AI Aliyun Content Moderation Changelog

Released changes to the AI Aliyun Content Moderation plugin (`ai-aliyun-content-moderation`), newest release first.

24 released changes name ai-aliyun-content-moderation, newest release first — 4 in Apache APISIX, 20 in API7 Gateway. Each row links to the change itself.

Apache APISIX

Release	Date	Type	Change
3.18.0	2026-08-18	Feature	Moderate system and tool role content
3.18.0	2026-08-18	Fix	Return nil instead of ngx.OK in lua_body_filter
3.18.0	2026-08-18	Feature	role-aware request_check_mode and O(n) content chunking. Request moderation now covers the user role of the latest turn by default instead of every message in the body
3.14.0	2025-10-09	Feature	Add ai-aliyun-content-moderation plugin

API7 Gateway

Release	Date	Type	Change
3.10.7 (opens in API7 Gateway docs)	2026-09-08	Fix	AI AWS Content Moderation and AI Aliyun Content Moderation: Fixed issue: A streaming response cut short by the gateway's own max_response_bytes or max_stream_duration_ms limit was given a synthetic completion event, s… (opens in API7 Gateway docs)
3.10.5 (opens in API7 Gateway docs)	2026-08-11	Feature	Added request_check_roles and request_check_mode to choose which message roles are moderated and whether only the last message or every message of the selected roles is checked, matching the options already available… (opens in API7 Gateway docs)
3.10.5 (opens in API7 Gateway docs)	2026-08-11	Fix	Fixed issue: In realtime stream check mode with a protocol converter in use — for example an Anthropic client in front of an OpenAI-compatible upstream — the same response text was submitted to the moderation service… (opens in API7 Gateway docs)
3.10.5 (opens in API7 Gateway docs)	2026-08-11	Fix	Fixed issue: With system selected in request_check_roles, content placed in a developer role message was not sent for moderation. developer is the role OpenAI uses in place of system on newer models and on the Respons… (opens in API7 Gateway docs)
3.10.3 (opens in API7 Gateway docs)	2026-07-14	Feature	Added request_check_roles to choose which request roles are moderated (user, tool, and/or system). user and tool content follow request_check_mode (last or all, default last), while system content is checked on every… (opens in API7 Gateway docs)
3.10.3 (opens in API7 Gateway docs)	2026-07-14	Fix	AI AWS Content Moderation and AI Aliyun Content Moderation: Fixed issue: deny_code accepted arbitrary numbers. It is now validated as an integer HTTP status code in the 200–599 range (default 200), so an out-of-range… (opens in API7 Gateway docs)
3.10.3 (opens in API7 Gateway docs)	2026-07-14	Fix	Fixed issue: Returning ngx.OK from the body filter could interrupt later body-filter processing. The plugin now returns normally so other filters can continue. (opens in API7 Gateway docs)
3.10.2 (opens in API7 Gateway docs)	2026-06-29	Feature	Added request_check_mode (last or all, default last) to control how much of a multi-turn conversation is moderated: last checks only the final user turn, while all checks every user turn. Only user-role content is mod… (opens in API7 Gateway docs)
3.10.1 (opens in API7 Gateway docs)	2026-06-15	Feature	AI content security plugins (ai-aliyun-content-moderation, ai-aws-content-moderation, ai-prompt-guard): Added a fail_mode option (skip, warn, or error; default skip) that controls how the plugin handles non-AI or non-… (opens in API7 Gateway docs)
3.9.19 (opens in API7 Gateway docs)	2026-08-26	Fix	AI AWS Content Moderation and AI Aliyun Content Moderation: Fixed issue: When the gateway cut a stream short itself — max_response_bytes or max_stream_duration_ms on AI Proxy reaching its limit — these plugins still a… (opens in API7 Gateway docs)
3.9.18 (opens in API7 Gateway docs)	2026-08-12	Feature	Added request_check_roles and request_check_mode to choose which message roles are moderated and whether only the last message or every message of the selected roles is checked, matching the options already available… (opens in API7 Gateway docs)
3.9.18 (opens in API7 Gateway docs)	2026-08-12	Fix	Fixed issue: In realtime stream check mode with a protocol converter in use — for example an Anthropic client in front of an OpenAI-compatible upstream — the same response text was submitted to the moderation service… (opens in API7 Gateway docs)
3.9.18 (opens in API7 Gateway docs)	2026-08-12	Fix	Fixed issue: With system selected in request_check_roles, content placed in a developer role message was not sent for moderation. developer is the role OpenAI uses in place of system on newer models and on the Respons… (opens in API7 Gateway docs)
3.9.17 (opens in API7 Gateway docs)	2026-07-28	Change	AI Aliyun Content Moderation requires deny_code to be an integer HTTP status code in the 200–599 range. AI AWS Content Moderation was already validated this way by the Control Plane; this release brings the Data Plane… (opens in API7 Gateway docs)
3.9.17 (opens in API7 Gateway docs)	2026-07-28	Fix	AI AWS Content Moderation and AI Aliyun Content Moderation: Fixed issue: deny_code accepted arbitrary numbers. It is now validated as an integer HTTP status code in the 200–599 range (default 200), so an out-of-range… (opens in API7 Gateway docs)
3.9.17 (opens in API7 Gateway docs)	2026-07-28	Fix	Fixed issue: deny_code accepted arbitrary numbers. It is now validated as an integer HTTP status code in the 200–599 range (default 200), so an out-of-range value is rejected at configuration time. For ai-aws-content-… (opens in API7 Gateway docs)
3.9.16 (opens in API7 Gateway docs)	2026-07-10	Feature	Added request_check_roles to choose which request roles are moderated (user, tool, and/or system). user and tool content follow request_check_mode (last or all, default last), while system content is checked on every… (opens in API7 Gateway docs)
3.9.16 (opens in API7 Gateway docs)	2026-07-10	Fix	Fixed issue: Returning ngx.OK from the body filter could interrupt later body-filter processing. The plugin now returns normally so other filters can continue. (opens in API7 Gateway docs)
3.9.8 (opens in API7 Gateway docs)	2026-04-07	Fix	Fixed issue: Empty or whitespace-only content caused a 400 error from the Alibaba Cloud moderation API. Additionally, LLM error responses (status ≥ 400) triggered a 500 error during response moderation, and multimodal… (opens in API7 Gateway docs)
3.8.0 (opens in API7 Gateway docs)	2025-04-22	Feature	Added support for streaming (HTTP SSE) scenarios. (opens in API7 Gateway docs)