From f91707b5b50bf73a90a4ee4837dfa833c5c71944 Mon Sep 17 00:00:00 2001
From: Livio Meuli <livio.meuli@ksb-sg.ch>
Date: Thu, 21 May 2026 12:06:32 +0200
Subject: [PATCH] remove some testcases

---
 tests/test_chat_manager.py    | 92 +----------------------------------
 tests/test_coding_agent.py    | 64 ------------------------
 tests/test_debug_logger.py    | 64 ++----------------------
 tests/test_file_manager.py    | 13 -----
 tests/test_system_prompter.py | 54 +-------------------
 5 files changed, 8 insertions(+), 279 deletions(-)

diff --git a/tests/test_chat_manager.py b/tests/test_chat_manager.py
index 91aaa92..009e51e 100644
--- a/tests/test_chat_manager.py
+++ b/tests/test_chat_manager.py
@@ -24,25 +24,10 @@ def _mock_ok(content="AI reply"):
     return mock
 
 
-# ── Initialization ────────────────────────────────────────────────────────────
-
-class TestChatManagerInit:
-    """Verify that a fresh ChatManager starts in a clean, predictable state."""
-
-    def test_chat_history_starts_empty(self):
-        cm = ChatManager()
-        assert cm.chat_history == []
-
-    def test_api_url_contains_endpoint(self):
-        cm = ChatManager()
-        assert isinstance(cm.api_url, str)
-        assert "/v1/chat/completions" in cm.api_url
-
-
 # ── History management ────────────────────────────────────────────────────────
 
 class TestHistory:
-    """Tests for add_message, get_history, and clear_history."""
+    """Tests for add_message and clear_history."""
 
     @pytest.fixture
     def cm(self):
@@ -58,22 +43,11 @@ class TestHistory:
         assert cm.chat_history[0]["role"] == "user"
         assert cm.chat_history[1]["role"] == "assistant"
 
-    def test_get_history_returns_copy_not_reference(self, cm):
-        """Mutating the returned list must not corrupt internal history."""
-        cm.add_message("user", "Hi")
-        history = cm.get_history()
-        assert history == cm.chat_history
-        assert history is not cm.chat_history
-
     def test_clear_history_empties_list(self, cm):
         cm.add_message("user", "Hi")
         cm.clear_history()
         assert cm.chat_history == []
 
-    def test_clear_history_on_empty_is_safe(self, cm):
-        cm.clear_history()
-        assert cm.chat_history == []
-
 
 # ── send_message (mocked HTTP) ────────────────────────────────────────────────
 
@@ -108,12 +82,6 @@ class TestSendMessage:
         assert payload["messages"][0]["role"] == "system"
         assert payload["messages"][1]["role"] == "user"
 
-    def test_history_grows_by_two_per_call(self, cm):
-        with patch("requests.post", return_value=_mock_ok()):
-            cm.send_message("First")
-            cm.send_message("Second")
-        assert len(cm.chat_history) == 4
-
     def test_connection_error_raises_and_adds_error_to_history(self, cm):
         with patch("requests.post", side_effect=requests.exceptions.ConnectionError("refused")):
             with pytest.raises(Exception, match="Connection Error"):
@@ -141,14 +109,6 @@ class TestSendMessage:
             with pytest.raises(Exception, match="Invalid API response format"):
                 cm.send_message("Hello")
 
-    def test_missing_choices_key_raises(self, cm):
-        mock = MagicMock()
-        mock.status_code = 200
-        mock.json.return_value = {}
-        with patch("requests.post", return_value=mock):
-            with pytest.raises(Exception):
-                cm.send_message("Hello")
-
     def test_api_key_included_in_header_when_set(self, cm):
         cm.api_key = "test-key-123"
         with patch("requests.post", return_value=_mock_ok()) as mock_post:
@@ -164,13 +124,6 @@ class TestSendMessage:
         headers = mock_post.call_args.kwargs["headers"]
         assert "Authorization" not in headers
 
-    def test_api_key_excluded_from_header_when_empty_string(self, cm):
-        cm.api_key = ""
-        with patch("requests.post", return_value=_mock_ok()) as mock_post:
-            cm.send_message("Hello")
-        headers = mock_post.call_args.kwargs["headers"]
-        assert "Authorization" not in headers
-
     def test_json_decode_error_raises(self, cm):
         import json
         mock = MagicMock()
@@ -184,15 +137,12 @@ class TestSendMessage:
 # ── get_chat_display ──────────────────────────────────────────────────────────
 
 class TestGetChatDisplay:
-    """Tests for get_chat_display: correct shape, ordering, isolation, and role coverage."""
+    """Tests for get_chat_display: correct shape and ordering."""
 
