Fix user message retry lifecycle and TUI sync

strix/core/agents.py

@@ -291,6 +291,12 @@ class AgentCoordinator:
             self.pending_counts[target_agent_id] = self.pending_counts.get(target_agent_id, 0) + 1
             if from_user:
                 runtime.user_wake_required = False
+                self.errors.pop(target_agent_id, None)
+                self.wait_kinds.pop(target_agent_id, None)
+                self.recovery_counts.pop(target_agent_id, None)
+                self.idle_resume_counts.pop(target_agent_id, None)
+                self._parent_notified.discard(target_agent_id)
+                self.statuses[target_agent_id] = "waiting"
             runtime.wake.set()
             stream = runtime.stream
             interrupt_on_message = runtime.interrupt_on_message

strix/interface/tui/backend/controller.py

@@ -411,6 +411,7 @@ class TuiController:
             delivered = await asyncio.wrap_future(future)
         if not delivered:
             raise RuntimeError("Message could not be delivered")
+        self.live_view.upsert_agent(agent_id, status="waiting", error_message=None)
         return {"sent": True}
 
     async def _stop_agent(self, payload: dict[str, Any]) -> dict[str, Any]:

strix/interface/tui/backend/live_view.py

@@ -60,6 +60,9 @@ class TuiLiveView(BaseLiveView):
         if error_message and current.get("error_message") != error_message:
             current["error_message"] = error_message
             changed = True
+        elif error_message is None and "error_message" in current:
+            current.pop("error_message", None)
+            changed = True
         if changed:
             current["updated_at"] = now
         return changed

strix/interface/tui/backend/projection.py

@@ -164,13 +164,14 @@ def bounded_state_projection(state: dict[str, Any]) -> dict[str, Any]:
         "scan_state": state["scan_state"],
         "targets": state["targets"][:4],
         "target_count": state["target_count"],
+        "working_dir": terminal_projection(state.get("working_dir", ""), max_string=256),
+        "pending_mount": terminal_projection(state.get("pending_mount", ""), max_string=256),
         "instruction": terminal_projection(state["instruction"], max_string=128),
         "scan_mode": state["scan_mode"],
         "max_budget_usd": state["max_budget_usd"],
         "max_turns": state["max_turns"],
         "scope_mode": state["scope_mode"],
         "diff_base": state["diff_base"],
-        "provider": state["provider"],
         "model": state["model"],
         "model_warning": "",
         "caido_url": None,

strix/interface/tui/internal/app/model.go

@@ -359,7 +359,9 @@ func (m Model) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 				m.resyncRequested[msg.collection] = false
 			}
 		} else if msg.command == "collection.resync" && msg.requestID != "" && msg.collection != "" {
-			m.resyncRequests[msg.requestID] = msg.collection
+			if m.resyncRequested[msg.collection] {
+				m.resyncRequests[msg.requestID] = msg.collection
+			}
 		}
 	case selectionCopiedMsg:
 		text := "Copied to clipboard"

strix/interface/tui/internal/app/model_test.go

@@ -103,6 +103,21 @@ func bootstrapEnvelope(t *testing.T, collection string, revision int, items ...a
 	return protocol.Envelope{Version: protocol.Version, Type: "collection_bootstrap", Payload: rawJSON(t, payload)}
 }
 
+func TestStateSnapshotClearsNilError(t *testing.T) {
+	model := New(nil)
+	errText := "provider rejected"
+	model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "failed", Error: &errText}))
+	if model.errorText != errText {
+		t.Fatalf("error was not installed: %q", model.errorText)
+	}
+
+	model.handleEnvelope(stateEnvelope(t, 2, protocol.Snapshot{ScanState: "running"}))
+
+	if model.errorText != "" {
+		t.Fatalf("nil snapshot error did not clear errorText: %q", model.errorText)
+	}
+}
+
 func TestBackendDisconnectBecomesFatalUnlessUserIsQuitting(t *testing.T) {
 	model := New(nil)
 	updated, cmd := model.Update(wireErrMsg{err: fmt.Errorf("socket closed")})
@@ -160,6 +175,27 @@ func TestCollectionBootstrapChunksAndVersionedDelta(t *testing.T) {
 	}
 }
 
