feat(dashboard): add light/dark mode toggle with warm parchment palette

Adds a theme system to the EXO dashboard with a "Mission Control, Dawn Shift" light mode — warm parchment backgrounds (oklch(0.97 0.015 80)) and deep amber/brass accents (oklch(0.50 0.14 65)) that feel premium rather than cold. Changes: - dashboard/src/lib/stores/theme.svelte.ts: new Svelte 5 rune store, persists choice to localStorage under 'exo-theme' - dashboard/src/app.html: FOUC prevention — html starts as class="dark", inline script reads localStorage and switches to class="light" before first paint - dashboard/src/routes/+layout.svelte: calls theme.init() on mount to sync rune state with the DOM class - dashboard/src/lib/components/HeaderNav.svelte: sun/moon toggle button in the right nav area - dashboard/src/app.css: full html.light palette + utility overrides (scrollbar, logo filter, graph links, scanlines, etc.) No new npm dependencies — avoids mode-watcher entirely. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
feat: only show thinking toggle for models that support it (#1497 )
2026-02-19 07:17:30 -05:00 · 2026-02-18 12:36:51 -08:00 · 2026-02-18 17:05:00 +00:00
37 changed files with 396 additions and 73 deletions
--- a/dashboard/src/app.css
+++ b/dashboard/src/app.css
@@ -16,9 +16,10 @@
 	/* Gotham-inspired accent colors */
 	--exo-grid: oklch(0.25 0 0);
 	--exo-scanline: oklch(0.15 0 0);
-	--exo-glow-yellow: 0 0 20px oklch(0.85 0.18 85 / 0.3);
-	--exo-glow-yellow-strong: 0 0 40px oklch(0.85 0.18 85 / 0.5);
-	
+	--exo-glow-yellow: oklch(0.85 0.18 85 / 0.3);
+	--exo-glow-yellow-strong: oklch(0.85 0.18 85 / 0.5);
+	--exo-bg-hover: oklch(0.18 0 0);
+
 	/* Theme Variables */
 	--radius: 0.375rem;
 	--background: var(--exo-black);
@@ -41,6 +42,237 @@
 	--ring: var(--exo-yellow);
 }

