3 Commits

Include renames

Author	SHA1	Message	Date
Jon Saad-FalconandClaude Opus 4.6	82ef2664a6	fix: codebase cleanup — bug fixes, test hardening, and lint ... - Remove pynvml from core deps (optional, behind pynvml import guard) - Fix SystemBuilder wiring bugs (agent/tools/telemetry initialization) - Fix LoopGuard hash tracking and ping-pong detection edge cases - Fix OrchestratorAgent/NativeReActAgent tool_calls handling - Fix OpenAI-compat engine streaming and error handling - Fix Ollama engine model listing and health checks - Fix eval display, config parsing, and runner edge cases - Fix guardrails engine scan mode handling - Fix dashboard panel rendering and data formatting - Fix web_search tool error handling - Fix quickstart CLI detection and setup flow - Harden channel tests (WhatsApp, Matrix, IRC, Signal, Teams, etc.) - Harden optimizer, trace judge, and personal synthesizer tests - Add missing test coverage for types, engine, system, and security Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-05 05:29:42 +00:00
Jon Saad-FalconandClaude Opus 4.6	3c39995476	feat(optimize): add trace-aware multi-objective optimization ... Surface per-instance scores (SampleScore), structured feedback (TrialFeedback), Pareto frontier tracking, pillar-targeted mutation, and config merge strategies. Store migration adds new columns with backward-compatible deserialization. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-05 01:04:30 +00:00
Jon Saad-FalconandClaude Opus 4.6	d234471c03	feat(optimize): add optimization engine, SQLite store, and config loader ... Add the orchestration layer that ties together the LLM optimizer, trial runner, and persistence into a propose-evaluate-analyze loop with early stopping and recipe export. 36 new tests pass. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-04 23:56:30 +00:00