test(app): pre-bundle the JSX dev runtime for browser tests

Compiling test JSX with the automatic runtime imports react/jsx-dev-runtime. Vite discovered it mid-run on a cold cache and reloaded the page, which failed the first browser test file to import it.

.github/workflows/ci.yml

@@ -8,9 +8,13 @@ on:
   merge_group:
   workflow_dispatch:
 
+# A newer push to the same ref cancels the run still in progress, main included.
+# A full run costs about 200 runner-minutes against the org's 20 concurrent
+# jobs, and a superseded main run only answers a question the newer commit
+# answers again.
 concurrency:
   group: ci-${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+  cancel-in-progress: true
 
 env:
   # CI does not use the CUDA execution provider, and the onnxruntime-node
@@ -54,10 +58,10 @@ jobs:
       - name: Validate CI contracts
         run: node --test scripts/ci-workflow.test.mjs scripts/daemon-launch-contract.test.mjs scripts/sync-fdroid-changelogs.test.mjs scripts/upload-release-assets.test.mjs
 
-  format:
-    name: format
+  quality:
+    name: quality
     needs: changes
-    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.format != 'false') }}
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.format != 'false' || needs.changes.outputs.quality != 'false' || needs.changes.outputs.relay != 'false' || needs.changes.outputs.sdk != 'false') }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -68,36 +72,63 @@ jobs:
           cache: "npm"
 
       - name: Install dependencies
+        id: install
         run: node scripts/npm-retry.mjs ci
 
+      # Explicit status checks keep independent domains running after a failure.
+      # A failed step still fails quality; no continue-on-error or success shim.
       - name: Check formatting
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.format != 'false') }}
         run: npm run format:check
 
-  lint:
-    name: lint
-    needs: changes
-    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.quality != 'false') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: "22"
-          cache: "npm"
-
-      - name: Install dependencies
-        run: node scripts/npm-retry.mjs ci
-
       - name: Lint lockfile
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.quality != 'false') }}
         run: npx --yes lockfile-lint --path package-lock.json --type npm --allowed-hosts npm --validate-https --validate-integrity
 
       - name: Verify dependency signatures
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.quality != 'false') }}
         run: npm audit signatures
 
       - name: Lint
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.quality != 'false') }}
         run: npm run lint
 
+      - name: Build relay
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.relay != 'false') }}
+        run: npm run build:relay
+
+      - name: Run relay tests
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.relay != 'false') }}
+        run: npm run test --workspace=@getpaseo/relay
+
+      - name: Build client dependencies
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run build:relay && npm run build:client
+
+      - name: Build plugin SDK
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run build:plugin
+
+      - name: Run plugin SDK tests
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run test --workspace=@getpaseo/plugin
+
+      - name: Run protocol tests
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run test --workspace=@getpaseo/protocol
+
+      - name: Run client tests
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run test --workspace=@getpaseo/client
+
+      - name: Run highlight tests
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run test --workspace=@getpaseo/highlight
+
+      - name: Typecheck client examples
+        if: ${{ !cancelled() && steps.install.outcome == 'success' && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
+        run: npm run typecheck:examples --workspace=@getpaseo/client
+
   typecheck:
     name: typecheck
     needs: changes
@@ -143,43 +174,56 @@ jobs:
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' || needs.changes.outputs.hub != 'false') }}
     runs-on: ubuntu-latest
-    steps: &server_test_steps
-      - uses: actions/checkout@v4
+    steps:
+      - &server_capacity
+        name: Log runner capacity
+        run: |
+          node -e "const os = require('node:os'); console.log(JSON.stringify({cpus: os.cpus().length, model: os.cpus()[0].model, ramGiB: os.totalmem() / 2 ** 30}))"
+
+      - &server_checkout
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - uses: actions/setup-node@v4
+      - &server_node
+        uses: actions/setup-node@v4
         with:
           node-version: "22"
           cache: "npm"
 
-      - name: Fetch origin/main (worktree tests)
+      - &server_fetch
+        name: Fetch origin/main (worktree tests)
         if: ${{ needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' }}
         run: git fetch --no-tags origin main:refs/remotes/origin/main
 
-      - name: Install dependencies
+      - &server_install
+        name: Install dependencies
         run: node scripts/npm-retry.mjs ci
 
-      - name: Install agent CLIs for provider tests
+      - &server_agent_clis
+        name: Install agent CLIs for provider tests
         if: ${{ needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' }}
         run: node scripts/npm-retry.mjs install -g @anthropic-ai/claude-code opencode-ai
 
-      - name: Build server dependencies
+      - &server_build
+        name: Build server dependencies
         run: npm run build:server-deps
 
       - name: Run server tests
         if: ${{ needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' }}
         run: npm run test --workspace=@getpaseo/server
-        env:
+        env: &server_test_env
           CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
 
-      - name: Run built-in plugin tests
+      - &server_plugin_tests
+        name: Run built-in plugin tests
         if: ${{ needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' }}
         run: npm run test --workspace=@getpaseo/builtin-plugins
 
-      - name: Run Hub CLI/daemon contract
+      - &server_hub_contract
+        name: Run Hub CLI/daemon contract
         if: ${{ needs.changes.outputs.full == 'false' && needs.changes.outputs.server == 'false' && needs.changes.outputs.hub != 'false' }}
         run: npm run test:hub-cli-contract --workspace=@getpaseo/server
 
@@ -188,7 +232,41 @@ jobs:
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' || needs.changes.outputs.hub != 'false') }}
     runs-on: windows-latest
-    steps: *server_test_steps
+    steps:
+      - *server_capacity
+      - *server_checkout
+      - *server_node
+      - *server_fetch
+      - *server_install
+      - *server_agent_clis
+      - *server_build
+
+      - name: Run server unit tests
+        if: ${{ needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false' }}
+        run: npm run test:unit --workspace=@getpaseo/server
+        env: *server_test_env
+
+      - *server_plugin_tests
+      - *server_hub_contract
+
+  # Keep the serial integration chain off the Windows unit critical path.
+  server-integration-windows:
+    name: server-integration (windows-latest)
+    needs: changes
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.server != 'false') }}
+    runs-on: windows-latest
+    steps:
+      - *server_capacity
+      - *server_checkout
+      - *server_node
+      - *server_fetch
+      - *server_install
+      - *server_agent_clis
+      - *server_build
+
+      - name: Run server integration tests
+        run: npm run test:integration --workspace=@getpaseo/server
+        env: *server_test_env
 
   # native-recursive.ts serves darwin and win32, but windows-latest above is the only
   # runner that exercises it. macOS — the platform the reported watcher bug was on —
@@ -332,52 +410,19 @@ jobs:
       - name: Run app unit tests
         run: npm run test --workspace=@getpaseo/app
 
-  sdk-tests:
-    name: sdk-tests
-    needs: changes
-    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.sdk != 'false') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: "22"
-          cache: "npm"
-
-      - name: Install dependencies
-        run: node scripts/npm-retry.mjs ci
-
-      - name: Build client dependencies
-        run: npm run build:relay && npm run build:client
-
-      - name: Build plugin SDK
-        run: npm run build:plugin
-
-      - name: Run plugin SDK tests
-        run: npm run test --workspace=@getpaseo/plugin
-
-      - name: Run protocol tests
-        run: npm run test --workspace=@getpaseo/protocol
-
-      - name: Run client tests
-        run: npm run test --workspace=@getpaseo/client
-
-      - name: Run highlight tests
-        run: npm run test --workspace=@getpaseo/highlight
-
-      - name: Typecheck client examples
-        run: npm run typecheck:examples --workspace=@getpaseo/client
-
   playwright-1:
-    name: playwright (shard 1/4)
+    name: playwright (shard 1/8)
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
     runs-on: ubuntu-latest
     env:
-      PLAYWRIGHT_SHARD: "1/4"
+      PLAYWRIGHT_SHARD: "1/8"
       PLAYWRIGHT_ARTIFACT: "1"
     steps: &playwright_test_steps
+      - name: Log runner capacity
+        run: |
+          node -e "const os = require('node:os'); console.log(JSON.stringify({cpus: os.cpus().length, model: os.cpus()[0].model, ramGiB: os.totalmem() / 2 ** 30}))"
+
       - uses: actions/checkout@v4
 
       - uses: actions/setup-node@v4
@@ -405,9 +450,9 @@ jobs:
         run: npm run test:e2e --workspace=@getpaseo/app -- --shard=${{ env.PLAYWRIGHT_SHARD }}
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          # Weight file groups by observed duration; raw test counts overload
-          # early agent/Changes specs. Required check names remain unchanged.
-          PWTEST_SHARD_WEIGHTS: "111:172:137:160"
+          E2E_WORKERS: "2"
+          # File groups are weighted by observed reporter durations.
+          PWTEST_SHARD_WEIGHTS: "93:100:101:104:91:94:122:110"
 
       - name: Upload test artifacts
         uses: actions/upload-artifact@v4
@@ -420,56 +465,74 @@ jobs:
           retention-days: 7
 
   playwright-2:
-    name: playwright (shard 2/4)
+    name: playwright (shard 2/8)
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
     runs-on: ubuntu-latest
     env:
-      PLAYWRIGHT_SHARD: "2/4"
+      PLAYWRIGHT_SHARD: "2/8"
       PLAYWRIGHT_ARTIFACT: "2"
     steps: *playwright_test_steps
 
   playwright-3:
-    name: playwright (shard 3/4)
+    name: playwright (shard 3/8)
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
     runs-on: ubuntu-latest
     env:
-      PLAYWRIGHT_SHARD: "3/4"
+      PLAYWRIGHT_SHARD: "3/8"
       PLAYWRIGHT_ARTIFACT: "3"
     steps: *playwright_test_steps
 
   playwright-4:
-    name: playwright (shard 4/4)
+    name: playwright (shard 4/8)
     needs: changes
     if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
     runs-on: ubuntu-latest
     env:
-      PLAYWRIGHT_SHARD: "4/4"
+      PLAYWRIGHT_SHARD: "4/8"
       PLAYWRIGHT_ARTIFACT: "4"
     steps: *playwright_test_steps
 