+/* ============================================================
+   LIGHT THEME — "Mission Control, Dawn Shift"
+   Warm parchment + deep amber. Applied when <html> has .light class.
+   ============================================================ */
+html.light {
+	/* EXO brand palette — warm amber shift */
+	--exo-black: oklch(0.97 0.015 80);
+	--exo-dark-gray: oklch(0.92 0.012 80);
+	--exo-medium-gray: oklch(0.83 0.009 78);
+	--exo-light-gray: oklch(0.50 0.018 75);
+	--exo-yellow: oklch(0.50 0.14 65);
+	--exo-yellow-darker: oklch(0.40 0.13 65);
+	--exo-yellow-glow: oklch(0.60 0.14 65);
+
+	--exo-grid: oklch(0.88 0.009 80);
+	--exo-scanline: oklch(0.93 0.010 80);
+	--exo-glow-yellow: oklch(0.50 0.14 65 / 0.12);
+	--exo-glow-yellow-strong: oklch(0.50 0.14 65 / 0.22);
+	--exo-bg-hover: oklch(0.89 0.010 80);
+
+	/* Semantic tokens */
+	--background: oklch(0.97 0.015 80);
+	--foreground: oklch(0.13 0.015 75);
+	--card: oklch(0.92 0.012 80);
+	--card-foreground: oklch(0.13 0.015 75);
+	--popover: oklch(0.95 0.012 80);
+	--popover-foreground: oklch(0.13 0.015 75);
+	--primary: oklch(0.50 0.14 65);
+	--primary-foreground: oklch(0.97 0.015 80);
+	--secondary: oklch(0.88 0.008 80);
+	--secondary-foreground: oklch(0.15 0.012 75);
+	--muted: oklch(0.90 0.009 80);
+	--muted-foreground: oklch(0.50 0.018 75);
+	--accent: oklch(0.88 0.008 80);
+	--accent-foreground: oklch(0.15 0.012 75);
+	--destructive: oklch(0.52 0.22 25);
+	--border: oklch(0.84 0.007 78);
+	--input: oklch(0.87 0.008 80);
+	--ring: oklch(0.50 0.14 65);
+}
+
+/* ============================================================
+   LIGHT MODE UTILITY OVERRIDES
+   ============================================================ */
+html.light {
+	& .text-white,
+	& .text-white\/90,
+	& .text-white\/80,
+	& .text-white\/70 {
+		color: var(--foreground) !important;
+	}
+	& .text-white\/60,
+	& .text-white\/50 {
+		color: color-mix(in oklch, var(--foreground) 60%, transparent) !important;
+	}
+	& .text-white\/40,
+	& .text-white\/30 {
+		color: color-mix(in oklch, var(--foreground) 38%, transparent) !important;
+	}
+
+	& .bg-black\/80,
+	& .bg-black\/60,
+	& .bg-black\/50,
+	& .bg-black\/40 {
+		background-color: oklch(0.90 0.010 80 / 0.7) !important;
+	}
+	& [class*="bg-exo-black/"] {
+		background-color: oklch(0.90 0.010 80 / 0.6) !important;
+	}
+	& [class*="shadow-black"] {
+		--tw-shadow-color: oklch(0.30 0.010 75 / 0.10) !important;
+	}
+
+	& ::-webkit-scrollbar-track {
+		background: oklch(0.93 0.010 80) !important;
+	}
+	& ::-webkit-scrollbar-thumb {
+		background: oklch(0.76 0.010 78) !important;
+	}
+	& ::-webkit-scrollbar-thumb:hover {
+		background: oklch(0.50 0.14 65 / 0.6) !important;
+	}
+
+	& .command-panel {
+		background: linear-gradient(
+			180deg,
+			oklch(0.94 0.012 80 / 0.96) 0%,
+			oklch(0.91 0.010 80 / 0.98) 100%
+		) !important;
+		border-color: oklch(0.82 0.008 78) !important;
+		box-shadow:
+			inset 0 1px 0 oklch(1 0 0 / 0.6),
+			0 4px 20px oklch(0.30 0.010 75 / 0.08) !important;
+	}
+
+	& .glow-text {
+		text-shadow:
+			0 0 12px oklch(0.50 0.14 65 / 0.20),
+			0 1px 3px oklch(0.30 0.010 75 / 0.12) !important;
+	}
+
+	& .grid-bg {
+		background-image:
+			linear-gradient(oklch(0.75 0.008 78 / 0.25) 1px, transparent 1px),
+			linear-gradient(90deg, oklch(0.75 0.008 78 / 0.25) 1px, transparent 1px) !important;
+	}
+
+	& .scanlines::before {
+		background: repeating-linear-gradient(
+			0deg,
+			transparent,
+			transparent 2px,
+			oklch(0.50 0.010 78 / 0.018) 2px,
+			oklch(0.50 0.010 78 / 0.018) 4px
+		) !important;
+	}
+
+	& .crt-screen {
+		background: radial-gradient(
+			ellipse at center,
+			oklch(0.95 0.012 80) 0%,
+			oklch(0.92 0.010 80) 50%,
+			oklch(0.89 0.009 80) 100%
+		) !important;
+		box-shadow:
+			inset 0 0 60px oklch(0.30 0.010 75 / 0.04),
+			0 0 30px oklch(0.50 0.14 65 / 0.04) !important;
+	}
+
+	& .graph-link {
+		stroke: oklch(0.50 0.018 75 / 0.45) !important;
+		filter: none !important;
+	}
+	& .graph-link-active {
+		stroke: oklch(0.50 0.14 65 / 0.75) !important;
+		filter: none !important;
+	}
+
+	& .shooting-stars {
+		display: none !important;
+	}
+
+	& img[alt="EXO"] {
+		filter: brightness(0) drop-shadow(0 0 6px oklch(0.30 0.010 75 / 0.10)) !important;
+	}
+
+	& .text-red-400 { color: oklch(0.52 0.22 25) !important; }
+	& .text-green-400 { color: oklch(0.48 0.17 155) !important; }
