From 7edfae8569364373419d1c0301d1bfd26c581843 Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Mon, 14 Sep 2026 04:52:03 -0600 Subject: [PATCH] docs(agents): escalation_timeout default is 0 (wait indefinitely); nonzero opts into a bounded wait --- Agents.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/Agents.md b/Agents.md index 2ddc271..881d1b0 100644 --- a/Agents.md +++ b/Agents.md @@ -88,7 +88,7 @@ max_agent_depth: 3 # Max nesting depth (prevents runaway) inject_spawn_instructions: true # Inject spawning instructions into system prompt summarization_model: null # Model for summarizing sub-agent output (e.g. 'openai:gpt-4o-mini') summarization_threshold: 4000 # Char count above which sub-agent output is summarized -escalation_timeout: 300 # Seconds sub-agents wait for escalated user input (default: 5 min) +escalation_timeout: 0 # 0 = wait indefinitely for escalated user input (default); N = give up after N seconds ``` As mentioned previously: Agents utilize function calling to extend a model's capabilities. However, agents operate in @@ -572,7 +572,7 @@ see the [domain-reviewer](https://github.com/Dark-Alex-17/coyote/blob/main/asset | `inject_spawn_instructions` | boolean | `true` | Inject the default spawning instructions into the agent's system prompt | | `summarization_model` | string | current model | Model to use for summarizing long sub-agent output (e.g. `openai:gpt-4o-mini`) | | `summarization_threshold` | integer | `4000` | Character count above which sub-agent output is summarized before returning | -| `escalation_timeout` | integer | `300` | Seconds a sub-agent waits for an escalated user interaction response | +| `escalation_timeout` | integer | `0` | Seconds a sub-agent waits for an escalated user interaction response; `0` = wait indefinitely (default) | **Example configuration:** ```yaml @@ -838,9 +838,10 @@ the request is **automatically escalated** to the root agent: `agent__reply_escalation` to unblock the child 4. The child receives the reply and continues -The escalation timeout is configurable via `escalation_timeout` in the agent's `config.yaml` (default: 300 -seconds / 5 minutes). If the timeout expires, the child receives a fallback message asking it to use its -best judgment. +The escalation wait is configurable via `escalation_timeout` in the agent's `config.yaml` (default: `0` = +wait indefinitely, so autonomous runs never lose an approval while the user is away). When a nonzero +timeout is configured and expires, the child receives a fallback message asking it to use its best +judgment. | Tool | Description | |---------------------------|--------------------------------------------------------------------------|