     @pytest.fixture
     def cm(self):
         return ChatManager()
 
-    def test_empty_history_returns_empty_list(self, cm):
-        assert cm.get_chat_display() == []
-
     def test_display_has_role_and_content_keys(self, cm):
         cm.add_message("user", "Hello")
         entry = cm.get_chat_display()[0]
@@ -205,41 +155,3 @@ class TestGetChatDisplay:
         display = cm.get_chat_display()
         assert display[0]["role"] == "user"
         assert display[1]["role"] == "assistant"
-
-    def test_display_returns_copy_not_reference(self, cm):
-        """Mutating the returned list must not corrupt internal history."""
-        cm.add_message("user", "Hi")
-        display = cm.get_chat_display()
-        display.clear()
-        assert len(cm.chat_history) == 1
-
-    def test_system_messages_included_in_display(self, cm):
-        cm.add_message("system", "Be helpful.")
-        assert cm.get_chat_display()[0]["role"] == "system"
-
-
-# ── Integration (skipped when API unreachable) ────────────────────────────────
-
-class TestSendMessageIntegration:
-    """End-to-end tests against the live API. Skipped automatically when the API is unreachable."""
-
-    @pytest.fixture
-    def cm(self):
-        return ChatManager()
-
-    def test_real_api_returns_non_empty_string(self, cm):
-        try:
-            response = cm.send_message("Reply with exactly the word PONG.")
-            assert isinstance(response, str)
-            assert len(response) > 0
-            assert len(cm.chat_history) == 2
-        except Exception as e:
-            pytest.skip(f"API not reachable: {e}")
-
-    def test_real_api_multi_turn_history_grows(self, cm):
-        try:
-            cm.send_message("Remember the number 42.")
-            cm.send_message("What number did I ask you to remember?")
-            assert len(cm.chat_history) == 4
-        except Exception as e:
-            pytest.skip(f"API not reachable: {e}")
diff --git a/tests/test_coding_agent.py b/tests/test_coding_agent.py
index e04d3f1..bb69056 100644
--- a/tests/test_coding_agent.py
+++ b/tests/test_coding_agent.py
@@ -73,10 +73,6 @@ class TestTruncateResult:
         assert len(result) < len(long)
         assert "TRUNCATED" in result
 
-    def test_exact_limit_not_truncated(self):
-        text = "a" * MAX_RESULT_LENGTH
-        assert truncate_result(text) == text
-
     def test_truncated_keeps_start_and_end(self):
         text = "START" + "x" * MAX_RESULT_LENGTH + "END"
         result = truncate_result(text)
@@ -144,9 +140,6 @@ class TestStripCodeFences:
         text = "```\nhello\n```"
         assert _strip_code_fences(text) == "hello"
 
-    def test_strips_whitespace(self):
-        assert _strip_code_fences("  hello  ") == "hello"
-
 
 # ═════════════════════════════════════════════════════════════════════════════
 # TestCodingAgentInit
@@ -162,11 +155,6 @@ class TestCodingAgentInit:
         assert agent.is_done is False
         assert agent.iteration == 0
 
-    def test_api_url_is_set(self):
-        agent = CodingAgent()
-        assert agent.api_url.startswith("http://")
-        assert "/v1/chat/completions" in agent.api_url
-
     def test_start_task_sets_messages(self):
         agent = CodingAgent()
         agent.start_task("Write fibonacci.py")
@@ -397,55 +385,3 @@ class TestReject:
         assert not list(tmp_path.glob("*"))
 
