Keep long-running monitors polling after prose turns

plans/galaxy-local-first-rig.md

@@ -432,6 +432,8 @@ assigned to the phase that owns the affected flow before the related work is con
     monitor.
   - [x] Monitor teardown now clears orphaned in-memory state when completion metadata is missing.
   - [x] Refresh requests ignore completed or no-longer-long-running blocks.
+  - [x] A monitor turn that ends after a snapshot without a polling action now receives one bounded
+    continuation nudge, with shared prompts requiring a tool call while the command is running.
 - [ ] ChatGPT subscription follow-up: a reported OAuth-backed tool turn failed because the
   Responses request lacked `call_id`. Rig's stream fallback and the serialized assistant/tool
   follow-up are now covered by hermetic tests; complete a fresh authenticated end-to-end check and

plans/long-running-command-side-agent.md

@@ -207,6 +207,8 @@ Tasks:
 - Build the initial structured monitoring prompt.
 - Reuse `RunningCommand` and shell snapshot conversion where possible.
 - Add throttled snapshot updates.
+- [x] If a monitor turn finishes with a still-running command but no polling tool call, issue one
+  bounded continuation nudge; reset that guard after a real snapshot/action result.
 - Add explicit completion/cancellation summaries.
 - Redact secrets using the existing input redaction path before sending snapshots to the side agent.
 
@@ -264,5 +266,8 @@ Manual verification:
 4. Run a command with no output but successful completion: side agent does not claim failure prematurely and receives the final exit code.
 5. Run a command that exits non-zero: side agent identifies failure and main agent receives the summary.
 6. Run a simulated database lock/wait: side agent flags suspicious lack of progress with uncertainty.
-7. Trigger a provider budget limit on the thinking model: coding model is tried once.
-8. Trigger limits on both profile models: clear rate-limit message is shown and no crash occurs.
+7. Run `count_forever() { i=0; while :; do i=$((i+1)); printf 'tick=%d\\n' "$i"; sleep 1; done; }; count_forever`
+   and ask the monitor to stop it at tick 50; verify it continues polling after each snapshot and
+   interrupts the original process at the requested point.
+8. Trigger a provider budget limit on the thinking model: coding model is tried once.
+9. Trigger limits on both profile models: clear rate-limit message is shown and no crash occurs.