feat(conductor): task state machine — TIMED_OUT state and retriable steps

- Add 'timed_out' to flow_runs/flow_steps CHECK constraints
- Add retry_count and max_retries columns to flow_steps
- Add timeout detection in advanceInner loop (configurable FLOW_STEP_TIMEOUT_MS)
- Add retriable logic: re-dispatch on timeout if maxRetries > 0 and retryCount < maxRetries
- Add isRetriable() + shouldRetry() pure decision functions
- Add timed_out handling to reconcileResumeStep and reconcileRun
- Add 'timed_out' to ws-frames enum, publishStep status type

apps/coder/src/services/flow-runner-decisions.ts

@@ -33,11 +33,13 @@ export interface SchedulerState {
   readonly inFlight: ReadonlySet<string>;
   /** step ids pre-skipped at launch (band/when gating) — never given a row */
   readonly excluded: ReadonlySet<string>;
+  /** step ids that timed out (terminal — no retries remaining or not retriable) */
+  readonly timedOut: ReadonlySet<string>;
 }
 
-/** A dependency is satisfied once it is done, skipped, or excluded. */
+/** A dependency is satisfied once it is done, skipped, excluded, or timed out. */
 function isSatisfied(state: SchedulerState, id: string): boolean {
-  return state.done.has(id) || state.skipped.has(id) || state.excluded.has(id);
+  return state.done.has(id) || state.skipped.has(id) || state.excluded.has(id) || state.timedOut.has(id);
 }
 
 /**
@@ -118,25 +120,50 @@ export function isStuck(flow: Flow, state: SchedulerState): boolean {
  * - 'mark-cancelled': task was cancelled before the callback ran; propagate so
  *                     advance() cancels the run.
  */
+/**
+ * True when the step definition allows retries on timeout.
+ * Pure — no IO.
+ */
+export function isRetriable(step: { maxRetries?: number }): boolean {
+  return (step.maxRetries ?? 0) > 0;
+}
+
+/**
+ * True when the step has retries remaining.
+ * Pure — no IO.
+ */
+export function shouldRetry(maxRetries: number | undefined | null, retryCount: number): boolean {
+  return retryCount < (maxRetries ?? 0);
+}
+
 export type ResumeAction =
   | 'keep'
   | 're-dispatch'
   | 'mark-done'
   | 'mark-failed'
-  | 'mark-cancelled';
+  | 'mark-cancelled'
+  | 'retry';
 
 /**
  * Decide what to do with ONE flow step during startup resume (D-9). Pure.
  *
- * @param status    - flow_steps.status
- * @param taskId    - flow_steps.task_id (null for code steps or unstarted agent steps)
- * @param taskState - tasks.state for taskId, or null if the task row is absent
+ * @param status     - flow_steps.status
+ * @param taskId     - flow_steps.task_id (null for code steps or unstarted agent steps)
+ * @param taskState  - tasks.state for taskId, or null if the task row is absent
+ * @param retryCount - flow_steps.retry_count (default 0)
+ * @param maxRetries - flow_steps.max_retries (null = no retry)
  */
 export function reconcileResumeStep(
   status: string,
   taskId: string | null,
   taskState: string | null,
+  retryCount?: number,
+  maxRetries?: number | null,
 ): ResumeAction {
+  if (status === 'timed_out') {
+    if (shouldRetry(maxRetries, retryCount ?? 0)) return 'retry';
+    return 'mark-failed';
+  }
   if (status !== 'running') return 'keep';
   // Running step: decide by its task's current state.
   if (!taskId || taskState === null) return 're-dispatch'; // task gone or never created
@@ -198,7 +225,7 @@ export function evaluateTriggerRule(
  * decision per step. Pure — no IO.
  */
 export function reconcileRun(
-  steps: ReadonlyArray<{ stepId: string; taskId: string | null; status: string }>,
+  steps: ReadonlyArray<{ stepId: string; taskId: string | null; status: string; retryCount?: number; maxRetries?: number | null }>,
   taskStates: ReadonlyMap<string, string>,
 ): StepResumeDecision[] {
   return steps.map((step) => ({
@@ -207,6 +234,8 @@ export function reconcileRun(
       step.status,
       step.taskId,
       step.taskId ? (taskStates.get(step.taskId) ?? null) : null,
+      step.retryCount,
+      step.maxRetries,
     ),
   }));
 }