proxy: support timings for /infill from llama-server

fixes: #463

.coderabbit.yaml

@@ -4,7 +4,7 @@ early_access: false
 reviews:
   profile: "chill"
   request_changes_workflow: false
-  high_level_summary: false
+  high_level_summary: true
   poem: false
   review_status: true
   collapse_walkthrough: false

.github/workflows/containers.yml

@@ -17,13 +17,6 @@ on:
       - 'docker/build-container.sh'
       - 'docker/*.Containerfile'
 
-# grant permissions on GITHUB_TOKEN to publish packages
-# ref: https://docs.github.com/en/packages/managing-github-packages-using-github-actions-workflows/publishing-and-installing-a-package-with-github-actions#publishing-a-package-using-an-action
-permissions:
-  contents: read
-  packages: write
-  id-token: write
-
 jobs:
   build-and-push:
     runs-on: ubuntu-latest

AGENTS.md

@@ -1,50 +0,0 @@
-## Project Description:
-
-llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
-
-## Tech stack
-
-- golang
-- typescript, vite and svelt5 for UI (located in ui/)
-
-## Workflow Tasks
-
-- when summarizing changes only include details that require further action
-- just say "Done." when there is no further action
-- use the github CLI `gh` to create pull requests and work with github
-- Rules for creating pull requests:
-  - keep them short and focused on changes.
-  - never include a test plan
-  - write the summary using the same style rules as commit message
-
-## Testing
-
-- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
-- Use `go test -v -run <name pattern for new tests>` to run any new tests you've written.
-- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
-- Use `make test-all` before completing work. This includes long running concurrency tests.
-
-### Commit message example format:
-
-```
-proxy: add new feature
-
-Add new feature that implements functionality X and Y.
-
-- key change 1
-- key change 2
-- key change 3
-
-fixes #123
-```
-
-## Code Reviews
-
-- use three levels High, Medium, Low severity
-- label each discovered issue with a label like H1, M2, L3 respectively
-- High severity are must fix issues (security, race conditions, critical bugs)
-- Medium severity are recommended improvements (coding style, missing functionality, inconsistencies)
-- Low severity are nice to have changes and nits
-- Include a suggestion with each discovered item
-- Limit your code review to three items with the highest priority first
-- Double check your discovered items and recommended remediations

CLAUDE.md

@@ -1 +1,49 @@
-@AGENTS.md
+## Project Description:
+
+llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
+
+## Tech stack
+
+- golang
+- typescript, vite and react for UI (located in ui/)
+
+## Workflow Tasks
+
+- when summarizing changes only include details that require further action
+- just say "Done." when there is no further action
+- use `gh` to create PRs and load issues
+- do include Co-Authored-By or created by when committing changes or creating PRs
+- keep PR descriptions short and focused on changes.
+  - never include a test plan
+
+## Testing
+
+- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
+- Use `go test -v -run <name pattern for new tests>` to run any new tests you've written.
+- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
+- Use `make test-all` before completing work. This includes long running concurrency tests.
+
+### Commit message example format:
+
+```
+proxy: add new feature
+
+Add new feature that implements functionality X and Y.
+
+- key change 1
+- key change 2
+- key change 3
+
+fixes #123
+```
+
+## Code Reviews
+
+- use three levels High, Medium, Low severity
+- label each discovered issue with a label like H1, M2, L3 respectively
+- High severity are must fix issues (security, race conditions, critical bugs)
+- Medium severity are recommended improvements (coding style, missing functionality, inconsistencies)
+- Low severity are nice to have changes and nits
+- Include a suggestion with each discovered item
+- Limit your code review to three items with the highest priority first
+- Double check your discovered items and recommended remediations

docker/build-container.sh

@@ -142,7 +142,7 @@ for CONTAINER_TYPE in non-root root; do
   fi
 
   log_info "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
-  docker build --provenance=false -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
+  docker build -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
     --build-arg LS_REPO=${LS_REPO} --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} \
     --build-arg BASE_IMAGE=${BASE_IMAGE} .
 