+	& .text-blue-200,
+	& .text-blue-300,
+	& .text-blue-400 { color: oklch(0.48 0.17 250) !important; }
+
+	& .bg-red-500\/10 { background-color: oklch(0.52 0.22 25 / 0.07) !important; }
+	& .bg-red-500\/20 { background-color: oklch(0.52 0.22 25 / 0.11) !important; }
+	& .bg-red-500\/30 { background-color: oklch(0.52 0.22 25 / 0.14) !important; }
+
+	& textarea,
+	& input[type="text"] { color: var(--foreground) !important; }
+	& textarea::placeholder,
+	& input::placeholder { color: oklch(0.50 0.012 78 / 0.55) !important; }
+
+	& .code-block-wrapper,
+	& .math-display-wrapper {
+		background: oklch(0.95 0.010 80) !important;
+		border-color: oklch(0.83 0.007 78) !important;
+	}
+	& .code-block-header,
+	& .math-display-header {
+		background: oklch(0.91 0.009 80) !important;
+		border-color: oklch(0.85 0.007 78) !important;
+	}
+	& .inline-code {
+		background: oklch(0.89 0.009 80) !important;
+		color: oklch(0.20 0.012 75) !important;
+	}
+
+	& blockquote { background: oklch(0.93 0.010 80) !important; }
+	& th {
+		background: oklch(0.90 0.009 80) !important;
+		border-color: oklch(0.80 0.007 78) !important;
+	}
+	& td { border-color: oklch(0.84 0.007 78) !important; }
+	& hr { border-color: oklch(0.84 0.007 78) !important; }
+
+	& .hljs { color: oklch(0.22 0.012 75) !important; }
+	& .hljs-keyword, & .hljs-selector-tag, & .hljs-literal, & .hljs-section, & .hljs-link {
+		color: oklch(0.45 0.18 300) !important;
+	}
+	& .hljs-string, & .hljs-title, & .hljs-name, & .hljs-type,
+	& .hljs-attribute, & .hljs-symbol, & .hljs-bullet, & .hljs-addition,
+	& .hljs-variable, & .hljs-template-tag, & .hljs-template-variable {
+		color: oklch(0.45 0.14 65) !important;
+	}
+	& .hljs-comment, & .hljs-quote, & .hljs-deletion, & .hljs-meta {
+		color: oklch(0.55 0.010 78) !important;
+	}
+	& .hljs-number, & .hljs-regexp, & .hljs-built_in {
+		color: oklch(0.45 0.15 160) !important;
+	}
+	& .hljs-function, & .hljs-class .hljs-title {
+		color: oklch(0.42 0.17 240) !important;
+	}
+
+	& .katex, & .katex .mord, & .katex .minner, & .katex .mop,
+	& .katex .mbin, & .katex .mrel, & .katex .mpunct {
+		color: oklch(0.15 0.012 75) !important;
+	}
+	& .katex .frac-line, & .katex .overline-line, & .katex .underline-line,
+	& .katex .hline, & .katex .rule {
+		border-color: oklch(0.25 0.012 75) !important;
+		background: oklch(0.25 0.012 75) !important;
+	}
+	& .katex svg { fill: oklch(0.25 0.012 75) !important; stroke: oklch(0.25 0.012 75) !important; }
+	& .katex svg path { stroke: oklch(0.25 0.012 75) !important; }
+	& .katex .mopen, & .katex .mclose,
+	& .katex .delimsizing, & [class^="katex .delim-size"] {
+		color: oklch(0.35 0.012 75) !important;
+	}
+
+	& .latex-proof { background: oklch(0.96 0.010 80) !important; border-left-color: oklch(0.72 0.010 78) !important; }
+	& .latex-proof-header { color: oklch(0.22 0.012 75) !important; }
+	& .latex-proof-content { color: oklch(0.15 0.012 75) !important; }
+	& .latex-proof-content::after { color: oklch(0.48 0.012 75) !important; }
+	& .latex-theorem { background: oklch(0.94 0.010 80) !important; border-color: oklch(0.80 0.008 78) !important; }
+	& .latex-diagram-placeholder {
+		background: oklch(0.96 0.010 80) !important;
+		border-color: oklch(0.80 0.008 78) !important;
+		color: oklch(0.38 0.012 75) !important;
+	}
+}
+
@theme inline {
 	--radius-sm: calc(var(--radius) - 2px);
 	--radius-md: var(--radius);
--- a/dashboard/src/app.html
+++ b/dashboard/src/app.html
@@ -1,7 +1,15 @@
 <!doctype html>
-<html lang="en">
+<html lang="en" class="dark">
 	<head>
 		<meta charset="utf-8" />
+		<script>
+			try {
+				if (localStorage.getItem('exo-theme') === 'light') {
+					document.documentElement.classList.remove('dark');
+					document.documentElement.classList.add('light');
+				}
+			} catch (_) {}
+		</script>
 		<link rel="icon" href="%sveltekit.assets%/favicon.ico" />
 		<meta name="viewport" content="width=device-width, initial-scale=1" />
 		<title>EXO</title>
--- a/dashboard/src/lib/components/ChatForm.svelte
+++ b/dashboard/src/lib/components/ChatForm.svelte
@@ -103,7 +103,7 @@
  const modelSupportsThinking = $derived(() => {
    if (!currentModel) return false;
    const caps = modelCapabilities[currentModel] || [];
-    return caps.includes("thinking") && caps.includes("text");
+    return caps.includes("thinking_toggle") && caps.includes("text");
  });

