199 lines
8.2 KiB
Python
Raw Normal View History

feat(tanya): Execute four recursive verification rounds and compile final report Outcome: done Changed: none (read-only; rounds run via PYTHONPATH=src python3 heredocs) Verified by: make verify -> exit_code 0 "Ran 219 tests in 0.968s OK verification passed" Findings: - R1 2026-08-07T23:31:17Z PASS engine-optimality: empty world closes round1 (lfp halt); chain4 -> 6 rounds/5 urls (no depth cap); dedup unique-only; S* size5 > F^2 size2. - R2 2026-08-07T23:34:35Z PASS verifies R1: chain6 pool1 -> 8 rounds/7 urls, F^3=3 subset S*=7; content-only closes round2; fanout 2 urls/5 queries. - R3 2026-08-07T23:35:02Z PASS verifies R2: pools 1/4/8 identical (8,7,14,1); cached 2nd run 0 network calls, identical report; pool_size==max_concurrency. - R4 2026-08-07T23:36:26Z PASS verifies R3: stress 38 items=succ+fail, 4 content kinds, closed; ""/whitespace -> ValueError, zero calls; chain5 pool8 7 rounds/6 urls; slow client completes. - Engine C1-C8 all PASS (sibling f7f10c64): rsearch-only, bound 8, one _request 4 content types, dedup 64->1, closure, annotations/logging/header, no TODO, verify green. - Live probe (fde105db, "python asyncio"): 86 queries, 754 urls, 281 contents, 164 requests, $0.002075, 264.91s; no closure in 240s guard -> TimeoutError, 2835 enqueued. - Rounds' initial failures were tester-expectation only (MIN_QUERY_LENGTH=2 frontier.py:13, description seeds, non-http tokens kept); engine correct; reflect() recorded. Open: none for this node; PR creation deferred to run coordinator (deepresearch.md exists, sibling 7d91ddb) Confidence: high - four round Typosaurus-Run: 4e2afb673c7f4578a12276d9181b982d Typosaurus-Node: 0cee401df29142ecb2bf3bca088d5953 Typosaurus-Agent: @tanya Refs: #31
2026-08-08 01:37:59 +02:00
# retoor <retoor@molodetz.nl>
import unittest
from collections.abc import Callable
from typosaurus_sandbox.research.config import ResearchConfig
from typosaurus_sandbox.research.engine import ResearchEngine
from typosaurus_sandbox.research.envelopes import ChatResponse, DescribeResponse, SearchResponse, SearchResult
class FakeResearchClient:
def __init__(
self,
*,
web_results: list[SearchResult] | None = None,
web_result_factory: Callable[[str], list[SearchResult]] | None = None,
chat_text: str = "",
describe_text: str = "",
) -> None:
self.config = ResearchConfig(max_concurrency=4, default_count=5)
self._web_results = web_results if web_results is not None else []
self._web_result_factory = web_result_factory
self._chat_text = chat_text
self._describe_text = describe_text
self.calls: list[tuple[str, str, str | None]] = []
def search_cached(
self,
query: str,
*,
source: str | None = None,
count: int | None = None,
content: bool = False,
type: str | None = None,
deep: bool = False,
ai: bool = False,
cache: bool = True,
) -> None:
return None
def describe_cached(self, url: str) -> None:
return None
async def search(
self,
query: str,
*,
source: str | None = None,
count: int | None = None,
content: bool = False,
type: str | None = None,
deep: bool = False,
ai: bool = False,
cache: bool = True,
) -> SearchResponse:
self.calls.append(("search", query, type))
if type == "images":
return SearchResponse(query=query, source="wikimedia", count=0, success=True, results=[])
results = self._web_result_factory(query) if self._web_result_factory is not None else list(self._web_results)
return SearchResponse(query=query, source="duckduckgo", count=len(results), success=True, results=results)
async def chat(self, prompt: str, *, system: str | None = None, json_mode: bool = False, cache: bool = True) -> ChatResponse:
self.calls.append(("chat", prompt, None))
return ChatResponse(response=self._chat_text, prompt=prompt)
async def describe(self, url: str) -> DescribeResponse:
self.calls.append(("describe", url, None))
return DescribeResponse(description=self._describe_text, url=url)
class TestEngineClosureDetection(unittest.IsolatedAsyncioTestCase):
async def test_run_closes_after_single_round_when_nothing_new(self) -> None:
client = FakeResearchClient(web_results=[], chat_text="", describe_text="")
engine = ResearchEngine(client=client)
report = await engine.run(" deep research ")
self.assertEqual(report.subject, "deep research")
self.assertTrue(report.closed)
self.assertEqual(report.total_rounds, 1)
self.assertEqual(len(report.rounds), 1)