-  relay-tests:
-    name: relay-tests
+  playwright-5:
+    name: playwright (shard 5/8)
     needs: changes
-    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.relay != 'false') }}
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
     runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
+    env:
+      PLAYWRIGHT_SHARD: "5/8"
+      PLAYWRIGHT_ARTIFACT: "5"
+    steps: *playwright_test_steps
 
-      - uses: actions/setup-node@v4
-        with:
-          node-version: "22"
-          cache: "npm"
+  playwright-6:
+    name: playwright (shard 6/8)
+    needs: changes
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
+    runs-on: ubuntu-latest
+    env:
+      PLAYWRIGHT_SHARD: "6/8"
+      PLAYWRIGHT_ARTIFACT: "6"
+    steps: *playwright_test_steps
 
-      - name: Install dependencies
-        run: node scripts/npm-retry.mjs ci
+  playwright-7:
+    name: playwright (shard 7/8)
+    needs: changes
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
+    runs-on: ubuntu-latest
+    env:
+      PLAYWRIGHT_SHARD: "7/8"
+      PLAYWRIGHT_ARTIFACT: "7"
+    steps: *playwright_test_steps
 
-      - name: Build relay
-        run: npm run build:relay
-
-      - name: Run relay tests
-        run: npm run test --workspace=@getpaseo/relay
+  playwright-8:
+    name: playwright (shard 8/8)
+    needs: changes
+    if: ${{ !cancelled() && (needs.changes.outputs.full != 'false' || needs.changes.outputs.browser != 'false') }}
+    runs-on: ubuntu-latest
+    env:
+      PLAYWRIGHT_SHARD: "8/8"
+      PLAYWRIGHT_ARTIFACT: "8"
+    steps: *playwright_test_steps
 
   cli-tests-1:
     name: cli-tests (shard 1/3)

docs/design.md

@@ -70,7 +70,7 @@ the sidebar. Apply it as `backgroundColor`; setting `opacity` on the control als
 
 Sizes: `xs` for ultra-tight inline triggers. `sm` for any button sitting in a row. `md` is the page default. `lg` is reserved for large standalone CTAs.
 
-Sizes are a shared contract across control kinds, defined once in `control-geometry.ts`: `xs` = 28px tall with `fontSize.sm` labels, `sm` = 32px with `fontSize.base`, `md`/`lg` = 44px with `fontSize.base`. `<SegmentedControl>` (`packages/app/src/components/ui/segmented-control.tsx`) takes the same `xs`/`sm`/`md` sizes — a segmented control next to a `<Button>` of the same size always matches in height, label size, and corner radius. Its segments run one padding step tighter than a button, because the gap between segments already reads as padding. The selected segment is a `surface3` fill with `foreground` text, not an inverted one — inverting it inside thin chrome puts a white slab in the toolbar. Thin chrome such as the file toolbar uses `xs`; settings rows use `sm`. Never shrink a control's font or padding locally to fit a context — if the context needs a smaller control, the size tier is missing or the wrong one is in use.
+Sizes are a shared contract across control kinds, defined once in `control-geometry.ts`: `xs` = 28px tall with `fontSize.sm` labels, `sm` = 32px with `fontSize.base`, `md`/`lg` = 44px with `fontSize.base`. `<SegmentedControl>` (`packages/app/src/components/ui/segmented-control.tsx`) takes the same `xs`/`sm`/`md` sizes — a segmented control next to a `<Button>` of the same size always matches in height, label size, and corner radius. Its segments run one padding step tighter than a button, because the gap between segments already reads as padding. The selected segment is a `surface3` fill with `foreground` text, not an inverted one — inverting it inside thin chrome puts a white slab in the toolbar. Text fields take `xs`, `sm` and `md`. Thin chrome such as the file toolbar uses `xs`. A settings row sizes the controls in its trailing slot itself, `sm` in a card and `xs` when nested (`packages/app/src/components/ui/control-size.tsx`), so don't pass a size to a button, dropdown or field placed in a row. Never shrink a control's font or padding locally to fit a context — if the context needs a smaller control, the size tier is missing or the wrong one is in use.
 
 A `<Pressable>` wrapping a `<Text>` is a sixth variant. It is wrong. `<Button>` accepts `style`, `textStyle`, `leftIcon`, `disabled`, `size`, and `variant`.
 
@@ -126,6 +126,8 @@ Cards inside a section sit closer than sections. Rows inside a card touch — on
 
 Rows have generous vertical padding: roughly 16px of content plus 16px of vertical padding for settings rows, 8–12px for sidebar list items where many rows must fit. Compressing rows below the established density to fit more on the screen is wrong. Too many rows means more cards or more sections, not smaller rows.
 
+Rows revealed under a `<SettingsCollapsibleRow>` are nested rows, one step smaller than card rows: 8px of vertical padding, `fontSize.sm` text, `xs` controls, and one fixed height so rows with and without a trailing button line up. The collapsible row sets this for everything under it (`packages/app/src/components/settings/row-density.tsx`). Never pass a density to a row, and never pad or resize a nested row by hand.
+
 The whitespace is the design.
 
 ---

docs/markdown-renderer.md

@@ -18,7 +18,7 @@ Math and video are disabled. Task lists and admonitions are enabled; task checkb
 
 Mermaid fences use the existing isolated diagram runtime and fullscreen viewer. Web dispatches them through the library’s code-block override. Native has no block-renderer hook, so the renderer extracts only Mermaid fences and places the existing WebView host between library-rendered segments. This is the only block exception; see [native selection limitations](native-text-selection.md) for diagram grouping and leading inline images. Streaming keeps the last valid diagram visible while the next revision renders.
 
-Native code blocks use the library's copy control and compiled grammars. Web code blocks use `HighlightedCodeBlock` through the library's `renderers.codeBlock` override. The patch also preserves web list numbering and link titles, marks pending parses with `aria-busy` so Find waits for rendered text, and carries link syntax through native and web tap events. Web inline code inside a link inherits only the link colour; its code font, size and background stay intact. Keep link variants colour-only: native pills replace text runs and prevent paths from wrapping; Android pills also use the surrounding block’s font size. The package patch is tracked by [upstream PR #997](https://github.com/software-mansion/enriched-markdown/pull/997); remove the patch when the pinned release includes it.
+Native code blocks use the library's copy control and compiled grammars. Web code blocks use `HighlightedCodeBlock` through the library's `renderers.codeBlock` override. The patch also keeps the library's block spacing around the web code block override, preserves web list numbering and link titles, marks pending parses with `aria-busy` so Find waits for rendered text, and carries link syntax through native and web tap events. Web inline code inside a link inherits only the link colour; its code font, size and background stay intact. Keep link variants colour-only: native pills replace text runs and prevent paths from wrapping; Android pills also use the surrounding block’s font size. The package patch is tracked by [upstream PR #997](https://github.com/software-mansion/enriched-markdown/pull/997); remove the patch when the pinned release includes it.
 
 The package patch also keeps overflowing native horizontal blocks in control of their drags: Android claims parent interception at touch-down and releases it for vertical drags so the chat list can scroll; iOS keeps its scroll recognizer active for outward drags at the leading edge. This prevents compact sidebar pans from taking block scrolling without changing sidebar swipes on prose or non-overflowing blocks. Native changes require a client rebuild.
 

docs/timeline-sync.md

@@ -251,7 +251,8 @@ do not imply local ownership or authorization. Capture the sender title at deliv
 removed senders must remain understandable without a live directory lookup.
 
 The optional `agentMessage` payload carries event, sender, and delivered text. Shared client
-presentation (`protocol/agent-message-display`) owns its heading and expanded details. The daemon
+presentation (`protocol/paseo-tool-presentation`) owns its heading and expanded details, next to the
+labels for every Paseo MCP tool. The daemon
 must not construct UI labels or prepend sender labels to the semantic message body. The existing
 `tool_call` / `plain_text` envelope is a compatibility adapter: older clients still parse the row and
 expand its body. New clients use the typed payload, never infer the event from a tool name or parse

packages/app/e2e/browser/paseo-tool-call-details.codex.real.spec.ts

@@ -84,7 +84,7 @@ test.describe("real Codex Paseo tool-call presentation", () => {
         expectedText: ["Prompt", GREETING, "Greeting child", "codex/gpt-5.4-mini", "Result"],
       });
       await captureToolCall(page, testInfo, {
-        label: "Send agent prompt",
+        label: "Send message",
         artifact: "send-prompt-presentation",
         expectedText: ["Prompt", GREETING, "Agent", "Result"],
       });

packages/app/e2e/browser/plan-card-markdown.spec.ts

@@ -259,3 +259,71 @@ async function openInlineRegressionFile(page: Page, path: string) {
     .getByRole("link", { name: path, exact: true })
     .click();
 }
+
+// Web links are styled inline by the library, so hover state has to restyle the anchor.
+test("markdown links underline on hover", async ({ page }) => {
+  const session = await seedMockAgentWorkspace({
+    repoPrefix: "markdown-link-hover-",
+    title: "Markdown link hover",
+    featureValues: {
+      mockAssistantResponse: "See [the docs](https://example.com/docs) and [README](README.md).",
+    },
+    initialPrompt: "Show links",
+  });
+  try {
+    await session.client.waitForFinish(session.agentId, 30_000);
+    await openAgentRoute(page, session);
+    const message = page.getByTestId("assistant-message");
+    for (const name of ["the docs", "README"]) {
+      const link = message.getByRole("link", { name, exact: true });
+      await expect(link).toHaveCSS("text-decoration-line", "none");
+      await link.hover();
+      await expect(link).toHaveCSS("text-decoration-line", "underline");
+      await page.mouse.move(0, 0);
+      await expect(link).toHaveCSS("text-decoration-line", "none");
+    }
+  } finally {
+    await session.cleanup();
+  }
+});
+
+// The web code block replaces the library's own block, which must keep its spacing.
+test("blocks around a web code block keep their spacing", async ({ page }) => {
+  const session = await seedMockAgentWorkspace({
+    repoPrefix: "markdown-block-spacing-",
+    title: "Markdown block spacing",
+    featureValues: {
+      mockAssistantResponse:
+        "Intro.\n\n```sh\nnpx playwright test\n```\n\n| Step | Result |\n| --- | --- |\n| hover | none |\n\nMiddle.\n\n```ts\nconst a = 1;\n```\n\nClosing.",
+    },
+    initialPrompt: "Show blocks",
+  });
+  try {
+    await session.client.waitForFinish(session.agentId, 30_000);
+    await openAgentRoute(page, session);
+    const message = page.getByTestId("assistant-message");
+    await expect(message.getByRole("table")).toBeVisible();
+    const gaps = await measureBlockGaps(message.locator(".enrm-text").first());
+    for (const { between, gap } of gaps) expect(gap, between).toBeGreaterThanOrEqual(8);
+  } finally {
+    await session.cleanup();
+  }
+});
+
+async function measureBlockGaps(root: Locator) {
+  return root.evaluate((element) => {
+    const blocks = Array.from(element.children).map((block) => {
+      // Wrappers with display: contents have no box; measure their first rendered child.
+      let box: Element = block;
+      while (box.getBoundingClientRect().height === 0 && box.firstElementChild) {
+        box = box.firstElementChild;
+      }
+      const rect = box.getBoundingClientRect();
+      return { text: (block.textContent ?? "").slice(0, 20), top: rect.top, bottom: rect.bottom };
+    });
+    return blocks.slice(1).map((block, index) => ({
+      between: `${blocks[index].text} -> ${block.text}`,
+      gap: Math.round(block.top - blocks[index].bottom),
+    }));
+  });
+}

