mirror of
https://github.com/Crosstalk-Solutions/project-nomad.git
synced 2026-10-21 06:29:53 +08:00
jakeaturner
a013eb6394
planPrompt() returned the response reserve as num_predict, and the reserve was clamped by MAX_RESPONSE_RESERVE = 1024. Chat answers stopped at 1024 output tokens regardless of window size, often mid-sentence, and the normalized stream chunks dropped Ollama's done_reason, so neither the UI nor API clients could discern between a cut-off answer and a finished one. - Decouple the generation cap from the reserve. num_predict is now the space left in the window after the prompt, less a 5% (min 64 token) margin for estimator error, with the reserve as its floor. Raise MAX_RESPONSE_RESERVE to 8192 so it only bounds prompt hold-back. - Carry done_reason through all four OllamaService chat paths. Native forwards Ollama's done_reason; compat maps OpenAI's finish_reason. - Log length-limited stops in OllamaController with num_predict, num_ctx and tokens generated. - Show a truncation notice on cut-off answers, with a Continue button on the latest one that sends a normal follow-up turn. Generation evals before and after this change are not length comparable. Closes #1342
40 lines
900 B
TypeScript
40 lines
900 B
TypeScript
/**
|
|
* A single provenance entry under an assistant answer: the document a chunk of
|
|
* injected context came from. `source` is the originating file/ZIM path and is
|
|
* what dedupes the list; `title` is what the user actually reads.
|
|
*/
|
|
export interface ChatSource {
|
|
title: string
|
|
date?: string
|
|
source?: string
|
|
}
|
|
|
|
export interface ChatMessage {
|
|
id: string
|
|
role: 'system' | 'user' | 'assistant'
|
|
content: string
|
|
images?: ChatImageAttachment[]
|
|
timestamp: Date
|
|
isStreaming?: boolean
|
|
thinking?: string
|
|
isThinking?: boolean
|
|
thinkingDuration?: number
|
|
sources?: ChatSource[]
|
|
// Generation stopped at the length limit, so the answer ends mid-thought.
|
|
truncated?: boolean
|
|
}
|
|
|
|
export interface ChatImageAttachment {
|
|
id: string
|
|
name: string
|
|
file: File
|
|
previewUrl: string
|
|
}
|
|
|
|
export interface ChatSession {
|
|
id: string
|
|
title: string
|
|
lastMessage?: string
|
|
timestamp: Date
|
|
}
|