 
-# ═════════════════════════════════════════════════════════════════════════════
-# TestFullLoop  (integration – real API, skipped if unreachable)
-# ═════════════════════════════════════════════════════════════════════════════
-
-class TestFullLoop:
-    """End-to-end test: agent runs a real task against the live API.
-    Skipped automatically if the API is not reachable.
-    """
-
-    MAX_STEPS = 15
-
-    async def _run_until_done(self, agent) -> list:
-        steps = []
-        for _ in range(self.MAX_STEPS):
-            action = await agent.propose_next_action()
-            result = await agent.approve()
-            steps.append(result)
-            if result["is_done"]:
-                break
-        return steps
-
-    @pytest.mark.asyncio
-    async def test_agent_completes_hello_world_task(self, tmp_path):
-        try:
-            with patch("backend.agent.coding_agent.WORKSPACE", tmp_path):
-                agent = CodingAgent()
-                agent.start_task(
-                    "Write a Python file called hello.py that prints 'Hello World'. "
-                    "Validate it and run it."
-                )
-                steps = await self._run_until_done(agent)
-            assert agent.is_done, "Agent did not reach done state"
-            tools_used = [s["tool"] for s in steps]
-            assert "done" in tools_used
-        except Exception as e:
-            pytest.skip(f"API not reachable or environment incomplete: {e}")
-
-    @pytest.mark.asyncio
-    async def test_agent_creates_file_on_disk(self, tmp_path):
-        try:
-            with patch("backend.agent.coding_agent.WORKSPACE", tmp_path):
-                agent = CodingAgent()
-                agent.start_task("Write a file called output.txt containing the text 'test passed'.")
-                await self._run_until_done(agent)
-            py_files = list(tmp_path.glob("*.txt")) + list(tmp_path.glob("*.py"))
-            assert len(py_files) > 0, "Agent did not create any file"
-        except Exception as e:
-            pytest.skip(f"API not reachable or environment incomplete: {e}")
-
-
-if __name__ == "__main__":
-    pytest.main([__file__, "-v", "-s"])
diff --git a/tests/test_debug_logger.py b/tests/test_debug_logger.py
index 50f7b3f..1ee6eca 100644
--- a/tests/test_debug_logger.py
+++ b/tests/test_debug_logger.py
@@ -17,19 +17,10 @@ def logger():
     return DebugLogger()
 
 
-# ── Initialization ────────────────────────────────────────────────────────────
-
-class TestInit:
-    """Tests that a fresh DebugLogger starts with an empty log list."""
-
-    def test_logs_start_empty(self, logger):
-        assert logger.logs == []
-
-
 # ── log() ─────────────────────────────────────────────────────────────────────
 
 class TestLog:
-    """Tests for log(): each call appends an INFO-level entry with message and timestamp."""
+    """Tests for log(): each call appends an INFO-level entry with message."""
 
     def test_log_appends_entry(self, logger):
         logger.log("started")
@@ -43,31 +34,16 @@ class TestLog:
         logger.log("executing file.py")
         assert logger.logs[0]["message"] == "executing file.py"
 
-    def test_log_adds_timestamp(self, logger):
-        logger.log("started")
-        ts = logger.logs[0]["timestamp"]
-        # HH:MM:SS format — exactly 8 chars with two colons
-        assert len(ts) == 8
-        assert ts[2] == ":" and ts[5] == ":"
-
 
 # ── log_error() ───────────────────────────────────────────────────────────────
 
 class TestLogError:
-    """Tests for log_error(): same shape as log() but level is ERROR, not INFO."""
-
-    def test_log_error_appends_entry(self, logger):
-        logger.log_error("something broke")
-        assert len(logger.logs) == 1
+    """Tests for log_error(): level is ERROR, not INFO."""
 
     def test_log_error_sets_level_error(self, logger):
         logger.log_error("something broke")
         assert logger.logs[0]["level"] == "ERROR"
 
-    def test_log_error_stores_message(self, logger):
-        logger.log_error("exit code 1")
-        assert logger.logs[0]["message"] == "exit code 1"
-
     def test_log_and_log_error_are_distinct_levels(self, logger):
         logger.log("info message")
         logger.log_error("error message")
@@ -78,24 +54,18 @@ class TestLogError:
 # ── get_logs() ────────────────────────────────────────────────────────────────
 
 class TestGetLogs:
-    """Tests for get_logs(): returns all entries and a copy, not a reference to the internal list."""
+    """Tests for get_logs()."""
 
     def test_get_logs_returns_all_entries(self, logger):
         logger.log("first")
         logger.log_error("second")
         assert len(logger.get_logs()) == 2
 
-    def test_get_logs_returns_copy_not_reference(self, logger):
-        logger.log("entry")
-        logs = logger.get_logs()
-        assert logs == logger.logs
-        assert logs is not logger.logs
-
 
 # ── clear() ───────────────────────────────────────────────────────────────────
 
 class TestClear:
-    """Tests for clear(): empties the log list and leaves the logger ready for reuse."""
+    """Tests for clear()."""
 