packages/app/e2e/browser/usage-modal.spec.ts

@@ -16,6 +16,7 @@ import {
 } from "../support/helpers/usage-reports";
 import {
   installLoginUsage,
+  expectLoginUsageFreshness,
   installCodexWindowUsage,
   expectCodexReportedWindows,
   refreshLoginUsage,
@@ -588,6 +589,69 @@ async function expectLoginErrors(page: Page, lines: string[]) {
 
 async function expectLoginUsageOnly(page: Page, percentage: string) {
   const card = page.getByTestId("usage-report-login-journey:account");
-  await expect(card.getByText(percentage, { exact: true })).toBeVisible();
+  await expect(card.getByText(new RegExp(`^${percentage}(?:$| ·)`))).toBeVisible();
   await expect(card.getByTestId("usage-login-error")).toHaveCount(0);
 }
+
+for (const compact of [false, true]) {
+  test(`failed polls retain usage and successful freshness (${compact ? "footer" : "tooltip"})`, async ({
+    page,
+  }) => {
+    const fixture = await installLoginUsage({ status: "error", error: "Initial failure" });
+    try {
+      await page.setViewportSize(
+        compact ? { width: 390, height: 844 } : { width: 1440, height: 900 },
+      );
+      await gotoAppShell(page);
+      if (compact) await openCompactSidebar(page);
+      await openUsageFromIcon(page);
+      await expectLoginErrors(page, ["Claude: Initial failure"]);
+      await expectLoginUsageFreshness(page, "No successful update", compact);
+
+      await fixture.setReport({
+        status: "available",
+        windows: [{ id: "weekly", label: "Weekly", usedPct: 42, resetsAt: "2000-01-01T00:00:00Z" }],
+      });
+      // Move only the browser clock; real daemon fetches continue using the host clock.
+      await page.clock.setFixedTime(new Date(Date.now() + 3_900_000));
+      await refreshLoginUsage(page);
+      await expectLoginUsageOnly(page, "42%");
+      await expectLoginUsageFreshness(page, "Updated 1h ago", compact);
+
+      await fixture.setReport({ status: "error", error: "Rate limited" });
+      await refreshLoginUsage(page);
+      await expectRetainedLoginUsage(page, "Claude: Rate limited");
+      await expectLoginUsageFreshness(page, "Last updated 1h ago", compact);
+      await refreshLoginUsage(page);
+      await expectRetainedLoginUsage(page, "Claude: Rate limited");
+      await expectLoginUsageFreshness(page, "Last updated 1h ago", compact);
+
+      await fixture.setReport({
+        status: "unavailable",
+        problem: { kind: "no_quota", detail: "No active quota" },
+      });
+      await refreshLoginUsage(page);
+      await expectRetainedLoginUsage(page, "Claude: No active quota");
+      await expectLoginUsageFreshness(page, "Last updated 1h ago", compact);
+
+      await fixture.setReport({
+        status: "available",
+        windows: [{ id: "weekly", label: "Weekly", usedPct: 43 }],
+      });
+      await page.clock.setFixedTime(new Date(Date.now() + 150_000));
+      await refreshLoginUsage(page);
+      await expectLoginUsageOnly(page, "43%");
+      await expect(page.getByText("42%", { exact: true })).toHaveCount(0);
+      await expectLoginUsageFreshness(page, "Updated 2m ago", compact);
+    } finally {
+      await fixture.cleanup();
+    }
+  });
+}
+
+async function expectRetainedLoginUsage(page: Page, message: string) {
+  const card = page.getByTestId("usage-report-login-journey:account");
+  await expect(card.getByText(/^42%(?:$| ·)/)).toBeVisible();
+  await expect(card.getByTestId("usage-login-error")).toHaveText(message);
+  await expect(card.getByText("Reset time passed", { exact: false })).toBeVisible();
+}

packages/app/e2e/support/helpers/usage-login.ts

@@ -135,3 +135,14 @@ export async function expectCodexReportedWindows(page: Page, shape: "seven-day-o
     );
   }
 }
+
+export async function expectLoginUsageFreshness(page: Page, text: string, compact: boolean) {
+  const card = page.getByTestId("usage-report-login-journey:account");
+  if (compact) {
+    await expect(card.getByTestId("usage-freshness")).toHaveText(text);
+    return;
+  }
+  await card.getByRole("button", { name: "Refresh Claude", exact: true }).hover();
+  await expect(page.getByTestId("usage-freshness-tooltip")).toHaveText(text);
+  await page.mouse.move(0, 0);
+}

packages/app/src/agent-stream/native-scroll-animation.test.ts

@@ -0,0 +1,34 @@
+import { describe, expect, it } from "vitest";
+import { shouldAnimateNativeScrollToBottom } from "./native-scroll-animation";
+
+describe("native scroll-to-bottom animation", () => {
+  it("jumps across unmounted history instead of animating through blank rows", () => {
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 60_000, viewportHeight: 600, windowSize: 10 }),
+    ).toBe(false);
+  });
+
+  it("keeps near-bottom movement eligible for animation", () => {
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 300, viewportHeight: 600, windowSize: 10 }),
+    ).toBe(true);
+  });
+
+  it("bounds travel by the bottom-side overscan, not the whole window", () => {
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 2700, viewportHeight: 600, windowSize: 10 }),
+    ).toBe(true);
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 2701, viewportHeight: 600, windowSize: 10 }),
+    ).toBe(false);
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 1500, viewportHeight: 600, windowSize: 5 }),
+    ).toBe(false);
+  });
+
+  it("does not animate before the viewport has been measured", () => {
+    expect(
+      shouldAnimateNativeScrollToBottom({ offsetY: 0, viewportHeight: 0, windowSize: 10 }),
+    ).toBe(false);
+  });
+});

packages/app/src/agent-stream/native-scroll-animation.ts

@@ -0,0 +1,10 @@
+export function shouldAnimateNativeScrollToBottom(input: {
+  offsetY: number;
+  viewportHeight: number;
+  windowSize: number;
+}): boolean {
+  // VirtualizedList splits the extra window around the viewport. An animated
+  // jump farther than the bottom-side overscan crosses unmounted history.
+  const bottomOverscanHeight = ((input.windowSize - 1) / 2) * input.viewportHeight;
+  return input.viewportHeight > 0 && input.offsetY <= bottomOverscanHeight;
+}

packages/app/src/agent-stream/strategy-native.tsx

@@ -23,6 +23,7 @@ import type { StreamItem } from "@/types/stream";
 import type { Theme } from "@/styles/theme";
 import { useStableEvent } from "@/hooks/use-stable-event";
 import { useKeyboardStreamInset } from "@/keyboard/shift";
+import { shouldAnimateNativeScrollToBottom } from "./native-scroll-animation";
 import { useRevisedHistoryRows } from "./history-row-revision";
 import { useBottomAnchorController } from "./bottom-anchor-controller";
 import { useScrollKeyboardDismiss } from "./scroll-keyboard-dismiss/use-scroll-keyboard-dismiss";
@@ -64,6 +65,7 @@ const historyStartSlotStyle: ViewStyle = {
   flexShrink: 0,
 };
 const HISTORY_START_SETTLE_FRAMES = 2;
+const NATIVE_STREAM_WINDOW_SIZE = 10;
 
 function keyExtractor(item: { id: string }): string {
   return item.id;
@@ -238,7 +240,13 @@ function NativeStreamViewport(props: StreamRenderInput & { strategy: StreamStrat
       programmaticScrollEventBudgetRef.current = 3;
       flatListRef.current?.scrollToOffset({
         offset: 0,
-        animated,
+        animated:
+          animated &&
+          shouldAnimateNativeScrollToBottom({
+            offsetY: scrollOffsetYRef.current,
+            viewportHeight: streamViewportMetricsRef.current.viewportHeight,
+            windowSize: NATIVE_STREAM_WINDOW_SIZE,
+          }),
       });
       scrollOffsetYRef.current = 0;
       streamViewportMetricsRef.current = {
@@ -591,11 +599,11 @@ function NativeStreamViewport(props: StreamRenderInput & { strategy: StreamStrat
       scrollEventThrottle={16}
       onContentSizeChange={handleContentSizeChange}
       maintainVisibleContentPosition={maintainVisibleContentPosition}
-      // A history row can contain an entire long reply. Keep synchronous native
-      // Markdown measurement bounded while FlatList fills the surrounding window.
+      // Tall Markdown rows exhaust a shallow window during flings. Keep the initial
+      // render small, then refill a deeper window in batches large enough to keep up.
       initialNumToRender={2}
-      maxToRenderPerBatch={2}
-      windowSize={5}
+      maxToRenderPerBatch={10}
+      windowSize={NATIVE_STREAM_WINDOW_SIZE}
       removeClippedSubviews={false}
       scrollEnabled={scrollEnabled}
       showsVerticalScrollIndicator

packages/app/src/agent-stream/view.tsx

@@ -771,6 +771,7 @@ const AgentStreamViewComponent = forwardRef<AgentStreamViewHandle, AgentStreamVi
               status={data.status}
               detail={data.detail}
               cwd={context.cwd}
+              serverId={resolvedServerId}
               metadata={data.metadata}
               agentMessage={data.agentMessage}
               isLastInSequence={isLastInSequence}
@@ -795,7 +796,7 @@ const AgentStreamViewComponent = forwardRef<AgentStreamViewHandle, AgentStreamVi
           />
         );
       },
-      [context.cwd, setInlineDetailsExpanded, handleToolCallOpenFile],
+      [context.cwd, resolvedServerId, setInlineDetailsExpanded, handleToolCallOpenFile],
     );
 