+func TestAgentCollectionDeltaClearsErrorMessage(t *testing.T) {
+	model := New(nil)
+	failed := protocol.Agent{ID: "root", Name: "Strix", Status: "failed", ErrorMessage: "provider rejected"}
+	model.handleEnvelope(bootstrapEnvelope(t, "agents", 1, failed))
+
+	resumed := protocol.Agent{ID: "root", Name: "Strix", Status: "waiting"}
+	delta := protocol.CollectionDelta{
+		Collection: "agents", BaseRevision: 1, Revision: 2, Cursor: 0, NextCursor: 1, Done: true,
+		Operations: []protocol.CollectionOperation{{Op: "upsert", Item: rawJSON(t, resumed)}},
+	}
+	model.handleEnvelope(protocol.Envelope{Version: protocol.Version, Type: "collection_delta", Payload: rawJSON(t, delta)})
+
+	if len(model.snapshot.Agents) != 1 {
+		t.Fatalf("agents were not retained: %#v", model.snapshot.Agents)
+	}
+	agent := model.snapshot.Agents[0]
+	if agent.Status != "waiting" || agent.ErrorMessage != "" {
+		t.Fatalf("agent error was not cleared: %#v", agent)
+	}
+}
+
 func TestCollectionMismatchRequestsOneResync(t *testing.T) {
 	connection := &recordingConn{}
 	model := New(newClient(connection))
@@ -184,6 +220,42 @@ func TestCollectionMismatchRequestsOneResync(t *testing.T) {
 	}
 }
 
+func TestFailedResyncResultBeforeSentMsgRearmsResync(t *testing.T) {
+	connection := &recordingConn{}
+	model := New(newClient(connection))
+	model.collectionRevisions["events"] = 4
+	bad := protocol.CollectionDelta{
+		Collection: "events", BaseRevision: 2, Revision: 3, Cursor: 0, NextCursor: 0, Done: true,
+	}
+
+	cmd := model.handleEnvelope(protocol.Envelope{Version: protocol.Version, Type: "collection_delta", Payload: rawJSON(t, bad)})
+	if cmd == nil {
+		t.Fatal("revision mismatch did not request a resync")
+	}
+	sent, ok := cmd().(sentMsg)
+	if !ok || sent.err != nil || sent.requestID == "" {
+		t.Fatalf("resync send = %#v", sent)
+	}
+
+	failed := protocol.CommandResult{
+		OK:      false,
+		Command: "collection.resync",
+		Error:   &protocol.CommandError{Code: "command_failed", Message: "resync failed"},
+	}
+	model.handleEnvelope(protocol.Envelope{
+		Version: protocol.Version, Type: "command_result", RequestID: sent.requestID, Payload: rawJSON(t, failed),
+	})
+	updated, _ := model.Update(sent)
+	model = updated.(Model)
+
+	if model.resyncRequested["events"] {
+		t.Fatal("failed resync result left resync suppressed")
+	}
+	if retry := model.handleEnvelope(protocol.Envelope{Version: protocol.Version, Type: "collection_delta", Payload: rawJSON(t, bad)}); retry == nil {
+		t.Fatal("resync was not rearmed after failure")
+	}
+}
+
 func TestAgentsCollectionPreservesSelectedIDAcrossUpsertsAndDeletes(t *testing.T) {
 	model := New(nil)
 	model.handleEnvelope(bootstrapEnvelope(t, "agents", 1,

strix/interface/tui/internal/app/wire.go

@@ -33,6 +33,8 @@ func (m *Model) handleEnvelope(envelope protocol.Envelope) tea.Cmd {
 		m.stateRevision = update.Revision
 		if m.snapshot.Error != nil {
 			m.errorText = *m.snapshot.Error
+		} else {
+			m.errorText = ""
 		}
 		if m.snapshot.SetupMode {
 			// The start screen is its own landing page; never sit on the
@@ -79,6 +81,10 @@ func (m *Model) handleEnvelope(envelope protocol.Envelope) tea.Cmd {
 				if collection := m.resyncRequests[envelope.RequestID]; collection != "" {
 					m.resyncRequested[collection] = false
 					delete(m.resyncRequests, envelope.RequestID)
+				} else {
+					for collection := range m.resyncRequested {
+						m.resyncRequested[collection] = false
+					}
 				}
 			}
 			message := "Command failed"

