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>

@@ -84,0 +87,4 @@
+// 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

@@ -84,0 +92,4 @@
+type factory struct {
+	store    CheckpointStore
+	throttle time.Duration
+	now      func() time.Time

@@ -84,0 +100,4 @@
+// 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 {

@@ -84,0 +104,4 @@
+	return &factory{store: store, throttle: throttle}
+}
+
+// Begin mints the per-run Checkpointer. The prompt is read from

@@ -0,0 +20,4 @@
+// WithResumeState; the executor reads it (single-loop seeds the saved transcript
+// as history; multi-phase skips completed phases and seeds the active phase).
+type ResumeState struct {
+	History         []llm.Message // single-loop transcript OR active-phase transcript

@@ -0,0 +32,4 @@
+	return context.WithValue(ctx, resumeStateKey{}, rs)
+}
+
+func resumeStateFromContext(ctx context.Context) *ResumeState {

@@ -0,0 +51,4 @@
+	return cp
+}
+
+// checkpointOutcome is the finalize decision for a durable run.

@@ -0,0 +70,4 @@
+	switch {
+	case runErr == nil:
+		return checkpointComplete
+	case errors.Is(cause, ErrShutdown):

@@ -0,0 +83,4 @@
+	if cp == nil {
+		return
+	}
+	switch classifyCheckpointOutcome(runErr, cause) {

@@ -183,0 +185,4 @@
+	// Durable recovery (optional): a recovered run carries a ResumeState (prior
+	// transcript / completed phases) + an existing Checkpointer in ctx so it
+	// continues on the SAME durable record; a fresh run mints a per-run
+	// Checkpointer via the factory (which decides durability — nil = non-durable).

@@ -183,0 +190,4 @@
+	resume := resumeStateFromContext(ctx)
+	ckpt := existingCheckpointerFromContext(ctx)
+	if ckpt == nil && e.cfg.Ports.Checkpointer != nil {
+		if c, cerr := e.cfg.Ports.Checkpointer.Begin(ctx, info); cerr == nil {

@@ -333,0 +351,4 @@
+		// transcript as history and continues with no new input. acc starts from the
+		// resume history (or the opening user message) and grows as steps complete.
+		obs := stepObserver
+		if ckpt != nil {

@@ -333,0 +364,4 @@
+				if len(s.Results) > 0 {
+					acc = append(acc, llm.ToolResultsMessage(s.Results...))
+				}
+				_ = ckpt.Save(runCtx, RunCheckpointState{Messages: acc, Iteration: s.Index + 1})

@@ -355,1 +401,4 @@
 
+	// Finalize durable recovery: clear the checkpoint on success/terminal failure,
+	// or leave it for boot recovery when the run was interrupted by shutdown.
+	finalizeCheckpoint(ctx, ckpt, runErr, context.Cause(runCtx))

@@ -64,6 +64,13 @@ type phaseDeps struct {
 	stepObserver func(agent.Step)
 	steer        func() []llm.Message
 	rec          RunRecorder
+	// checkpointer records phase-boundary progress (completed phases) for durable

@@ -73,10 +80,22 @@ type phaseDeps struct {
 // deadline/critic-kill — returns the error.
 func (e *Executor) runPhases(runCtx context.Context, ra RunnableAgent, deps phaseDeps, query string, images []llm.ImagePart) (*agent.Result, error) {
 	outputs := make(map[string]string, len(ra.Phases))
+	var completed []PhaseOutput

@@ -92,1 +111,4 @@
 	for i, phase := range ra.Phases {
+		// Skip phases already completed on a resumed run (key presence, not output
+		// emptiness — a legitimately-empty phase output still counts as done).
+		if _, done := outputs[phase.Name]; done {

@@ -154,0 +181,4 @@
+		// hold/serialize it asynchronously.)
+		completed = append(completed, PhaseOutput{Name: phase.Name, Output: output})
+		if deps.checkpointer != nil {
+			_ = deps.checkpointer.Save(runCtx, RunCheckpointState{

@@ -188,2 +200,3 @@
-// minimal here; the executor extends what it records during the merge.
+// RunCheckpointState is the resumable snapshot a Checkpointer persists.
 type RunCheckpointState struct {
+	// Messages is the running transcript (single-loop run) OR the active phase's

@@ -192,0 +207,4 @@
+	// already finished, in phase order. nil for single-loop runs.
+	CompletedPhases []PhaseOutput
+	// ActivePhase is the name of the in-progress phase (multi-phase only).
+	ActivePhase string