     // Read through a stable event so live group updates do not change the renderer identity

packages/app/src/components/markdown/renderers.web.tsx

@@ -1,5 +1,5 @@
 import { Text } from "react-native";
-import { forwardRef, useMemo, type ComponentProps } from "react";
+import { forwardRef, useCallback, useMemo, useState, type ComponentProps } from "react";
 import type {
   CodeBlockRendererProps,
   LinkRendererProps,
@@ -27,14 +27,29 @@ function WebCodeBlock({ code, language }: CodeBlockRendererProps) {
   return <ThemedCodeBlock code={code} language={language} uniProps={codeStyle} />;
 }
 
+// The library styles links inline, so a stylesheet :hover rule cannot underline them.
+const LINK_HOVER_STYLE = { textDecoration: "underline" } as const;
+
 function WebLink({ link, anchorProps, children }: LinkRendererProps) {
   const { tooltipPath, onHoverIn } = useFileLink(markdownLinkSource(link.url, link.sourceType));
+  const [hovered, setHovered] = useState(false);
+  const handleMouseEnter = useCallback(() => setHovered(true), []);
+  const handleMouseLeave = useCallback(() => setHovered(false), []);
   const anchorStyle = useMemo(
-    () => ({ ...anchorProps.style, overflowWrap: "anywhere" as const }),
-    [anchorProps.style],
+    () => ({
+      ...anchorProps.style,
+      overflowWrap: "anywhere" as const,
+      ...(hovered ? LINK_HOVER_STYLE : null),
+    }),
+    [anchorProps.style, hovered],
   );
   const anchor = (
-    <a {...anchorProps} style={anchorStyle}>
+    <a
+      {...anchorProps}
+      style={anchorStyle}
+      onMouseEnter={handleMouseEnter}
+      onMouseLeave={handleMouseLeave}
+    >
       {children}
     </a>
   );

packages/app/src/components/message.tsx

@@ -26,6 +26,7 @@ import { writeMarkdownToRichClipboard } from "@/utils/rich-clipboard";
 import { getDefaultMarkdownClipboardEnvironment } from "@/utils/rich-clipboard-default-environment";
 import { formatDuration, formatMessageTimestamp } from "@/utils/time";
 import { resolveToolCallIcon } from "@/utils/tool-call-icon";
+import { useTargetAgentTitle } from "@/tool-calls/use-target-agent-title";
 import type { DaemonClient } from "@getpaseo/client/internal/daemon-client";
 import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { AgentCapabilityFlags, ToolCallDetail } from "@getpaseo/protocol/agent-types";
@@ -2208,6 +2209,7 @@ function areExpandableBadgePropsEqual(previous: ExpandableBadgeProps, next: Expa
 
 interface ToolCallProps {
   agentMessage?: AgentMessage;
+  serverId?: string;
   toolName: string;
   args?: unknown;
   result?: unknown;
@@ -2228,6 +2230,7 @@ interface ToolCallProps {
 
 export const ToolCall = memo(function ToolCall({
   agentMessage,
+  serverId,
   toolName,
   args,
   result,
@@ -2265,6 +2268,7 @@ export const ToolCall = memo(function ToolCall({
     return undefined;
   }, [detail, args, result]);
 
+  const targetAgentTitle = useTargetAgentTitle({ serverId, toolName, detail: effectiveDetail });
   const presentation = useMemo(
     () =>
       buildToolCallPresentation({
@@ -2275,9 +2279,10 @@ export const ToolCall = memo(function ToolCall({
         detail: effectiveDetail,
         metadata,
         cwd,
+        targetAgentTitle,
         resolveIcon: resolveToolCallIcon,
       }),
-    [toolName, status, error, effectiveDetail, metadata, cwd, agentMessage],
+    [toolName, status, error, effectiveDetail, metadata, cwd, agentMessage, targetAgentTitle],
   );
   const handleOpenFile = useMemo(() => {
     const openFilePath = presentation.openFilePath;
@@ -2393,6 +2398,8 @@ export const ToolCall = memo(function ToolCall({
 
 function areToolCallPropsEqual(previous: ToolCallProps, next: ToolCallProps) {
   if (previous.toolName !== next.toolName) return false;
+  if (previous.serverId !== next.serverId) return false;
+  if (previous.agentMessage !== next.agentMessage) return false;
   if (previous.args !== next.args) return false;
   if (previous.result !== next.result) return false;
   if (previous.error !== next.error) return false;

packages/app/src/components/settings/collapsible-row.tsx

@@ -6,15 +6,18 @@ import { mutedIconColorMapping } from "@/components/ui/icon-color";
 import { isWeb } from "@/constants/platform";
 import { settingsStyles } from "@/styles/settings";
 import { ICON_SIZE, type Theme } from "@/styles/theme";
+import { NestedSettingsRows, useSettingsRowLayout } from "./row-density";
 
 const ThemedChevron = withUnistyles(ChevronRight);
 const hoveredIconColorMapping = (theme: Theme) => ({ color: theme.colors.foreground });
 
 interface SettingsCollapsibleRowProps {
   label: string;
+  /** A short status shown before the chevron, so the row says something while collapsed. */
+  summary?: string;
   defaultExpanded?: boolean;
   testID?: string;
-  /** The rows revealed underneath, separated like the rows of a `SettingsCard`. */
+  /** The rows revealed underneath, separated like the rows of a `SettingsCard` and laid out as nested rows. */
   children: ReactNode;
 }
 
@@ -25,6 +28,7 @@ interface SettingsCollapsibleRowProps {
  */
 export function SettingsCollapsibleRow({
   label,
+  summary,
   defaultExpanded = false,
   testID,
   children,
@@ -37,13 +41,14 @@ export function SettingsCollapsibleRow({
     () => (isWeb ? ({ "aria-expanded": expanded } as const) : null),
     [expanded],
   );
+  const layout = useSettingsRowLayout();
   const headerStyle = useCallback(
     ({ hovered, pressed }: PressableStateCallbackType & { hovered?: boolean }) => [
-      settingsStyles.row,
+      layout.row,
       hovered && styles.headerHovered,
       pressed && styles.headerPressed,
     ],
-    [],
+    [layout],
   );
   const chevronStyle = useMemo(
     () => [styles.chevron, expanded && styles.chevronExpanded],
@@ -55,7 +60,7 @@ export function SettingsCollapsibleRow({
       <Pressable
         {...webExpandedProps}
         accessibilityRole="button"
-        accessibilityLabel={label}
+        accessibilityLabel={summary ? `${label}, ${summary}` : label}
         accessibilityState={accessibilityState}
         onPress={toggle}
         style={headerStyle}
@@ -64,8 +69,9 @@ export function SettingsCollapsibleRow({
         {({ hovered }: PressableStateCallbackType & { hovered?: boolean }) => (
           <>
             <View style={settingsStyles.rowContent}>
-              <Text style={settingsStyles.rowTitle}>{label}</Text>
+              <Text style={layout.title}>{label}</Text>
             </View>
+            {summary ? <Text style={styles.summary}>{summary}</Text> : null}
             <View style={chevronStyle}>
               <ThemedChevron
                 size={ICON_SIZE.sm}
@@ -75,18 +81,34 @@ export function SettingsCollapsibleRow({
           </>
         )}
       </Pressable>
-      {expanded
-        ? Children.toArray(children).map((child, index) => (
-            <View key={isValidElement(child) ? child.key : index} style={settingsStyles.rowBorder}>
-              {child}
-            </View>
-          ))
-        : null}
+      {expanded ? (
+        <View style={styles.children}>
+          <NestedSettingsRows>
+            {Children.toArray(children).map((child, index) => (
+              <View
+                key={isValidElement(child) ? child.key : index}
+                style={settingsStyles.rowBorder}
+              >
+                {child}
+              </View>
+            ))}
+          </NestedSettingsRows>
+        </View>
+      ) : null}
     </View>
   );
 }
 
 const styles = StyleSheet.create((theme) => ({
+  summary: {
+    color: theme.colors.foregroundMuted,
+    fontSize: theme.fontSize.sm,
+    marginRight: theme.spacing[2],
+  },
+  // The revealed rows keep the card's rails; the tint is what groups them under their header.
+  children: {
+    backgroundColor: theme.colors.surface0,
+  },
   headerHovered: {
     backgroundColor: theme.colors.surface2,
   },

packages/app/src/components/settings/headings/settings-info-tip.tsx

@@ -1,4 +1,4 @@
-import type { ReactNode } from "react";
+import type { ComponentType, ReactNode } from "react";
 import { Pressable, Text } from "react-native";
 import { useTranslation } from "react-i18next";
 import { Info } from "lucide-react-native";
@@ -6,7 +6,13 @@ import { StyleSheet, withUnistyles } from "react-native-unistyles";
 import { Tooltip, TooltipContent, TooltipTrigger } from "@/components/ui/tooltip";
 import { ICON_SIZE, type Theme } from "@/styles/theme";
 
-const ThemedInfo = withUnistyles(Info);
+type TipIconComponent = ComponentType<{ size: number; color: string }>;
+
+function TipIcon({ icon: Icon, color }: { icon: TipIconComponent; color: string }) {
+  return <Icon size={ICON_SIZE.sm} color={color} />;
+}
+
+const ThemedTipIcon = withUnistyles(TipIcon);
 
 const mutedIconMapping = (theme: Theme) => ({ color: theme.colors.foregroundMuted });
 
