinds) ...

Real Ollama test showed qwen2.5:3b inventing invalid strategy kinds (FUTURES_CONTRACTS, MARKET_RETURN, ...)
because the prompt never listed the engine's available() kinds. Now the analyst is given the allowed kinds,
the prompt forbids inventing others, and proposals with an unknown/empty kind are dropped — so the fleet only
emits backtestable hypotheses. The gauntlet still filters the rest.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-14 21:44:16 +02:00

..

test_analyst_fleet.py

fix(factory): constrain LlmAnalyst to backtestable kinds (no hallucinated kinds)

2026-06-14 21:44:16 +02:00

test_crypto_execution.py

fix(exec): stable data-derived rebalance_id + rate-limit signal + cover/drift invariant tests

2026-06-14 17:39:29 +02:00

test_dashboard_service.py

feat(cockpit): dashboard port + view-models + DashboardService

2026-06-14 11:46:45 +02:00

test_discovery.py

feat: wire FDR into the gauntlet/discovery — multiple-testing complement over the whole search

2026-06-13 09:35:18 +02:00

test_execution.py

feat: multi-strategy execution layer (domain netting + Broker port + ExecutionService)

2026-06-09 13:52:32 +02:00

test_factory_cycle_wiring.py

fix(factory): closure hardening — zero-sum HRP guard, read-only dry-run, single trial-count authority, funnel + E501

2026-06-14 21:27:23 +02:00

test_factory_loop.py

fix(factory): capital-correct loop — record_cycle, sequential HRP-weighted admission, kill-switch, tests

2026-06-14 20:24:50 +02:00

test_factory_store.py

fix(factory): capital-correct loop — record_cycle, sequential HRP-weighted admission, kill-switch, tests

2026-06-14 20:24:50 +02:00

test_feature_pipeline.py

feat: SSOT feature-warehouse foundation + first feature TDD-ported (microprice)

2026-06-13 02:01:04 +02:00

test_fetch_cli.py

fix(fetch): clean missing-key error + day-aligned funding array

2026-06-14 12:30:07 +02:00

test_fleet.py

feat: fleet orchestrator (factory layer 3) — the standing research force

2026-06-09 19:28:08 +02:00

test_forward_ingest.py

feat(cockpit): forward ingest ETL (registry-driven, best-effort)

2026-06-14 11:34:24 +02:00

test_forward_nav_repo.py

fix(cockpit): port-protocol web dep + bulk nav histories + lint/log/title

2026-06-14 11:56:01 +02:00

test_forward.py

fix(factory): scale DSR bar by global N + remove gate-bypass promote + silence HRP warning

2026-06-14 20:54:16 +02:00

test_global_n_flows.py

fix(factory): scale DSR bar by global N + remove gate-bypass promote + silence HRP warning

2026-06-14 20:54:16 +02:00

test_portfolio_eval.py

feat: agentic research layer — LangGraph agent + LLM port + compute tools

2026-06-09 16:22:59 +02:00

test_regime_execution.py

fix(factory): closure hardening — zero-sum HRP guard, read-only dry-run, single trial-count authority, funnel + E501

2026-06-14 21:27:23 +02:00

test_research_slice.py

feat: fxhnt foundation — hexagonal architecture + proven gauntlet + vertical slice

2026-06-09 12:21:47 +02:00

test_runtime.py

feat: LLM-driven hunters (fxhnt 2) — agents direct their own search

2026-06-13 01:20:53 +02:00

test_strategy_store.py

feat: strategy-lifecycle store (factory layer 2) — the persistent backbone

2026-06-09 19:24:07 +02:00

test_web_funnel.py

feat(factory): cockpit funnel view (funnel counts + global trials + HRP weights)

2026-06-14 20:37:54 +02:00

test_web.py

feat(cockpit): FastAPI+HTMX web app, templates, branding, factory view

2026-06-14 11:49:10 +02:00