The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
TypeScript agentai-chatai-studioall-in-onecoding-agentdesktop-appfluximage-generationlinuxllmlocal-ailocal-llmopen-sourceprivacyself-hostedstable-diffusionuncensoreduncensored-aivideo-generationwindows
/**
* When the model's own chat template refuses the conversation (bug B3, 2.6.7).
*
* llama.cpp, the bundled engine, LM Studio and Ollama all render the GGUF's
* Jinja chat template before the model sees anything. A strict template calls
* raise_exception when the message sequence breaks its rules, the engine turns
* that into HTTP 400, and the turn dies without a single token. The text that
* comes back is written by the template author, not by us:
*
* "System message must be at the beginning" (Mistral style)
* "Conversation roles must alternate user/assistant/..." (Gemma 3)
* "Unable to generate parser for this template ... Jinja Exception: ..."
*
* Two things were wrong with how that reached the user. It was pasted in raw,
* a Jinja stack trace with a line and column number into a chat bubble. And in
* plain chat it arrived under the heading "Agent error", because the chat
* tools route their turn through the agent executor, so a user who had never
* touched Agent mode was told the agent had failed.
*
* The sequence itself is fixed in api/providers/normalize-system.ts. This is
* what the user reads when a template refuses anyway.
*/
import { detailOf, withDetail } from './error-text'
import { httpStatusOf } from './http-status'
import { isContextOverflow } from './context-overflow'
/**
* Wordings from the templates themselves plus the wrappers the engines put
* around them. Deliberately narrow: a plain "invalid request" must not be
* explained as a template problem.
*/
const TEMPLATE_MARKERS =
/jinja|raise_exception|chat[ _]template|template error|generate parser for this template|system message must be at the beginning|roles must alternate|conversation roles|last message must be/i
/** Did the model's chat template refuse to render this conversation? */
export function isTemplateRefusal(err: unknown): boolean {
return TEMPLATE_MARKERS.test(detailOf(err))
}
export const TEMPLATE_REFUSAL_SENTENCE =
"This model's chat template refused the conversation, so the request never reached the model. " +
'Templates like this one accept only a strict order of turns. LU reshapes the history for them, ' +
'and this one still did not fit. Send the message again, start a new chat, or pick a model whose ' +
'template is more forgiving.'
export const BAD_REQUEST_SENTENCE =
'The model backend refused the request before generating anything (HTTP 400). ' +
'Nothing was sent to the model, so nothing was charged. Send the message again, and if it keeps ' +
'happening, start a new chat or pick another model.'
/** A request longer than the window of the model. Sending it again cannot
* help, and a local model charges nothing: the general 400 sentence said
* both (T1 Nacht-Durchtest 3.0.9, 204K characters into a 16K window). The
* sentence names the chat, not the message: in a group the overflow can come
* from an earlier speaker's long answer while the user's line is short. */
export const CONTEXT_OVERFLOW_REFUSAL_SENTENCE =
'This chat is more than the model can read at once, so nothing was generated. Shorten the last ' +
'message or start a new chat, attach long text with Docs instead of pasting it, or raise the Context ' +
'window above the message box if this model offers one.'
/** A backend that names the temperature in its refusal (A33): one LU Cloud
* model takes 0 to 1 and answered 1.9 with a bare 400. */
const TEMPERATURE_MARKERS = /\btemperature\b/i
export const TEMPERATURE_REFUSAL_SENTENCE =
'This model does not accept the temperature this chat uses, so nothing was generated and nothing ' +
'was charged. Open Sampling next to the model picker and press Reset to default, or set Temperature ' +
'to 1.0 or lower.'
/**
* The English sentence for a refusal that produced no output at all, or null
* when this error is not one of those. Callers put it in place of the raw
* message; the raw text is kept underneath it, because support reads it.
*/
export function explainSendRefusal(err: unknown): string | null {
// fit-to-window.ts: the request was measured too big and never sent (CA,
// 14.11.2026). Same sentence as the engine's own refusal, no detail to add.
if (err instanceof Error && err.name === 'ContextFullError') return CONTEXT_OVERFLOW_REFUSAL_SENTENCE
if (isTemplateRefusal(err)) return withDetail(TEMPLATE_REFUSAL_SENTENCE, err)
if (httpStatusOf(err) === 400 && TEMPERATURE_MARKERS.test(detailOf(err))) return withDetail(TEMPERATURE_REFUSAL_SENTENCE, err)
if (httpStatusOf(err) === 400 && isContextOverflow(detailOf(err))) return withDetail(CONTEXT_OVERFLOW_REFUSAL_SENTENCE, err)
if (httpStatusOf(err) === 400) return withDetail(BAD_REQUEST_SENTENCE, err)
return null
}