@@ -14,27 +20,37 @@ interface SettingsInfoTipProps {
   /** Header the tip belongs to; used for the accessibility label. */
   title: string;
   info: ReactNode;
+  /** Defaults to the info icon. */
+  icon?: TipIconComponent;
+  /** Defaults to "About {title}". */
+  accessibilityLabel?: string;
   testID?: string;
 }
 
 /**
  * The one way a settings group or section explains itself: an info icon on the
  * header that opens a tooltip. Never a paragraph under the header — see
- * docs/design.md §7.
+ * docs/design.md §7. Rows use it the same way to keep secondary details on one line.
  */
-export function SettingsInfoTip({ title, info, testID }: SettingsInfoTipProps) {
+export function SettingsInfoTip({
+  title,
+  info,
+  icon = Info,
+  accessibilityLabel,
+  testID,
+}: SettingsInfoTipProps) {
   const { t } = useTranslation();
   return (
     <Tooltip delayDuration={0} enabledOnDesktop enabledOnMobile>
       <TooltipTrigger asChild>
         <Pressable
           accessibilityRole="button"
-          accessibilityLabel={t("settings.groupInfo", { title })}
+          accessibilityLabel={accessibilityLabel ?? t("settings.groupInfo", { title })}
           testID={testID}
           hitSlop={8}
           style={styles.button}
         >
-          <ThemedInfo size={ICON_SIZE.sm} uniProps={mutedIconMapping} />
+          <ThemedTipIcon icon={icon} uniProps={mutedIconMapping} />
         </Pressable>
       </TooltipTrigger>
       <TooltipContent side="top" align="start" offset={8}>

packages/app/src/components/settings/index.tsx

@@ -24,9 +24,12 @@ import { DropdownMenu, DropdownMenuContent, DropdownMenuItem } from "@/component
 import { DropdownTrigger } from "@/components/ui/dropdown-trigger";
 import { useIsCompactFormFactor } from "@/constants/layout";
 import { settingsStyles } from "@/styles/settings";
+import { ControlSizeProvider } from "@/components/ui/control-size";
+import { useSettingsRowLayout } from "./row-density";
 export { SettingsGroup } from "./headings/settings-group";
 export { SettingsSection } from "./headings/settings-section";
 export { SettingsCollapsibleRow } from "./collapsible-row";
+export { SettingsInfoTip } from "./headings/settings-info-tip";
 
 interface AppSettingsRowProps extends Omit<SettingsRowProps, "hint"> {
   hint?: ReactNode;
@@ -57,26 +60,32 @@ export function SettingsRow({
   testID,
 }: AppSettingsRowProps) {
   const compact = useIsCompactFormFactor();
-  const rowStyle = useMemo(() => [settingsStyles.row, compact && styles.compactRow], [compact]);
+  const layout = useSettingsRowLayout();
+  const rowStyle = useMemo(() => [layout.row, compact && styles.compactRow], [compact, layout]);
+  const accessoryTitleStyle = useMemo(() => [layout.title, styles.accessoryLabel], [layout]);
   return (
     <View style={rowStyle} testID={testID}>
       <View style={styles.label}>
         {labelAccessory ? (
           <View style={styles.labelRow}>
-            <Text style={[settingsStyles.rowTitle, styles.accessoryLabel]}>{label}</Text>
+            <Text style={accessoryTitleStyle}>{label}</Text>
             {labelAccessory}
           </View>
         ) : (
-          <Text style={settingsStyles.rowTitle}>{label}</Text>
+          <Text style={layout.title}>{label}</Text>
         )}
-        {typeof hint === "string" ? <Text style={settingsStyles.rowHint}>{hint}</Text> : hint}
+        {typeof hint === "string" ? <Text style={layout.hint}>{hint}</Text> : hint}
         {error ? (
           <Text accessibilityRole="alert" style={settingsStyles.rowError}>
             {error}
           </Text>
         ) : null}
       </View>
-      {children ? <View style={styles.control}>{children}</View> : null}
+      {children ? (
+        <View style={styles.control}>
+          <ControlSizeProvider size={layout.controlSize}>{children}</ControlSizeProvider>
+        </View>
+      ) : null}
     </View>
   );
 }
@@ -175,7 +184,7 @@ export function SettingsInput({
         editable={!disabled}
         secureTextEntry={secureTextEntry}
         accessibilityLabel={row.label}
-        size={compact ? "md" : "sm"}
+        size={compact ? "md" : undefined}
         style={styles.input}
       />
     </SettingsRow>
@@ -185,7 +194,7 @@ export function SettingsInput({
 export function SettingsAction({ actionLabel, onPress, disabled, ...row }: SettingsActionProps) {
   return (
     <SettingsRow {...row}>
-      <Button variant="outline" size="sm" onPress={onPress} disabled={disabled}>
+      <Button variant="outline" onPress={onPress} disabled={disabled}>
         {actionLabel}
       </Button>
     </SettingsRow>

packages/app/src/components/settings/row-density.browser.test.tsx

@@ -0,0 +1,77 @@
+import React, { act } from "react";
+import { createRoot, type Root } from "react-dom/client";
+import { afterEach, describe, expect, it } from "vitest";
+import { Button } from "@/components/ui/button";
+import { SettingsCard, SettingsCollapsibleRow, SettingsRow } from "@/components/settings";
+
+let root: Root | null = null;
+let container: HTMLDivElement | null = null;
+
+afterEach(() => {
+  act(() => root?.unmount());
+  container?.remove();
+  root = null;
+  container = null;
+});
+
+function mountRows() {
+  container = document.createElement("div");
+  document.body.appendChild(container);
+  root = createRoot(container);
+  act(() =>
+    root?.render(
+      <SettingsCard>
+        <SettingsRow label="Card row" testID="card-row">
+          <Button variant="outline" testID="card-button">
+            Download
+          </Button>
+        </SettingsRow>
+        <SettingsCollapsibleRow label="Group" defaultExpanded testID="group">
+          <SettingsRow label="Nested with a button" testID="nested-with-button">
+            <Button variant="outline" testID="nested-button">
+              Download
+            </Button>
+          </SettingsRow>
+          <SettingsRow label="Nested without a button" testID="nested-without-button" />
+        </SettingsCollapsibleRow>
+      </SettingsCard>,
+    ),
+  );
+}
+
+function element(testID: string): HTMLElement {
+  const found = document.querySelector(`[data-testid="${testID}"]`);
+  if (!(found instanceof HTMLElement)) throw new Error(`Nothing rendered as ${testID}`);
+  return found;
+}
+
+function heightOf(testID: string): number {
+  return element(testID).getBoundingClientRect().height;
+}
+
+function titleFontSize(rowTestID: string, label: string): number {
+  const title = [...element(rowTestID).querySelectorAll("div")].find(
+    (node) => node.textContent === label && node.children.length === 0,
+  );
+  if (!title) throw new Error(`No title ${label}`);
+  return Number.parseFloat(getComputedStyle(title).fontSize);
+}
+
+describe("settings row density", () => {
+  it("lines up nested rows with and without a button, tighter than card rows", () => {
+    mountRows();
+
+    expect(heightOf("nested-with-button")).toBe(heightOf("nested-without-button"));
+    expect(heightOf("nested-with-button")).toBeLessThan(heightOf("card-row"));
+    expect(heightOf("group-toggle")).toBeGreaterThan(heightOf("nested-without-button"));
+  });
+
+  it("sizes nested text and controls one step below card rows", () => {
+    mountRows();
+
+    expect(heightOf("nested-button")).toBeLessThan(heightOf("card-button"));
+    expect(titleFontSize("nested-with-button", "Nested with a button")).toBeLessThan(
+      titleFontSize("card-row", "Card row"),
+    );
+  });
+});

packages/app/src/components/settings/row-density.tsx

@@ -0,0 +1,57 @@
+import { createContext, useContext, useMemo, type ReactNode } from "react";
+import type { StyleProp, TextStyle, ViewStyle } from "react-native";
+import { StyleSheet } from "react-native-unistyles";
+import { CONTROL_HEIGHTS } from "@/components/ui/control-geometry";
+import type { ContainedControlSize } from "@/components/ui/control-size";
+import { settingsStyles } from "@/styles/settings";
+
+// Rows revealed under a collapsible row belong to it, so they sit one step smaller than the rows
+// of the card: tighter padding, smaller text, smaller controls. The container decides; a row
+// never knows on its own that it is nested.
+const NestedRowsContext = createContext(false);
+
+export function NestedSettingsRows({ children }: { children: ReactNode }) {
+  return <NestedRowsContext.Provider value>{children}</NestedRowsContext.Provider>;
+}
+
+export interface SettingsRowLayout {
+  row: StyleProp<ViewStyle>;
+  title: StyleProp<TextStyle>;
+  hint: StyleProp<TextStyle>;
+  /** The size of the controls in the row's trailing slot. */
+  controlSize: ContainedControlSize;
+}
+
+/** How a row lays out where it is rendered: in a card, or nested under a collapsible row. */
+export function useSettingsRowLayout(): SettingsRowLayout {
+  const nested = useContext(NestedRowsContext);
+  return useMemo(
+    () =>
+      nested
+        ? {
+            row: [settingsStyles.row, styles.nestedRow],
+            title: [settingsStyles.rowTitle, styles.nestedText],
+            hint: [settingsStyles.rowHint, styles.nestedText],
+            controlSize: "xs",
+          }
+        : {
+            row: settingsStyles.row,
+            title: settingsStyles.rowTitle,
+            hint: settingsStyles.rowHint,
+            controlSize: "sm",
+          },
+    [nested],
+  );
+}
+
+const styles = StyleSheet.create((theme) => ({
+  // Every nested row is as tall as one holding an `xs` control, so rows with and without a
+  // trailing button line up.
+  nestedRow: {
+    paddingVertical: theme.spacing[2],
+    minHeight: CONTROL_HEIGHTS.tight + theme.spacing[2] * 2,
+  },
+  nestedText: {
+    fontSize: theme.fontSize.sm,
+  },
+}));

packages/app/src/components/tool-call-details.tsx

@@ -14,7 +14,7 @@ import type { ToolCallDetail } from "@getpaseo/protocol/agent-types";
 import {
   buildPaseoToolDetailSections,
   type PaseoToolDetailSection,
-} from "@getpaseo/protocol/paseo-tool-call-detail";
+} from "@getpaseo/protocol/paseo-tool-presentation/index";
 import { buildLineDiff, parseUnifiedDiff, type DiffLine } from "@/utils/tool-call-parsers";
 import { highlightDiffLines } from "@/utils/diff-highlight";
 import { hasMeaningfulToolCallDetail } from "@/utils/tool-call-detail-state";

packages/app/src/components/ui/button.tsx

@@ -1,4 +1,5 @@
 import { LoadingSpinner } from "@/components/ui/loading-spinner";
+import { useContainedControlSize } from "@/components/ui/control-size";
 import {
   default as React,
   useCallback,
@@ -162,7 +163,7 @@ const styles = StyleSheet.create((theme) => {
 export function Button({
   children,
   variant = "secondary",
-  size = "md",
+  size: sizeProp,
   leftIcon,
   trailing,
   style,
@@ -185,6 +186,8 @@ export function Button({
   }
 >) {
   const [hovered, setHovered] = useState(false);
+  const containedSize = useContainedControlSize();
+  const size = sizeProp ?? containedSize ?? "md";
   const isDisabled = disabled || loading;
 
   let variantStyle: ViewStyle;

packages/app/src/components/ui/control-geometry.test.ts

@@ -81,6 +81,8 @@ describe("control geometry", () => {
   it("keeps field text sizing tied to control size", () => {
     const geometry = createControlGeometry(theme);
 