@@ -150,7 +150,7 @@ for CONTAINER_TYPE in non-root root; do
   case "$ARCH" in
     "musa" | "vulkan")
       log_info "Adding sd-server to $CONTAINER_TAG"
-      docker build --provenance=false -f llama-swap-sd.Containerfile \
+      docker build -f llama-swap-sd.Containerfile \
         --build-arg BASE=${CONTAINER_TAG} \
         --build-arg SD_IMAGE=${SD_IMAGE} --build-arg SD_TAG=${SD_TAG} \
         --build-arg UID=${USER_UID} --build-arg GID=${USER_GID} \

ui-svelte/src/App.svelte

@@ -6,28 +6,23 @@
   import Models from "./routes/Models.svelte";
   import Activity from "./routes/Activity.svelte";
   import Playground from "./routes/Playground.svelte";
-  import PlaygroundStub from "./routes/PlaygroundStub.svelte";
   import { enableAPIEvents } from "./stores/api";
   import { initScreenWidth, isDarkMode, appTitle, connectionState } from "./stores/theme";
-  import { currentRoute } from "./stores/route";
 
   const routes = {
-    "/": PlaygroundStub,
+    "/": Playground,
     "/models": Models,
     "/logs": LogViewer,
     "/activity": Activity,
-    "*": PlaygroundStub,
+    "*": Playground,
   };
 
-  function handleRouteLoaded(event: { detail: { route: string | RegExp } }) {
-    const route = event.detail.route;
-    currentRoute.set(typeof route === "string" ? route : "/");
-  }
-
+  // Sync theme to document attribute
   $effect(() => {
     document.documentElement.setAttribute("data-theme", $isDarkMode ? "dark" : "light");
   });
 
+  // Sync title to document
   $effect(() => {
     const icon = $connectionState === "connecting" ? "\u{1F7E1}" : $connectionState === "connected" ? "\u{1F7E2}" : "\u{1F534}";
     document.title = `${icon} ${$appTitle}`;
@@ -48,11 +43,6 @@
   <Header />
 
   <main class="flex-1 overflow-auto p-4">
-    <div class="h-full" class:hidden={$currentRoute !== "/"}>
-      <Playground />
-    </div>
-    <div class="h-full" class:hidden={$currentRoute === "/"}>
-      <Router {routes} on:routeLoaded={handleRouteLoaded} />
-    </div>
+    <Router {routes} />
   </main>
 </div>

ui-svelte/src/components/Header.svelte

@@ -1,8 +1,6 @@
 <script lang="ts">
-  import { link } from "svelte-spa-router";
+  import { link, location } from "svelte-spa-router";
   import { screenWidth, toggleTheme, isDarkMode, appTitle, isNarrow } from "../stores/theme";
-  import { currentRoute } from "../stores/route";
-  import { playgroundActivity } from "../stores/playgroundActivity";
   import ConnectionStatus from "./ConnectionStatus.svelte";
 
   function handleTitleChange(newTitle: string): void {
@@ -24,10 +22,9 @@
     handleTitleChange(target.textContent || "(set title)");
   }
 
-  function isActive(path: string, current: string): boolean {
-    return path === "/" ? current === "/" : current.startsWith(path);
+  function isActive(path: string, currentLocation: string): boolean {
+    return path === "/" ? currentLocation === "/" : currentLocation.startsWith(path);
   }
-
 </script>
 
 <header
@@ -50,7 +47,8 @@
     <a
       href="/"
       use:link
-      class="p-1 whitespace-nowrap {isActive('/', $currentRoute) ? 'font-semibold' : ''} {$playgroundActivity ? 'activity-link' : 'text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100'}"
+      class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1 whitespace-nowrap"
+      class:font-semibold={isActive("/", $location)}
     >
       Playground
     </a>
@@ -58,7 +56,7 @@
       href="/models"
       use:link
       class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1 whitespace-nowrap"
-      class:font-semibold={isActive("/models", $currentRoute)}
+      class:font-semibold={isActive("/models", $location)}
     >
       Models
     </a>
@@ -66,7 +64,7 @@
       href="/activity"
       use:link
       class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1 whitespace-nowrap"
-      class:font-semibold={isActive("/activity", $currentRoute)}
+      class:font-semibold={isActive("/activity", $location)}
     >
       Activity
     </a>
@@ -74,7 +72,7 @@
       href="/logs"
       use:link
       class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1 whitespace-nowrap"
-      class:font-semibold={isActive("/logs", $currentRoute)}
+      class:font-semibold={isActive("/logs", $location)}
     >
       Logs
     </a>
@@ -98,23 +96,3 @@
     <ConnectionStatus />
   </menu>
 </header>
-
-<style>
-  .activity-link {
-    background: linear-gradient(90deg, #6366f1, #8b5cf6, #a855f7, #8b5cf6, #6366f1);
-    background-size: 200% 100%;
-    -webkit-background-clip: text;
-    background-clip: text;
-    -webkit-text-fill-color: transparent;
-    animation: gradient-shift 2s linear infinite;
-  }
-
-  @keyframes gradient-shift {
-    0% {
-      background-position: 0% 50%;
-    }
-    100% {
-      background-position: 200% 50%;
-    }
-  }
-</style>

ui-svelte/src/components/playground/AudioInterface.svelte

@@ -2,7 +2,6 @@
   import { models } from "../../stores/api";
   import { persistentStore } from "../../stores/persistent";
   import { transcribeAudio } from "../../lib/audioApi";
-  import { playgroundStores } from "../../stores/playgroundActivity";
   import ModelSelector from "./ModelSelector.svelte";
 
   const selectedModelStore = persistentStore<string>("playground-audio-model", "");
@@ -23,10 +22,6 @@
 
   let canTranscribe = $derived(selectedFile !== null && $selectedModelStore !== "" && !isTranscribing);
 
