3b024e132b
Refactor genai client logic to avoid circular imports
2025-06-07 06:06:35 +00:00
f1d08908c3
Applying previous commit.
2025-06-07 06:04:39 +00:00
d1ec42fa51
big ass formatting
2025-06-05 21:31:06 -06:00
308f893df6
fix: Add helper function to normalize finish_reason in TetoCog and update related logic
2025-05-28 23:53:41 -06:00
55af27a133
fix: Update system prompt handling to conditionally include shell command and web search capabilities
2025-05-28 23:48:16 -06:00
c55113a4ca
fix: Refactor tool call processing in TetoCog to improve error handling and streamline execution logic
2025-05-28 23:46:27 -06:00
72b0ce1a4d
fix: Add error handling for tool call processing in TetoCog
2025-05-28 23:33:51 -06:00
4308aec6c1
fix: Update model path in TetoCog for Vertex AI content generation
2025-05-28 23:31:02 -06:00
d17b224975
fix: Simplify model path in TetoCog for Vertex AI content generation
2025-05-28 23:26:16 -06:00
04bbc056d2
fix: Enhance generation configuration by adding system_instruction, tools, and tool_config
2025-05-28 23:24:58 -06:00
2db6b0f850
fix: Update generation configuration to include system_instruction for model content generation
2025-05-28 23:24:02 -06:00
8e6b9b6270
fix: Update import path for SafetySetting in TetoCog
2025-05-28 23:22:45 -06:00
03825d0f62
Fix: Use genai.types.SafetySetting for safety settings
...
This commit updates the `STANDARD_SAFETY_SETTINGS` to explicitly use `genai.types.SafetySetting` instead of just `types.SafetySetting`. This ensures correct type referencing for the safety settings in the `teto_cog.py` file.
2025-05-28 23:21:39 -06:00
0ee02ef854
fix: Update default AI model to gemini-2.5-flash-preview-05-20 for Vertex AI
2025-05-28 23:20:05 -06:00
9e4ac54949
Feat: Migrate TetoCog to Google Vertex AI backend
...
This commit transitions TetoCog from OpenRouter to Google Generative AI,
utilizing the Vertex AI backend.
Key changes include:
- Integration of Google GenAI SDK with project-specific configuration.
- Definition of `STANDARD_SAFETY_SETTINGS`, disabling all content blocking
(Hate Speech, Dangerous Content, Sexually Explicit, Harassment).
- Addition of `_get_response_text` helper function to safely extract
text content from `GenerateContentResponse` objects, with detailed logging.
- Removal of OpenRouter API endpoint, model configuration, and related logic.
- Removal of previous direct shell command execution logic.
2025-05-28 23:18:25 -06:00
07130c6e6e
fix: Update system prompt to clarify character context regarding sexual activities
2025-05-28 23:06:55 -06:00
369d22633d
fix: Update system prompt to clarify character context and usage of terminal commands
2025-05-28 23:06:34 -06:00
208cdb5948
feat: Refactor command groups for TetoCog to improve structure and organization
2025-05-27 21:39:21 -06:00
eef0d99817
feat: Introduce /ame command group and update related commands for Ame-chan AI
2025-05-27 21:25:44 -06:00
1b0fdb86ca
feat: update instruction for character responses to use lowercase text style
2025-05-26 13:58:46 -06:00
5c0ea71b69
fix: clarify instruction on username usage in TetoCog's character prompt
2025-05-26 13:56:32 -06:00
9af3a9eb42
Refactor: Enhance Ame-chan's character prompt for TetoCog
...
Expand the system prompt for Ame-chan (TetoCog) to provide a more detailed and nuanced psychological profile, background, and distinct public (KAngel) and private (Ame) personas. This aims to improve the bot's ability to embody the character's complex personality, including dissociation, anxiety, validation addiction, and specific speech patterns and mannerisms for both identities.
2025-05-26 13:54:58 -06:00
pancakes-proxy
1b48d2eb6e
feat: update character persona for TetoCog to reflect Ame-chan's traits and behaviors
2025-05-26 07:56:51 -04:00
62c752a569
feat: implement web search functionality using Tavily API and add related commands
2025-05-23 16:08:53 -06:00
bb0a6e5734
refactor: Clarify system prompt for Teto AI regarding user message context and username usage
2025-05-22 21:07:17 -06:00
8788cea989
feat: Add upload cog, update AI model, and refine Teto prompt
...
