Fix interactive lifecycle and resume history

strix/agents/factory.py

@@ -236,11 +236,11 @@ def build_strix_agent(
         instructions=instructions,
         tools=tools,
         tool_use_behavior=_finish_tool_use_behavior,
-        # Autonomous Strix runs must keep forcing tool calls after each
-        # tool result; otherwise the SDK resets tool_choice to auto and a
-        # plain-text model response can become final output before
-        # finish_scan / agent_finish.
-        reset_tool_choice=False,
+        # Non-interactive runs must keep forcing tool calls until the
+        # lifecycle tool completes. Interactive runs need the SDK default
+        # reset so a tool-assisted answer can end as plain text instead of
+        # looping through think/list_todos forever.
+        reset_tool_choice=interactive,
         # model=None so ``RunConfig.model`` drives provider selection
         # via :func:`build_multi_provider` rather than the SDK's default.
         model=None,

strix/agents/prompts/system_prompt.jinja

@@ -30,6 +30,9 @@ INTERACTIVE BEHAVIOR:
 - EVERY message while working MUST contain exactly one tool call — this is what keeps execution moving. No tool call = execution stops.
 - You may include brief explanatory text BEFORE the tool call
 - Respond naturally when the user asks questions or gives instructions
+- For simple conversation, acknowledgements, or direct questions that you can answer from current context, reply in plain text and stop. Do NOT call think just to prepare wording.
+- If you use a tool to answer a user question (for example list_todos, view_agent_graph, or a file read), then after the tool result arrives, provide the answer in plain text and stop unless the user explicitly asked you to continue working.
+- Never loop through think or other tools just to prepare, polish, confirm, or announce a final answer. Once you know the answer, say it.
 - NEVER send empty messages — if you have nothing to do or say, call the wait_for_message tool
 - If you catch yourself about to describe multiple steps without a tool call, STOP and call the think tool instead
 {% else %}
@@ -149,7 +152,7 @@ OPERATIONAL PRINCIPLES:
 - Use custom Python or shell code when you want to dig deeper, automate custom workflows, batch operations, triage results, build target-specific validation, or do work that existing tools do not cover cleanly
 - Chain related weaknesses when needed to demonstrate real impact
 - Consider business logic and context in validation
-- NEVER skip think tool - it's your most important tool for reasoning and success
+- Use think for non-trivial planning, uncertainty, multi-step security work, or choosing what to do next. Do NOT use think for simple conversational answers, acknowledgements, summaries, or as a bridge before final text.
 - WORK METHODICALLY - Don't stop at shallow checks when deeper in-scope validation is warranted
 - Continue iterating until the most promising in-scope vectors have been properly assessed
 - Try multiple approaches simultaneously - don't wait for one to fail