A flaky MCP server that keeps dropping event streams now gets a pause instead of endless instant reconnects.
tengu_mcp_listen_reopen_park Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.233: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
tengu_mcp_listen_reopen_park_tuning Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.233: not a boolean we can read
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.233. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
When an MCP server repeatedly kills a held event-subscription stream, the client now counts reopens in a trailing window and, past a threshold, pauses re-listening for a jittered delay rather than reconnecting immediately. This is on by default (tengu_mcp_listen_reopen_park, fallback true).
- The window size and pause length come from a separate tuning flag
tengu_mcp_listen_reopen_park_tuning(fallback null), validated aswindowMax1-100 andparkDelayMinutes1-1440; with no server value the built-in constants apply. - Each pause logs a
tengu_mcp_listen_reopenevent with outcome "parked".
subscriptions/listen reopened ${i.length} times in the trailing window (the server keeps killing held streams); parking re-listen
Strings lifted out of the shipped bundle, so the claim above can be checked against them.