Qredence Documentation

Fleet RLM runs the native DSPy dspy.RLM loop. DSPy owns the loop, the REPL history, trajectory semantics, and provider retries. Fleet supplies Turn-scoped tools, budgets, and finalization. There is no second planner or model router.

Root and Sub models

Fleet configures two model roles in config/fleet.toml.

Role	Table	Used for
Root	`[llm.root]`	The main RLM loop that plans, writes Python, and produces the answer.
Sub	`[llm.sub]`	Semantic calls from Sandbox code through `llm_query` and `llm_query_batched`.

Both roles call an OpenAI-compatible Chat Completions endpoint through a stock dspy.LM. See Configure models.

Three ways to do sub-work

Pick the lightest option that solves the problem.

Option	Runs	Use it for
Sandbox Python	In the root Sandbox	Deterministic inspection, parsing, math, and reduction.
`llm_query`, `llm_query_batched`	Native DSPy semantic calls on the Sub model	Bounded semantic questions inside the current invocation, such as classifying or summarizing a chunk.
`rlm_query`, `rlm_query_batched`	A separate child RLM in its own Sandbox	An independent investigation that needs its own iterative loop.

Recursive child RLMs

rlm_query investigates one bounded task. rlm_query_batched runs several independent tasks in parallel and returns results in input order. Both are available only to the root RLM. Each call takes a task, a list of staged relative inputs, and an optional context. Fleet then:

Resolves the selected inputs under the Session’s authority.
Stages bounded copies in private scratch.
Runs the child in a Volume-less Daytona Sandbox, using FLEET_DAYTONA_CHILD_SNAPSHOT when set.
Validates and harvests declared result files.
Cleans up the child Sandbox.

Children stop at depth one and share the parent Turn budget. They receive no parent Workspace tools, memory, task checkpoint, publication capability, credentials, or writable Volume. The root RLM verifies child findings and owns every durable update. A Turn can’t commit successfully while a child or its cleanup is unresolved. Recursion is on in the shipped configuration. Set rlm.recursion_enabled = false and restart for native-only operation.

Turn budgets

Every Turn has a shared budget. When a dimension runs out, Fleet stops new work and finalizes.

Setting	Shipped value	Limits
`rlm.max_iters`	12	RLM loop iterations.
`rlm.max_llm_calls`	32	Prompts sent through `llm_query` and `llm_query_batched`.
`rlm.max_tool_calls`	256	Host tool calls.
`rlm.recursion_max_calls`	4	Child RLM calls.
`rlm.recursion_max_parallel_children`	4	Concurrent children. The maximum is 8.
`rlm.recursion_child_max_iters`	8	Iterations per child.
`rlm.recursion_child_max_llm_calls`	12	Semantic calls per child.
`runtime.turn_timeout_seconds`	1800	Wall-clock time for one Turn.
`rlm.wrap_up_seconds`	300	Part of the Turn deadline held back for finalization.

Fleet enforces no separate per-Turn deadline on the models themselves. See the configuration reference for every limit.

Fleet-RLM

Fleet Prime Agent

Fleet Pi

GEPA Omni

Qredence Skills

Fleet Reasoner

Qredence Plugins

Reasoning and recursion

Root and Sub models

Three ways to do sub-work

Recursive child RLMs

Turn budgets

​Root and Sub models

​Three ways to do sub-work

​Recursive child RLMs

​Turn budgets

Root and Sub models

Three ways to do sub-work

Recursive child RLMs

Turn budgets