fix(prompt-gate): pin duplicate prompt dispatches

Keep prompt reservations briefly after successful dispatch so rapid idle/message/error transitions cannot inject the same follow-up twice.

Route all production session prompt calls through the shared gate, restore skipped background resume state, release holds after abort/recovery paths, and preserve Ralph/ULW loop state when a dispatch is deferred.

Add regression coverage for session routing, static prompt route auditing, team-mode live messaging, model suggestion retries, call-omo-agent reuse, background parent wakes, runtime fallback, compaction recovery, Atlas, and Ralph/ULW loops.

src/hooks/runtime-fallback/auto-retry.ts

@@ -147,7 +147,6 @@ export function createAutoRetryHelpers(deps: HookDeps) {
           sessionID,
           source: `runtime-fallback:${source}`,
           settleMs: 0,
-          postDispatchHoldMs: 0,
           input: {
             path: { id: sessionID },
             body: {

src/hooks/runtime-fallback/message-update-handler.ts

@@ -66,14 +66,14 @@ export function createMessageUpdateHandler(deps: HookDeps, helpers: AutoRetryHel
     }
 
     if (sessionID && role === "assistant" && error) {
-      sessionAwaitingFallbackResult.delete(sessionID)
+      const wasAwaitingFallbackResult = sessionAwaitingFallbackResult.delete(sessionID)
       if (sessionRetryInFlight.has(sessionID) && !retrySignal) {
         log(`[${HOOK_NAME}] message.updated fallback skipped (retry in flight)`, { sessionID })
         return
       }
 
-      if (retrySignal && sessionRetryInFlight.has(sessionID) && timeoutEnabled) {
-        log(`[${HOOK_NAME}] Overriding in-flight retry due to provider auto-retry signal`, {
+      if (retrySignal && timeoutEnabled && (sessionRetryInFlight.has(sessionID) || wasAwaitingFallbackResult)) {
+        log(`[${HOOK_NAME}] Overriding active retry due to provider auto-retry signal`, {
           sessionID,
           model,
         })