- Introduce `upload_cog.py` for handling file uploads.
- Update AI model from `google/gemini-2.5-flash-preview` to `google/gemini-2.5-flash-preview-05-20` for improved performance and stability.
- Refine Teto's roleplay system prompt:
- Add explicit 18+ age disclaimer for all roleplay characters.
- Include context about prepended usernames for better AI understanding.
- Adjust Teto's perceived age to 18 for consistency.
- Remove outdated or unnecessary prompt instructions.
2025-05-21 11:14:06 -06:00
a0bf8e2f8e
fuck
2025-05-20 06:34:53 -06:00
7bb762d21d
fix: Correct typo in AI personality description for clarity
2025-05-19 22:42:49 -06:00
909616fb60
feat: Enhance shell command extraction and response formatting in Teto AI
2025-05-19 22:34:50 -06:00
c747bd9f2f
feat: Update AI instructions to allow showing full command output
2025-05-19 21:33:01 -06:00
241fb7b140
fix: Escape pipe character in command safety checks and update error message for blocked commands
2025-05-19 21:30:38 -06:00
9054471707
feat: Add debug logging for blocked shell commands in Teto AI
2025-05-19 21:27:29 -06:00
90c024acce
feat: Add command safety checks to prevent execution of dangerous shell commands
2025-05-19 21:22:27 -06:00
decc7aa2fb
feat: Enhance shell command extraction with debug logging and update AI instructions
2025-05-19 21:11:22 -06:00
b643e14a9e
feat: Add shell command extraction and execution handling in Teto AI responses
2025-05-19 21:08:41 -06:00
8c451f1a48
fix: Update age reference for Teto character description in context
2025-05-19 20:54:38 -06:00
ebdef222c0
feat: Implement shell command execution feature in Teto AI with toggle option
2025-05-19 20:52:43 -06:00
61e18a68d2
feat: Enhance Teto image command with interactive button for fetching another image
2025-05-19 20:37:57 -06:00
eccc670823
fix: Update HTTP-Referer in Teto AI headers to point to the correct file location
2025-05-17 15:24:23 -06:00
c3a7693804
fix: Update Teto AI's system prompt to clarify naivety regarding sexual concepts and refine emotional expression guidelines
2025-05-17 13:38:34 -06:00
db1e87287a
fix: Clarify Teto AI's naivety regarding sexual concepts in personality description
2025-05-17 13:23:32 -06:00
10771b0390
fix: Update Teto AI's personality description to clarify naivety regarding nudity and exposure
2025-05-17 13:19:37 -06:00
16f2b64ccf
fix: Clarify character naivety in Teto AI's personality description
2025-05-17 13:17:33 -06:00
be397ffa2b
fix: Update system prompt for Teto AI to enhance character context and clarify naivety
2025-05-17 13:17:05 -06:00
e731cad7ad
Fix: Improve error message formatting in Teto AI conversation
...
This commit adjusts the formatting of the error message sent when the Teto AI conversation fails. The newline character is now placed before the error message for better readability.
2025-05-17 12:48:22 -06:00
e285ad6ce2
Revert "feat: Implement user timeout functionality and enhance conversation context with user IDs"
...
This reverts commit 7eb0180dce6e74f5dd3026bd1abc86496ea88070.
2025-05-17 12:47:01 -06:00
be15146667
Revert "fix: Correct error handling message formatting in Teto AI conversation"
...
This reverts commit a806ba980dfc4e2eab71fafc4414fd9a31aa713b.
2025-05-17 12:46:54 -06:00
39e5ba98e9
Revert "fix: Streamline user ID extraction from conversation history and improve message formatting"
...
This reverts commit 7cfcfe21dab8c002c9e147a44e269cc016d51556.
2025-05-17 12:46:45 -06:00
7cfcfe21da
fix: Streamline user ID extraction from conversation history and improve message formatting
2025-05-17 12:32:06 -06:00
a806ba980d
fix: Correct error handling message formatting in Teto AI conversation
2025-05-17 12:28:05 -06:00
