feat(run): durable checkpoint + resume (wire Ports.Checkpointer)

The kernel defined run.Ports.Checkpointer + the checkpoint battery but never
drove them (the documented "P2 follow-up"). This wires durable recovery into
the run loop so a run interrupted by shutdown can resume on the next boot
instead of being lost — the executus-side half of mort's durable-agent-recovery
parity (mort #1355).

Kernel (run/):
- Ports.Checkpointer is now a CheckpointerFactory (Begin per run → a per-run
  Checkpointer, or nil for a non-durable run). The single per-instance
  Checkpointer couldn't distinguish runs; a factory mints one per run, matching
  mort's agentexec.CheckpointerFactory.
- RunInfo gains GuildID + ModelTier (so the factory can build resume meta);
  RunCheckpointState gains CompletedPhases + ActivePhase (+ PhaseOutput).
- run/checkpoint.go: ResumeState + WithResumeState / WithExistingCheckpointer
  context carriers, classifyCheckpointOutcome (success→Complete, shutdown→leave
  for boot recovery, else→Fail using run.ErrShutdown), and finalizeCheckpoint.
- run/executor.go: resolve the per-run checkpointer (existing-from-ctx on a
  recovery re-run, else factory.Begin); single-loop wraps the step observer to
  accumulate the transcript + Save each step (host throttles), and a recovered
  run seeds the saved transcript via WithHistory and continues with no new
  input; finalize on exit.
- run/phases.go: phase-boundary checkpointing — record completed phases after
  each phase; a resumed run skips already-completed phases (the interrupted
  phase re-runs from its start — boundary-granular, documented; only the
  single-loop path resumes mid-loop).

Battery (checkpoint/): NewFactory wires the battery into the factory port
(per-run handle, meta derived from RunInfo); RunCheckpoint + handle.Save carry
the phase fields.

Tests (run/checkpoint_test.go): the finalize decision matrix; single-loop
Save+Complete; terminal-error Fail; resume seeds history; phase-boundary Saves
completed phases; resume skips completed phases. Full ./... green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

checkpoint/checkpoint.go

@@ -4,9 +4,9 @@
 // run.Ports.Checkpointer.
 //
 // Mort backs CheckpointStore with its durable-job table; Memory() is the
-// zero-dependency default; contrib/store can add a SQLite one. NOTE: the
-// executor's call into run.Ports.Checkpointer is a P2 follow-up — this battery
-// provides the seam + impls ahead of that wiring.
+// zero-dependency default; contrib/store can add a SQLite one. The executor calls
+// run.Ports.Checkpointer (a CheckpointerFactory) during the run loop; NewFactory
+// wires this battery into that seam.
 package checkpoint
 
 import (
@@ -14,6 +14,8 @@ import (
 	"time"
 
 	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+
+	"gitea.stevedudenhoeffer.com/steve/executus/run"
 )
 
 // RunCheckpointMeta is the run attribution needed to resume a run from scratch
@@ -32,11 +34,12 @@ type RunCheckpointMeta struct {
 
 // RunCheckpoint is one persisted snapshot of a run's resumable progress.
 type RunCheckpoint struct {
-	Meta        RunCheckpointMeta
-	Messages    []llm.Message // conversation so far
-	Iteration   int           // completed agent-loop iterations
-	ActivePhase string        // current phase name (multi-phase agents); "" otherwise
-	UpdatedAt   time.Time
+	Meta            RunCheckpointMeta
+	Messages        []llm.Message     // conversation so far (single-loop or active phase)
+	Iteration       int               // completed agent-loop iterations
+	CompletedPhases []run.PhaseOutput // finished phases, in order (multi-phase agents)
+	ActivePhase     string            // current phase name (multi-phase agents); "" otherwise
+	UpdatedAt       time.Time
 }
 
 // CheckpointStore persists run checkpoints keyed by run id. A live checkpoint

checkpoint/handle.go

@@ -54,10 +54,12 @@ func (h *handle) Save(ctx context.Context, st run.RunCheckpointState) error {
 	// caller believes was saved. (A run drives one Save goroutine, so the brief
 	// unguarded window here can't double-write.)
 	if err := h.store.Save(ctx, RunCheckpoint{
-		Meta:      h.meta,
-		Messages:  st.Messages,
-		Iteration: st.Iteration,
-		UpdatedAt: now,
+		Meta:            h.meta,
+		Messages:        st.Messages,
+		Iteration:       st.Iteration,
+		CompletedPhases: st.CompletedPhases,
+		ActivePhase:     st.ActivePhase,
+		UpdatedAt:       now,
 	}); err != nil {
 		return err
 	}
@@ -81,3 +83,41 @@ var _ run.Checkpointer = noop{}
 func (noop) Save(context.Context, run.RunCheckpointState) error { return nil }
 func (noop) Complete(context.Context) error                     { return nil }
 func (noop) Fail(context.Context, error) error                  { return nil }
+
+// factory is a run.CheckpointerFactory that mints a per-run handle over store,
+// deriving the per-run meta from the kernel's RunInfo. It is the battery's glue
+// for the Ports.Checkpointer (factory) seam: every run becomes durable (the
+// store persists snapshots; a host wanting lazy/short-run skipping uses its own
+// factory, as mort does over its durable-job table).
+type factory struct {
+	store    CheckpointStore
+	throttle time.Duration
+	now      func() time.Time
+}
+
+var _ run.CheckpointerFactory = (*factory)(nil)
+
+// NewFactory returns a run.CheckpointerFactory backed by store: each run gets a
+// per-run Checkpointer (throttled to at most once per throttle). A nil store
+// yields factory.Begin returning a no-op Checkpointer.
+func NewFactory(store CheckpointStore, throttle time.Duration) run.CheckpointerFactory {
+	return &factory{store: store, throttle: throttle}
+}
+
+// Begin mints the per-run Checkpointer. The prompt is read from
+// info.Inputs["prompt"] when present so a recovered run can re-dispatch.
+func (f *factory) Begin(_ context.Context, info run.RunInfo) (run.Checkpointer, error) {
+	prompt, _ := info.Inputs["prompt"].(string)
+	meta := RunCheckpointMeta{
+		RunID:       info.RunID,
+		AgentID:     info.SubjectID,
+		AgentName:   info.Name,
+		CallerID:    info.CallerID,
+		ChannelID:   info.ChannelID,
+		GuildID:     info.GuildID,
+		Prompt:      prompt,
+		ModelTier:   info.ModelTier,
+		ParentRunID: info.ParentRunID,
+	}
+	return New(f.store, meta, f.throttle, f.now), nil
+}