Obsidian Retry¶
Synchronous bridge-aware retry for Obsidian-dependent capabilities. Checks bridge health before each attempt, waits between retries, and returns a structured result. Use when you need the result before proceeding (e.g., step 1 of a multi-step task). For fire-and-forget retries, the gateway's automatic background retry handles it.
MCP name: obsidian_retry
Category: obsidian
Parameters¶
| Name | Type | Required | Description |
|---|---|---|---|
max_retries |
int |
No | Maximum number of attempts including the first (default: 3) |
operation_id |
str |
Yes | Operation ID from a previously failed or timed-out call (included in wb_run/consent_request timeout returns; visible via wb_status). Capability name and params are loaded from the record, so the agent does not re-supply them. If you don't have an operation_id you don't need retry — just call the capability directly; the gateway's automatic background retry handles transient bridge hiccups. |
wait_seconds |
int |
No | Seconds to wait between attempts (default: 60) |