  const isEditOnlyWithoutImage = $derived(
--- a/dashboard/src/lib/components/HeaderNav.svelte
+++ b/dashboard/src/lib/components/HeaderNav.svelte
@@ -1,5 +1,6 @@
 <script lang="ts">
  import { browser } from "$app/environment";
+  import { theme } from "$lib/stores/theme.svelte";

  export let showHome = true;
  export let onHome: (() => void) | null = null;
@@ -79,10 +80,48 @@
    />
  </button>

-  <!-- Right: Home + Downloads -->
+  <!-- Right: Theme toggle + Home + Downloads -->
  <div
    class="absolute right-6 top-1/2 -translate-y-1/2 flex items-center gap-4"
  >
+    <button
+      onclick={() => theme.toggle()}
+      class="p-2 rounded border border-exo-medium-gray/40 hover:border-exo-yellow/50 transition-colors cursor-pointer"
+      title={theme.isLight ? "Switch to dark mode" : "Switch to light mode"}
+      aria-label={theme.isLight
+        ? "Switch to dark mode"
+        : "Switch to light mode"}
+    >
+      {#if theme.isLight}
+        <svg
+          class="w-4 h-4 text-exo-light-gray"
+          fill="none"
+          viewBox="0 0 24 24"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <path
+            stroke-linecap="round"
+            stroke-linejoin="round"
+            d="M21 12.79A9 9 0 1111.21 3a7 7 0 009.79 9.79z"
+          />
+        </svg>
+      {:else}
+        <svg
+          class="w-4 h-4 text-exo-light-gray"
+          fill="none"
+          viewBox="0 0 24 24"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <circle cx="12" cy="12" r="5" />
+          <path
+            stroke-linecap="round"
+            d="M12 1v2m0 18v2M4.22 4.22l1.42 1.42m12.72 12.72l1.42 1.42M1 12h2m18 0h2M4.22 19.78l1.42-1.42M18.36 5.64l1.42-1.42"
+          />
+        </svg>
+      {/if}
+    </button>
    {#if showHome}
      <button
        onclick={handleHome}
--- a/dashboard/src/lib/stores/theme.svelte.ts
+++ b/dashboard/src/lib/stores/theme.svelte.ts
@@ -0,0 +1,28 @@
+import { browser } from "$app/environment";
+
+let _isLight = $state(false);
+
+export const theme = {
+  get isLight() {
+    return _isLight;
+  },
+
+  init() {
+    if (!browser) return;
+    _isLight = document.documentElement.classList.contains("light");
+  },
+
+  toggle() {
+    if (!browser) return;
+    _isLight = !_isLight;
+    if (_isLight) {
+      document.documentElement.classList.remove("dark");
+      document.documentElement.classList.add("light");
+      localStorage.setItem("exo-theme", "light");
+    } else {
+      document.documentElement.classList.remove("light");
+      document.documentElement.classList.add("dark");
+      localStorage.setItem("exo-theme", "dark");
+    }
+  },
+};
--- a/dashboard/src/routes/+layout.svelte
+++ b/dashboard/src/routes/+layout.svelte
@@ -1,7 +1,13 @@
 <script lang="ts">
  import "../app.css";
+  import { onMount } from "svelte";
+  import { theme } from "$lib/stores/theme.svelte";

  let { children } = $props();
+
+  onMount(() => {
+    theme.init();
+  });
 </script>

 <svelte:head>
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -6,6 +6,8 @@ readme = "README.md"
 requires-python = ">=3.13"
 dependencies = [
    "aiofiles>=24.1.0",
+    "aiohttp>=3.12.14",
+    "types-aiofiles>=24.1.0.20250708",
    "pydantic>=2.11.7",
    "fastapi>=0.116.1",
    "filelock>=3.18.0",
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "4bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 405874409472
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "8bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 765577920512
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 122406567936
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "bf16"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 229780750336
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 198556925568
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 286737579648
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 396963397248
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 19327352832
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "5bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 22548578304
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 26843545600
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 34359738368
--- a/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 706522120192
--- a/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2.5"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 662498705408
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "3bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 100086644736
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "8bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 242986745856
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 342884352
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 698351616
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 141733920768
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 268435456000
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 17612931072
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 33279705088
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 47080074240
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 88814387200
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "4bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 114572190076
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "6bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 159039627774
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "8bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]

