'Choose the color theme for the interface. You can choose between System (follows your device settings), Light, or Dark.',
pasteLongTextToFileLen:
'On pasting long text, it will be converted to a file. You can control the file length by setting the value of this parameter. Value 0 means disable.',
'When copying a message with text attachments, combine them into a single plain text string instead of a special format that can be pasted back as attachments.',
'The order at which samplers are applied, in simplified way. Default is "top_k;typ_p;top_p;min_p;temperature": top_k->typ_p->top_p->min_p->temperature',
'Controls the randomness of the generated text by affecting the probability distribution of the output tokens. Higher = more random, lower = more focused.',
dynatemp_range:
'Addon for the temperature sampler. The added value to the range of dynamic temperature, which adjusts probabilities by entropy of tokens.',
dynatemp_exponent:
'Addon for the temperature sampler. Smoothes out the probability redistribution based on the most probable token.',
top_k:'Keeps only k top tokens.',
top_p:'Limits tokens to those that together have a cumulative probability of at least p',
min_p:
'Limits tokens based on the minimum probability for a token to be considered, relative to the probability of the most likely token.',
xtc_probability:
'XTC sampler cuts out top tokens; this parameter controls the chance of cutting tokens at all. 0 disables XTC.',
xtc_threshold:
'XTC sampler cuts out top tokens; this parameter controls the token probability that is required to cut that token.',
typ_p:'Sorts and limits tokens based on the difference between log-probability and entropy.',
repeat_last_n:'Last n tokens to consider for penalizing repetition',
repeat_penalty:'Controls the repetition of token sequences in the generated text',
presence_penalty:'Limits tokens based on whether they appear in the output or not.',
frequency_penalty:'Limits tokens based on how often they appear in the output.',
dry_multiplier:
'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the DRY sampling multiplier.',
dry_base:
'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the DRY sampling base value.',
dry_allowed_length:
'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the allowed length for DRY sampling.',
dry_penalty_last_n:
'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets DRY penalty for the last n tokens.',
max_tokens:'The maximum number of token per output. Use -1 for infinite (no limit).',
custom:'Custom JSON parameters to send to the API. Must be valid JSON format.',
showThoughtInProgress:'Expand thought process by default when generating messages.',
'Strip thinking from previous messages before sending. When off, thinking is sent back via the reasoning_content field so the model sees its own chain-of-thought across turns.',
'Configure MCP servers as a JSON list. Use the form in the MCP Client settings section to edit.',
mcpServerUsageStats:
'Usage statistics for MCP servers. Tracks how many times tools from each server have been used.',
agenticMaxTurns:
'Maximum number of tool execution cycles before stopping (prevents infinite loops).',
agenticMaxToolPreviewLines:
'Number of lines shown in tool output previews (last N lines). Only these previews and the final LLM response persist after the agentic loop completes.',
showToolCallInProgress:
'Automatically expand tool call details while executing and keep them expanded after completion.',
'After each response, re-submit the conversation to pre-fill the server KV cache. Makes the next turn faster since the prompt is already encoded while you read the response.',