+    expect(geometry.fieldTextXs.fontSize).toBe(12);
+    expect(geometry.fieldTextXs.lineHeight).toBe(17);
     expect(geometry.fieldTextSm.fontSize).toBe(14);
     expect(geometry.fieldTextSm.lineHeight).toBe(20);
     expect(geometry.fieldTextMd.fontSize).toBe(14);
@@ -95,6 +97,13 @@ describe("control geometry", () => {
     const geometry = createControlGeometry(theme);
     const borderWidth = theme.borderWidth[1];
 
+    expect(geometry.fieldControlXs.minHeight).toBe(28);
+    expect(
+      geometry.fieldTextXs.lineHeight +
+        geometry.fieldControlXs.paddingVertical * 2 +
+        borderWidth * 2,
+    ).toBe(geometry.fieldControlXs.minHeight);
+
     expect(geometry.fieldControlSm.minHeight).toBe(32);
     expect(geometry.fieldControlSm.paddingVertical).toBe(5);
     expect(

packages/app/src/components/ui/control-geometry.ts

@@ -2,7 +2,7 @@ import type { StyleProp, ViewStyle } from "react-native";
 import { ICON_SIZE, type Theme } from "@/styles/theme";
 
 export type ButtonControlSize = "xs" | "sm" | "md" | "lg";
-export type FieldControlSize = "sm" | "md";
+export type FieldControlSize = "xs" | "sm" | "md";
 export type SegmentedControlSize = "xs" | "sm" | "md";
 export type ControlInteractionPhase = "rest" | "hover" | "active";
 
@@ -188,8 +188,19 @@ export function resolveControlInteractionStyles(
 
 export function createControlGeometry(theme: Theme) {
   const controlBorderWidth = theme.borderWidth[1];
+  const fieldTextXsLineHeight = fieldLineHeight(theme.fontSize.sm);
   const fieldTextSmLineHeight = fieldLineHeight(theme.fontSize.base);
   const fieldTextMdLineHeight = fieldLineHeight(theme.fontSize.base);
+  const fieldControlXs = {
+    minHeight: CONTROL_HEIGHTS.tight,
+    paddingHorizontal: theme.spacing[2],
+    paddingVertical: fieldVerticalPadding(
+      CONTROL_HEIGHTS.tight,
+      fieldTextXsLineHeight,
+      controlBorderWidth,
+    ),
+    borderRadius: theme.borderRadius.md,
+  };
   const fieldControlSm = {
     minHeight: CONTROL_HEIGHTS.compact,
     paddingHorizontal: theme.spacing[3],
@@ -210,6 +221,10 @@ export function createControlGeometry(theme: Theme) {
     ),
     borderRadius: theme.borderRadius.lg,
   };
+  const fieldTextXs = {
+    fontSize: theme.fontSize.sm,
+    lineHeight: fieldTextXsLineHeight,
+  };
   const fieldTextSm = {
     fontSize: theme.fontSize.base,
     lineHeight: fieldTextSmLineHeight,
@@ -252,6 +267,10 @@ export function createControlGeometry(theme: Theme) {
       fontSize: theme.fontSize.sm,
     },
     alert,
+    formTextInputXs: {
+      ...fieldControlXs,
+      ...fieldTextXs,
+    },
     formTextInputSm: {
       ...fieldControlSm,
       ...fieldTextSm,
@@ -264,8 +283,10 @@ export function createControlGeometry(theme: Theme) {
       ...fieldControlMd,
       ...fieldTextMd,
     },
+    fieldControlXs,
     fieldControlSm,
     fieldControlMd,
+    fieldTextXs,
     fieldTextSm,
     fieldTextMd,
     controlRest: {

packages/app/src/components/ui/control-size.tsx

@@ -0,0 +1,23 @@
+import { createContext, useContext, type ReactNode } from "react";
+
+/** The control sizes a container can ask of the controls placed in it. */
+export type ContainedControlSize = "xs" | "sm";
+
+// A row decides how big its controls are, so a button or field placed in it needs no size of
+// its own. A size passed to the control still wins.
+const ControlSizeContext = createContext<ContainedControlSize | null>(null);
+
+export function ControlSizeProvider({
+  size,
+  children,
+}: {
+  size: ContainedControlSize;
+  children: ReactNode;
+}) {
+  return <ControlSizeContext.Provider value={size}>{children}</ControlSizeContext.Provider>;
+}
+
+/** The size the surrounding container asks for, or null outside one. */
+export function useContainedControlSize(): ContainedControlSize | null {
+  return useContext(ControlSizeContext);
+}

packages/app/src/components/ui/dropdown-trigger.tsx

@@ -9,6 +9,7 @@ import {
 } from "@/components/ui/control-geometry";
 import type { Theme } from "@/styles/theme";
 import { DropdownMenuTrigger, type DropdownMenuTriggerProps } from "@/components/ui/dropdown-menu";
+import { useContainedControlSize } from "@/components/ui/control-size";
 
 const ThemedChevronDown = withUnistyles(ChevronDown);
 
@@ -32,10 +33,12 @@ interface DropdownTriggerProps extends Omit<DropdownMenuTriggerProps, "children"
 export function DropdownTrigger({
   children,
   leading,
-  size = "sm",
+  size: sizeProp,
   disabled,
   ...props
 }: DropdownTriggerProps): ReactElement {
+  const containedSize = useContainedControlSize();
+  const size = sizeProp ?? containedSize ?? "sm";
   let sizeStyle: ViewStyle;
   if (size === "xs") {
     sizeStyle = styles.xs;

packages/app/src/components/ui/form-field.tsx

@@ -23,6 +23,16 @@ import {
   resolveControlInteractionStyles,
   type FieldControlSize,
 } from "@/components/ui/control-geometry";
+import { useContainedControlSize } from "@/components/ui/control-size";
+
+const FIELD_CHROME = { xs: "chromeXs", sm: "chromeSm", md: "chromeMd" } as const satisfies Record<
+  FieldControlSize,
+  string
+>;
+const FIELD_TEXT = { xs: "inputXs", sm: "inputSm", md: "inputMd" } as const satisfies Record<
+  FieldControlSize,
+  string
+>;
 
 interface FieldProps {
   label: string;
@@ -159,11 +169,13 @@ function assignTextInputRef(
 }
 
 export const FormTextInput = forwardRef<EditingTextInputHandle, FormTextInputProps>(
-  function FormTextInput({ size = "md", style, onFocus, onBlur, editable, ...props }, ref) {
+  function FormTextInput({ size: sizeProp, style, onFocus, onBlur, editable, ...props }, ref) {
     const [focused, setFocused] = useState(false);
+    const containedSize = useContainedControlSize();
+    const size = sizeProp ?? containedSize ?? "md";
     const isDisabled = editable === false;
-    const chromeSizeStyle = size === "sm" ? formInputStyles.chromeSm : formInputStyles.chromeMd;
-    const inputSizeStyle = size === "sm" ? formInputStyles.inputSm : formInputStyles.inputMd;
+    const chromeSizeStyle = formInputStyles[FIELD_CHROME[size]];
+    const inputSizeStyle = formInputStyles[FIELD_TEXT[size]];
     const splitStyle = useMemo(() => splitFormTextInputStyle(style), [style]);
     const setInputRef = useCallback(
       (node: EditingTextInputHandle | null) => {
@@ -262,6 +274,9 @@ const formInputStyles = StyleSheet.create((theme) => {
     chrome: {
       backgroundColor: theme.colors.surface2,
     },
+    chromeXs: {
+      ...geometry.fieldControlXs,
+    },
     chromeSm: {
       ...geometry.fieldControlSm,
     },
@@ -289,6 +304,9 @@ const formInputStyles = StyleSheet.create((theme) => {
       outlineColor: "transparent",
       outlineWidth: 0,
     },
+    inputXs: {
+      ...geometry.fieldTextXs,
+    },
     inputSm: {
       ...geometry.fieldTextSm,
     },

