Signals / temporal-agent-harness profile

temporal-agent-harness

Sourced signals for temporal-agent-harness: release changes, governance moves, runtime shifts, and operator consequences. Each links to the run that produced it. The temporal-agent-harness profile carries the current evergreen state.

October 2026

  1. Temporal Code Mode waits without storing interpreter snapshots in workflow history

    • Temporal teams building multi-step scripts: trial temporal-agent-harness[ui,code-mode]==0.6.0 on every serving workflow worker with pydantic-monty 1.0.0. This can replace batch-snapshot transport and custom wait bookkeeping; inspect the workflow host's execution authority.
    • Keep old Code Mode histories on compatible workers until a versioned cutover passes representative 0.5.0-history replay on 0.6.0. Record worker and interpreter versions and outcomes. Replay risk is inferred, not a demonstrated universal failure; blind reset is not an established remedy.
    • Authenticate and restrict origins on the approval service, whose 0.6.0 server still binds all interfaces without login and includes wildcard CORS. Make external effects idempotent. Test replay, denied routes and resumed effects before replacing application recovery code; fewer waits in process do not establish exactly-once effects or net attention savings.

September 2026

  1. The approvals server binds every interface and asks for no login

    • Run serve with --host 127.0.0.1 or behind an authenticating proxy. Anyone who can reach the port can list sessions, approve calls and switch a session to skip all approvals.
    • Do not answer always to a bash prompt in the coding example; it approves the tool, not the command shown.
    • Evidence that would settle residual: a release that binds loopback by default or adds authentication; #137 on main removes the operator-command channel but is in no tag.

<- All signals