Skip to main content

AgentXchain v2.155.61

v2.155.61 fixes BUG-107: Full Auto Mode now recovers the stranded shape where a continuous session is marked paused even though the governed run is still active, unblocked, and dispatchable. This was discovered in the real tusq.dev DOGFOOD-100 run after [email protected] accepted dev turn turn_fc4027d5c8789062, advanced to QA, then exited with session cont-7dc5b5df paused at strict counter 89.

Bug Fixes​

  • BUG-107: recover paused active continuous sessions. advanceContinuousRunOnce() now detects a paused continuous session whose governed run is still active, unblocked, and ready for a next role, sets the session back to running, emits continuous_paused_active_run_recovered, and continues the same governed run.
  • Preserve CLI-owned continuous session identity. agentxchain run --continuous now adopts an existing paused or running CLI-owned continuous session with the same vision path instead of replacing it on reinvocation. This keeps DOGFOOD-100 same-session evidence intact.
  • Keep legitimate pauses fail-closed. Pending approvals, queued approvals, blockers, run-ID drift, missing next-role resolution, and failed retained active turns such as failed_acceptance remain non-recoverable by this path.
  • Tighten auth negative-test fixtures. Connector check, connector validate, and governed doctor auth-hang tests now explicitly blank inherited Claude auth environment variables so shell-level credentials cannot mask the intended negative case.

Evidence​

  • npm test -- --test-timeout=60000 -> 7320 tests / 1483 suites / 0 failures / 0 skipped

Tester Re-Run Contract​

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

For BUG-107: resume tusq.dev from continuous session cont-7dc5b5df and governed run run_083e290f5ee318f4 using the shipped package. The CLI must preserve the existing session ID, emit continuous_session_resumed, emit continuous_paused_active_run_recovered, and dispatch the natural QA turn from the stranded QA phase without manual staging JSON edits, accept-turn, unblock, or gate mutation.

For BUG-106 carry-forward: undeclared non-zero verification.machine_evidence[] exit codes under verification.status: "pass" must still auto-normalize to matching expected_exit_code values.

For BUG-105 carry-forward: strict intent coverage must still search normalized verification evidence summaries and remaining command-shaped machine evidence after staged-result normalization.

For BUG-104 carry-forward: typed verification observations must still be moved out of machine_evidence[] while preserving them in evidence_summary.

For BUG-103 carry-forward: decisions[].title must still normalize into required statement fields before validation.

For BUG-102 carry-forward: deliberate negative-case verification commands with explicitly expected non-zero exits must still accept.

For BUG-101 carry-forward: decision objects that include summary plus rationale must still normalize summary into missing statement fields while decisions with no statement source fail closed.

For BUG-100 carry-forward: productive retries-exhausted local_cli timeout blockers must still auto-retry once with a 60-minute deadline, while silent/no-output failures remain fail-closed.

For BUG-99 carry-forward: pre-acceptance gate_semantic_coverage must still evaluate workflow-kit ownership with accepted turn history.

For BUG-98 carry-forward: retained QA skip-forward requests from implementation to launch must still normalize to immediate next phase qa, with stale proposed_next_role aligned only when routing-safe.

For BUG-97 carry-forward: retained active-turn run_id drift must still auto-normalize only when the staged turn_id proves active-turn ownership.

For BUG-96 carry-forward: decision entries that include existing decision text but omit rationale must still auto-normalize before schema validation.

For BUG-95 carry-forward: staged results that use files_modified instead of files_changed and omit runtime_id, summary, artifact, and proposed_next_role must still auto-normalize before schema validation.

For review-only carry-forward: a review_only role with missing or empty objections must still fail protocol challenge enforcement.

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.