fix defects D1-D12 batch 1, structured envelope, saf gates + ops kill-switches

tests/test_spec_defects.py

@@ -0,0 +1,132 @@
+"""Unit coverage for the FDB-004 defect-fix requirements (ENV-12..17)."""
+
+import threading
+import unittest
+from unittest.mock import AsyncMock, MagicMock, Mock, patch
+
+import httpx
+import openai
+from discord import Message, TextChannel
+
+from fjerkroa_bot.ai_responder import AIMessage, AIResponder
+from fjerkroa_bot.openai_responder import OpenAIResponder, openai_chat
+
+from .test_bdd_envelope import FakeModelResponder, envelope
+from .test_main import TestBotBase
+
+
+def make_entry(channel: str, text: str = "x"):
+    import json
+
+    return {"role": "user", "content": json.dumps({"message": text, "channel": channel})}
+
+
+class TestSendBackoff(unittest.IsolatedAsyncioTestCase):
+    async def test_send_sleeps_between_retries(self):
+        """ENV-12: failed attempts are separated by exponential-backoff sleeps (D1)."""
+        responder = FakeModelResponder({"system": "s", "history-limit": 5}, "chat")
+        with patch("fjerkroa_bot.ai_responder.asyncio.sleep", new_callable=AsyncMock) as sleep:
+            with self.assertRaises(RuntimeError):
+                await responder.send(AIMessage("alice", "hei", "chat"))
+        self.assertGreaterEqual(sleep.await_count, 2)
+        for call in sleep.await_args_list:
+            self.assertGreater(call.args[0], 0)
+
+
+class TestReactionClear(TestBotBase):
+    async def test_on_reaction_clear_discord_signature(self):
+        """ENV-13: on_reaction_clear(message, reactions) memoizes the clearing (D7)."""
+        message = MagicMock(spec=Message)
+        message.content = "Some message text"
+        message.author.name = "alice"
+        message.channel = MagicMock(spec=TextChannel)
+        self.bot.airesponder.memoize = AsyncMock()
+        await self.bot.on_reaction_clear(message, [Mock()])
+        self.bot.airesponder.memoize.assert_awaited_once()
+
+
+class TestUpdateMemory(unittest.TestCase):
+    def test_update_memory_uses_argument(self):
+        """ENV-14: update_memory persists the passed value, not stale state (D12)."""
+        responder = AIResponder({"system": "s", "history-limit": 5}, "chat")
+        responder.update_memory("NEW MEMORY")
+        self.assertEqual(responder.memory, "NEW MEMORY")
+
+
+class TestRetryModel(unittest.IsolatedAsyncioTestCase):
+    async def test_retry_model_used_after_rate_limit(self):
+        """ENV-15: the attempt after a rate limit uses retry-model, then switches back (D2)."""
+        config = {
+            "openai-token": "test",
+            "model": "main-model",
+            "retry-model": "fallback-model",
+            "system": "s",
+            "history-limit": 5,
+        }
+        responder = OpenAIResponder(config, "chat")
+        rate_limit = openai.RateLimitError(
+            "rate limited", response=httpx.Response(429, request=httpx.Request("POST", "http://test")), body=None
+        )
+
+        def ok_result():
+            message = Mock(content=envelope(answer="x", answer_needed=True), role="assistant", tool_calls=None)
+            return Mock(choices=[Mock(message=message)], usage="usage")
+
+        with (
+            patch("fjerkroa_bot.openai_responder.openai_chat", new_callable=AsyncMock) as chat_mock,
+            patch("asyncio.sleep", new_callable=AsyncMock),
+        ):
+            chat_mock.side_effect = [rate_limit, ok_result(), ok_result()]
+            messages = [{"role": "user", "content": "hi"}]
+            first, _ = await responder.chat(list(messages), 10)
+            self.assertIsNone(first)
+            second, _ = await responder.chat(list(messages), 10)
+            self.assertIsNotNone(second)
+            third, _ = await responder.chat(list(messages), 10)
+            self.assertIsNotNone(third)
+        self.assertEqual(chat_mock.await_args_list[0].kwargs["model"], "main-model")
+        self.assertEqual(chat_mock.await_args_list[1].kwargs["model"], "fallback-model")
+        self.assertEqual(chat_mock.await_args_list[2].kwargs["model"], "main-model")
+
+
+class TestNoDiskCache(unittest.IsolatedAsyncioTestCase):
+    async def test_chat_hits_client_every_time(self):
+        """ENV-16: identical chat calls reach the client every time — no pickle cache (D3)."""
+        client = Mock()
+        client.chat.completions.create = AsyncMock(return_value="RESPONSE")
+        kwargs = {"model": "m", "messages": [{"role": "user", "content": "hi"}]}
+        await openai_chat(client, **kwargs)
+        await openai_chat(client, **kwargs)
+        self.assertEqual(client.chat.completions.create.await_count, 2)
+
+
+class TestIgdbOffEventLoop(unittest.IsolatedAsyncioTestCase):
+    async def test_igdb_search_runs_in_worker_thread(self):
+        """ENV-17: IGDB lookups run in a worker thread, results unchanged (D5)."""
+        responder = OpenAIResponder({"openai-token": "test", "model": "m", "system": "s", "history-limit": 5}, "chat")
+        responder.igdb = Mock()
+        calling_thread = {}
+
+        def capture_search(query, limit):
+            calling_thread["thread"] = threading.current_thread()
+            return [{"name": "Zelda"}]
+
+        responder.igdb.search_games = capture_search
+        result = await responder._execute_igdb_function("search_games", {"query": "zelda"})
+        self.assertEqual(result, {"games": [{"name": "Zelda"}]})
+        self.assertIsNot(calling_thread["thread"], threading.main_thread())
+
+
+class TestShrinkTolerance(unittest.TestCase):
+    def test_shrink_tolerates_non_json_entries(self):
+        """ENV-11: non-JSON history entries do not crash shrinking (D10 rewrite)."""
+        responder = AIResponder({"system": "s", "history-limit": 4}, "chat")
+        responder.history = [
+            {"role": "user", "content": "plain, not json"},
+            make_entry("a", "a0"),
+            make_entry("a", "a1"),
+            make_entry("a", "a2"),
+            make_entry("a", "a3"),
+        ]
+        responder.shrink_history_by_one()
+        self.assertEqual(len(responder.history), 4)