packages/app/src/i18n/resources/ar.ts

@@ -2106,6 +2106,7 @@ export const ar: TranslationResources = {
       connections: "اتصالات",
       agents: "Agents",
       metadata: "البيانات الوصفية",
+      voice: "الصوت",
       workspaces: "Workspaces",
       providers: "مقدمي الخدمات",
       usage: "الاستخدام",
@@ -2128,6 +2129,75 @@ export const ar: TranslationResources = {
       docs: "الوثائق",
       saveError: "تعذر تحديث إنشاء البيانات الوصفية",
     },
+    voice: {
+      offline: "اتصل بهذا المضيف لضبط الصوت.",
+      updateHost: "حدّث المضيف لضبط الصوت.",
+      saveError: "تعذّر تحديث إعدادات الصوت",
+      provider: "المزوّد",
+      providers: {
+        local: "محلي",
+        openai: "OpenAI",
+      },
+      sttModel: "نموذج تحويل الكلام إلى نص",
+      ttsModel: "نموذج الصوت",
+      voice: "الصوت",
+      notDownloadedOption: "{{label}} (غير منزّل)",
+      save: "حفظ",
+      retry: "إعادة المحاولة",
+      dictation: {
+        title: "الإملاء",
+        enabled: "الإملاء",
+        enabledHint: "تحدّث في مربع الرسالة بدلًا من الكتابة",
+      },
+      voiceMode: {
+        title: "وضع الصوت",
+        info: "يحوّل وضع الصوت كلامك إلى نص ويقرأ ردود الوكيل بصوت عالٍ.",
+        enabled: "وضع الصوت",
+        enabledHint: "تحدّث مع وكلائك دون استخدام يديك",
+        sttProvider: "تحويل الكلام إلى نص",
+        ttsProvider: "تحويل النص إلى كلام",
+      },
+      openai: {
+        apiKey: "مفتاح API",
+        apiKeyHint: "يُحفظ على المضيف ولا يُعرض مرة أخرى.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "مفتاح جديد",
+        removeKey: "إزالة",
+        removeKeyTitle: "إزالة مفتاح OpenAI؟",
+        removeKeyMessage: "ستتوقف الميزات المضبوطة على OpenAI عن العمل حتى تضيف مفتاحًا.",
+        baseUrl: "عنوان URL الأساسي",
+        baseUrlHint: "للخوادم المتوافقة مع OpenAI. اتركه فارغًا لاستخدام OpenAI.",
+        missingKeyWarning: "تم اختيار OpenAI لكن لم يُضبط مفتاح API.",
+      },
+      models: {
+        loading: "جارٍ تحميل النماذج...",
+        loadError: "تعذّر تحميل النماذج المحلية",
+        downloaded: "منزّل",
+        inUse: "قيد الاستخدام",
+        recommended: "موصى به",
+        download: "تنزيل",
+        downloading: "جارٍ التنزيل...",
+        downloadingPercent: "جارٍ التنزيل {{percent}}%",
+        extracting: "جارٍ الاستخراج...",
+        delete: "حذف",
+        deleteAction: "حذف {{label}}",
+        deleteTitle: "حذف {{label}}؟",
+        deleteMessage: "سيؤدي هذا إلى تحرير {{size}}. يمكنك تنزيله مرة أخرى لاحقًا.",
+        languages: "لغات {{label}}",
+        moreLanguages: "{{languages}} و{{count}} أخرى",
+      },
+      providerSettings: {
+        title: "المزوّدون",
+        info: "النماذج وبيانات الاعتماد لكل مزوّد. تعمل النماذج المحلية على هذا المضيف وتعرض حجمها ولغاتها قبل التنزيل.",
+        localStt: "تحويل الكلام إلى نص محليًا",
+        localTts: "تحويل النص إلى كلام محليًا",
+        openai: "OpenAI",
+        downloaded_one: "تم تنزيل {{count}} نموذج",
+        downloaded_other: "تم تنزيل {{count}} نماذج",
+        configured: "تم الإعداد",
+        notConfigured: "غير مُعد",
+      },
+    },
     general: {
       title: "عام",
       sending: "الإرسال",

packages/app/src/i18n/resources/en.ts

@@ -2169,6 +2169,7 @@ export const en = {
       connections: "Connections",
       agents: "Agents",
       metadata: "Metadata",
+      voice: "Voice",
       workspaces: "Workspaces",
       providers: "Providers",
       usage: "Usage",
@@ -2253,6 +2254,75 @@ export const en = {
       docs: "Docs",
       saveError: "Unable to update metadata generation",
     },
+    voice: {
+      offline: "Connect to this host to configure voice.",
+      updateHost: "Update the host to configure voice.",
+      saveError: "Unable to update voice settings",
+      provider: "Provider",
+      providers: {
+        local: "Local",
+        openai: "OpenAI",
+      },
+      sttModel: "Speech-to-text model",
+      ttsModel: "Voice model",
+      voice: "Voice",
+      notDownloadedOption: "{{label}} (not downloaded)",
+      save: "Save",
+      retry: "Retry",
+      dictation: {
+        title: "Dictation",
+        enabled: "Dictation",
+        enabledHint: "Speak into the message box instead of typing",
+      },
+      voiceMode: {
+        title: "Voice mode",
+        info: "Voice mode transcribes what you say and reads agent replies aloud.",
+        enabled: "Voice mode",
+        enabledHint: "Talk with your agents hands-free",
+        sttProvider: "Speech-to-text",
+        ttsProvider: "Text-to-speech",
+      },
+      openai: {
+        apiKey: "API key",
+        apiKeyHint: "Saved on the host and never shown again.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "New key",
+        removeKey: "Remove",
+        removeKeyTitle: "Remove the OpenAI API key?",
+        removeKeyMessage: "Features set to OpenAI stop working until you add a key.",
+        baseUrl: "Base URL",
+        baseUrlHint: "For OpenAI-compatible servers. Leave empty to use OpenAI.",
+        missingKeyWarning: "OpenAI is selected but no API key is set.",
+      },
+      models: {
+        loading: "Loading models...",
+        loadError: "Couldn't load local models",
+        downloaded: "Downloaded",
+        inUse: "In use",
+        recommended: "Recommended",
+        download: "Download",
+        downloading: "Downloading...",
+        downloadingPercent: "Downloading {{percent}}%",
+        extracting: "Extracting...",
+        delete: "Delete",
+        deleteAction: "Delete {{label}}",
+        deleteTitle: "Delete {{label}}?",
+        deleteMessage: "This frees {{size}}. You can download it again later.",
+        languages: "{{label}} languages",
+        moreLanguages: "{{languages}} and {{count}} more",
+      },
+      providerSettings: {
+        title: "Providers",
+        info: "Models and credentials for each provider. Local models run on this host and list their size and languages before you download.",
+        localStt: "Local speech-to-text",
+        localTts: "Local text-to-speech",
+        openai: "OpenAI",
+        downloaded_one: "{{count}} model downloaded",
+        downloaded_other: "{{count}} models downloaded",
+        configured: "Configured",
+        notConfigured: "Not configured",
+      },
+    },
     general: {
       title: "General",
       sending: "Sending",

packages/app/src/i18n/resources/es.ts

@@ -2154,6 +2154,7 @@ export const es: TranslationResources = {
       connections: "Conexiones",
       agents: "Agents",
       metadata: "Metadatos",
+      voice: "Voz",
       workspaces: "Workspaces",
       providers: "Proveedores",
       usage: "Uso",
@@ -2176,6 +2177,77 @@ export const es: TranslationResources = {
       docs: "Documentación",
       saveError: "No se pudo actualizar la generación de metadatos",
     },
+    voice: {
+      offline: "Conéctate a este host para configurar la voz.",
+      updateHost: "Actualiza el host para configurar la voz.",
+      saveError: "No se pudo actualizar la configuración de voz",
+      provider: "Proveedor",
+      providers: {
+        local: "Local",
+        openai: "OpenAI",
+      },
+      sttModel: "Modelo de voz a texto",
+      ttsModel: "Modelo de voz",
+      voice: "Voz",
+      notDownloadedOption: "{{label}} (sin descargar)",
+      save: "Guardar",
+      retry: "Reintentar",
+      dictation: {
+        title: "Dictado",
+        enabled: "Dictado",
+        enabledHint: "Habla en el cuadro de mensaje en lugar de escribir",
+      },
+      voiceMode: {
+        title: "Modo de voz",
+        info: "El modo de voz transcribe lo que dices y lee en voz alta las respuestas del agente.",
+        enabled: "Modo de voz",
+        enabledHint: "Habla con tus agentes sin usar las manos",
+        sttProvider: "Voz a texto",
+        ttsProvider: "Texto a voz",
+      },
+      openai: {
+        apiKey: "Clave de API",
+        apiKeyHint: "Se guarda en el host y no se vuelve a mostrar.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "Nueva clave",
+        removeKey: "Quitar",
+        removeKeyTitle: "¿Quitar la clave de API de OpenAI?",
+        removeKeyMessage:
+          "Las funciones configuradas con OpenAI dejarán de funcionar hasta que añadas una clave.",
+        baseUrl: "URL base",
+        baseUrlHint: "Para servidores compatibles con OpenAI. Déjala vacía para usar OpenAI.",
+        missingKeyWarning:
+          "OpenAI está seleccionado, pero no hay ninguna clave de API configurada.",
+      },
+      models: {
+        loading: "Cargando modelos...",
+        loadError: "No se pudieron cargar los modelos locales",
+        downloaded: "Descargado",
+        inUse: "En uso",
+        recommended: "Recomendado",
+        download: "Descargar",
+        downloading: "Descargando...",
+        downloadingPercent: "Descargando {{percent}} %",
+        extracting: "Extrayendo...",
+        delete: "Eliminar",
+        deleteAction: "Eliminar {{label}}",
+        deleteTitle: "¿Eliminar {{label}}?",
+        deleteMessage: "Esto libera {{size}}. Puedes volver a descargarlo más tarde.",
+        languages: "Idiomas de {{label}}",
+        moreLanguages: "{{languages}} y {{count}} más",
+      },
+      providerSettings: {
+        title: "Proveedores",
+        info: "Modelos y credenciales de cada proveedor. Los modelos locales se ejecutan en este host e indican su tamaño e idiomas antes de descargarlos.",
+        localStt: "Voz a texto local",
+        localTts: "Texto a voz local",
+        openai: "OpenAI",
+        downloaded_one: "{{count}} modelo descargado",
+        downloaded_other: "{{count}} modelos descargados",
+        configured: "Configurado",
+        notConfigured: "Sin configurar",
+      },
+    },
     general: {
       title: "General",
       sending: "Envío",