 [storage_size]
 in_bytes = 209082699847
--- a/src/exo/download/download_utils.py
+++ b/src/exo/download/download_utils.py
@@ -8,13 +8,13 @@ import traceback
 from collections.abc import Awaitable
 from datetime import timedelta
 from pathlib import Path
-from typing import Callable, Literal, cast
+from typing import Callable, Literal
 from urllib.parse import urljoin

 import aiofiles
 import aiofiles.os as aios
+import aiohttp
 import certifi
-import httpx
 from huggingface_hub import (
    snapshot_download,  # pyright: ignore[reportUnknownVariableType]
 )
@@ -330,17 +330,17 @@ async def _fetch_file_list(
    headers = await get_download_headers()
    async with (
        create_http_session(timeout_profile="short") as session,
+        session.get(url, headers=headers) as response,
    ):
-        response = await session.get(url, headers=headers)
-        if response.status_code in [401, 403]:
-            msg = await _build_auth_error_message(response.status_code, model_id)
+        if response.status in [401, 403]:
+            msg = await _build_auth_error_message(response.status, model_id)
            raise HuggingFaceAuthenticationError(msg)
-        elif response.status_code == 429:
+        elif response.status == 429:
            raise HuggingFaceRateLimitError(
                f"Couldn't download {model_id} because of HuggingFace rate limit."
            )
-        elif response.status_code == 200:
-            data_json = response.text
+        elif response.status == 200:
+            data_json = await response.text()
            data = TypeAdapter(list[FileListEntry]).validate_json(data_json)
            files: list[FileListEntry] = []
            for item in data:
@@ -353,7 +353,7 @@ async def _fetch_file_list(
                    files.extend(subfiles)
            return files
        else:
-            raise Exception(f"Failed to fetch file list: {response.status_code}")
+            raise Exception(f"Failed to fetch file list: {response.status}")


 async def get_download_headers() -> dict[str, str]:
@@ -361,29 +361,34 @@ async def get_download_headers() -> dict[str, str]:


 def create_http_session(
+    auto_decompress: bool = False,
    timeout_profile: Literal["short", "long"] = "long",
-) -> httpx.AsyncClient:
+) -> aiohttp.ClientSession:
    if timeout_profile == "short":
        total_timeout = 30
        connect_timeout = 10
-        read_timeout = 30
+        sock_read_timeout = 30
+        sock_connect_timeout = 10
    else:
        total_timeout = 1800
        connect_timeout = 60
-        read_timeout = 60
+        sock_read_timeout = 60
+        sock_connect_timeout = 60

    ssl_context = ssl.create_default_context(
        cafile=os.getenv("SSL_CERT_FILE") or certifi.where()
    )
+    connector = aiohttp.TCPConnector(ssl=ssl_context)

-    # default here is to load env vars
-    return httpx.AsyncClient(
-        verify=ssl_context,
-        timeout=httpx.Timeout(
+    return aiohttp.ClientSession(
+        auto_decompress=auto_decompress,
+        connector=connector,
+        proxy=os.getenv("HTTPS_PROXY") or os.getenv("HTTP_PROXY") or None,
+        timeout=aiohttp.ClientTimeout(
+            total=total_timeout,
            connect=connect_timeout,
-            read=read_timeout,
-            write=total_timeout,
-            pool=total_timeout,
+            sock_read=sock_read_timeout,
+            sock_connect=sock_connect_timeout,
        ),
    )

