[rudycelekli]

Bug

When a tool response is over the truncation limit, findArraysRecursive (internal/truncate/truncator.go) collects candidate record arrays by ranging over each JSON object, and chooseBestArray picks one. On a tie, chooseBestArray keeps whichever candidate came first. Go randomizes map iteration, so identical payloads with equally good sibling arrays get a different RecordPath on different calls. The read_cache handle minted for that response then pages a different array each time.

Trigger

An upstream tool returns, for example, {"zeta":[…20 rows], "alpha":[…20 rows], "mid":[…20 rows]} and the response is over the limit. content_forward.go calls Truncate on every such response. Repeated identical calls return record_path values of zeta, alpha, or mid depending on map order.

Fix

Object keys are now traversed in sorted order, so the tie-break is stable: the first key in sorted order wins. Non-tied selection is unchanged.

Verification

• go test -count=1 -run TestTruncate_TiedArraysPickStableRecordPath ./internal/truncate/ passes. The test runs 50 calls on the payload above and expects alpha every time.
• With truncator.go reverted (git stash push internal/truncate/truncator.go), the same test fails: call 0: record path "zeta", want "alpha".
• go test -count=1 ./internal/truncate/ passes.
• go vet ./internal/truncate/ is clean.
• gofmt -l internal/truncate/ is clean.
• I also ran go test -count=1 ./internal/server/ locally, but it hit the default 10-minute test timeout, which isn't a result either way. A narrower rerun failed at setup because of a local build-cache error. I'm relying on CI for that package.

Commands were run with GOFLAGS=-mod=readonly CGO_ENABLED=0.

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[Dumbris]

Verified: the PR test fails on main for the reason described and passes on this branch merged with main; race tests for the touched packages and CI lint (bare and server tags) are clean. Also built and tested together with the rest of this batch, independently reviewed, and cross-reviewed with a second model.

[Dumbris]

Merged. Thank you, @rudycelekli! read_cache record paths are stable when sibling arrays tie.