test: tighten qa live scenarios

qa/scenarios/config-apply-restart-wakeup.md

@@ -57,6 +57,9 @@ steps:
       - set: wakeMarker
         value:
           expr: "`QA-RESTART-${randomUUID().slice(0, 8)}`"
+      - set: wakeStartIndex
+        value:
+          expr: "state.getSnapshot().messages.length"
       - call: applyConfig
         args:
           - env:
@@ -65,6 +68,8 @@ steps:
               ref: nextConfig
             sessionKey:
               ref: sessionKey
+            deliveryContext:
+              expr: "({ channel: 'qa-channel', to: `channel:${config.channelId}` })"
             note:
               ref: wakeMarker
       - try:
@@ -99,6 +104,8 @@ steps:
                     params: [candidate]
                     expr: "candidate.text.includes(wakeMarker)"
                 - 60000
+                - sinceIndex:
+                    ref: wakeStartIndex
           catchAs: wakeError
           catch:
             - throw:

qa/scenarios/memory-failure-fallback.md

@@ -8,7 +8,7 @@ objective: Verify the agent degrades gracefully when memory tools are unavailabl
 successCriteria:
   - Memory tools are absent from the effective tool inventory.
   - Agent does not hallucinate the hidden fact.
-  - Agent says it could not confirm and surfaces the limitation.
+  - Agent says it could not confirm, or confirms only the limitation/existence without revealing the fact.
 docsRefs:
   - docs/concepts/memory.md
   - docs/tools/index.md
@@ -39,6 +39,8 @@ execution:
       - won't reveal
       - won’t reveal
       - will not reveal
+      - confirmed: the hidden fact is present
+      - hidden fact is present
 ```
 
 ```yaml qa-flow

qa/scenarios/model-switch-tool-continuity.md

@@ -19,8 +19,8 @@ execution:
   kind: flow
   summary: Verify switching models preserves session context and tool use instead of dropping into plain-text only behavior.
   config:
-    initialPrompt: "Read QA_KICKOFF_TASK.md and summarize the QA mission in one clause before any model switch."
-    followupPrompt: "Switch models now. Tool continuity check: reread QA_KICKOFF_TASK.md and mention the handoff in one short sentence."
+    initialPrompt: "Read repo/qa/scenarios/index.md and summarize the QA scenario pack mission in one clause before any model switch."
+    followupPrompt: "The harness has already requested the alternate model for this turn. Do not call session_status or change models yourself. Tool continuity check: use the read tool to reread repo/qa/scenarios/index.md, then mention the model handoff and QA mission in one short sentence."
     promptSnippet: "Tool continuity check"
 ```
 
@@ -64,7 +64,7 @@ steps:
         args:
           - lambda:
               expr: "state.getSnapshot().messages.slice(beforeSwitchCursor).filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === 'qa-operator' && hasModelSwitchContinuityEvidence(candidate.text)).at(-1)"
-          - 10000
+          - expr: resolveQaLiveTurnTimeoutMs(env, 20000, env.alternateModel)
       - assert:
           expr: hasModelSwitchContinuityEvidence(outbound.text)
           message: