fix(editor+agent): multilignes conservees (cause reelle) + validation des modeles Nvidia
Editeur: - sync() lisait el.textContent qui supprime les <br> : ajout de gt() (innerText) utilise par sync(), tableaux (toggle/columns) et _resultText. - Scission sur Entree + limites haut/bas de bloc via splitCaret() (marqueur temporaire au curseur), plus de perte de fin de bloc multi-lignes. Agent: - fetch_provider_models() valide la liste nvidia : filtre des modeles non-chat (nom) puis probe reelle /chat/completions (6 paralleles, 6s), seuls les modeles 2xx restent. 429 conserve (route, donc utilisable). - Repli sur la liste filtree si toutes les validations echouent. - tests/test_llm_config.py : 5 cas (catalogue mock, 404 chat, autres providers non valides, chute de securite, offline). 276 tests passent.
This commit is contained in:
+1
-1
@@ -60,7 +60,7 @@ async def lifespan(_app: FastAPI):
|
||||
|
||||
app = FastAPI(
|
||||
title="FlowDeck",
|
||||
version="5.1.7",
|
||||
version="5.1.8",
|
||||
docs_url="/docs" if settings.log_level == "DEBUG" else None,
|
||||
redoc_url=None,
|
||||
lifespan=lifespan,
|
||||
|
||||
@@ -11,11 +11,32 @@ Rows are created lazily, so .env stays the default until saved from the UI.
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import time
|
||||
from typing import Optional
|
||||
|
||||
from app.config import settings
|
||||
from app.services.llm_client import PROVIDERS, PROVIDER_MODELS
|
||||
|
||||
# Providers whose /v1/models lists far more entries than /v1/chat/completions
|
||||
# actually serves. The fetched list is validated (name filter + live probe)
|
||||
# before being exposed as "usable models". NVIDIA exposes all of its catalog
|
||||
# (embeddings, rerank, image/video/audio gen…) many of which answer 404 on
|
||||
# chat completions — the exact failure the user hit.
|
||||
_CHAT_VALIDATED_PROVIDERS = frozenset({"nvidia"})
|
||||
|
||||
# Markers that identify clearly non-chat models (embeddings, rerank, media gen…).
|
||||
_NON_CHAT_MARKERS = (
|
||||
"embed", "bge-", "rerank", "retriev", "tts", "asr", "stt", "whisper", "speech",
|
||||
"transcrib", "translate", "image", "video", "audio", "music", "sound", "dall",
|
||||
"stable", "diffus", "flux", "sora", "veo", "midjourney", "clip", "segmentation",
|
||||
"ocr", "inpainting", "depth", "motion", "sento-",
|
||||
)
|
||||
|
||||
|
||||
def _is_likely_chat(model_id: str) -> bool:
|
||||
ml = model_id.lower()
|
||||
return not any(m in ml for m in _NON_CHAT_MARKERS)
|
||||
|
||||
__all__ = [
|
||||
"get_llm_config", "set_llm_config", "provider_info",
|
||||
"get_user_llm_key", "list_user_llm_keys", "upsert_user_llm_key",
|
||||
@@ -315,4 +336,59 @@ async def fetch_provider_models(provider: str, *, api_key: str = "",
|
||||
if i not in seen:
|
||||
seen.add(i)
|
||||
out.append(i)
|
||||
return out[:300]
|
||||
|
||||
# Providers like NVIDIA list their whole catalog, most of which is NOT served
|
||||
# by /v1/chat/completions (404 sur « model not found »). Filter by name first,
|
||||
# then probe the survivors with a minimal chat call so only usable models stay.
|
||||
if provider in _CHAT_VALIDATED_PROVIDERS and out:
|
||||
candidates = [m for m in out if _is_likely_chat(m)] or out
|
||||
validated = await _validate_chat_models(base_url, api_key, candidates)
|
||||
# Ne vidons jamais la liste : en cas d'échec de validation (débit limité,
|
||||
# indisponibilité passagère) on garde la liste filtrée par nom.
|
||||
out = validated if validated else candidates
|
||||
|
||||
return out[:300]
|
||||
|
||||
|
||||
async def _validate_chat_models(base_url: str, api_key: str, candidates: list[str],
|
||||
*, timeout: float = 6.0, concurrency: int = 6,
|
||||
deadline: float = 55.0) -> list[str]:
|
||||
"""Probe `POST {base_url}/chat/completions` for each candidate with a minimal
|
||||
payload and keep the models that accept it. A 429 (rate limit) is treated as
|
||||
"probably fine" since it proves the model is routed, not that it's invalid."""
|
||||
import asyncio
|
||||
import httpx
|
||||
|
||||
valid: list[str] = []
|
||||
sem = asyncio.Semaphore(concurrency)
|
||||
start = time.monotonic()
|
||||
headers = {"Content-Type": "application/json"}
|
||||
if api_key:
|
||||
headers["Authorization"] = f"Bearer {api_key}"
|
||||
payload: dict = {
|
||||
"model": None,
|
||||
"messages": [{"role": "user", "content": "ping"}],
|
||||
"max_tokens": 4,
|
||||
}
|
||||
|
||||
async def probe(model: str) -> str | None:
|
||||
if time.monotonic() - start > deadline:
|
||||
return None
|
||||
payload["model"] = model
|
||||
try:
|
||||
async with sem:
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
resp = await client.post(
|
||||
f"{base_url}/chat/completions", headers=headers, json=payload
|
||||
)
|
||||
if resp.status_code < 300 or resp.status_code == 429:
|
||||
return model
|
||||
except Exception: # noqa: BLE001 — réseau/timeout ⇒ rejeté
|
||||
return None
|
||||
return None
|
||||
|
||||
results = await asyncio.gather(*(probe(m) for m in candidates))
|
||||
for m in results:
|
||||
if m:
|
||||
valid.append(m)
|
||||
return valid
|
||||
@@ -15,6 +15,16 @@
|
||||
|
||||
let _bid=0;function genId(){return 'b'+(++_bid)+'_'+Date.now().toString(36);}
|
||||
function cp(e){const s=window.getSelection();if(!s.rangeCount)return 0;const r=s.getRangeAt(0).cloneRange();r.selectNodeContents(e);r.setEnd(s.getRangeAt(0).endContainer,s.getRangeAt(0).endOffset);return r.toString().length;}
|
||||
function gt(e){return (e&&e.innerText!==undefined)?e.innerText:(e?e.textContent:'');}
|
||||
function splitCaret(e){
|
||||
const s=window.getSelection(); if(!s.rangeCount||!s.rangeCount)return null; const sel=s.getRangeAt(0);
|
||||
const MK='\uF000FD'; const mark=document.createElement('span'); mark.textContent=MK;
|
||||
sel.insertNode(mark);
|
||||
const full=gt(e)||'';
|
||||
const parts=full.split(MK);
|
||||
mark.remove(); e.normalize();
|
||||
return {before:parts[0]||'',after:(parts.length>1?parts[1]:'')||'',content:full.split(MK).join('')};
|
||||
}
|
||||
function ce(e){const r=document.createRange();r.selectNodeContents(e);r.collapse(false);window.getSelection().removeAllRanges();window.getSelection().addRange(r);}
|
||||
function cs(e){const r=document.createRange();r.selectNodeContents(e);r.collapse(true);window.getSelection().removeAllRanges();window.getSelection().addRange(r);}
|
||||
function esc(s){return s.replace(/&/g,'&').replace(/</g,'<').replace(/>/g,'>');}
|
||||
@@ -339,7 +349,7 @@
|
||||
_err(msg){ this._html='<p style="color:#e5484d">⚠ '+esc(msg)+'</p>'; this._stage='result'; this.paint(); },
|
||||
insert(){ const E=window.E; if(!E||typeof E.applyAIBlocks!=='function')return; E.sync();
|
||||
const result=this._resultText(); if(!result)return; E.applyAIBlocks(result); E.dirty=true; E.autoSave(); this.close(); },
|
||||
_resultText(){ const el=this.ROOT&&this.ROOT.querySelector('.aici-result'); return el?el.textContent:''; },
|
||||
_resultText(){ const el=this.ROOT&&this.ROOT.querySelector('.aici-result'); if(!el)return ''; const r=document.createRange();r.selectNodeContents(el);return r.toString(); },
|
||||
toast(m){ if(window.showToast)window.showToast(m,'info'); }
|
||||
};
|
||||
window.AIC=AIC;
|
||||
@@ -741,9 +751,9 @@
|
||||
sync(){const ct=document.getElementById('_blocksCt');if(!ct)return;for(const b of this.blocks){if(b.type==='table'){const wrap=ct.querySelector(`[data-bid="${b.id}"].ftable-editor`);if(wrap){const rows=[];wrap.querySelectorAll('tr.ftable-row').forEach(function(tr){const cells=tr.querySelectorAll('th.ftable-cell,td.ftable-cell');if(!cells.length)return;const rowarr=[];cells.forEach(function(cell){rowarr.push(cell.textContent||'');});rows.push(rowarr);});if(rows.length)b.rows=rows;}continue;}
