mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-07-06 22:12:12 +02:00
bdacea8b6e
Wire captchatools as the StealthyFetcher-tier page_action to detect, harvest (egressing from the crawl's own proxy IP), inject, and submit reCAPTCHA v2/v3 and hCaptcha tokens. Opt-in and off by default (zero attempts, zero cost). Licensing split: - Apache-2 app/utils/captcha/ holds the generic, vendor-agnostic config (CaptchaConfig + captcha_enabled() = flag AND key present). - Proprietary app/proprietary/web_crawler/captcha.py holds the bypass logic (detect/harvest/inject) plus a process-wide solver latch that halts solving on unrecoverable errors (no balance / bad key). Crawler: CrawlOutcome gains captcha_attempts/captcha_solved, surfaced via a per-call captcha_state dict threaded crawl_url -> _crawl_with_stealthy(_sync) and stamped onto every stealth terminal outcome. The stealth tier captures the proxy once and reuses it for both the fetch and the solver (IP-coherence). Billing: WebCrawlCreditService gains captcha_billing_enabled, captcha_solves_to_micros, charge_captcha, and a generic check_balance, sharing a single _apply_debit path. The indexer accumulates attempts (even on failed crawls), runs a combined crawl+captcha pre-flight, and posts a per-attempt owner charge as usage_type="web_crawl_captcha". The captcha worst-case is only reserved when solving is actually enabled, so a solving-off deployment is never blocked for captcha that can never run. Both chat scrape tools fold attempts into the current turn before the success/fail branch. Fully config-driven prices; no migration. New unit tests cover the config, factory (detection/latch/timeout/cap), credit service, indexer wiring, and the chat fold. Co-authored-by: Cursor <cursoragent@cursor.com>
47 lines
1.9 KiB
Python
47 lines
1.9 KiB
Python
"""Unit tests for the generic captcha config gate (Phase 3d, Apache-2 layer)."""
|
|
|
|
import pytest
|
|
|
|
from app.config import config
|
|
from app.utils.captcha import captcha_enabled, get_captcha_config
|
|
|
|
pytestmark = pytest.mark.unit
|
|
|
|
|
|
class TestCaptchaEnabled:
|
|
def test_off_by_default(self, monkeypatch):
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVING_ENABLED", False)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_API_KEY", "key")
|
|
assert captcha_enabled() is False
|
|
|
|
def test_flag_on_but_no_key_is_disabled(self, monkeypatch):
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVING_ENABLED", True)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_API_KEY", None)
|
|
assert captcha_enabled() is False
|
|
|
|
def test_flag_on_with_key_is_enabled(self, monkeypatch):
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVING_ENABLED", True)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_API_KEY", "key")
|
|
assert captcha_enabled() is True
|
|
|
|
|
|
class TestGetCaptchaConfig:
|
|
def test_snapshot_reflects_config(self, monkeypatch):
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVING_ENABLED", True)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_API_KEY", "key")
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_PROVIDER", "2captcha")
|
|
monkeypatch.setattr(config, "CAPTCHA_MAX_ATTEMPTS_PER_URL", 3)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVE_TIMEOUT_S", 90)
|
|
monkeypatch.setattr(config, "CAPTCHA_TYPE_DEFAULT", "hcaptcha")
|
|
|
|
cfg = get_captcha_config()
|
|
assert cfg.enabled is True
|
|
assert cfg.solving_site == "2captcha"
|
|
assert cfg.max_attempts_per_url == 3
|
|
assert cfg.timeout_s == 90
|
|
assert cfg.captcha_type_default == "hcaptcha"
|
|
|
|
def test_keyless_config_is_not_enabled(self, monkeypatch):
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVING_ENABLED", True)
|
|
monkeypatch.setattr(config, "CAPTCHA_SOLVER_API_KEY", None)
|
|
assert get_captcha_config().enabled is False
|