Commit Graph

3 Commits

Author SHA1 Message Date
steve 306d575c31 critic: overflow-guard maxSteps += RaiseStepsBy (gadfly 5-model convergence)
executus CI / test (pull_request) Has been cancelled
A buggy/hostile Escalator returning a huge RaiseStepsBy could wrap handle.maxSteps
negative (which the executor reads as defer-to-base). Clamp at math.MaxInt.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 14:38:48 -04:00
steve 4ba83ab905 run: critic can raise a run's step ceiling mid-flight (CriticHandle.MaxSteps)
executus CI / test (pull_request) Failing after 1m1s
Adversarial Review (Gadfly) / review (pull_request) Successful in 21m8s
Prerequisite for a full-fidelity mort agentcritic adapter (which adjusts a
healthy-but-long run's iteration budget, not just its deadline). executus's
CriticHandle was deadline+steer only; this adds the dynamic step ceiling above
an unchanged majordomo (which already exposes WithMaxStepsFunc).

- run.RunInfo += MaxIterations (the run's base ceiling, so a critic can raise it
  relative to the baseline).
- run.CriticHandle += MaxSteps() int — polled by the executor each step via
  agent.WithMaxStepsFunc; <=0 defers to the base. The executor uses
  WithMaxStepsFunc(critic.MaxSteps) when a critic is active, else WithMaxSteps.
- critic battery: handle.maxSteps (initialised from RunInfo.MaxIterations) +
  MaxSteps(); Decision gains RaiseStepsBy so an Escalator can raise the ceiling
  alongside ExtendBy. ExtendOnce default is unchanged (time-only).

Test: a critic returning MaxSteps=5 lets a base-MaxIterations=1 run complete two
tool-dispatch steps past the base ceiling. Core stays battery-free (run doesn't
import critic).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 14:16:03 -04:00
steve dc2d4ec425 P4c: remaining batteries — checkpoint + schedule + critic
executus CI / test (push) Failing after 1m6s
Completes the P4 battery set (squashed onto main from phase-4c-batteries).
- checkpoint/: run.Checkpointer durable-resume (CheckpointStore + throttled
  handle + Memory).
- schedule/: generic cron Runner (Tick/Loop; no cron grammar of its own).
- critic/: two-tier timeout watchdog (run.Critic) + Escalator policy seam +
  ExtendOnce default.
Includes the verified gadfly #6 fixes (ExtendOnce per-run, Kill-sticky, watch
panic-recovery; checkpoint throttle-after-success; schedule Next-before-Run +
nil-guard + Loop recovery).

P4 battery set complete: audit, budget, persona, skill, checkpoint, schedule,
critic — each nil-safe, each with a default, each core-import-clean. Executor
wiring for Critic/Checkpointer remains a P2 follow-up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 00:15:32 -04:00