- 13 commands with full gRPC implementations: service, train, tune, model, trade, broker, agent, data, risk, config, cluster, auth, backtest - Streaming support: train logs --follow, broker executions --follow - --json output on every command via OutputFormat/HumanReadable - Fix web-gateway monitoring URL default (50057 → 50051, API Gateway) - Rewire 7 remaining build.rs to consolidated proto/ root (web-gateway, backtesting_service, training_uploader, 3 test crates, e2e) - Fix web-gateway ml_training.proto new fields (mode, max_epochs, resume) - 75 fxt tests + 139 web-gateway tests, 0 clippy warnings, workspace clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
training_uploader
K8s sidecar that uploads training artifacts to S3 and reports completion via gRPC.
Usage
Deployed as a sidecar container alongside training jobs. Watches for training artifacts (checkpoints, metrics) and uploads them to the configured S3 bucket.
Configuration
S3_BUCKET— target bucket for artifactsTRAINING_SERVICE_URL— gRPC endpoint for completion reporting