Skip to main content

Overview

AURA manages per-request state (cancellation tokens, subscriptions) across streaming SSE connections. This document covers the lifecycle, timeout configuration, and known limitations.

Request Flow


Timeout Configuration

Production Defaults

Rationale

  • First chunk timeout (90 sec): Catches provider connection failures early. If the LLM hasn’t sent any data within this window, the request is aborted rather than hanging for the full stream timeout. The window is sized for reasoning models, which can legitimately take over a minute before the first chunk.
  • Stream timeout (15 min): Supports long-running MCP tools. Set to 0 to disable (not recommended).
  • Heartbeat (15 sec): Standard SSE keepalive. Detects disconnect during silent tool execution.

Tool Event Correlation

Rig spawns tool execution in separate tokio tasks. The hook context (where the LLM decides to call a tool) and the execution context (where MCP actually runs) are decoupled, requiring a mechanism to correlate tool_call_id across these boundaries — AURA does this with a per-request FIFO queue. This relies on Rig’s streaming mode executing tools sequentially within a request; see Rig Fork Changes for the validation methodology if you’re tracking Rig upstream compatibility.

Cleanup Mechanism

Request resources (cancellation registration, progress/tool-event subscriptions) are cleaned up via an RAII guard that ensures cleanup runs even on panic. If the async runtime is already gone (process exit), cleanup is skipped — resources are reclaimed with the process.

MCP Cancellation

On client disconnect or timeout:
  1. The cancellation token signals all waiting code
  2. Aura sends notifications/cancelled to MCP servers
  3. The agent is evicted from its connection pool to prevent stale connections
MCP servers receive the cancellation notification and can abort in-progress operations.

Graceful Shutdown

The server uses a two-phase shutdown with separate cancellation tokens:

Shutdown Sequence

  1. SIGTERM/SIGINT received
  2. Phase 1 (immediate): shutdown_token cancelled — middleware returns 503 for all new requests
  3. Grace period: In-flight streams continue running for up to SHUTDOWN_TIMEOUT_SECS (default 30s). Streams that complete naturally during this window are unaffected.
  4. Phase 2 (drain): stream_shutdown_token cancelled — remaining streams:
    • Cancel hook + request registry (stops in-flight MCP tool execution)
    • Send [DONE] to client (before MCP cleanup, so client gets clean termination)
    • Run MCP cleanup (send notifications/cancelled, close connections)
    • No pool eviction (pool is dying with the server)
  5. Server stops: Workers have 10s to complete Phase 2 cleanup

Shutdown vs Disconnect/Timeout