@@ -410,28 +415,26 @@ async def file_meta(
    headers = await get_download_headers()
    async with (
        create_http_session(timeout_profile="short") as session,
-        session.stream("HEAD", url, headers=headers) as r,
+        session.head(url, headers=headers) as r,
    ):
-        if r.status_code == 307:
+        if r.status == 307:
            # On redirect, only trust Hugging Face's x-linked-* headers.
-            x_linked_size = cast(str | None, r.headers.get("x-linked-size"))
-            x_linked_etag = cast(str | None, r.headers.get("x-linked-etag"))
+            x_linked_size = r.headers.get("x-linked-size")
+            x_linked_etag = r.headers.get("x-linked-etag")
            if x_linked_size and x_linked_etag:
                content_length = int(x_linked_size)
                etag = trim_etag(x_linked_etag)
                return content_length, etag
            # Otherwise, follow the redirect to get authoritative size/hash
-            redirected_location = cast(str | None, r.headers.get("location"))
+            redirected_location = r.headers.get("location")
            return await file_meta(model_id, revision, path, redirected_location)
-        if r.status_code in [401, 403]:
-            msg = await _build_auth_error_message(r.status_code, model_id)
+        if r.status in [401, 403]:
+            msg = await _build_auth_error_message(r.status, model_id)
            raise HuggingFaceAuthenticationError(msg)
-        content_length = cast(
-            str | None,
-            r.headers.get("x-linked-size") or r.headers.get("content-length"),
+        content_length = int(
+            r.headers.get("x-linked-size") or r.headers.get("content-length") or 0
        )
-        content_length = 0 if content_length is None else int(content_length)
-        etag = cast(str | None, r.headers.get("x-linked-etag") or r.headers.get("etag"))
+        etag = r.headers.get("x-linked-etag") or r.headers.get("etag")
        assert content_length > 0, f"No content length for {url}"
        assert etag is not None, f"No remote hash for {url}"
        etag = trim_etag(etag)
@@ -534,20 +537,20 @@ async def _download_file(
        n_read = resume_byte_pos or 0
        async with (
            create_http_session(timeout_profile="long") as session,
-            session.stream("GET", url, headers=headers, follow_redirects=True) as r,
+            session.get(url, headers=headers) as r,
        ):
-            if r.status_code == 404:
+            if r.status == 404:
                raise FileNotFoundError(f"File not found: {url}")
-            if r.status_code in [401, 403]:
-                msg = await _build_auth_error_message(r.status_code, model_id)
+            if r.status in [401, 403]:
+                msg = await _build_auth_error_message(r.status, model_id)
                raise HuggingFaceAuthenticationError(msg)
-            assert r.status_code in [200, 206], (
-                f"Failed to download {path} from {url}: {r.status_code}"
+            assert r.status in [200, 206], (
+                f"Failed to download {path} from {url}: {r.status}"
            )
            async with aiofiles.open(
                partial_path, "ab" if resume_byte_pos else "wb"
            ) as f:
-                async for chunk in r.aiter_bytes(8 * 1024 * 1024):
+                while chunk := await r.content.read(8 * 1024 * 1024):
                    n_read = n_read + (await f.write(chunk))
                    on_progress(n_read, length, False)

--- a/src/exo/download/impl_shard_downloader.py
+++ b/src/exo/download/impl_shard_downloader.py
@@ -189,7 +189,6 @@ class ResumableShardDownloader(ShardDownloader):
            try:
                yield await task
            except Exception as e:
-                task.cancel()
                logger.warning(f"Error downloading shard: {type(e).__name__}")

    async def get_shard_download_status_for_shard(
--- a/src/exo/utils/keyed_backoff.py
+++ b/src/exo/utils/keyed_backoff.py
@@ -1,8 +1,10 @@
 import time
-from collections.abc import Hashable
+from typing import Generic, TypeVar
+
+K = TypeVar("K")


-class KeyedBackoff[K: Hashable]:
+class KeyedBackoff(Generic[K]):
    """Tracks exponential backoff state per key."""

    def __init__(self, base: float = 0.5, cap: float = 10.0):
--- a/uv.lock
+++ b/uv.lock
@@ -367,6 +367,7 @@ version = "0.3.0"
 source = { editable = "." }
 dependencies = [
    { name = "aiofiles", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "aiohttp", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "anyio", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "exo-pyo3-bindings", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "fastapi", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -388,6 +389,7 @@ dependencies = [
    { name = "rustworkx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "tiktoken", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "tomlkit", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "types-aiofiles", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "zstandard", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]

@@ -404,6 +406,7 @@ dev = [
 [package.metadata]
 requires-dist = [
    { name = "aiofiles", specifier = ">=24.1.0" },
+    { name = "aiohttp", specifier = ">=3.12.14" },
    { name = "anyio", specifier = "==4.11.0" },
    { name = "exo-pyo3-bindings", editable = "rust/exo_pyo3_bindings" },
    { name = "fastapi", specifier = ">=0.116.1" },
@@ -425,6 +428,7 @@ requires-dist = [
    { name = "rustworkx", specifier = ">=0.17.1" },
    { name = "tiktoken", specifier = ">=0.12.0" },
    { name = "tomlkit", specifier = ">=0.14.0" },
+    { name = "types-aiofiles", specifier = ">=24.1.0.20250708" },
    { name = "zstandard", specifier = ">=0.23.0" },
 ]