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

# Continue a paused task

> Resume bounded work while preserving its context and permissions.

When a human-requested task reaches a run limit, Mesh saves its context and asks
whether to continue. The original requester can reply in the same thread without
mentioning the agent again. This is available when the durable database is
configured; no per-agent switch is needed.

## What happens at the limit

The default work allowance is 60 model calls with a separate 30-minute wall-clock
backstop; operators can change those limits. The closing completion removes
tools and either delivers the finished result or explains what is done, what is
saved, and what remains. A hard deadline can use a saved-context fallback.
Explicit cancellation does not automatically ask to restart the task.

A pause ends the current run. Its consumed budget is not reset. Continuing starts
another bounded run with the saved task context and the requester's new message.
[Commitment](/runtime/commitments) attempts have separate authorization and cannot
treat their own notices as human consent.

## Replying to the pause

| Reply | Current behavior |
| - | - |
| Clear approval, such as “yes, keep going until the PR is ready” | Restore the task for another bounded run. Explicit approval does not require the fast model. |
| Clear decline or stop | Leave the task stopped. |
| New independent request | Answer the new request and leave the old task available for later continuation. |
| Ambiguous reply or unavailable classifier | Restore context for the primary model to judge the reply. It must not assume approval; a status question or partial instruction should receive an answer and a specific continuation question. |

Silence, a timer, a bot message, or a different participant cannot authorize
continuation. Source and audience checks bind the decision to the original
requester, agent, conversation, and message. An atomic transition allows one child
run to consume a pause. Every later exhausted allowance asks again.

The ambiguous path is conversational judgment, not a deterministic proof that the
person approved more work. Its instructions preserve the original scope and
require the model to resolve uncertainty before continuing that work.

## What survives

The checkpoint includes the objective, summary, admitted background, working
model/tool transcript, requester corrections, and source lineage. Restoration
regenerates current system policy and tool authority. Saved system/developer
instructions and raw image bytes are not replayed. Whole historical records are
selected under the ordinary prompt budget; the objective, progress summary, and
latest reply remain required context.

Completed declared external effects reuse their recorded results. An interrupted
operation without a recorded outcome is marked unknown, never assumed to have
failed. Shell and browser writes require inspecting actual state before retrying.

## Workspace retention

The default and maximum continuation hold is **14 days**. An idle-persistent
backend can retain a ready workspace during that window, which may incur idle
cost. A snapshot-only backend restores from its available checkpoint instead of
inheriting an expired sandbox reference. Neither mode guarantees every file
survives: the resumed run must inspect the workspace and report missing state.

Accepting continuation transfers an eligible workspace atomically; credentials
are resolved again. Decline or expiration makes retained work eligible for
cleanup. An unrelated question does not dismiss the paused task or its hold.
Backend changes fail safely rather than reusing an incompatible workspace.

The pause is saved before sending, and becomes eligible for consent only after
the delivered question is recorded. A failed or uncertain send is not an approved
continuation. [Restart recovery](/runtime/turn-checkpoints) handles a process exit
within a run; it is a different mechanism from renewing a finished run's allowance.

Implementation: [`internal/continuation` (repository)](https://github.com/TextureHQ/mesh/tree/main/internal/continuation)
and [`internal/turn/continuation.go` (repository)](https://github.com/TextureHQ/mesh/blob/main/internal/turn/continuation.go).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.