mirror of
https://github.com/openswarm-ai/openswarm.git
synced 2026-09-26 19:44:51 +02:00
* [haik]: ckpt, added in the test runner skelton i made in another repo -> still gotta make tweaks to fold it onto the current repo * [haik]: restructure backend test layout: move 37 test files from backend/tests/ into backend/tests/test_cases/, add backend/tests/run.sh one-command launcher that auto-provisions both runner and test venvs with stamp-based caching, update runner config.json to point test_paths at test_cases/ and fix venv_python path, revise runner README with run.sh usage and clearer setup instructions, and gitignore the .runner-venv directory * [haik]: refactor: reorganize backend/tests/test_cases from flat structure into domain subdirectories — moved 36 test files into auth/, browser/, labeling/, service/, settings/, and web_search/ for better discoverability and grouping * [haik]: overhaul test picker UI and add post-run rerun loop: replace checkbox glyphs with fzf-style row recolouring (coral=full, lighter coral=partial) and a right-pinned selection dot, add config-driven icon tiers (nerd/emoji/unicode/ascii) with per-glyph graceful degradation, replace the modal -k keyword screen with an inline live-filtering search bar that prunes the tree on every keystroke, add warm Anthropic-dark coral theme, toolbar flag chips replacing the old status line, and a floating help badge overlay; add rerun_prompt.py with inline Textual pill prompt (rerun all/failed/passed/exit) shown after each TTY run, wire it into main.py as a post-run loop; change run_tests to return (exit_code, RunSummary) tracking collected/passed/failed node IDs via new Dashboard methods; add icons field to config.py and config.json (set to nerd), document icon tiers and Nerd Font setup in README, set Hack Nerd Font in .vscode/settings.json, add .runner-venv to linter excludes
65 lines
2.1 KiB
Python
65 lines
2.1 KiB
Python
"""Aux-LLM stuck-adjudication for the browser sub-agent."""
|
|
|
|
import asyncio
|
|
|
|
from backend.apps.agents.browser.browser_validator import adjudicate_stuck, p_extract_text # p-private-ignore: p_extract_text
|
|
|
|
|
|
class Block:
|
|
def __init__(self, type_, text=""):
|
|
self.type = type_
|
|
self.text = text
|
|
|
|
|
|
class Resp:
|
|
def __init__(self, blocks):
|
|
self.content = blocks
|
|
|
|
|
|
class FakeClient:
|
|
"""Minimal Anthropic-shaped client: client.messages.create(...)."""
|
|
|
|
def __init__(self, resp=None, raise_exc=None):
|
|
self.resp = resp
|
|
self.raise_exc = raise_exc
|
|
self.calls = []
|
|
self.messages = self
|
|
|
|
async def create(self, **kwargs):
|
|
self.calls.append(kwargs)
|
|
if self.raise_exc:
|
|
raise self.raise_exc
|
|
return self.resp
|
|
|
|
|
|
def test_returns_extracted_guidance_and_assembles_prompt():
|
|
fc = FakeClient(resp=Resp([Block("text", "Press Tab then Enter to focus the field.")]))
|
|
out = asyncio.run(adjudicate_stuck(fc, "cheap-model", "share the doc", "- click -> not found", "the page"))
|
|
assert out == "Press Tab then Enter to focus the field."
|
|
call = fc.calls[0]
|
|
assert call["model"] == "cheap-model"
|
|
assert call["max_tokens"] == 300
|
|
prompt = call["messages"][0]["content"]
|
|
assert "share the doc" in prompt
|
|
assert "not found" in prompt
|
|
|
|
|
|
def test_swallows_provider_error_and_returns_empty():
|
|
fc = FakeClient(raise_exc=RuntimeError("429 rate limited"))
|
|
out = asyncio.run(adjudicate_stuck(fc, "m", "g", "r", "p"))
|
|
assert out == ""
|
|
|
|
|
|
def test_extract_text_joins_text_blocks_and_ignores_others():
|
|
resp = Resp([Block("text", "First."), Block("tool_use"), Block("text", "Second.")])
|
|
assert p_extract_text(resp) == "First. Second."
|
|
|
|
|
|
def test_handles_empty_inputs_without_crashing():
|
|
fc = FakeClient(resp=Resp([Block("text", "ok")]))
|
|
out = asyncio.run(adjudicate_stuck(fc, "m", "", "", ""))
|
|
assert out == "ok"
|
|
# placeholders keep the prompt well-formed
|
|
prompt = fc.calls[0]["messages"][0]["content"]
|
|
assert "(unknown)" in prompt and "(none)" in prompt and "(empty)" in prompt
|