Files
executus/run/critic.go
T
steve 390e6cf905
executus CI / test (pull_request) Successful in 46s
Adversarial Review (Gadfly) / review (pull_request) Successful in 22m30s
run: critic parity — fuller RecordStep + cause-carrying Kill (distinct status)
Completes the run-critic seam so a host adapter (mort's agentcritic) has full
fidelity, closing the two limitations gadfly surfaced on mort #1334.

- RecordStep(iter int, resp *llm.Response): the completed step's model response
  is now passed to the critic (was index-only), so a host that records a trace
  (mort's ProgressRecorder) can show what the agent actually produced, not just
  an iteration count. The executor forwards s.Response; the battery ignores it
  (its Progress is count-based).
- CriticHandle.KillCause() error + ErrCriticKill: the executor now distinguishes
  an explicit critic KILL from a natural backstop expiry. runCtx uses a
  cause-carrying cancel (WithCancelCause + a MaxRuntime timer cancelling with
  DeadlineExceeded); the deadline-watch cancels with ErrCriticKill when
  KillCause()!=nil, else DeadlineExceeded. statusFor reads context.Cause →
  killed / timeout / cancelled are now distinct (were all "cancelled"). The
  battery sets killCause from Decision.KillReason on a Kill.

Tests: statusFor "killed" case (cause=ErrCriticKill, err=Canceled); fake handle
+ battery RecordStep/KillCause signatures. Core stays battery-free.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 16:35:13 -04:00

125 lines
4.4 KiB
Go

package run
import (
"context"
"fmt"
"time"
"gitea.stevedudenhoeffer.com/steve/majordomo/agent"
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)
// criticDeadlineCheck is how often the deadline-watch goroutine polls the
// critic's hard deadline. Small relative to any realistic soft timeout.
const criticDeadlineCheck = time.Second
// criticBinding wires a CriticHandle into a run: the executor forwards activity
// (steps + tool starts) to it, binds the run's hard cancellation to the critic's
// extendable deadline, and exposes the critic's Steer messages as an agent
// RunOption. All methods are nil-safe so the executor can call them
// unconditionally when no critic is configured.
type criticBinding struct {
h CriticHandle
}
// startCritic begins critic monitoring for this run when one is configured and
// the agent enables it. It launches a goroutine that cancels runCtx (via
// cancelCause) the moment the critic's hard deadline passes — the critic may
// extend that deadline, so a healthy-but-slow run is given room while a hung one
// is killed. When the deadline passes because the critic KILLED the run
// (KillCause() != nil), the cancellation cause is ErrCriticKill (→ status
// "killed"); when the backstop simply expired, it is context.DeadlineExceeded (→
// "timeout"). Returns (nil, no-op stop) when there is no critic. The caller MUST
// defer the returned stop.
func (e *Executor) startCritic(runCtx context.Context, cancelCause context.CancelCauseFunc, ra RunnableAgent, info RunInfo) (*criticBinding, func()) {
noop := func() {}
if e.cfg.Ports.Critic == nil || !ra.Critic.Enabled {
return nil, noop
}
soft := e.cfg.Defaults.CriticSoftTimeout
if soft <= 0 {
soft = 90 * time.Second // defensive: withFallbacks normally guarantees >0
}
h := e.cfg.Ports.Critic.Monitor(runCtx, info, soft)
if h == nil {
return nil, noop
}
done := make(chan struct{})
go func() {
// A host CriticHandle.Deadline() that panics must not crash the process
// (this runs on its own goroutine, so the executor's top-level recover
// can't catch it). Log-free best-effort: just stop watching.
defer func() { _ = recover() }()
t := time.NewTicker(criticDeadlineCheck)
defer t.Stop()
for {
select {
case <-done:
return
case <-runCtx.Done():
return
case <-t.C:
// A zero deadline = no hard cap (not yet set); otherwise cancel
// once we're at or past it, distinguishing an explicit kill from a
// natural backstop expiry so the run gets the right status.
if d := h.Deadline(); !d.IsZero() && !time.Now().Before(d) {
if cause := h.KillCause(); cause != nil {
cancelCause(fmt.Errorf("%w: %s", ErrCriticKill, cause.Error()))
} else {
cancelCause(context.DeadlineExceeded)
}
return
}
}
}
}()
return &criticBinding{h: h}, func() {
close(done)
h.Stop()
}
}
func (b *criticBinding) recordStep(iter int, resp *llm.Response) {
if b != nil {
b.h.RecordStep(iter, resp)
}
}
// recordToolStart forwards a tool call to the critic. NOTE: majordomo's step
// observer only fires AFTER an iteration completes, so this currently lands
// post-tool, not at dispatch — the activity clock is refreshed once per
// iteration, not mid-tool. A single very long tool call (e.g. a 30-min render)
// therefore won't refresh the clock until it returns; a host that runs such
// tools should feed interim progress to its Critic (mort's InstallProgressBridge
// pattern). A true pre-dispatch refresh needs a majordomo hook (follow-up).
func (b *criticBinding) recordToolStart(name, args string) {
if b != nil {
b.h.RecordToolStart(name, args)
}
}
// maxStepsOption returns the agent step-ceiling Option. With no critic it's a
// fixed WithMaxSteps(base); with a critic it's a DYNAMIC WithMaxStepsFunc that
// polls the handle each step (so the critic can raise a long run's budget),
// falling back to base when the handle defers (MaxSteps() <= 0).
func (b *criticBinding) maxStepsOption(base int) agent.Option {
if b == nil {
return agent.WithMaxSteps(base)
}
return agent.WithMaxStepsFunc(func() int {
if n := b.h.MaxSteps(); n > 0 {
return n
}
return base
})
}
// steerOptions returns the agent RunOptions that drain the critic's steer
// messages into the loop. Empty when there is no critic.
func (b *criticBinding) steerOptions() []agent.RunOption {
if b == nil {
return nil
}
return []agent.RunOption{agent.WithSteer(b.h.Steer)}
}