-  $effect(() => {
-    playgroundStores.audioTranscribing.set(isTranscribing);
-  });
-
   function validateFile(file: File): { valid: boolean; error?: string } {
     const ext = '.' + file.name.split('.').pop()?.toLowerCase();
 

ui-svelte/src/components/playground/ChatInterface.svelte

@@ -2,7 +2,6 @@
   import { models } from "../../stores/api";
   import { persistentStore } from "../../stores/persistent";
   import { streamChatCompletion } from "../../lib/chatApi";
-  import { playgroundStores } from "../../stores/playgroundActivity";
   import type { ChatMessage, ContentPart } from "../../lib/types";
   import ChatMessageComponent from "./ChatMessage.svelte";
   import ModelSelector from "./ModelSelector.svelte";
@@ -12,16 +11,7 @@
   const systemPromptStore = persistentStore<string>("playground-system-prompt", "");
   const temperatureStore = persistentStore<number>("playground-temperature", 0.7);
 
-  function loadMessages(): ChatMessage[] {
-    try {
-      const saved = localStorage.getItem("playground-messages");
-      return saved ? JSON.parse(saved) : [];
-    } catch {
-      return [];
-    }
-  }
-
-  let messages = $state<ChatMessage[]>(loadMessages());
+  let messages = $state<ChatMessage[]>([]);
   let userInput = $state("");
   let isStreaming = $state(false);
   let isReasoning = $state(false);
@@ -34,52 +24,21 @@
   let imageError = $state<string | null>(null);
 
   let hasModels = $derived($models.some((m) => !m.unlisted));
-  let userScrolledUp = $state(false);
 
+  // Auto-scroll when messages change
   $effect(() => {
-    playgroundStores.chatStreaming.set(isStreaming);
-  });
-
-  function handleMessagesScroll() {
-    if (!messagesContainer) return;
-    const { scrollTop, scrollHeight, clientHeight } = messagesContainer;
-    // Consider "at bottom" if within 40px of the bottom
-    userScrolledUp = scrollHeight - scrollTop - clientHeight > 40;
-  }
-
-  // Auto-scroll when messages change — skip if user scrolled up
-  $effect(() => {
-    if (messages.length > 0 && messagesContainer && !userScrolledUp) {
+    if (messages.length > 0 && messagesContainer) {
       messagesContainer.scrollTo({
         top: messagesContainer.scrollHeight,
-        behavior: isStreaming ? "instant" : "smooth",
+        behavior: "smooth",
       });
     }
   });
 
-  // Persist messages to localStorage (throttled to once per 2s)
-  let lastSaveTime = 0;
-  $effect(() => {
-    const json = JSON.stringify(messages);
-    const elapsed = Date.now() - lastSaveTime;
-    const save = () => {
-      try { localStorage.setItem("playground-messages", json); } catch {}
-      lastSaveTime = Date.now();
-    };
-    if (elapsed >= 2000) {
-      save();
-      return;
-    }
-    const timer = setTimeout(save, 2000 - elapsed);
-    return () => clearTimeout(timer);
-  });
-
   async function sendMessage() {
     const trimmedInput = userInput.trim();
     if ((!trimmedInput && attachedImages.length === 0) || !$selectedModelStore || isStreaming) return;
 
-    userScrolledUp = false;
-
     // Build message content (multimodal if images attached)
     let content: string | ContentPart[];
     if (attachedImages.length > 0) {
@@ -362,7 +321,6 @@
     <div
       class="flex-1 overflow-y-auto mb-4 px-2"
       bind:this={messagesContainer}
-      onscroll={handleMessagesScroll}
     >
       {#if messages.length === 0}
         <div class="h-full flex items-center justify-center text-txtsecondary">

ui-svelte/src/components/playground/ChatMessage.svelte

@@ -1,6 +1,5 @@
 <script lang="ts">
-  import { renderMarkdown, escapeHtml, renderStreamingMarkdown, createStreamingCache } from "../../lib/markdown";
-  import type { RenderedBlock } from "../../lib/markdown";
+  import { renderMarkdown, escapeHtml } from "../../lib/markdown";
   import { Copy, Check, Pencil, X, Save, RefreshCw, ChevronDown, ChevronRight, Brain, Code } from "lucide-svelte";
   import { getTextContent, getImageUrls } from "../../lib/types";
   import type { ContentPart } from "../../lib/types";
@@ -23,17 +22,11 @@
   let hasImages = $derived(imageUrls.length > 0);
   let canEdit = $derived(onEdit !== undefined && !hasImages);
 
