Class: AgentRequestJob

Inherits:
ApplicationJob show all
Defined in:
app/jobs/agent_request_job.rb

Overview

Executes an LLM agent loop as a background job with retry logic for transient failures (network errors, rate limits, server errors).

Emits events via Events::Bus as it progresses, making results visible to any subscriber (TUI, WebSocket clients). All retry and failure notifications are emitted as Events::SystemMessage to avoid polluting the LLM context window.

Examples:

Inline execution (TUI)

AgentRequestJob.perform_now(session.id)

Background execution (future Brain/TUI separation)

AgentRequestJob.perform_later(session.id)

Instance Method Summary collapse

Instance Method Details

#perform(session_id) ⇒ Object

Parameters:

  • session_id (Integer) —

    ID of the session to process



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
 
# File 'app/jobs/agent_request_job.rb', line 43

def perform(session_id)
  session = Session.find(session_id)

  # Atomic: only one job processes a session at a time. If another job
  # is already running, this one exits — the running job will pick up
  # any pending messages after its current loop completes.
  return unless claim_processing(session_id)

  agent_loop = AgentLoop.new(session: session)
  loop do
    agent_loop.run
    promoted = session.promote_pending_messages!
    break if promoted == 0
  end
ensure
  release_processing(session_id)
  agent_loop&.finalize
end