Bitter Frontier What coding agents just made possible, where the bottleneck moved, and what deserves attention.

Signals

2026-10-13 / temporal-agent-harness

Temporal Code Mode waits without storing interpreter snapshots in workflow history

Edited by Michael Ruescher

Runtime

Preview 0.6.0 (2026-10-03) moves Monty script stepping from batch activities into workflow workers. Scripts use workflow time and durable timers; suspended tool or human waits hold no interpreter subprocess. Host tools retain their dispatch semantics. The code-mode extra pins Monty 1.0.0, and no compatibility path for relevant 0.5.0 histories was established.

What this changes for operators

  • 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.

Primary sources

Signal metadata

Confidence
high

Source findings

Featured in

Run: 2026-10-13-profile-refresh-2026-09-21_2026-10-13-frontier-v0

Schema: bitter.frontier_signals.v0 / ID: 2026-10-13-temporal-agent-harness-code-mode-moves-into-workflow

Research evidence and publication history are open in the repository.