strix/interface/tui/live_view.py

@@ -103,6 +103,7 @@ class TuiLiveView:
         statuses = agents_data.get("statuses") or {}
         names = agents_data.get("names") or {}
         parent_of = agents_data.get("parent_of") or {}
+        errors = agents_data.get("errors") or {}
         if not isinstance(statuses, dict):
             return
         for agent_id, status in statuses.items():
@@ -113,6 +114,7 @@ class TuiLiveView:
                 name=names.get(agent_id, agent_id) if isinstance(names, dict) else agent_id,
                 parent_id=parent_of.get(agent_id) if isinstance(parent_of, dict) else None,
                 status=str(status),
+                error_message=errors.get(agent_id) if isinstance(errors, dict) else None,
             )
         # Ahead of the replayed history, so it opens the transcript.
         self.flush_user_instruction()

strix/interface/tui/runtime.py

@@ -258,6 +258,9 @@ class GoTuiRuntime:
             scan_state = "failed"
             if root_id is not None and errors.get(root_id):
                 self.controller.error = errors[root_id]
+        elif scan_state == "failed" and root_status in {"running", "waiting", "budget_paused"}:
+            scan_state = "running"
+            self.controller.error = None
         elif scan_state != "failed":
             if report_status == "completed":
                 scan_state = "completed"

tests/test_execution.py

@@ -458,6 +458,49 @@ async def test_non_user_send_does_not_resume_budget_pause(tmp_path: Any) -> None
     session.close()
 
 
+@pytest.mark.asyncio
+async def test_user_send_starts_fresh_resume_attempt_after_failure() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "recon", parent_id="root")
+    await coordinator.park_waiting("child", wait_kind="stalled")
+    await coordinator.record_recovery("child")
+    await coordinator.record_idle_resume("child")
+    await coordinator.set_status("child", "failed", error="provider rejected request")
+    assert await coordinator.claim_parent_notice("child") is True
+
+    delivered = await coordinator.send("child", {"from": "user", "content": "try again"})
+
+    assert delivered is True
+    assert coordinator.statuses["child"] == "waiting"
+    assert coordinator.pending_counts["child"] == 1
+    assert "child" not in coordinator.errors
+    assert "child" not in coordinator.wait_kinds
+    assert "child" not in coordinator.recovery_counts
+    assert "child" not in coordinator.idle_resume_counts
+    assert await coordinator.claim_parent_notice("child") is True
+
+
+@pytest.mark.asyncio
+async def test_non_user_send_preserves_failed_resume_state() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "recon", parent_id="root")
+    await coordinator.park_waiting("child", wait_kind="stalled")
+    await coordinator.record_recovery("child")
+    await coordinator.record_idle_resume("child")
+    await coordinator.set_status("child", "failed", error="provider rejected request")
+
+    delivered = await coordinator.send("child", {"from": "root", "content": "status"})
+
+    assert delivered is True
+    assert coordinator.statuses["child"] == "failed"
+    assert coordinator.errors["child"] == "provider rejected request"
+    assert coordinator.wait_kinds["child"] == "stalled"
+    assert coordinator.recovery_counts["child"] == 1
+    assert coordinator.idle_resume_counts["child"] == 1
+
+
 @pytest.mark.asyncio
 async def test_reset_budget_stops_clears_pause_and_normalizes_statuses() -> None:
     coordinator = AgentCoordinator()

tests/test_go_tui_runtime.py

@@ -857,6 +857,37 @@ async def test_agent_state_sync_does_not_mask_root_failure_with_completed_report
     assert runtime.controller.error == "finalization failed"
 
 
+@pytest.mark.asyncio
+async def test_agent_state_sync_clears_root_failure_after_user_resume() -> None:
+    runtime = GoTuiRuntime(args())
+    await runtime.coordinator.register("root", "Strix", parent_id=None)
+    await runtime.coordinator.set_status("root", "failed", error="provider rejected request")
+
+    await runtime._sync_agent_state()
+    assert runtime.controller.scan_state == "failed"
+    assert runtime.live_view.agents["root"]["error_message"] == "provider rejected request"
+
+    await runtime.coordinator.send("root", {"from": "user", "content": "try again"})
+    await runtime._sync_agent_state()
+
+    assert runtime.controller.scan_state == "running"
+    assert runtime.controller.error is None
+    root = runtime.live_view.agents["root"]
+    assert root["status"] == "waiting"
+    assert "error_message" not in root
+
+
+@pytest.mark.asyncio
+async def test_agent_state_sync_does_not_reopen_stopped_scan_with_active_root() -> None:
+    runtime = GoTuiRuntime(args())
+    runtime.controller.scan_state = "stopped"
+    await runtime.coordinator.register("root", "Strix", parent_id=None)
+
+    await runtime._sync_agent_state()
+
+    assert runtime.controller.scan_state == "stopped"
+
+
 def _direct_launch_args() -> argparse.Namespace:
     launch_args = args()
     launch_args.needs_setup = False

