3 Commits

Author	SHA1	Message	Date
jgrusewski	e4870b17b9	fix: tune log levels across workspace — demote noisy warn to debug/trace ... Reduce log noise for non-critical operational paths: connection retries, expected fallbacks, graceful degradation, and optional feature absence. Keeps warn/error for genuine failures requiring attention. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-14 11:35:15 +01:00
jgrusewski	46f84f6770	feat(hyperopt): wire hyperopt dispatch through fxt CLI and K8s dispatcher ... Add --hyperopt, --trials, and --parallel flags to `fxt train start` so users can dispatch PSO hyperparameter optimization jobs alongside regular training. The mode=hyperopt tag propagates through the service layer which selects the correct binary (hyperopt_baseline_rl for DQN/PPO, hyperopt_baseline_supervised for all others) and builds hyperopt-specific CLI arguments via a new extra_args field on TrainingJobParams. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-28 22:29:51 +01:00
jgrusewski	abc5ee6af1	feat(training): add in-process queue consumer for K8s job dispatch ... Background tokio task polls JobSpawner.get_next_pending_job() every 5s, marks found jobs as Running, builds TrainingJobParams, and dispatches to K8s via K8sDispatcher. On dispatch failure the job is marked Failed. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-27 22:45:57 +01:00