Architecture

Agent work and durable state

How application objectives, agent execution, and managed delivery stay connected across sessions.

Maintaining a managed application involves two kinds of state: the application's records and the work used to change its behavior. Redgold keeps issues, conversation history and delivery evidence so a change can be understood beyond one agent session.

From objective to execution

A workstream groups an application objective and its issues. An issue carries a bounded change, dependencies and acceptance criteria. An assigned agent works in a repository workspace, reads the relevant context, edits the application contract and records verification evidence. Fleet capacity and scheduling policy determine when eligible work can start.

flowchart LR
  Work[Workstream objective] --> Issue[Issue and acceptance criteria]
  Issue --> Run[Assigned agent run]
  Run --> Workspace[Repository workspace]
  Run --> History[Conversation and tool history]
  Workspace --> Review[Diff and checks]
  Review --> Delivery[Managed publication and verification]
  Delivery --> Issue

The agent runtime and the application runtime serve different purposes. An agent workspace is where a change is authored. The deployed pipeline executor serves application requests. Closing an authoring session is not an application shutdown; starting an agent is not an application deployment.

What survives, and where

StateDurable record or boundaryRecovery implication
Objective and acceptanceWorkstream, issue and commentsAnother run can recover the task's purpose
Source changesWorkspace checkout and Git commitsInspect local edits and the recorded revision before continuing
Conversation and tool activityPersisted session historyRecover prior evidence; do not assume identical model replay
Current processAgent runtimeA restarted process may need a fresh session and context
Intended releaseReviewed Git change and published artifactsIdentify what was approved
Running releaseDeployment and verification evidenceConfirm what actually reached users
Application dataManaged datasetsIndependent of the authoring session's lifetime

Persistent workspace storage supports continuity across sessions. It does not make every terminal process or in-memory context durable. Before recovering an interrupted run, inspect the issue, workspace diff, commit and latest check result. Avoid starting a second writer while the original assignment may still be active.

Coordination and authority

A proposed workstream can hold issues before its human approval. Automatic scheduling checks the workstream root's approval and pause policy, together with issue eligibility and capacity. Adding an issue does not prove it was dispatched; a dispatch acknowledgement does not prove the agent has started.

Application permissions, repository permissions and approval decisions remain separate from task instructions. A prompt to connect an external system cannot grant credentials or tenant access. Redgold supplies the managed execution environment; the configured account policy determines which actions it may take.

Recovery follows the last verified boundary

If tests failed, resume from the failure and changed files. If a change merged but publication failed, recover delivery for the approved revision. If deployment succeeded but the smoke request failed, investigate the running contract and application data. Repeating the whole task can create duplicate edits or writes.

For externally hosted repositories, the same work records can lead to an external pull request and that repository's checks. Its hosting and release policy remain with the configured external system. See agent lifecycle and supervision and recovery for the customer workflow.

Copyright © 2026