web search via exa (spec-015): web_search tool, sanitized results, per-user cap, host-config key

2026-07-14 12:08:48 +02:00
parent 5d01400638
commit cdd5a4cd48
6 changed files with 388 additions and 0 deletions
@@ -0,0 +1,102 @@
+"""Unit coverage for SPEC-015 web search via Exa (WEB-01..05)."""
+
+import os
+import unittest
+from unittest.mock import AsyncMock, patch
+
+from fjerkroa_bot.openai_responder import OpenAIResponder
+from fjerkroa_bot.websearch import WEB_SEARCH_TOOL, WebSearch, _format_results
+
+CONFIG = {"openai-token": "t", "model": "m", "system": "s", "history-limit": 5}
+
+
+def _tool_names(responder):
+    return [f["name"] for f in responder._available_tools()]
+
+
+class TestToolOffered(unittest.TestCase):
+    def test_gate_needs_flag_and_key(self):
+        """WEB-01: web_search offered only with enable-web-search AND a key."""
+        off = OpenAIResponder(CONFIG, "chat")  # flag off -> absent even if env key exists
+        self.assertNotIn("web_search", _tool_names(off))
+        on = OpenAIResponder(dict(CONFIG, **{"enable-web-search": True, "exa-api-key": "k"}), "chat")
+        self.assertIn("web_search", _tool_names(on))
+        self.assertEqual(WEB_SEARCH_TOOL["name"], "web_search")
+        with patch.dict(os.environ, {"EXA_API_KEY": ""}):
+            nokey = OpenAIResponder(dict(CONFIG, **{"enable-web-search": True}), "chat")
+            self.assertNotIn("web_search", _tool_names(nokey))
+
+
+class TestFormat(unittest.TestCase):
+    def test_results_sanitized_and_capped(self):
+        """WEB-02: title/snippet sanitized + capped; non-dict rows skipped."""
+        data = {
+            "results": [
+                {"title": "@everyone Hi", "url": "https://x.com/a", "text": "@here " + "y" * 1000, "publishedDate": "2026-01-01"},
+                {"title": "T2", "url": "https://x.com/b", "text": "short"},
+                "not a dict",
+            ]
+        }
+        rows = _format_results(data, 50)
+        self.assertEqual(len(rows), 2)
+        self.assertNotIn("@everyone", rows[0]["title"])
+        self.assertNotIn("@here", rows[0]["snippet"])
+        self.assertLessEqual(len(rows[0]["snippet"]), 50)
+        self.assertEqual(rows[0]["url"], "https://x.com/a")
+        self.assertEqual(rows[0]["published"], "2026-01-01")
+
+
+class TestSearch(unittest.IsolatedAsyncioTestCase):
+    async def test_num_results_clamped(self):
+        """WEB-03: numResults clamped to 1..10; 0 falls back to default."""
+        ws = WebSearch(lambda: {"exa-api-key": "k"})
+        with patch.object(ws, "_post", new=AsyncMock(return_value={"results": []})) as post:
+            await ws.search("hi", num_results=999)
+            self.assertEqual(post.await_args.args[0]["numResults"], 10)
+            await ws.search("hi", num_results=0)
+            self.assertEqual(post.await_args.args[0]["numResults"], 5)
+
+    async def test_no_key_returns_error(self):
+        """WEB-04: no key -> error dict, no network call."""
+        with patch.dict(os.environ, {"EXA_API_KEY": ""}):
+            ws = WebSearch(lambda: {})
+            with patch.object(ws, "_post", new=AsyncMock()) as post:
+                result = await ws.search("hi")
+            post.assert_not_awaited()
+        self.assertIn("error", result)
+
+    async def test_api_failure_returns_error(self):
+        """WEB-04: a raising request is caught, returns an error dict."""
+        ws = WebSearch(lambda: {"exa-api-key": "k"})
+        with patch.object(ws, "_post", new=AsyncMock(side_effect=RuntimeError("boom"))):
+            result = await ws.search("hi")
+        self.assertIn("error", result)
+
+    async def test_empty_query_no_call(self):
+        """WEB-04: blank query returns empty results without a call."""
+        ws = WebSearch(lambda: {"exa-api-key": "k"})
+        with patch.object(ws, "_post", new=AsyncMock()) as post:
+            result = await ws.search("   ")
+        post.assert_not_awaited()
+        self.assertEqual(result["results"], [])
+
+    async def test_search_returns_formatted(self):
+        """WEB-02: a successful search returns sanitized rows."""
+        ws = WebSearch(lambda: {"exa-api-key": "k"})
+        payload = {"results": [{"title": "Norge", "url": "https://ex.com/n", "text": "fakta"}]}
+        with patch.object(ws, "_post", new=AsyncMock(return_value=payload)):
+            result = await ws.search("norge")
+        self.assertEqual(result["results"][0]["title"], "Norge")
+        self.assertEqual(result["results"][0]["url"], "https://ex.com/n")
+
+
+class TestPerUserCap(unittest.IsolatedAsyncioTestCase):
+    async def test_dispatch_caps_searches(self):
+        """WEB-05: over web-daily-per-user, web_search refuses without calling the API."""
+        responder = OpenAIResponder(dict(CONFIG, **{"enable-web-search": True, "exa-api-key": "k", "web-daily-per-user": 2}), "chat")
+        responder.web_search.search = AsyncMock(return_value={"query": "x", "results": []})
+        for _ in range(2):
+            self.assertIn("results", await responder._dispatch_tool("web_search", {"query": "hi"}, "bob"))
+        blocked = await responder._dispatch_tool("web_search", {"query": "hi"}, "bob")
+        self.assertIn("error", blocked)
+        self.assertEqual(responder.web_search.search.await_count, 2)