-  let streamingCache = createStreamingCache();
-  let renderedParts = $derived.by(() => {
-    if (role !== "assistant") {
-      return { blocks: [{ id: -1, html: escapeHtml(textContent).replace(/\n/g, '<br>') }] as RenderedBlock[], pendingHtml: "" };
-    }
-    if (!isStreaming) {
-      streamingCache = createStreamingCache();
-      return { blocks: [{ id: -1, html: renderMarkdown(textContent) }] as RenderedBlock[], pendingHtml: "" };
-    }
-    return renderStreamingMarkdown(textContent, streamingCache);
-  });
+  let renderedContent = $derived(
+    role === "assistant" && !isStreaming
+      ? renderMarkdown(textContent)
+      : escapeHtml(textContent).replace(/\n/g, '<br>')
+  );
   let copied = $state(false);
   let showRaw = $state(false);
   let isEditing = $state(false);
@@ -120,9 +113,9 @@
 
 <div class="flex {role === 'user' ? 'justify-end' : 'justify-start'} mb-4">
   <div
-    class="relative group rounded-lg px-4 py-2 {role === 'user'
-      ? 'max-w-[85%] bg-primary text-btn-primary-text'
-      : 'w-full sm:w-4/5 bg-surface border border-gray-200 dark:border-white/10'}"
+    class="relative group max-w-[85%] rounded-lg px-4 py-2 {role === 'user'
+      ? 'bg-primary text-btn-primary-text'
+      : 'bg-surface border border-gray-200 dark:border-white/10'}"
   >
     {#if role === "assistant"}
       {#if reasoning_content || isReasoning}
@@ -175,10 +168,7 @@
         <div class="whitespace-pre-wrap font-mono text-sm">{textContent}</div>
       {:else}
         <div class="prose prose-sm dark:prose-invert max-w-none">
-          {#each renderedParts.blocks as block (block.id)}
-            {@html block.html}
-          {/each}
-          {@html renderedParts.pendingHtml}
+          {@html renderedContent}
           {#if isStreaming && !isReasoning}
             <span class="inline-block w-2 h-4 bg-current animate-pulse ml-0.5"></span>
           {/if}

ui-svelte/src/components/playground/ImageInterface.svelte

@@ -2,7 +2,6 @@
   import { models } from "../../stores/api";
   import { persistentStore } from "../../stores/persistent";
   import { generateImage } from "../../lib/imageApi";
-  import { playgroundStores } from "../../stores/playgroundActivity";
   import ModelSelector from "./ModelSelector.svelte";
   import ExpandableTextarea from "./ExpandableTextarea.svelte";
 
@@ -18,10 +17,6 @@
 
   let hasModels = $derived($models.some((m) => !m.unlisted));
 
-  $effect(() => {
-    playgroundStores.imageGenerating.set(isGenerating);
-  });
-
   async function generate() {
     const trimmedPrompt = prompt.trim();
     if (!trimmedPrompt || !$selectedModelStore || isGenerating) return;

ui-svelte/src/components/playground/SpeechInterface.svelte

@@ -2,7 +2,6 @@
   import { models } from "../../stores/api";
   import { persistentStore } from "../../stores/persistent";
   import { generateSpeech } from "../../lib/speechApi";
-  import { playgroundStores } from "../../stores/playgroundActivity";
   import ModelSelector from "./ModelSelector.svelte";
   import ExpandableTextarea from "./ExpandableTextarea.svelte";
 
@@ -21,9 +20,11 @@
   let availableVoices = $state<string[]>(["coral", "alloy", "echo", "fable", "onyx", "nova", "shimmer"]);
   let isLoadingVoices = $state(false);
 
+  // Default voices to fall back to if API call fails
   const defaultVoices = ["coral", "alloy", "echo", "fable", "onyx", "nova", "shimmer"];
   const CACHE_KEY = "playground-speech-voices-cache";
 
+  // Load voices cache from localStorage
   function getVoicesCache(): Record<string, string[]> {
     if (typeof window === "undefined") return {};
     try {
@@ -34,6 +35,7 @@
     }
   }
 
+  // Save voices cache to localStorage
   function saveVoicesCache(cache: Record<string, string[]>) {
     if (typeof window === "undefined") return;
     try {
@@ -45,12 +47,9 @@
 
   let hasModels = $derived($models.some((m) => !m.unlisted));
 
