> ## Documentation Index
> Fetch the complete documentation index at: https://maestro.rasa.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Context Management

> How Maestro stays coherent without overwhelming the model.

A long conversation produces a lot of history. Maestro's job is to stay coherent
across all of it while giving the LLM only what it needs on any given turn. It
does this at three levels.

## The tracker

Everything that happens (messages, replies, tool calls, results, and every
change to what the agent knows) is written to an append-only log called the
**tracker**. This is the source of truth. It survives across turns and sessions;
if the same user returns, the history is still there.

The tracker is complete but large, which is exactly why it is *not* what the LLM
sees each turn.

## Scoped context

Maestro does not dump the full log into the LLM. Each turn, at step 2 of the
[runtime loop](/maestro/runtime-loop), it builds a **focused view**: the active
skill's instructions, only the tools that are relevant right now, and the memory
values that actually matter. Keeping the context tight is what keeps the agent
fast and on-topic, and it's how [guardrails](/maestro/guarantees) like `if:`
markers work: a stripped branch simply isn't in the prompt.

Memory is scoped per skill. A skill can mark values as **public**, and that is
how skills share results: a later skill never re-asks for something an earlier
one already collected. See [Memory](/concepts/memory) for the schema and
visibility rules.

## Memory outlives the task

A value set during a skill stays set when that skill ends, and remains readable
for the rest of the conversation. This is what stops a later skill re-asking for
something the customer already said.

The exception is the bundled default skills, such as the greeting and wrap-up.
Those reset their own declared entries on activation so each run starts clean.
Skills you write keep their values.

## Answering from references

When a user asks something no skill covers, Maestro searches your
[references](/concepts/references) and answers from what it found. If the
knowledge base has no answer, the model declines through the built-in
`cannot_help` tool rather than guessing, and the bundled decline skill delivers
the message. Redeclare its responses in your own `responses.yml` to change the
wording.

## Reference

Memory types, visibility, and access control are documented in the
[`memory.yml` reference](/reference/memory-yml).