     def test_clear_removes_all_entries(self, logger):
         logger.log("first")
@@ -103,23 +73,11 @@ class TestClear:
         logger.clear()
         assert logger.logs == []
 
-    def test_clear_on_empty_is_safe(self, logger):
-        logger.clear()
-        assert logger.logs == []
-
-    def test_log_after_clear_works(self, logger):
-        logger.log("before")
-        logger.clear()
-        logger.log("after")
-        assert len(logger.logs) == 1
-        assert logger.logs[0]["message"] == "after"
-
 
 # ── format_debug_output() ─────────────────────────────────────────────────────
 
 class TestFormatDebugOutput:
-    """Tests for format_debug_output(): renders a dict of {rc, stdout, stderr} plus
-    accumulated log entries into a human-readable string for the UI."""
+    """Tests for format_debug_output(): renders rc, stdout, stderr, and log entries."""
 
     def test_success_exit_code_shows_success(self, logger):
         result = logger.format_debug_output({"rc": 0, "stdout": "", "stderr": ""})
@@ -129,10 +87,6 @@ class TestFormatDebugOutput:
         result = logger.format_debug_output({"rc": 1, "stdout": "", "stderr": ""})
         assert "[FAILED]" in result
 
-    def test_exit_code_included_in_output(self, logger):
-        result = logger.format_debug_output({"rc": 42, "stdout": "", "stderr": ""})
-        assert "42" in result
-
     def test_stdout_included_when_present(self, logger):
         result = logger.format_debug_output({"rc": 0, "stdout": "Hello", "stderr": ""})
         assert "Hello" in result
@@ -143,10 +97,6 @@ class TestFormatDebugOutput:
         assert "NameError" in result
         assert "stderr" in result
 
-    def test_no_output_message_when_both_empty(self, logger):
-        result = logger.format_debug_output({"rc": 0, "stdout": "", "stderr": ""})
-        assert "No output produced." in result
-
     def test_log_entries_appended_to_output(self, logger):
         logger.log("Executing file.py...")
         logger.log_error("exit code 1")
@@ -154,10 +104,6 @@ class TestFormatDebugOutput:
         assert "Executing file.py..." in result
         assert "exit code 1" in result
 
-    def test_returns_string(self, logger):
-        result = logger.format_debug_output({"rc": 0, "stdout": "", "stderr": ""})
-        assert isinstance(result, str)
-
     def test_missing_keys_do_not_raise(self, logger):
         # Defensive: format_debug_output uses .get() so missing keys are safe
         result = logger.format_debug_output({})
diff --git a/tests/test_file_manager.py b/tests/test_file_manager.py
index f1e4184..5f9f522 100644
--- a/tests/test_file_manager.py
+++ b/tests/test_file_manager.py
@@ -99,11 +99,6 @@ class TestReadFile:
     def test_nonexistent_file_returns_empty_string(self, fm, tmp_path):
         assert fm.read_file(tmp_path / "ghost.py") == ""
 
-    def test_directory_path_returns_empty_string(self, fm, tmp_path):
-        sub = tmp_path / "subdir"
-        sub.mkdir()
-        assert fm.read_file(sub) == ""
-
     def test_file_outside_workspace_returns_empty_string(self, fm, tmp_path):
         outside = tmp_path.parent / "outside.py"
         outside.write_text("secret")
@@ -195,9 +190,6 @@ class TestDeleteFolder:
         assert result is True
         assert not sub.exists()
 
-    def test_nonexistent_folder_returns_false(self, fm):
-        assert fm.delete_folder("ghost") is False
-
     def test_path_traversal_returns_false(self, fm):
         assert fm.delete_folder("../../") is False
 
@@ -226,8 +218,3 @@ class TestGetFileTree:
         tree = fm.get_file_tree()
         assert tree["src"]["app.py"] is None
 
-    def test_entries_are_sorted(self, fm, tmp_path):
-        (tmp_path / "z_file.py").touch()
-        (tmp_path / "a_file.py").touch()
-        keys = list(fm.get_file_tree().keys())
-        assert keys == sorted(keys)
diff --git a/tests/test_system_prompter.py b/tests/test_system_prompter.py
index e256d87..b17c69d 100644
--- a/tests/test_system_prompter.py
+++ b/tests/test_system_prompter.py
@@ -6,33 +6,17 @@ from pathlib import Path
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
 import pytest
-from backend.managers.system_prompter import SystemPrompter, MAX_FILE_CHARS  # MAX_FILE_CHARS: character limit before content is truncated
+from backend.managers.system_prompter import SystemPrompter, MAX_FILE_CHARS
 
 
 class TestSystemPrompterBasePrompt:
     """Tests for generate_prompt() without file context."""
 
