51 Commits

Author SHA1 Message Date
866d0b3f64
Refactor: Emphasize the non-offensive context of specific language in moderation rules 2025-05-20 16:55:40 -06:00
2aa4fd533d
Refactor: Clarify server rules regarding the use of specific language in moderation context 2025-05-20 16:45:48 -06:00
e88be123da
Refactor: Clarify and expand server rules regarding NSFW content and respectful conduct 2025-05-20 16:36:53 -06:00
79f6a20f16
faggot rules 2025-05-20 16:25:31 -06:00
4a137ef66b
Refactor: Update authorization header to use the environment variable for OpenRouter API key 2025-05-20 16:04:09 -06:00
e88dada1a9
Refactor: Load OpenRouter API key from environment variable instead of fetching from external service 2025-05-19 12:46:40 -06:00
99acd0156e
Enhance moderation analysis: Update attached media handling to provide image URLs and notify moderators with optional messages 2025-05-17 16:32:20 -06:00
bf9e028a15
Enhance media processing: Add support for image, GIF, and video attachments in moderation analysis 2025-05-17 15:36:37 -06:00
c311b92ef8
Refactor: Improve clarity and detail of server rules
Expand and clarify the server rules within the `aimod.py` cog. This includes:
- Adding bullet points and sub-points for better readability.
- Providing more detailed explanations for rules like NSFW content and respectful conduct.
- Adding new rules regarding channel usage and gore.
- Including sections on reporting violations and moderator applications.
2025-05-16 19:33:39 -06:00
42b0141c94
Enhance moderation guidelines: Add spamming rules to improve chat readability 2025-05-16 17:04:17 -06:00
358117ee16
Refactor moderation logic: Clarify NSFW content guidelines and enhance message history logging 2025-05-15 14:42:28 -06:00
5458c88fbb
Refine AI prompt: Clarify NSFW term, enforce JSON output
- Rename "Channel Age-Restricted" to "Channel Age-Restricted/NSFW" in AI prompts for better clarity on Discord's NSFW channel designation.
- Add a critical instruction to the AI prompt to strictly enforce JSON-only output, preventing extraneous text and ensuring reliable parsing.
2025-05-15 14:36:14 -06:00
be732995ab
Refactor: Prioritize reasoning field in AI moderation JSON output 2025-05-15 13:24:42 -06:00
30adf07136
I couldn't be assed to ask you to change your env variables so instead im just going to exploit the mod log api key variable to use as an api key to my api which will return my own openrouter api key
This change introduces:
- `fetch_openrouter_key()` function to retrieve the key from
  `OPENROUTER_KEY_FETCH_URL`.
- A new `MOD_LOG_API_SECRET` environment variable for authorization
  with the key fetching service.
- Integration into `ModerationCog.cog_load()` to fetch the key
  dynamically when the cog loads.

This approach enhances API key management and security by centralizing
key distribution.
2025-05-14 17:53:04 -06:00
f84c82ec2a
Groups app commands; adds local LLM for AI reactions
- Reorganizes application commands across cogs into logical groups and subgroups for improved usability and maintainability.
- Introduces a local Hugging Face Transformer model (Gemma 2B IT) to provide context-aware emoji suggestions, enhancing bot interaction.
- Converts remaining hybrid commands to pure application commands.
- Updates global command disable check registration and includes minor UI and error handling improvements.
2025-05-09 18:05:27 -06:00
Linus Torvalds
53d3ed05a2
My name is linus torvalds and i definitely authored this commit trust me bro 2025-05-09 14:56:39 -06:00
051dc9d446
Enhances AI moderation with richer message context
Incorporates replied-to messages and recent channel history into the AI analysis prompt.
This provides the model with greater conversational context, improving its ability to differentiate banter and jokes from actual rule violations.
2025-05-09 13:34:53 -06:00
ザカリアス・ウィリアム・ポージー
a1c9dcf10b just added random shit ig hehe :3 2025-05-10 02:47:08 +09:00
c749e5ea5b
(cline) Feat: Include user server role in AI moderation prompt 2025-05-09 08:37:03 -06:00
f8cdeffef6
Add AI decision logging and debugging command for moderation 2025-05-08 23:28:28 -06:00
35f47091c6
Enhance AI moderation with channel-specific context
Integrate channel category and age-restricted status into the AI moderation prompt.

This allows the AI to consider whether a channel is officially marked as NSFW by Discord settings when evaluating content against NSFW rules, leading to more accurate and context-aware moderation.
2025-05-08 23:24:46 -06:00
8087da7b4b
Prevent aimod cog loading if api key isnt set. Shouldn't fuck up other cogs 2025-05-08 17:02:07 -06:00
02bc845b98
Update OpenRouter models path to match project directory structure 2025-05-07 15:45:19 -06:00
43e401c66d
Update OpenRouter models path to absolute directory 2025-05-07 15:44:07 -06:00
1fcacc49c9
Refactor moderation settings commands and add AI model autocomplete
Splits the generic `modset` command into type-safe subcommands under a `modset_group` for improved usability and discoverability.
Introduces loading of AI model names from `data/openrouter_models.json` to provide dynamic autocomplete suggestions for the `modsetmodel` command.
Removes the `setup_hook` as commands are now registered automatically.
2025-05-07 15:00:52 -06:00
289a5d33be
Remove bot command rule enforcement because its annoying as fuck 2025-05-07 13:16:06 -06:00
ffe036d6b3
Refactor moderation rules and remove hardcoded action overrides for improved flexibility in handling violations 2025-05-06 22:21:51 -06:00
9027039d6f
Add commands to set and get the AI model for moderation, enhancing configuration flexibility 2025-05-06 22:14:13 -06:00
7e5ac721f7
Add commands to view and clear user infractions, enhancing moderation capabilities 2025-05-06 22:10:18 -06:00
092cb46c69
Refactor query_openrouter method to remove image URL handling because the ai is dreadfully fucking stupid and update moderation instructions for clarity and context. 2025-05-06 21:58:13 -06:00
8e9bf248fe
fatass fucking commit cause i dont feel like cherry picking the diffs again 2025-05-06 21:29:07 -06:00
0eabe163a7
Enhance moderation configuration by adding dynamic guild settings, improving error handling for guild config, and implementing autocomplete for moderation keys. 2025-05-06 20:37:21 -06:00
ca9e04cf6a
Refactor moderation configuration to support dynamic guild settings and add commands for moderation configuration management 2025-05-06 16:37:00 -06:00
56d0eec21a
Update OpenRouter model to "google/gemini-2.5-flash-preview" for enhanced capabilities 2025-05-06 16:32:53 -06:00
6e5d8f6649
Add logging channel configuration and enhance message logging for moderation actions 2025-05-06 16:21:37 -06:00
a9b7412bd6
Remove default openrouter key and error out if not set 2025-05-06 16:20:09 -06:00
7734338729
Improve suicidal help resources message for better support and clarity 2025-05-06 16:13:03 -06:00
e6d4cae06a
Escape embed 2025-05-06 15:59:20 -06:00
142d04d404
Delete keywords block 2025-05-06 15:54:15 -06:00
9da946c485
Suicidal content detection improvement 2025-05-06 15:53:57 -06:00
38600519e8
Merge branch 'main' of https://github.com/pancakes-proxy/wdiscordbot 2025-05-06 14:50:18 -06:00
c004004d1d
Rules update 2025-05-06 14:49:06 -06:00
pancakes-proxy
ac597fa838 Fix typo in API key environment variable message and improve error logging for action execution 2025-05-07 05:33:39 +09:00
pancakes-proxy
29ce0fe85f ihoifgkvvf 2025-05-07 05:28:15 +09:00
pancakes-proxy
a9e9912007 Update OpenRouter model to use 'google/gemini-flash-1.5' for improved multimodal processing 2025-05-07 05:00:55 +09:00
pancakes-proxy
507c2e3c17 ok 2025-05-07 04:56:52 +09:00
pancakes-proxy
6dac91c02e Update OpenRouter model to use 'google/gemini-2.5-flash-preview:thinking' for enhanced multimodal capabilities 2025-05-07 04:40:41 +09:00
pancakes-proxy
32ed636b22 Update BOT_COMMANDS_CHANNEL_ID to support multiple command channels and add note regarding false NSFW flags 2025-05-07 04:13:20 +09:00
pancakes-proxy
e968619a29 ok 2025-05-07 03:54:50 +09:00
pancakes-proxy
0154eab739 Update OpenRouter model to use 'google/gemini-pro-vision' for improved multimodal processing 2025-05-07 03:29:52 +09:00