Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.runaegis.co/llms.txt

Use this file to discover all available pages before exploring further.

A session in Aegis represents a single, continuous agent run, everything an agent does from the moment it starts a task to the moment it stops making tool calls. All actions within a run share a common session_id, which lets you view the complete history of what an agent did, in order, in one place. Sessions are created automatically; you do not configure or start them manually.

How sessions are created

When an agent makes its first MCP tool call through Aegis, Aegis records the session_id embedded in the call. Every subsequent call from the same agent run with the same session_id is grouped into that session. If an agent starts a new task and generates a new session_id, Aegis opens a new session automatically. You never need to declare or initialize a session. The aggregation happens on the backend as actions arrive.

Session fields

Each session surfaces the following information in the Aegis dashboard:
FieldDescription
session_idThe unique identifier for this agent run, generated by the agent
agent_nameThe name the agent reported when making tool calls
action_countTotal number of MCP tool calls made in this session
started_atTimestamp of the first action in the session
last_action_atTimestamp of the most recent action, useful for identifying whether a session is still active
reposList of GitHub repositories that were touched during this session
allowsCount of actions that received an ALLOW decision
deniesCount of actions that were blocked with a DENY decision
rewritesCount of actions that were redirected via a REWRITE decision
approvalsCount of actions that required or triggered a REQUIRE_APPROVAL decision
The sum of allows, denies, rewrites, and approvals equals action_count.

Individual actions within a session

Drilling into a session shows each individual tool call as a row. Every action includes:
FieldDescription
tool_nameThe GitHub MCP tool the agent called (e.g., push_files, create_pull_request)
action_summaryA plain-English description of what the action would do
decisionThe outcome Aegis assigned: ALLOW, DENY, REWRITE, or REQUIRE_APPROVAL
execution_timeHow long the action took to evaluate and (if allowed) execute, in milliseconds
blast_radiusSeverity rating: Low, Medium, High, or Critical
policyThe policy verdict, pass if all checks passed, or the enforced policy name if a rule fired
argumentsThe raw arguments the agent passed to the tool call
target_repoThe repository the action targeted
target_branchThe branch the action targeted, if applicable
Actions within a session are ordered by sequence_order, so you can follow the agent’s chain of reasoning step by step.

Viewing sessions in the dashboard

1

Open the Sessions page

Navigate to Dashboard → Sessions in the sidebar. The page lists all sessions, sorted by most recent activity. Each row shows the agent name, action count, start time, last activity time, and a summary of allow/deny/rewrite/approval counts.
2

Select a session

Click any session row to expand or navigate to its detail view. You will see the full list of individual actions in order, with their tool names, summaries, decisions, and blast radius ratings.
3

Inspect an action

Click an individual action row to see the full arguments, policy verdict, execution time, and any action pointers (human-readable bullet points that the backend generates for complex tool calls like PR creation).

How sessions relate to approvals

When an action in a session receives a REQUIRE_APPROVAL decision, the agent’s tool call does not return immediately. The session is effectively paused at that step, the agent waits for a human to act before it can continue. You review pending approvals from two places:
  • Dashboard home, the Pending approvals panel on the right side of the overview shows up to five queued actions. Each item displays the agent name, tool name, a plain-English summary, and Approve / Deny buttons.
  • Approvals page, navigate to Dashboard → Approvals to see the full list of all pending and historical approval requests.
When you click Approve, Aegis executes the held action immediately and returns the result to the waiting agent. The session then continues from where it paused. When you click Deny, Aegis sends an error back to the agent and discards the action. The agent receives a structured response indicating the action was denied and can decide how to proceed.
Multiple actions in the same session can be waiting for approval simultaneously if the agent made several qualifying tool calls in quick succession before any were reviewed.
The dashboard header badge shows the count of pending approvals across all sessions. Use it as a quick signal that an agent is waiting for you.