first = report.rounds[0]
self.assertEqual(first.number, 1)
self.assertEqual(first.items_processed, 3)
self.assertEqual(first.requests_succeeded, 3)
self.assertEqual(first.requests_failed, 0)
self.assertEqual(first.new_urls, 0)
self.assertEqual(first.new_queries, 0)
self.assertTrue(first.closed)
self.assertEqual(report.queries_issued, 1)
self.assertEqual(report.queries_enqueued, 1)
self.assertEqual(report.urls_collected, 0)
self.assertEqual(report.contents_seen, 0)
self.assertEqual(report.content_types, {"web": 1, "images": 1, "chat": 1})
self.assertEqual(len(client.calls), 3)
self.assertEqual({kind for kind, _, _ in client.calls}, {"search", "chat"})
async def test_run_discovery_rounds_then_closes(self) -> None:
client = FakeResearchClient(
web_results=[
SearchResult(
title="topic alpha",
url="https://example.com/alpha",
description="alpha details",
content="alpha body",
)
],
chat_text="",
describe_text="",
)
engine = ResearchEngine(client=client)
report = await engine.run("deep research")
self.assertTrue(report.closed)
self.assertEqual(report.total_rounds, 2)
first = report.rounds[0]
self.assertEqual(first.new_urls, 1)
self.assertEqual(first.new_queries, 2)
self.assertEqual(first.new_contents, 1)
self.assertFalse(first.closed)
second = report.rounds[1]
self.assertEqual(second.new_urls, 0)
self.assertEqual(second.new_queries, 0)
self.assertTrue(second.closed)
self.assertEqual(report.queries_generated, 7)
self.assertEqual(report.queries_enqueued, 3)
self.assertEqual(report.queries_issued, 3)
self.assertEqual(report.queries_duplicates_skipped, 4)
self.assertEqual(report.urls_collected, 1)
self.assertEqual(report.urls_duplicates_skipped, 2)
self.assertEqual(report.contents_seen, 1)
self.assertEqual(report.content_duplicates_skipped, 2)
self.assertEqual(report.requests_succeeded, 10)
self.assertEqual(report.requests_failed, 0)
self.assertEqual(report.cache_hits, 0)
self.assertEqual(report.cache_misses, 10)
self.assertEqual(report.content_types, {"web": 3, "images": 3, "chat": 3, "describe": 1})
self.assertEqual(len(client.calls), 10)
self.assertEqual(sum(1 for kind, _, type_value in client.calls if kind == "search" and type_value is None), 3)
self.assertEqual(sum(1 for kind, _, type_value in client.calls if kind == "search" and type_value == "images"), 3)
self.assertEqual(sum(1 for kind, _, _ in client.calls if kind == "chat"), 3)
self.assertEqual(sum(1 for kind, value, _ in client.calls if kind == "describe"), 1)
self.assertIn(("describe", "https://example.com/alpha", None), client.calls)
async def test_new_content_alone_does_not_prevent_closure(self) -> None:
def factory(query: str) -> list[SearchResult]:
return [
SearchResult(
title="dup title",
url="https://example.com/dup",
description="dup details",
content=f"body for {query}",
)
]
client = FakeResearchClient(web_result_factory=factory, chat_text="", describe_text="")
engine = ResearchEngine(client=client)
report = await engine.run("subject")
self.assertTrue(report.closed)
self.assertEqual(report.total_rounds, 2)
first = report.rounds[0]
self.assertEqual(first.new_urls, 1)
self.assertEqual(first.new_queries, 2)
self.assertFalse(first.closed)
second = report.rounds[1]
self.assertEqual(second.new_urls, 0)
self.assertEqual(second.new_queries, 0)
self.assertEqual(second.new_contents, 2)
self.assertTrue(second.closed)
self.assertEqual(report.contents_seen, 3)
async def test_round_summary_dict_is_serialisable(self) -> None:
client = FakeResearchClient(web_results=[], chat_text="", describe_text="")
engine = ResearchEngine(client=client)
report = await engine.run("serialisable subject")
summary_dict = report.rounds[0].to_dict()
self.assertEqual(summary_dict["number"], 1)
self.assertTrue(summary_dict["closed"])
report_dict = report.to_dict()
self.assertEqual(report_dict["subject"], "serialisable subject")
self.assertEqual(report_dict["total_rounds"], 1)
self.assertTrue(report_dict["closed"])
class TestEngineInputValidation(unittest.IsolatedAsyncioTestCase):
async def test_empty_subject_raises_without_requests(self) -> None:
client = FakeResearchClient(web_results=[], chat_text="", describe_text="")
engine = ResearchEngine(client=client)
with self.assertRaises(ValueError) as ctx:
await engine.run(" \n\t ")
self.assertEqual(str(ctx.exception), "research subject must not be empty")
self.assertEqual(client.calls, [])
if __name__ == "__main__":
unittest.main()