Surface output-limit truncation instead of misformat retries

Record the Chat Completions finish_reason on LLMResult and add a
message_loop_result extension that, when a turn stopped at the output
token limit (finish_reason "length"/"max_tokens") without a complete
tool request, retries with a warning naming truncation as the cause
rather than the generic misformat message. The warning counts toward
the existing unusable-response loop limit.

Context Doctor now leaves results already handled by an earlier
extension untouched, so truncated envelopes are not repaired and
dispatched with cut-off arguments.

Fixes #1836

extensions/python/_functions/agent/Agent/hist_add_warning/end/_90_stop_unusable_response_loop.py

@@ -25,6 +25,7 @@ class StopUnusableResponseLoop(Extension):
             self.agent.read_prompt("fw.msg_empty_response.md"),
             self.agent.read_prompt("fw.msg_reasoning_only.md"),
             self.agent.read_prompt("fw.msg_thoughts_fallback.md"),
+            self.agent.read_prompt("fw.msg_output_limit.md"),
         }:
             return
 

extensions/python/message_loop_result/AGENTS.md

@@ -7,6 +7,7 @@
 ## Ownership
 
 - Extensions receive mutable `result_data` with `llm_result` and may set `skip_default_processing` after fully handling the turn.
+- `_05_truncated_response.py` retries turns the provider cut off at the output token limit (`LLMResult.truncated`) that carry no complete tool request: add an agent-facing `fw.msg_output_limit.md` history warning with a separate `fw.msg_output_limit_response.md` user notice naming the finish reason, instead of the generic misformat warning, and count them through the stop-unusable-response-loop extension.
 - `_20_empty_response.py` retries fully empty turns (no response and no reasoning): count them toward the unusable-response limit without adding a warning to model history, and use `fw.msg_empty_response.md` for agent-prefixed UI warning text only.
 - `_20_empty_response.py` retries reasoning-only turns: add an agent-facing `fw.msg_reasoning_only.md` history warning with a separate `fw.msg_reasoning_only_response.md` user notice, and count them through the stop-unusable-response-loop extension.
 - `_30_repeat_response.py` compares `LLMResult.repeat_response_text()` for native calls (public text plus all calls), otherwise full response text. It retries content that exactly matches `loop_data.last_response`, regardless of separate reasoning or provider IDs, using `fw.msg_repeat.md` for history and `fw.msg_repeat_response.md` for the agent-prefixed UI warning text. State advancement is owned by `hist_add_ai_response`; do not call `_remember_llm_result_state` manually.

extensions/python/message_loop_result/_05_truncated_response.py

@@ -0,0 +1,41 @@
+"""Retry model turns cut off by the output token limit with a specific warning."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from helpers import extract_tools
+from helpers.extension import Extension
+from helpers.print_style import PrintStyle
+
+
+class TruncatedResponse(Extension):
+    def execute(self, result_data: dict[str, Any] | None = None, **kwargs: Any) -> None:
+        if not self.agent or not isinstance(result_data, dict):
+            return
+        if result_data.get("skip_default_processing"):
+            return
+
+        llm_result = result_data.get("llm_result")
+        if not getattr(llm_result, "truncated", False):
+            return
+        if getattr(llm_result, "function_calls", None):
+            return
+        response = getattr(llm_result, "response", "")
+        if isinstance(response, str) and extract_tools.extract_tool_request(response):
+            return
+
+        # Name truncation as the cause instead of the generic misformat warning.
+        warning = self.agent.read_prompt("fw.msg_output_limit.md")
+        warning_message = self.agent.hist_add_warning(message=warning)
+        notice = self.agent.read_prompt(
+            "fw.msg_output_limit_response.md",
+            finish_reason=getattr(llm_result, "finish_reason", ""),
+        )
+        PrintStyle(font_color="orange", padding=True).print(notice)
+        self.agent.context.log.log(
+            type="warning",
+            content=f"{self.agent.agent_name}: {notice}",
+            id=warning_message.id,
+        )
+        result_data["skip_default_processing"] = True