-    def test_returns_non_empty_string(self):
-        prompt = SystemPrompter.generate_prompt()
-        assert isinstance(prompt, str)
-        assert len(prompt) > 0
-
-    def test_describes_code_assistant(self):
-        prompt = SystemPrompter.generate_prompt()
-        assert "code assistant" in prompt.lower()
-
     def test_contains_no_file_xml_tag(self):
         prompt = SystemPrompter.generate_prompt()
         assert "<file" not in prompt
         assert "<code>" not in prompt
 
-    def test_none_equals_no_argument(self):
-        assert SystemPrompter.generate_prompt(file_context=None) == SystemPrompter.generate_prompt()
-
-    def test_empty_dict_behaves_like_none(self):
-        # {} is falsy in Python, so the implementation treats it the same as None (no file context).
-        assert SystemPrompter.generate_prompt(file_context={}) == SystemPrompter.generate_prompt()
-
 
 class TestSystemPrompterWithFileContext:
     """Tests for generate_prompt() with file_context provided."""
@@ -53,10 +37,6 @@ class TestSystemPrompterWithFileContext:
         prompt = SystemPrompter.generate_prompt(file_context={"name": "f.py", "content": "pass"})
         assert "<code>" in prompt
 
-    def test_missing_name_key_uses_unknown(self):
-        prompt = SystemPrompter.generate_prompt(file_context={"content": "some code"})
-        assert "unknown" in prompt
-
     def test_missing_content_key_does_not_raise(self):
         prompt = SystemPrompter.generate_prompt(file_context={"name": "empty.py"})
         assert "empty.py" in prompt
@@ -76,11 +56,6 @@ class TestSystemPrompterTruncation:
         assert "[truncated]" not in prompt
         assert content in prompt
 
-    def test_file_exactly_at_limit_is_not_truncated(self):
-        content = "x" * MAX_FILE_CHARS
-        prompt = SystemPrompter.generate_prompt(file_context={"name": "f.py", "content": content})
-        assert "[truncated]" not in prompt
-
     def test_file_one_over_limit_is_truncated(self):
         content = "x" * (MAX_FILE_CHARS + 1)
         prompt = SystemPrompter.generate_prompt(file_context={"name": "f.py", "content": content})
@@ -90,24 +65,6 @@ class TestSystemPrompterTruncation:
 class TestSystemPrompterSpecialCharacters:
     """Tests that XML special characters in file content are handled without breaking the prompt."""
 
-    def test_less_than_in_content_does_not_break_prompt(self):
-        prompt = SystemPrompter.generate_prompt(
-            file_context={"name": "f.py", "content": "if x < 10:"}
-        )
-        assert "if x < 10:" in prompt
-
-    def test_greater_than_in_content_does_not_break_prompt(self):
-        prompt = SystemPrompter.generate_prompt(
-            file_context={"name": "f.py", "content": "if x > 0:"}
-        )
-        assert "if x > 0:" in prompt
-
-    def test_ampersand_in_content_does_not_break_prompt(self):
-        prompt = SystemPrompter.generate_prompt(
-            file_context={"name": "f.py", "content": "# true & false"}
-        )
-        assert "true & false" in prompt
-
     def test_xml_tags_in_content_are_preserved_literally(self):
         # User code often contains HTML or XML. The prompt builder must embed it
         # verbatim — escaping or stripping tags would corrupt the file content.
@@ -115,12 +72,3 @@ class TestSystemPrompterSpecialCharacters:
             file_context={"name": "template.html", "content": "<div>hello</div>"}
         )
         assert "<div>hello</div>" in prompt
-
-    def test_prompt_still_contains_file_xml_tag_with_special_content(self):
-        # Verifies that special characters in the content don't corrupt the surrounding
-        # structural tags (<file ...> and <code>) that the LLM relies on for context.
-        prompt = SystemPrompter.generate_prompt(
-            file_context={"name": "f.py", "content": "x < y and a > b"}
-        )
-        assert "<file" in prompt
-        assert "<code>" in prompt