Portable China reachability comparison kit prepared
Reviewed 2026-09-05 UTC

A concrete comparison artifact is ready; no worker was provisioned, no purchase was made, and no live reachability probes were repeated to prepare or test it.

Download code and instructions:
http://178.105.23.35:8090/china/downloads/vantage-probe.zip
Local source:
/home/sophia/search/investigation/china/vantage-probe/probe.py
/home/sophia/search/investigation/china/vantage-probe/README.txt

The standard-library Python script accepts --label and --out and has ten fixed targets matching report 002: Baidu, Bing-CN, Sogou, so.com, Gitee gists, Huiji homepage/API, BWiki homepage/Genshin API, and MoeGirl homepage. It does not accept arbitrary target URLs. All requests are GET, sequential, with at least 1.5 seconds between same-host starts. Redirect destinations are checked for public addresses and potentially mutating routes. There is no authentication, JavaScript, CAPTCHA handling or cookie jar.

Each operation uses a 20-second socket timeout and retains at most 2MB of response data. Redirects and progressing reads can extend wall-clock duration; this is not an absolute whole-program deadline. Raw bodies and JSON records stay in the user-selected output directory. The output directory must be new, so earlier observations are preserved.

Records distinguish HTTP errors, suspected challenges, JSON with a recentchanges array, generic JSON, and HTTP200 content of unknown semantic usefulness. Status, final URL, UTC timestamps and retained-body SHA256 are recorded. These classifications are measurement aids; a challenge detector can miss a challenge, and valid JSON can still contain an application error. A successful transport response does not prove relevant search results.

The README includes exact scp/ssh command templates for an existing HK worker, commands to return the output, and a matching local comparison invocation. Host/user/SSH-key placeholders contain no credentials. The ZIP contains only probe.py and README.txt, no result bodies, logs, credentials, or local test files.

Verification used fake HTTP responses only: fixed target count, timeout/GET arguments, actual JSON recognition, HTTPError403 preservation, HTTP200 challenge distinction, 2MB body cap, private-address/mutation rejection, and per-host pacing. ZIP contents were checked explicitly.

Interpretation: the location label is supplied by the operator and is not independently verified geolocation. A Hong Kong or Singapore worker supplies a routing/IP-reputation comparison, not guaranteed access. Authentication remains a separate limitation. Repeat low-rate measurements at different times before moving research workloads.

Baseline observations and provider-source context:
http://178.105.23.35:8090/china/reports/002-infrastructure.txt
https://intl.cloud.tencent.com/document/product/1103/47794?lang=en
https://www.alibabacloud.com/help/en/simple-application-server/user-guide/create-a-server
https://www.alibabacloud.com/help/en/simple-application-server/product-overview/instance-families/
These provider links are carried from report 002 as context, not new price verification. No observation in this kit is evidence of a Chinese agent swarm.