- Replace simple message count with token-based calculation - Add token estimation function (4 chars ≈ 1 token) - Set MAX_TOKENS to 5000 and MIN_DISPLAY_PERCENTAGE to 20 - Update context usage display to show token count percentage - Track tokens for both user and assistant messages - Handle server-provided context usage as ratio of MAX_TOKENS
6 lines
88 B
JSON
6 lines
88 B
JSON
{
|
|
"name": "botserver",
|
|
"lockfileVersion": 3,
|
|
"requires": true,
|
|
"packages": {}
|
|
}
|