|
||||
if(b.type==='divider'||b.type==='image'||b.type==='embed'||b.type==='table_of_contents')continue;
|
||||
if(b.type==='math'){const te=ct.querySelector(`[data-math-bid="${b.id}"]`);if(te)b.content=te.value||'';continue;}
|
||||
const el=ct.querySelector(`[data-bid="${b.id}"]`);if(el&&!el.classList.contains('toggle-title'))b.content=el.textContent||'';else if(el)b.content=el.textContent||'';
|
||||
if(b.type==='toggle'&&b.children)b.children.forEach(function(ch){const che=ct.querySelector(`[data-bid="${ch.id}"]`);if(che)ch.content=che.textContent||'';});
|
||||
if(b.type==='columns'&&b.children)b.children.forEach(function(ch){const che=ct.querySelector(`[data-bid="${ch.id}"]`);if(che)ch.content=che.textContent||'';});
|
||||
const el=ct.querySelector(`[data-bid="${b.id}"]`);if(el&&!el.classList.contains('toggle-title'))b.content=gt(el)||'';else if(el)b.content=gt(el)||'';
|
||||
if(b.type==='toggle'&&b.children)b.children.forEach(function(ch){const che=ct.querySelector(`[data-bid="${ch.id}"]`);if(che)ch.content=gt(che)||'';});
|
||||
if(b.type==='columns'&&b.children)b.children.forEach(function(ch){const che=ct.querySelector(`[data-bid="${ch.id}"]`);if(che)ch.content=gt(che)||'';});
|
||||
}},
|
||||
render(){const ct=document.getElementById('_blocksCt');if(!ct)return;let html='';for(let i=0;i<this.blocks.length;i++)html+=renderBlock(this.blocks[i],i);ct.innerHTML=html;
|
||||
// Render math blocks with KaTeX
|
||||
@@ -1120,7 +1130,8 @@ applyAIBlocks(text){
|
||||
if(e.key==='Enter'){
|
||||
if(e.shiftKey){this.dirty=true;this.autoSave();return;}
|
||||
e.preventDefault();
|
||||
const text=el.textContent||'',pos=cp(el),before=text.substring(0,pos),after=text.substring(pos);
|
||||
const sp=splitCaret(el);
|
||||
const before=sp?sp.before:gt(el)||'',after=sp?sp.after:'';
|
||||
if(!before.trim()&&!after.trim()){
|
||||
const nt=(block.type==='bulleted_list'||block.type==='numbered_list'||block.type==='to_do')?block.type:'paragraph';
|
||||
this.sync();this.blocks.splice(idx+1,0,this.mkB(nt,''));this.render();
|
||||
@@ -1132,8 +1143,8 @@ applyAIBlocks(text){
|
||||
setTimeout(()=>{const ne=this.getEl(this.blocks[idx+1]?.id);if(ne){ne.focus();cs(ne);}},60);
|
||||
this.dirty=true;this.autoSave();return;
|
||||
}
|
||||
if(e.key==='ArrowUp'){if(cp(el)===0&&idx>0){e.preventDefault();const prev=this.getEl(this.blocks[idx-1]?.id);if(prev){prev.focus();ce(prev);}}return;}
|
||||
if(e.key==='ArrowDown'){if(cp(el)>=(el.textContent||'').length&&idx<this.blocks.length-1){e.preventDefault();const next=this.getEl(this.blocks[idx+1]?.id);if(next){next.focus();cs(next);}}return;}
|
||||
if(e.key==='ArrowUp'){const _sp=splitCaret(el);if(_sp&&!_sp.before.trim()&&idx>0){e.preventDefault();const prev=this.getEl(this.blocks[idx-1]?.id);if(prev){prev.focus();ce(prev);}}return;}
|
||||
if(e.key==='ArrowDown'){const _sp=splitCaret(el);if(_sp&&!_sp.after.trim()&&idx<this.blocks.length-1){e.preventDefault();const next=this.getEl(this.blocks[idx+1]?.id);if(next){next.focus();cs(next);}}return;}
|
||||
if(e.key==='Backspace'){if(!(el.textContent||'').trim()){this.sync();if(block.type!=='paragraph'){e.preventDefault();block.type='paragraph';block.content='';this.render();setTimeout(()=>{const ne=this.getEl(block.id);if(ne)ne.focus();},60);}else if(this.blocks.length>1){e.preventDefault();this.removeBlock(idx);}}return;}
|
||||
if(e.key===' '){const b2=bid;setTimeout(()=>this.checkMd(b2),15);}
|
||||
if((e.ctrlKey||e.metaKey)&&!e.altKey){const m={b:'bold',i:'italic',u:'underline'};if(m[e.key]){e.preventDefault();document.execCommand(m[e.key]);this.dirty=true;this.autoSave();}}
|
||||
|
||||
Reference in New Issue
Block a user