diff --git a/nanobot/agent/runner.py b/nanobot/agent/runner.py
index 83344763..9428be95 100644
--- a/nanobot/agent/runner.py
+++ b/nanobot/agent/runner.py
@@ -607,7 +607,7 @@ class AgentRunner:
                         reasoning_content=response.reasoning_content,
                         thinking_blocks=response.thinking_blocks,
                     ))
-                    messages.append(build_length_recovery_message())
+                    messages.append(build_length_recovery_message(clean))
                     await hook.after_iteration(context)
                     continue
 
diff --git a/nanobot/utils/runtime.py b/nanobot/utils/runtime.py
index 4f6599f6..8ffe6277 100644
--- a/nanobot/utils/runtime.py
+++ b/nanobot/utils/runtime.py
@@ -14,6 +14,7 @@ _MAX_REPEAT_EXTERNAL_LOOKUPS = 2
 
 # Third same-target workspace violation in a turn escalates to "stop retrying".
 _MAX_REPEAT_WORKSPACE_VIOLATIONS = 2
+_LENGTH_RECOVERY_TAIL_CHARS = 500
 
 EMPTY_FINAL_RESPONSE_MESSAGE = (
     "I completed the tool steps but couldn't produce a final answer. "
@@ -33,8 +34,10 @@ BUDGET_EXHAUSTED_FINALIZATION_PROMPT = (
 )
 
 LENGTH_RECOVERY_PROMPT = (
-    "Output limit reached. Continue exactly where you left off "
-    "— no recap, no apology. Break remaining work into smaller steps if needed."
+    "The previous assistant response was cut off. Continue the same response from its "
+    "exact endpoint. Output only new continuation text in the same language and style. "
+    "Do not acknowledge this instruction, restart the response, repeat its title or any "
+    "existing text, recap, or apologize."
 )
 
 SUSTAINED_GOAL_CONTINUE_PROMPT = (
@@ -79,9 +82,19 @@ def build_budget_exhausted_finalization_message() -> dict[str, str]:
     return {"role": "user", "content": BUDGET_EXHAUSTED_FINALIZATION_PROMPT}
 
 
-def build_length_recovery_message() -> dict[str, str]:
+def build_length_recovery_message(content: str) -> dict[str, str]:
     """Prompt the model to continue after hitting output token limit."""
-    return {"role": "user", "content": LENGTH_RECOVERY_PROMPT}
+    tail = content[-_LENGTH_RECOVERY_TAIL_CHARS:]
+    prompt = (
+        f"{LENGTH_RECOVERY_PROMPT}\n\n"
+        "The following tail was already delivered to the user. Treat it as immutable "
+        "context and do not output it again:\n"
+        "<already_delivered_tail>\n"
+        f"{tail}\n"
+        "</already_delivered_tail>\n"
+        "Begin with the text that belongs immediately after this tail."
+    )
+    return {"role": "user", "content": prompt}
 
 
 def build_goal_continue_message(custom: str | None = None) -> dict[str, str]:
diff --git a/tests/utils/test_runtime.py b/tests/utils/test_runtime.py
new file mode 100644
index 00000000..56e2f2bc
--- /dev/null
+++ b/tests/utils/test_runtime.py
@@ -0,0 +1,14 @@
+from nanobot.utils.runtime import build_length_recovery_message
+
+
+def test_length_recovery_message_anchors_the_existing_tail() -> None:
+    omitted_prefix = "OMITTED_PREFIX"
+    tail = "x" * 500
+
+    message = build_length_recovery_message(omitted_prefix + tail)
+
+    assert message["role"] == "user"
+    assert omitted_prefix not in message["content"]
+    assert f"<already_delivered_tail>\n{tail}\n</already_delivered_tail>" in message["content"]
+    assert "Output only new continuation text" in message["content"]
+    assert "Break remaining work into smaller steps" not in message["content"]