fleet-rlm

Delegate recursive work to child RLM sandboxes with budget management. Use when decomposing tasks into sub-queries, fanning out batched work, managing LLM call budgets, or building parent-child RLM hierarchies.

Diagnose fleet-rlm runtime failures, API contract drift, sandbox errors, and observability issues. Use when something is broken — Daytona connection failures, websocket mismatches, escalation not triggering, budget exhaustion, or missing traces.

Optimize fleet-rlm DSPy programs and RLM skill bundles using GEPA with MLflow tracking. Use when running optimization loops, designing feedback metrics, building training datasets, or comparing runs.

Hub skill for fleet-rlm: when to use dspy.RLM vs ReAct/CodeAct and which workflow skill to load next.

Design DSPy signatures and compose runtime modules for fleet-rlm tasks. Use when creating input/output field definitions, choosing between built-in signatures, selecting execution modes, or wiring custom modules.

Fetch and inspect JavaScript-heavy pages with Playwright in a Daytona browser-capable snapshot.

Process documents and codebases exceeding a single context window using canonical dspy.RLM variable mode in the Daytona REPL.

Execute Python in Daytona sandboxes with durable volume persistence. Use when running code, persisting results, inspecting volumes, managing workspace lifecycle, or validating Daytona connectivity.

Understand the pre-initialized Daytona volume filesystem. Use when operating inside a sandbox to know what directories exist, where to store state, how the memory DB works, and what guarantees hold across sessions.

Simplifies fleet-rlm backend by rewriting/deleting modules and updating tests

Simplify `src/fleet_rlm` internals while preserving or intentionally cleaning up validated public contracts.

Repair regressions discovered by validation during the `src/fleet_rlm` simplification mission.

Moves frontend files between directories, updates imports, renames symbols, and validates with type-check/lint/test/build.