perf: fix model reload thrash and cut time-to-first-token

Ollama reloaded the chat model mid-message because plan/summary/router
calls sent divergent runner options (no num_ctx/num_batch) and omitted
keep_alive — the main cause of perceived slowness.

- share one keep-alive httpx.AsyncClient for all Ollama calls
- unify runner options (runner_options) + keep_alive on every model
  call, embeddings included
- drop the blocking LLM routing fallback (pure lexical heuristic)
- run RAG recall + plan + code-model pick in parallel inside the SSE
  stream, after the start event
- RAG cosine scoring off the event loop; cache /api/tags 30s and
  nvidia-smi 5s; frontend polls 2s->5s, warm poll backoff, dedup
  config fetch

feat: working session menu in TopBar (switch/create/rename/delete)
feat: workspace file deletion (DELETE /api/files + UI trash buttons)
docs: recommended Ollama env vars (KEEP_ALIVE, MAX_LOADED_MODELS...)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
MichaelandClaude Opus 4.8 committed 2026-07-18 13:58:18 +02:00
1 parent 552548e4b4
commit cb2872c78a
23 files changed
+672 -224

No files matched your search

+16 -2
View File
@@ -1,6 +1,6 @@
import { useEffect } from "react";
import { downloadFile, type FileNode } from "../api/client";
import { DownloadIcon } from "../components/Icon";
import { DownloadIcon, TrashIcon } from "../components/Icon";
import { useStore } from "../store/useStore";
export function HistoryView({ onOpen }: { onOpen: () => void }) {
@@ -61,7 +61,14 @@ export function FilesView() {
}
function WorkspaceTree({ nodes, depth }: { nodes: FileNode[]; depth: number }) {
const { openPreview, previewPath } = useStore();
const { openPreview, previewPath, removeFile } = useStore();
const confirmDelete = (node: FileNode) => {
const msg =
node.type === "dir"
? `Supprimer le dossier ${node.path} et tout son contenu ?`
: `Supprimer ${node.path} ?`;
if (window.confirm(msg)) void removeFile(node.path);
};
return (
<>
{nodes.map((node) => (
@@ -93,6 +100,13 @@ function WorkspaceTree({ nodes, depth }: { nodes: FileNode[]; depth: number }) {
<DownloadIcon size={12} /> Télécharger
</button>
)}
<button
onClick={() => confirmDelete(node)}
className="flex items-center gap-1 border-2 border-line bg-base px-2 py-1 text-[11px] text-warn"
title={`Supprimer ${node.name}`}
>
<TrashIcon size={12} /> Supprimer
</button>
</div>
{node.children && <WorkspaceTree nodes={node.children} depth={depth + 1} />}
</div>
+20 -9
View File
@@ -1,7 +1,8 @@
import { useEffect } from "react";
import { useStore } from "../store/useStore";
import { DownloadIcon, PlusIcon } from "../components/Icon";
import { DownloadIcon, PlusIcon, TrashIcon } from "../components/Icon";
import { downloadFile, type FileNode } from "../api/client";
import { relTime } from "../lib/time";
/** Panneau gauche : historique des sessions + arborescence de fichiers. */
export function LeftPanel() {
@@ -116,7 +117,14 @@ export function LeftPanel() {
}
function FileTree({ nodes, depth }: { nodes: FileNode[]; depth: number }) {
const { openPreview, previewPath } = useStore();
const { openPreview, previewPath, removeFile } = useStore();
const confirmDelete = (n: FileNode) => {
const msg =
n.type === "dir"
? `Supprimer le dossier ${n.path} et tout son contenu ?`
: `Supprimer ${n.path} ?`;
if (window.confirm(msg)) void removeFile(n.path);
};
return (
<>
{nodes.map((n) => {
@@ -156,6 +164,16 @@ function FileTree({ nodes, depth }: { nodes: FileNode[]; depth: number }) {
<DownloadIcon size={13} />
</button>
)}
<button
onClick={(event) => {
event.stopPropagation();
confirmDelete(n);
}}
className="hidden flex-none text-muted-2 hover:text-warn group-hover:block"
title={`Supprimer ${n.name}`}
>
<TrashIcon size={13} />
</button>
</div>
{n.children && <FileTree nodes={n.children} depth={depth + 1} />}
</div>
@@ -165,10 +183,3 @@ function FileTree({ nodes, depth }: { nodes: FileNode[]; depth: number }) {
);
}
function relTime(ts: number): string {
const diff = Date.now() / 1000 - ts;
if (diff < 60) return "à l'instant";
if (diff < 3600) return `il y a ${Math.floor(diff / 60)} min`;
if (diff < 86400) return `il y a ${Math.floor(diff / 3600)} h`;
return `il y a ${Math.floor(diff / 86400)} j`;
}
+25 -10
View File
@@ -8,13 +8,14 @@ import {
type GitCommit,
type ToolCall,
} from "../api/client";
import { DownloadIcon } from "../components/Icon";
import { DownloadIcon, TrashIcon } from "../components/Icon";
type TabId = "preview" | "code" | "logs" | "git";
/** Panneau droit : onglets Aperçu / Code / Logs. */
export function PreviewPanel() {
const { previewPath, previewContent, messages, streamTools } = useStore();
const { previewPath, previewContent, messages, streamTools, removeFile } =
useStore();
const [tab, setTab] = useState<TabId>("preview");
const [width, setWidth] = useState(() => {
const saved = Number(window.localStorage.getItem("loki.preview.width"));
@@ -95,14 +96,28 @@ export function PreviewPanel() {
</span>
</div>
{previewPath && (
<button
onClick={() => downloadFile(previewPath)}
className="flex h-8 items-center gap-1.5 border-[3px] border-line bg-card px-2.5 text-[12px] text-accent"
title={`Télécharger ${previewPath}`}
>
<DownloadIcon size={13} />
Télécharger
</button>
<>
<button
onClick={() => downloadFile(previewPath)}
className="flex h-8 items-center gap-1.5 border-[3px] border-line bg-card px-2.5 text-[12px] text-accent"
title={`Télécharger ${previewPath}`}
>
<DownloadIcon size={13} />
Télécharger
</button>
<button
onClick={() => {
if (window.confirm(`Supprimer ${previewPath} ?`)) {
void removeFile(previewPath);
}
}}
className="flex h-8 items-center gap-1.5 border-[3px] border-line bg-card px-2.5 text-[12px] text-warn"
title={`Supprimer ${previewPath}`}
>
<TrashIcon size={13} />
Supprimer
</button>
</>
)}
</div>