Skip to main content

AgentXchain v2.155.68

v2.155.68 closes BUG-113, found immediately after v2.155.67 recovered the retained Claude provider timeout in the strict Tusq DOGFOOD-100 session. The reissued QA turn launched Claude Code through an older Node binary, failed with TypeError: Object not disposable, and was misclassified as repeated stdout_attach_failed ghost startup. AgentXchain now recognizes that signature as Claude runtime incompatibility and can recover retained state when a compatible Node binary is available.

Bug Fixes​

  • BUG-113: Claude Node runtime recovery. Fresh Claude local CLI dispatches that emit the old-Node Object not disposable failure are classified as claude_node_incompatible, not generic ghost startup.
  • Compatible Node wrapper. When the configured command is claude, the local CLI adapter resolves a compatible Node binary and invokes the Claude CLI entrypoint through it, avoiding stale /usr/bin/env node PATH selection.
  • Retained DOGFOOD recovery. Continuous startup inspects retained stdout_attach_failed ghost logs for the Claude Node incompatibility marker and auto-reissues the retained turn when compatible Node is available, even if stale ghost retry state had already exhausted.

Evidence​

  • node --test test/local-cli-adapter.test.js -> 38 tests / 5 suites / 0 failures
  • node --test test/continuous-run.test.js -> 83 tests / 13 suites / 0 failures
  • npm test -- --test-timeout=60000 -> 7332 tests / 1485 suites / 0 failures / 0 skipped

Tester Re-Run Contract​

Verify: npx --yes -p [email protected] -c "agentxchain --version"

For BUG-113: resume tusq.dev from continuous session cont-7dc5b5df, run run_73ffb608f7c8a510, and retained QA turn turn_07b1ca892daef9dc using the shipped package. If the retained dispatch log contains TypeError: Object not disposable under old Node and a compatible Node binary is available, startup must reissue the retained turn without agentxchain reissue-turn, manual state edits, or operator-side accept-turn.

If the recovered QA turn accepts, append counter value 98 to Tusq turn-counter.jsonl within the DOGFOOD-100 window.

For BUG-112 carry-forward: retained Claude provider Request timed out failures must still auto-reissue via auto_retried_productive_timeout only when explicit timeout markers exist.

For BUG-111 carry-forward: retained Claude 401/authentication failures must still reclassify to dispatch:claude_auth_failed before timeout or ghost recovery.

For BUG-110 carry-forward: fresh Claude local CLI auth failures must still block once as dispatch infrastructure instead of consuming turn retries.

For BUG-109 carry-forward: supplemental auto-checkpoint recovery must still run automatically under --auto-checkpoint.

For BUG-108 carry-forward: terminal blocked steps must surface once and must not re-enter paused-active recovery loops.

For BUG-107 carry-forward: paused active continuous sessions must still preserve the existing session ID and recover only when the governed run is active, unblocked, and dispatchable.

Carry-forward tester checks for shipped-package closure proof:

  • BUG-54 startup watchdog evidence should quote startup_latency_ms, elapsed_since_spawn_ms, and runtimes.<id>.startup_watchdog_ms.
  • BUG-55/87 verification-output evidence should quote undeclared_verification_outputs, verification.produced_files, and git status --short after accept-turn followed by checkpoint-turn. Clean tree means BUG-55 is fixed for your reproduction.
  • BUG-52/53 continuous recovery evidence should quote phase_entered, reconciled_before_dispatch, and session_continuation.