fix(mcp): bump go-sdk to v1.8.0 so tool results carry resultType #748
No reviewers
Labels
No labels
breaking
bug
documentation
enhancement
epic
good first issue
help wanted
refactoring
resolution/duplicate
resolution/invalid
resolution/wontfix
security
severity/critical
severity/high
severity/low
severity/medium
status/abandoned
status/blocked
status/needs-decision
status/needs-info
status/needs-verification
testing
upstream
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
sixfold-space/madtea!748
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "issue-740-bump-go-sdk-1-8-0"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Summary
Protocol revision 2026-07-28 requires resultType on every tools/call result, and a conforming client rejects a result that omits it. madtea does not frame results itself; the go-sdk sets resultType at the session layer for new-protocol clients. v1.7.0 predated that, so some results went out without resultType and clients rejected them (seen on madt_issues search, madt_finish, madt_branch_delete). v1.8.0 emits it, so the fix is the SDK bump, not a per-handler change.
internal/mcp/result_type_test.go is an integration guard: on a 2026-07-28 session it checks that representative tool results carry resultType, and fails if the server is ever built on an SDK that stops emitting it.
Verified: full local gate green (test-race, govulncheck, gosec, osv-scanner, mcp-conformance); the resultType guard passes; the rebuilt binary reports go-sdk v1.8.0.
Closes #740
Closes #740