6 Commits

Author	SHA1	Message	Date
freemo	a074b4846f	fix(provider): remove FakeListLLM defaults ... Remove FakeListLLM as a silent fallback in agent graph constructors (plan_generation.py, context_analysis.py, auto_debug.py). All three now raise ValueError when llm=None, making missing-provider errors explicit. Add Settings.mock_providers flag and validate_provider_availability() method. Update container.get_ai_provider() to check Settings.mock_providers first, with env-var fallback for backward compatibility. Add resolve_provider_by_name() helper to the provider registry and export it from cleveragents.providers. Add structlog trace logging to ProviderRegistry.get_default_provider_type() to record selection reasoning. Update all existing behave step files, robot tests, and benchmarks that relied on the implicit FakeListLLM default to pass an explicit LLM instance instead. Add new BDD tests (features/provider_fixes.feature with 17 scenarios), Robot Framework integration tests (robot/provider_detection_smoke.robot), and ASV benchmarks (benchmarks/provider_selection_bench.py). ISSUES CLOSED: #323	2026-02-27 09:47:10 -05:00
freemo	8c162d4009	Tests: Added benchmarks for PlanGenerationGraph	2025-12-11 13:55:55 -05:00
freemo	dd733b38d1	Feat: Finished stage 5, replacing manual retrys and auditing with LangChain based retrys	2025-12-10 20:25:11 -05:00
freemo	07fbe7afaf	Feat: Integrated PlanGenerationGraph for Context loading, added EntityMemory for project tracking	2025-12-10 18:39:00 -05:00
freemo	496f565a57	Chore: Completed stage 1.5	2025-11-24 20:04:18 -05:00
freemo	a47abd20b2	Feat: Added plan generation module	2025-11-18 21:39:03 -05:00