+  // Track if this is the initial page load to avoid fetching on refresh
   let isInitialLoad = $state(true);
 
-  $effect(() => {
-    playgroundStores.speechGenerating.set(isGenerating);
-  });
-
   // On page load, restore cached voices for the selected model if available
   $effect(() => {
     const model = $selectedModelStore;

ui-svelte/src/lib/markdown.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect } from "vitest";
-import { renderMarkdown, escapeHtml, splitCompleteBlocks, closePendingBlock, normalizeLatexDelimiters, renderStreamingMarkdown, createStreamingCache } from "./markdown";
+import { renderMarkdown, escapeHtml } from "./markdown";
 
 describe("renderMarkdown", () => {
   describe("basic markdown", () => {
@@ -130,35 +130,6 @@ More text here.
       expect(result).toContain("katex");
       expect(result).toContain("sqrt");
     });
-
-    it("renders \\[...\\] display math", () => {
-      const result = renderMarkdown("\\[\nx^2 + y^2 = z^2\n\\]");
-      expect(result).toContain("katex");
-    });
-
-    it("renders \\(...\\) inline math", () => {
-      const result = renderMarkdown("The equation \\(E = mc^2\\) is famous.");
-      expect(result).toContain("katex");
-    });
-  });
-
-  describe("normalizeLatexDelimiters", () => {
-    it("converts \\[...\\] to $$...$$", () => {
-      expect(normalizeLatexDelimiters("\\[\nx^2\n\\]")).toBe("$$\nx^2\n$$");
-    });
-
-    it("converts \\(...\\) to $...$", () => {
-      expect(normalizeLatexDelimiters("\\(x^2\\)")).toBe("$x^2$");
-    });
-
-    it("leaves $$ and $ delimiters unchanged", () => {
-      const text = "$$x^2$$ and $y$";
-      expect(normalizeLatexDelimiters(text)).toBe(text);
-    });
-
-    it("handles multiple occurrences", () => {
-      expect(normalizeLatexDelimiters("\\(a\\) and \\(b\\)")).toBe("$a$ and $b$");
-    });
   });
 
