Update werkend

tests/unit/services/devii/agentic/loop.py

@@ -206,6 +206,59 @@ class _FakeLLMWithRealLimit:
         return "short summary"
 
 
+def test_proactive_compaction_targets_40_percent_of_threshold():
+    messages = _long_message_history(100)
+    threshold = context_size(messages) - 50
+    llm = _FakeLLM([{"role": "assistant", "content": "done"}])
+    trace_events = []
+    result = run_async(
+        react_loop(
+            llm,
+            _FakeDispatcher(),
+            messages,
+            tools=[],
+            state=AgentState(),
+            settings=_settings_for_test(keep_tail=4, threshold=threshold),
+            max_iterations=5,
+            plan_required=False,
+            verify_required=False,
+            on_trace=lambda event, name, detail: trace_events.append(event),
+        )
+    )
+    assert result == "done"
+    assert "compact" in trace_events
+    assert context_size(messages) <= int(threshold * 0.4)
+
+
+def test_proactive_compaction_retries_when_first_pass_is_not_enough():
+    giant = "X" * 300_000
+    messages = _long_message_history(20)
+    messages.append(
+        {"role": "tool", "tool_call_id": "1", "name": "big_tool", "content": giant}
+    )
+    messages.append({"role": "user", "content": "please continue"})
+
+    llm = _FakeLLM([{"role": "assistant", "content": "done"}])
+    result = run_async(
+        react_loop(
+            llm,
+            _FakeDispatcher(),
+            messages,
+            tools=[],
+            state=AgentState(),
+            settings=_settings_for_test(keep_tail=2, threshold=50_000),
+            max_iterations=5,
+            plan_required=False,
+            verify_required=False,
+        )
+    )
+
+    assert result == "done"
+    assert llm.summarize_calls > 1
+    giant_message = next(m for m in messages if m.get("name") == "big_tool")
+    assert len(giant_message["content"]) < len(giant)
+
+
 def test_one_oversized_tail_message_alone_still_recovers():
     giant = "X" * 300_000
     messages = _long_message_history(16)

tests/unit/services/devii/llm.py

@@ -0,0 +1,46 @@
+# retoor <retoor@molodetz.nl>
+
+from devplacepy.services.devii.llm import _sanitize_tool_calls, _sanitize_tool_name
+
+
+def test_sanitize_tool_name_leaves_clean_names_untouched():
+    assert _sanitize_tool_name("plan") == "plan"
+    assert _sanitize_tool_name("project_write_file") == "project_write_file"
+
+
+def test_sanitize_tool_name_strips_a_harmony_channel_leak():
+    assert _sanitize_tool_name("plan<|channel|>commentary") == "plan"
+
+
+def test_sanitize_tool_name_strips_any_special_token_style_suffix():
+    assert _sanitize_tool_name("verify<|message|>") == "verify"
+    assert _sanitize_tool_name("recall<|end|>") == "recall"
+
+
+def test_sanitize_tool_name_falls_back_to_original_if_nothing_survives():
+    assert _sanitize_tool_name("<|channel|>commentary") == "<|channel|>commentary"
+
+
+def test_sanitize_tool_calls_mutates_leaked_names_in_place():
+    message = {
+        "role": "assistant",
+        "tool_calls": [
+            {"id": "1", "function": {"name": "plan<|channel|>commentary", "arguments": "{}"}},
+            {"id": "2", "function": {"name": "verify", "arguments": "{}"}},
+        ],
+    }
+    _sanitize_tool_calls(message)
+    assert message["tool_calls"][0]["function"]["name"] == "plan"
+    assert message["tool_calls"][1]["function"]["name"] == "verify"
+
+
+def test_sanitize_tool_calls_handles_no_tool_calls():
+    message = {"role": "assistant", "content": "hi"}
+    _sanitize_tool_calls(message)
+    assert message == {"role": "assistant", "content": "hi"}
+
+
+def test_sanitize_tool_calls_ignores_malformed_function_entries():
+    message = {"tool_calls": [{"id": "1", "function": "not-a-dict"}]}
+    _sanitize_tool_calls(message)
+    assert message["tool_calls"][0]["function"] == "not-a-dict"