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/conductor/types.ts

@@ -42,6 +42,14 @@ export type StepKind = 'agent' | 'code' | 'approval';
 
 export type TriggerRule = 'all_success' | 'one_success' | 'all_done';
 
+/** Possible statuses for a flow step (persisted in flow_steps.status). */
+export type StepStatus = 'pending' | 'running' | 'completed' | 'failed' | 'skipped' | 'cancelled' | 'timed_out';
+
+/** Retry policy for a step that times out. */
+export interface RetryConfig {
+  maxRetries: number;
+}
+
 export interface Step {
   /** unique id within the flow; other steps depend on it by this id */
   id: string;
@@ -59,6 +67,8 @@ export interface Step {
   run: (ctx: StepContext) => string | Promise<string>;
   /** optional guard — when it returns false the step is skipped (e.g. no repo) */
   when?: (ctx: StepContext) => boolean;
+  /** max retries on timeout (0 or unset = no retry) */
+  maxRetries?: number;
 }
 
 export interface Flow {