   describe("escapeHtml", () => {
@@ -187,237 +158,3 @@ More text here.
     });
   });
 });
-
-describe("splitCompleteBlocks", () => {
-  it("returns everything as pending when no blank line", () => {
-    const result = splitCompleteBlocks("Hello world");
-    expect(result.complete).toBe("");
-    expect(result.pending).toBe("Hello world");
-  });
-
-  it("returns empty for empty input", () => {
-    const result = splitCompleteBlocks("");
-    expect(result.complete).toBe("");
-    expect(result.pending).toBe("");
-  });
-
-  it("splits on blank line between paragraphs", () => {
-    const result = splitCompleteBlocks("First paragraph.\n\nSecond paragraph");
-    expect(result.complete).toBe("First paragraph.\n");
-    expect(result.pending).toBe("Second paragraph");
-  });
-
-  it("splits multiple paragraphs at last blank line", () => {
-    const result = splitCompleteBlocks("Para 1.\n\nPara 2.\n\nPara 3");
-    expect(result.complete).toBe("Para 1.\n\nPara 2.\n");
-    expect(result.pending).toBe("Para 3");
-  });
-
-  it("treats closed code fence as complete boundary", () => {
-    const text = "```js\nconst x = 1;\n```\nMore text";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("```js\nconst x = 1;\n```");
-    expect(result.pending).toBe("More text");
-  });
-
-  it("treats unclosed code fence as pending", () => {
-    const text = "Done paragraph.\n\n```js\nconst x = 1;";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("Done paragraph.\n");
-    expect(result.pending).toBe("```js\nconst x = 1;");
-  });
-
-  it("does not split on blank lines inside code fences", () => {
-    const text = "```\nline1\n\nline2\n```";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("```\nline1\n\nline2\n```");
-    expect(result.pending).toBe("");
-  });
-
-  it("handles tilde fences", () => {
-    const text = "~~~py\nprint('hi')\n~~~\nAfter";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("~~~py\nprint('hi')\n~~~");
-    expect(result.pending).toBe("After");
-  });
-
-  it("does not close backtick fence with tilde fence", () => {
-    const text = "```\ncode\n~~~\nstill code";
-    const result = splitCompleteBlocks(text);
-    // The ~~~ should not close a backtick fence, so everything from ``` onward is pending
-    expect(result.complete).toBe("");
-    expect(result.pending).toBe("```\ncode\n~~~\nstill code");
-  });
-
-  it("treats closed math block as complete boundary", () => {
-    const text = "$$\nx^2\n$$\nAfter";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("$$\nx^2\n$$");
-    expect(result.pending).toBe("After");
-  });
-
-  it("treats unclosed math block as pending", () => {
-    const text = "Before.\n\n$$\nx^2";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("Before.\n");
-    expect(result.pending).toBe("$$\nx^2");
-  });
-
-  it("treats closed \\[...\\] math block as complete boundary", () => {
-    const text = "\\[\nx^2\n\\]\nAfter";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("\\[\nx^2\n\\]");
-    expect(result.pending).toBe("After");
-  });
-
-  it("treats unclosed \\[ math block as pending", () => {
-    const text = "Before.\n\n\\[\nx^2";
-    const result = splitCompleteBlocks(text);
-    expect(result.complete).toBe("Before.\n");
-    expect(result.pending).toBe("\\[\nx^2");
-  });
-
-  it("handles trailing blank line making everything complete", () => {
-    const text = "Hello world.\n";
-    const result = splitCompleteBlocks(text);
-    // Last line is empty string after split, which is a blank line
-    expect(result.complete).toBe("Hello world.\n");
-    expect(result.pending).toBe("");
-  });
-});
-
-describe("closePendingBlock", () => {
-  it("returns empty string for empty input", () => {
-    expect(closePendingBlock("")).toBe("");
-  });
-
-  it("returns plain text unchanged", () => {
-    expect(closePendingBlock("Hello world")).toBe("Hello world");
-  });
-
-  it("closes an open backtick code fence", () => {
-    const result = closePendingBlock("```python\nprint('hi')");
-    expect(result).toBe("```python\nprint('hi')\n```");
-  });
-
-  it("closes an open tilde code fence", () => {
-    const result = closePendingBlock("~~~js\nconst x = 1;");
-    expect(result).toBe("~~~js\nconst x = 1;\n~~~");
-  });
-
-  it("does not modify already-closed code fence", () => {
