MCP reconnect logic fixes and improvements
Cluster 66092 · mcp. Data as of
Nothing open on GitHub. Fix merged in #68658 on 21 Jul 2026. Check it covers your case.
The short answer
- Known?
- Yes. 3 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #68658. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #68658. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address how the MCP client handles reconnection when SDK task groups fail or drop, focusing on immediate reconnection, exception-group unwrapping, budget-bounded retries, and improved transition logging.
Open issues0
Open PRs0
Fixes on record
-
#68658 fix(mcp): budget-bounded reconnects, exception-group unwrapping, and per-transition logging
files:
tests/tools/test_mcp_failure_classification.py,tests/tools/test_mcp_rapid_drop_budget.py,tests/tools/test_mcp_reconnect_log_hygiene.py,tests/tools/test_mcp_transport_group_reconnect.py,tools/mcp_tool.py
1 PR closed without merging
From the close comments: merged via another change 1
-
#66271 fix(mcp): reconnect immediately on transport TaskGroup drop instead o… · merged via another change →
#68658
Closed issues · 1
- Closed#66092fix(mcp): catch SDK TaskGroup BaseExceptionGroup and reconnect immediately instead of backoff/park
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- mcp
- Merged PRs
- #68658
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 21 Jul 2026