tests/test_tui_backend_controller.py

@@ -12,6 +12,16 @@ from strix.config.settings import DEFAULT_MAX_TURNS
 from strix.interface.tui.backend.controller import TuiController
 
 
+class _SendingCoordinator:
+    def __init__(self, delivered: bool = True) -> None:
+        self.delivered = delivered
+        self.messages: list[tuple[str, dict[str, object]]] = []
+
+    async def send(self, agent_id: str, message: dict[str, object]) -> bool:
+        self.messages.append((agent_id, message))
+        return self.delivered
+
+
 def args() -> argparse.Namespace:
     return argparse.Namespace(
         needs_setup=True,
@@ -313,6 +323,34 @@ def test_snapshot_exposes_working_directory() -> None:
     assert controller.snapshot()["pending_mount"] == ""
 
 
+@pytest.mark.asyncio
+async def test_user_message_updates_live_agent_projection_immediately() -> None:
+    coordinator = _SendingCoordinator()
+    controller = TuiController(args(), coordinator=coordinator)
+    controller.setup_mode = False
+    controller.scan_started = True
+    controller.scan_loop = asyncio.get_running_loop()
+    controller.live_view.upsert_agent(
+        "root",
+        name="Strix",
+        status="failed",
+        error_message="provider rejected request",
+    )
+
+    result = await controller.handle(
+        "agent.send_message",
+        {"agent_id": "root", "message": "try again"},
+    )
+
+    assert result == {"sent": True}
+    assert coordinator.messages == [
+        ("root", {"from": "user", "content": "try again", "type": "instruction"})
+    ]
+    agent = controller.live_view.agents["root"]
+    assert agent["status"] == "waiting"
+    assert "error_message" not in agent
+
+
 @pytest.mark.asyncio
 async def test_start_forwards_verify_flag_by_default() -> None:
     seen_verify: bool | None = None

tests/test_tui_backend_server.py

@@ -243,13 +243,15 @@ def test_defensive_state_projection_preserves_usage_summary() -> None:
         ),
     )
     state = controller.snapshot()
-    state["provider"] = None
+    state["pending_mount"] = "current-project"
     state["future_oversized_field"] = "x" * 100_000
 
     snapshot = bounded_state_projection(state)
 
     assert snapshot["projection_truncated"] is True
     assert snapshot["usage"] == {"total_tokens": 720_400, "cost": 20.0}
+    assert snapshot["working_dir"] == state["working_dir"]
+    assert snapshot["pending_mount"] == "current-project"
 
 
 @pytest.mark.asyncio

tests/test_tui_resume_history.py

@@ -104,6 +104,29 @@ def test_resume_hides_system_guidance_injected_as_user_turns(tmp_path: Path) ->
     ] == ["starting", "continuing"]
 
 
+def test_resume_hydrates_saved_agent_errors(tmp_path: Path) -> None:
+    run_dir = tmp_path / "run"
+    state_dir = runtime_state_dir(run_dir)
+    state_dir.mkdir(parents=True, exist_ok=True)
+    (state_dir / "agents.json").write_text(
+        json.dumps(
+            {
+                "statuses": {"root": "failed"},
+                "names": {"root": "Strix"},
+                "parent_of": {"root": None},
+                "errors": {"root": "provider rejected request"},
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    view = GoTuiLiveView()
+    view.hydrate_from_run_dir(run_dir)
+
+    assert view.agents["root"]["status"] == "failed"
+    assert view.agents["root"]["error_message"] == "provider rejected request"
+
+
 def test_resume_keeps_messages_the_user_actually_typed(tmp_path: Path) -> None:
     run_dir = tmp_path / "run"
     _write_run(