-    const text = "```py\ncode\n```";
-    expect(closePendingBlock(text)).toBe(text);
-  });
-
-  it("closes an open math block", () => {
-    const result = closePendingBlock("$$\nx^2 + y^2");
-    expect(result).toBe("$$\nx^2 + y^2\n$$");
-  });
-
-  it("does not modify already-closed math block", () => {
-    const text = "$$\nx^2\n$$";
-    expect(closePendingBlock(text)).toBe(text);
-  });
-
-  it("closes an open \\[ math block with \\]", () => {
-    const result = closePendingBlock("\\[\nx^2 + y^2");
-    expect(result).toBe("\\[\nx^2 + y^2\n\\]");
-  });
-
-  it("does not modify already-closed \\[...\\] math block", () => {
-    const text = "\\[\nx^2\n\\]";
-    expect(closePendingBlock(text)).toBe(text);
-  });
-
-  it("closes code fence when preceded by regular text", () => {
-    const result = closePendingBlock("Some text\n```\ncode");
-    expect(result).toBe("Some text\n```\ncode\n```");
-  });
-
-  it("leaves headers unchanged", () => {
-    expect(closePendingBlock("## Hello")).toBe("## Hello");
-  });
-
-  it("leaves tables unchanged", () => {
-    const table = "| a | b |\n| --- | --- |\n| 1 | 2 |";
-    expect(closePendingBlock(table)).toBe(table);
-  });
-
-  it("leaves lists unchanged", () => {
-    expect(closePendingBlock("- item 1\n- item 2")).toBe("- item 1\n- item 2");
-  });
-});
-
-describe("renderStreamingMarkdown", () => {
-  it("renders complete blocks and pending as markdown", () => {
-    const cache = createStreamingCache();
-    const text = "# Hello\n\nWorld";
-    const { blocks, pendingHtml } = renderStreamingMarkdown(text, cache);
-    expect(blocks).toHaveLength(1);
-    expect(blocks[0].html).toContain("<h1>Hello</h1>");
-    expect(pendingHtml).toContain("World");
-    expect(pendingHtml).toContain("<p>");
-  });
-
-  it("preserves existing blocks when complete portion is unchanged", () => {
-    const cache = createStreamingCache();
-    renderStreamingMarkdown("# Hello\n\nWor", cache);
-    const firstBlocks = cache.blocks;
-
-    const { blocks } = renderStreamingMarkdown("# Hello\n\nWorld", cache);
-    // Same block array reference — nothing changed in the complete section
-    expect(blocks).toBe(firstBlocks);
-    expect(cache.completeKey).toBe("# Hello\n");
-  });
-
-  it("appends a new block when a new section completes", () => {
-    const cache = createStreamingCache();
-    renderStreamingMarkdown("# Hello\n\nParagraph", cache);
-    expect(cache.blocks).toHaveLength(1);
-    const firstBlock = cache.blocks[0];
-
-    renderStreamingMarkdown("# Hello\n\nParagraph.\n\nMore", cache);
-    expect(cache.blocks).toHaveLength(2);
-    // First block is preserved with the same id and html
-    expect(cache.blocks[0].id).toBe(firstBlock.id);
-    expect(cache.blocks[0].html).toBe(firstBlock.html);
-    // Second block contains the new paragraph
-    expect(cache.blocks[1].html).toContain("Paragraph.");
-  });
-
-  it("assigns unique stable ids to each block", () => {
-    const cache = createStreamingCache();
-    renderStreamingMarkdown("A.\n\nB.\n\nC", cache);
-    expect(cache.blocks).toHaveLength(1);
-    const id0 = cache.blocks[0].id;
-
-    renderStreamingMarkdown("A.\n\nB.\n\nC.\n\nD", cache);
-    expect(cache.blocks).toHaveLength(2);
-    expect(cache.blocks[0].id).toBe(id0);
-    expect(cache.blocks[1].id).toBe(id0 + 1);
-  });
-
-  it("renders pending code block with syntax highlighting", () => {
-    const cache = createStreamingCache();
-    const text = "Done.\n\n```python\nprint('hello')";
-    const { pendingHtml } = renderStreamingMarkdown(text, cache);
-    expect(pendingHtml).toContain("<code");
-    expect(pendingHtml).toContain("hljs");
-  });
-
-  it("renders pending table as markdown", () => {
-    const cache = createStreamingCache();
-    const text = "Done.\n\n| a | b |\n| --- | --- |\n| 1 | 2 |";
-    const { pendingHtml } = renderStreamingMarkdown(text, cache);
-    expect(pendingHtml).toContain("<table>");
-    expect(pendingHtml).toContain("<td>");
-  });
-
-  it("renders pending portion through markdown pipeline", () => {
-    const cache = createStreamingCache();
-    const text = "Done.\n\nSome **bold** text";
-    const { pendingHtml } = renderStreamingMarkdown(text, cache);
-    expect(pendingHtml).toContain("<strong>bold</strong>");
-  });
-});

