fix: save and restore sub-agent state in checkpoints

Previously checkpoints only saved tracer.chat_messages and
tracer.vulnerability_reports, leaving tracer.agents and
tracer.tool_executions empty on resume — so all sub-agents
(both in-progress and completed) were invisible after resuming.

Changes:
- checkpoint.py: add tracer_agents, tracer_tool_executions,
  tracer_next_execution_id fields to CheckpointModel; populate
  them in CheckpointManager.save() from the live tracer
- cli.py: on resume, restore agents dict, tool_executions dict,
  and advance _next_execution_id to avoid ID collisions
- tui.py: same restore logic so TUI sidebar shows all previous
  agents and their tool results immediately on resume

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

strix/interface/cli.py

@@ -204,9 +204,18 @@ async def run_cli(args: Any) -> None:  # noqa: PLR0915
     tracer.set_scan_config(scan_config)
 
     # Added for Resume Feature — pre-populate tracer so stats/vulns are correct
+    # Also restores sub-agent registry and tool executions so the full run is visible
     if is_resuming and checkpoint_data:
         tracer.chat_messages.extend(checkpoint_data.tracer_chat_messages)
         tracer.vulnerability_reports.extend(checkpoint_data.tracer_vulnerability_reports)
+        # Restore every agent (root + sub-agents) with their last-known status
+        tracer.agents.update(checkpoint_data.tracer_agents)
+        # Restore tool execution records; keys were serialised as str, restore as int
+        for k, v in checkpoint_data.tracer_tool_executions.items():
+            tracer.tool_executions[int(k)] = v
+        # Advance the ID counter so new executions don't overwrite saved ones
+        if checkpoint_data.tracer_next_execution_id > tracer._next_execution_id:
+            tracer._next_execution_id = checkpoint_data.tracer_next_execution_id
 
     # Added for Resume Feature — show resume banner + replay previous output
     if is_resuming and checkpoint_data:

strix/interface/tui.py

@@ -711,10 +711,20 @@ class StrixTUIApp(App):  # type: ignore[misc]
 
         # Added for Resume Feature — pre-populate tracer with checkpoint data so
         # stats and findings reflect the full scan history including past sessions.
+        # Also restores sub-agents and their tool executions so the TUI sidebar
+        # shows every agent (completed or in-progress) from the previous session.
         _cp = getattr(args, "_checkpoint_data", None)
         if _cp and getattr(args, "resume_from_checkpoint", False):
             self.tracer.chat_messages.extend(_cp.tracer_chat_messages)
             self.tracer.vulnerability_reports.extend(_cp.tracer_vulnerability_reports)
+            # Restore full agent registry (root + all sub-agents)
+            self.tracer.agents.update(_cp.tracer_agents)
+            # Restore tool execution records (keys were serialised as str)
+            for k, v in _cp.tracer_tool_executions.items():
+                self.tracer.tool_executions[int(k)] = v
+            # Advance execution ID counter to avoid collisions
+            if _cp.tracer_next_execution_id > self.tracer._next_execution_id:
+                self.tracer._next_execution_id = _cp.tracer_next_execution_id
 
         self.agent_nodes: dict[str, TreeNode] = {}
 

strix/telemetry/checkpoint.py

@@ -41,6 +41,13 @@ class CheckpointModel(BaseModel):
     tracer_chat_messages: list[dict[str, Any]] = Field(default_factory=list)
     tracer_vulnerability_reports: list[dict[str, Any]] = Field(default_factory=list)
 
+    # Added for sub-agent persistence: full agent registry and tool execution log
+    # tracer.agents  → every agent (root + sub) with status, name, task, parent_id
+    # tracer.tool_executions → every tool call result across all agents
+    tracer_agents: dict[str, Any] = Field(default_factory=dict)
+    tracer_tool_executions: dict[str, Any] = Field(default_factory=dict)  # key is str(int)
+    tracer_next_execution_id: int = 1  # restore the ID counter so new IDs don't collide
+
     # Original scan configuration (passed to execute_scan)
     scan_config: dict[str, Any] = Field(default_factory=dict)
 
@@ -100,11 +107,21 @@ class CheckpointManager:
 
             tracer_chat_messages: list[dict[str, Any]] = []
             tracer_vulnerability_reports: list[dict[str, Any]] = []
+            tracer_agents: dict[str, Any] = {}
+            tracer_tool_executions: dict[str, Any] = {}
+            tracer_next_execution_id: int = 1
             if tracer:
                 tracer_chat_messages = list(getattr(tracer, "chat_messages", []))
                 tracer_vulnerability_reports = list(
                     getattr(tracer, "vulnerability_reports", [])
                 )
+                # Added for sub-agent persistence — capture full agent registry
+                # and all tool execution records so sub-agents are fully restored
+                tracer_agents = dict(getattr(tracer, "agents", {}))
+                # tool_executions keys are ints; serialise as strings for JSON
+                raw_execs = getattr(tracer, "tool_executions", {})
+                tracer_tool_executions = {str(k): v for k, v in raw_execs.items()}
+                tracer_next_execution_id = getattr(tracer, "_next_execution_id", 1)
 
             checkpoint = CheckpointModel(
                 run_name=self.run_name,
@@ -114,6 +131,9 @@ class CheckpointManager:
                 agent_state=state_dict,
                 tracer_chat_messages=tracer_chat_messages,
                 tracer_vulnerability_reports=tracer_vulnerability_reports,
+                tracer_agents=tracer_agents,
+                tracer_tool_executions=tracer_tool_executions,
+                tracer_next_execution_id=tracer_next_execution_id,
                 scan_config=scan_config,
             )