AgentXchain v2.47.0
v2.47.0 ships the run provenance surface and corrects terminal-state bootstrap behavior for continuation and recovery runs.
Run Provenance
Governed runs now carry explicit provenance metadata: trigger, parent_run_id, trigger_reason, and created_by. This closes the observability gap for long-horizon delivery chains where operators need to trace why a run was started and what it continues or recovers from.
CLI flags
| Flag | Description |
|---|---|
--continue-from <run_id> | Start a fresh run from a prior completed run, with trigger=continuation |
--recover-from <run_id> | Start a fresh run from a prior blocked run, with trigger=recovery |
Lineage query
agentxchain history --lineage <run_id> walks the parent_run_id chain to show the full ancestry of a run.
Provenance in operator surfaces
agentxchain statusnow shows anOrigin:line for non-manual provenance (e.g.,continuation from run_abc ("Continue after blocked review"))agentxchain status --jsonincludes a top-levelprovenancefieldagentxchain reportrenders provenance in text, markdown, and JSON formatsagentxchain exportincludes normalized provenance insummary.provenanceagentxchain historyshows aTriggercolumn withmanual,continuation,recovery,intake,schedule,coordinator, orlegacy
Terminal-State Bootstrap Fix
agentxchain run --continue-from and --recover-from now correctly bootstrap a fresh run envelope from terminal state. Previously, provenance-linked runs from a completed or blocked run reused the terminal state instead of initializing a new run, resulting in zero turns executed and no provenance written.
Behavior
agentxchain runfromcompletedstate starts a fresh manual runagentxchain run --continue-from <run_id>from any terminal state starts a fresh continuation runagentxchain run --recover-from <run_id>fromblockedstate starts a fresh recovery run- Fresh bootstrap resets phase, gate status, budget, and active turns from config truth
CLI Truth Corrections
--recover-fromhelp text no longer referencesfailedstate (onlyblockedis a valid recovery source)history --statusfilter help no longer listsfailedas a filterable status
Evidence
- 3462 tests / 741 suites / 0 failures
- Provenance E2E: 3 subprocess tests proving continuation, recovery, and plain rerun from terminal state
- Docusaurus production build clean