ui-svelte/src/lib/markdown.ts

@@ -69,189 +69,13 @@ const processor = unified()
   .use(rehypeHighlight)
   .use(rehypeStringify, { allowDangerousHtml: true });
 
-export function splitCompleteBlocks(text: string): { complete: string; pending: string } {
-  if (!text) {
-    return { complete: "", pending: "" };
-  }
-
-  const lines = text.split("\n");
-  let lastCompleteBoundary = -1; // index of last line that ends a complete block
-  let inFence = false;
-  let fenceChar = "";
-  let inMathBlock = false;
-
-  for (let i = 0; i < lines.length; i++) {
-    const trimmed = lines[i].trimEnd();
-
-    if (inFence) {
-      // Check for closing fence: same character, at least 3, no other content
-      if (new RegExp(`^\\s*${fenceChar.replace(/~/g, "\\~")}{3,}\\s*$`).test(trimmed)) {
-        inFence = false;
-        fenceChar = "";
-        lastCompleteBoundary = i;
-      }
-      continue;
-    }
-
-    if (inMathBlock) {
-      if (trimmed === "$$" || trimmed === "\\]") {
-        inMathBlock = false;
-        lastCompleteBoundary = i;
-      }
-      continue;
-    }
-
-    // Check for opening fence
-    const fenceMatch = trimmed.match(/^(\s*)(```|~~~)/);
-    if (fenceMatch) {
-      // Check if it's an opening fence (may have language info after)
-      // A line with just ``` or ~~~ could be opening or closing, but since we're not in a fence it's opening
-      fenceChar = fenceMatch[2][0]; // '`' or '~'
-      inFence = true;
-      continue;
-    }
-
-    // Check for opening math block
-    if (trimmed === "$$" || trimmed === "\\[") {
-      inMathBlock = true;
-      continue;
-    }
-
-    // Outside fences/math: blank line marks a complete boundary
-    if (trimmed === "") {
-      lastCompleteBoundary = i;
-    }
-  }
-
-  if (lastCompleteBoundary < 0) {
-    return { complete: "", pending: text };
-  }
-
-  const completeLines = lines.slice(0, lastCompleteBoundary + 1);
-  const pendingLines = lines.slice(lastCompleteBoundary + 1);
-
-  return {
-    complete: completeLines.join("\n"),
-    pending: pendingLines.join("\n"),
-  };
-}
-
-export function closePendingBlock(pending: string): string {
-  if (!pending) return "";
-
-  const lines = pending.split("\n");
-  let inFence = false;
-  let fenceStr = "";
-  let inMathBlock = false;
-  let mathClose = "";
-
-  for (const line of lines) {
-    const trimmed = line.trimEnd();
-
-    if (inFence) {
-      if (new RegExp(`^\\s*${fenceStr[0] === "~" ? "~~~" : "\\`\\`\\`"}\\s*$`).test(trimmed)) {
-        inFence = false;
-        fenceStr = "";
-      }
-      continue;
-    }
-
-    if (inMathBlock) {
-      if (trimmed === "$$" || trimmed === "\\]") {
-        inMathBlock = false;
-        mathClose = "";
-      }
-      continue;
-    }
-
-    const fenceMatch = trimmed.match(/^(\s*)(```|~~~)/);
-    if (fenceMatch) {
-      fenceStr = fenceMatch[2];
-      inFence = true;
-      continue;
-    }
-
-    if (trimmed === "$$") {
-      inMathBlock = true;
-      mathClose = "$$";
-      continue;
-    }
-
-    if (trimmed === "\\[") {
-      inMathBlock = true;
-      mathClose = "\\]";
-      continue;
-    }
-  }
-
-  if (inFence) return pending + "\n" + fenceStr;
-  if (inMathBlock) return pending + "\n" + mathClose;
-  return pending;
-}
-
-export interface RenderedBlock {
-  id: number;
-  html: string;
-}
-
-export interface StreamingCache {
-  blocks: RenderedBlock[];
-  nextId: number;
-  completeKey: string;
-}
-
-export function createStreamingCache(): StreamingCache {
-  return { blocks: [], nextId: 0, completeKey: "" };
-}
-
-export function renderStreamingMarkdown(
-  text: string,
-  cache: StreamingCache,
-): { blocks: RenderedBlock[]; pendingHtml: string } {
-  const { complete, pending } = splitCompleteBlocks(text);
-
-  if (complete) {
-    if (cache.completeKey !== complete) {
-      if (complete.startsWith(cache.completeKey) && cache.completeKey.length > 0) {
-        // Complete section grew — render only the new part as a new block
-        const newPart = complete.slice(cache.completeKey.length);
-        cache.blocks = [...cache.blocks, { id: cache.nextId++, html: renderMarkdown(newPart) }];
-      } else {
-        // Complete section changed unexpectedly — re-render as single block
-        cache.blocks = [{ id: cache.nextId++, html: renderMarkdown(complete) }];
-      }
-      cache.completeKey = complete;
-    }
-  } else if (cache.blocks.length > 0) {
-    cache.blocks = [];
-    cache.completeKey = "";
-  }
-
-  let pendingHtml = "";
-  if (pending) {
-    const closed = closePendingBlock(pending);
-    pendingHtml = renderMarkdown(closed);
-  }
-
-  return { blocks: cache.blocks, pendingHtml };
-}
-
-// Convert \[...\] to $$...$$ and \(...\) to $...$
-export function normalizeLatexDelimiters(text: string): string {
-  // Display math: \[...\] → $$...$$  (may span multiple lines)
-  text = text.replace(/\\\[([\s\S]*?)\\\]/g, (_match, inner) => `$$${inner}$$`);
-  // Inline math: \(...\) → $...$
-  text = text.replace(/\\\(([\s\S]*?)\\\)/g, (_match, inner) => `$${inner}$`);
-  return text;
-}
-
 export function renderMarkdown(content: string): string {
   if (!content) {
     return "";
   }
 
   try {
-    const result = processor.processSync(normalizeLatexDelimiters(content));
+    const result = processor.processSync(content);
     return String(result);
   } catch {
     // Fallback to escaped plain text if markdown parsing fails

ui-svelte/src/routes/PlaygroundStub.svelte

@@ -1 +0,0 @@
-<!-- empty: real Playground is always mounted in App.svelte -->

ui-svelte/src/stores/playgroundActivity.ts

@@ -1,18 +0,0 @@
-import { writable, derived } from "svelte/store";
-
-const chatStreaming = writable(false);
-const imageGenerating = writable(false);
-const speechGenerating = writable(false);
-const audioTranscribing = writable(false);
-
-export const playgroundActivity = derived(
-  [chatStreaming, imageGenerating, speechGenerating, audioTranscribing],
-  ([$chat, $image, $speech, $audio]) => $chat || $image || $speech || $audio
-);
-
-export const playgroundStores = {
-  chatStreaming,
-  imageGenerating,
-  speechGenerating,
-  audioTranscribing,
-};

ui-svelte/src/stores/route.ts

@@ -1,3 +0,0 @@
-import { writable } from "svelte/store";
-
-export const currentRoute = writable("/");