packages/app/src/i18n/resources/fr.ts

@@ -2153,6 +2153,7 @@ export const fr: TranslationResources = {
       connections: "Connexions",
       agents: "Agents",
       metadata: "Métadonnées",
+      voice: "Voix",
       workspaces: "Espaces de travail",
       providers: "Fournisseurs",
       usage: "Utilisation",
@@ -2175,6 +2176,76 @@ export const fr: TranslationResources = {
       docs: "Documentation",
       saveError: "Impossible de mettre à jour la génération de métadonnées",
     },
+    voice: {
+      offline: "Connectez-vous à cet hôte pour configurer la voix.",
+      updateHost: "Mettez à jour l'hôte pour configurer la voix.",
+      saveError: "Impossible de mettre à jour les réglages vocaux",
+      provider: "Fournisseur",
+      providers: {
+        local: "Local",
+        openai: "OpenAI",
+      },
+      sttModel: "Modèle de transcription",
+      ttsModel: "Modèle de voix",
+      voice: "Voix",
+      notDownloadedOption: "{{label}} (non téléchargé)",
+      save: "Enregistrer",
+      retry: "Réessayer",
+      dictation: {
+        title: "Dictée",
+        enabled: "Dictée",
+        enabledHint: "Parlez dans la zone de message au lieu de taper",
+      },
+      voiceMode: {
+        title: "Mode vocal",
+        info: "Le mode vocal transcrit ce que vous dites et lit à voix haute les réponses de l'agent.",
+        enabled: "Mode vocal",
+        enabledHint: "Parlez à vos agents sans les mains",
+        sttProvider: "Transcription",
+        ttsProvider: "Synthèse vocale",
+      },
+      openai: {
+        apiKey: "Clé d'API",
+        apiKeyHint: "Enregistrée sur l'hôte, jamais réaffichée.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "Nouvelle clé",
+        removeKey: "Supprimer",
+        removeKeyTitle: "Supprimer la clé d'API OpenAI ?",
+        removeKeyMessage:
+          "Les fonctions réglées sur OpenAI cesseront de fonctionner jusqu'à l'ajout d'une clé.",
+        baseUrl: "URL de base",
+        baseUrlHint: "Pour les serveurs compatibles OpenAI. Laissez vide pour utiliser OpenAI.",
+        missingKeyWarning: "OpenAI est sélectionné, mais aucune clé d'API n'est définie.",
+      },
+      models: {
+        loading: "Chargement des modèles...",
+        loadError: "Impossible de charger les modèles locaux",
+        downloaded: "Téléchargé",
+        inUse: "Utilisé",
+        recommended: "Recommandé",
+        download: "Télécharger",
+        downloading: "Téléchargement...",
+        downloadingPercent: "Téléchargement {{percent}} %",
+        extracting: "Extraction...",
+        delete: "Supprimer",
+        deleteAction: "Supprimer {{label}}",
+        deleteTitle: "Supprimer {{label}} ?",
+        deleteMessage: "Cela libère {{size}}. Vous pourrez le retélécharger plus tard.",
+        languages: "Langues de {{label}}",
+        moreLanguages: "{{languages}} et {{count}} autres",
+      },
+      providerSettings: {
+        title: "Fournisseurs",
+        info: "Modèles et identifiants de chaque fournisseur. Les modèles locaux s'exécutent sur cet hôte et indiquent leur taille et leurs langues avant le téléchargement.",
+        localStt: "Reconnaissance vocale locale",
+        localTts: "Synthèse vocale locale",
+        openai: "OpenAI",
+        downloaded_one: "{{count}} modèle téléchargé",
+        downloaded_other: "{{count}} modèles téléchargés",
+        configured: "Configuré",
+        notConfigured: "Non configuré",
+      },
+    },
     general: {
       title: "Général",
       sending: "Envoi",

packages/app/src/i18n/resources/ja.ts

@@ -2127,6 +2127,7 @@ export const ja: TranslationResources = {
       connections: "接続",
       agents: "エージェント",
       metadata: "メタデータ",
+      voice: "音声",
       workspaces: "ワークスペース",
       providers: "プロバイダー",
       usage: "使用状況",
@@ -2149,6 +2150,75 @@ export const ja: TranslationResources = {
       docs: "ドキュメント",
       saveError: "メタデータ生成を更新できません",
     },
+    voice: {
+      offline: "音声を設定するには、このホストに接続してください。",
+      updateHost: "音声を設定するには、ホストを更新してください。",
+      saveError: "音声設定を更新できませんでした",
+      provider: "プロバイダー",
+      providers: {
+        local: "ローカル",
+        openai: "OpenAI",
+      },
+      sttModel: "音声認識モデル",
+      ttsModel: "音声モデル",
+      voice: "ボイス",
+      notDownloadedOption: "{{label}}（未ダウンロード）",
+      save: "保存",
+      retry: "再試行",
+      dictation: {
+        title: "音声入力",
+        enabled: "音声入力",
+        enabledHint: "入力する代わりにメッセージ欄に話しかけます",
+      },
+      voiceMode: {
+        title: "ボイスモード",
+        info: "ボイスモードは話した内容を文字起こしし、エージェントの返答を読み上げます。",
+        enabled: "ボイスモード",
+        enabledHint: "ハンズフリーでエージェントと会話します",
+        sttProvider: "音声認識",
+        ttsProvider: "音声合成",
+      },
+      openai: {
+        apiKey: "API キー",
+        apiKeyHint: "ホストに保存され、再表示されません。",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "新しいキー",
+        removeKey: "削除",
+        removeKeyTitle: "OpenAI API キーを削除しますか？",
+        removeKeyMessage: "キーを追加するまで、OpenAI に設定された機能は動作しません。",
+        baseUrl: "ベース URL",
+        baseUrlHint: "OpenAI 互換サーバー用です。OpenAI を使う場合は空欄のままにします。",
+        missingKeyWarning: "OpenAI が選択されていますが、API キーが設定されていません。",
+      },
+      models: {
+        loading: "モデルを読み込み中...",
+        loadError: "ローカルモデルを読み込めませんでした",
+        downloaded: "ダウンロード済み",
+        inUse: "使用中",
+        recommended: "おすすめ",
+        download: "ダウンロード",
+        downloading: "ダウンロード中...",
+        downloadingPercent: "ダウンロード中 {{percent}}%",
+        extracting: "展開中...",
+        delete: "削除",
+        deleteAction: "{{label}} を削除",
+        deleteTitle: "{{label}} を削除しますか？",
+        deleteMessage: "{{size}} が解放されます。後で再ダウンロードできます。",
+        languages: "{{label}} の対応言語",
+        moreLanguages: "{{languages}} ほか {{count}} 言語",
+      },
+      providerSettings: {
+        title: "プロバイダー",
+        info: "各プロバイダーのモデルと認証情報です。ローカルモデルはこのホストで動作し、ダウンロード前にサイズと対応言語を確認できます。",
+        localStt: "ローカル音声認識",
+        localTts: "ローカル音声合成",
+        openai: "OpenAI",
+        downloaded_one: "{{count}} 個のモデルをダウンロード済み",
+        downloaded_other: "{{count}} 個のモデルをダウンロード済み",
+        configured: "設定済み",
+        notConfigured: "未設定",
+      },
+    },
     general: {
       title: "一般",
       sending: "送信",

packages/app/src/i18n/resources/ko.ts

@@ -2116,6 +2116,7 @@ export const ko: TranslationResources = {
       connections: "연결",
       agents: "에이전트",
       metadata: "메타데이터",
+      voice: "음성",
       workspaces: "워크스페이스",
       providers: "프로바이더",
       usage: "사용량",
@@ -2138,6 +2139,75 @@ export const ko: TranslationResources = {
       docs: "문서",
       saveError: "메타데이터 생성을 업데이트할 수 없습니다",
     },
+    voice: {
+      offline: "음성을 설정하려면 이 호스트에 연결하세요.",
+      updateHost: "음성을 설정하려면 호스트를 업데이트하세요.",
+      saveError: "음성 설정을 업데이트할 수 없습니다",
+      provider: "제공자",
+      providers: {
+        local: "로컬",
+        openai: "OpenAI",
+      },
+      sttModel: "음성 인식 모델",
+      ttsModel: "음성 모델",
+      voice: "목소리",
+      notDownloadedOption: "{{label}} (다운로드 안 됨)",
+      save: "저장",
+      retry: "다시 시도",
+      dictation: {
+        title: "받아쓰기",
+        enabled: "받아쓰기",
+        enabledHint: "입력하는 대신 메시지 상자에 말하세요",
+      },
+      voiceMode: {
+        title: "음성 모드",
+        info: "음성 모드는 말한 내용을 텍스트로 옮기고 에이전트의 답변을 소리 내어 읽어 줍니다.",
+        enabled: "음성 모드",
+        enabledHint: "손을 쓰지 않고 에이전트와 대화하세요",
+        sttProvider: "음성 인식",
+        ttsProvider: "음성 합성",
+      },
+      openai: {
+        apiKey: "API 키",
+        apiKeyHint: "호스트에 저장되며 다시 표시되지 않습니다.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "새 키",
+        removeKey: "제거",
+        removeKeyTitle: "OpenAI API 키를 제거할까요?",
+        removeKeyMessage: "키를 추가할 때까지 OpenAI로 설정된 기능이 작동하지 않습니다.",
+        baseUrl: "기본 URL",
+        baseUrlHint: "OpenAI 호환 서버용입니다. OpenAI를 사용하려면 비워 두세요.",
+        missingKeyWarning: "OpenAI가 선택되었지만 API 키가 설정되지 않았습니다.",
+      },
+      models: {
+        loading: "모델을 불러오는 중...",
+        loadError: "로컬 모델을 불러올 수 없습니다",
+        downloaded: "다운로드됨",
+        inUse: "사용 중",
+        recommended: "추천",
+        download: "다운로드",
+        downloading: "다운로드 중...",
+        downloadingPercent: "다운로드 중 {{percent}}%",
+        extracting: "압축 해제 중...",
+        delete: "삭제",
+        deleteAction: "{{label}} 삭제",
+        deleteTitle: "{{label}}을(를) 삭제할까요?",
+        deleteMessage: "{{size}}가 확보됩니다. 나중에 다시 다운로드할 수 있습니다.",
+        languages: "{{label}} 지원 언어",
+        moreLanguages: "{{languages}} 외 {{count}}개",
+      },
+      providerSettings: {
+        title: "제공자",
+        info: "제공자별 모델과 자격 증명입니다. 로컬 모델은 이 호스트에서 실행되며 다운로드 전에 크기와 지원 언어를 보여줍니다.",
+        localStt: "로컬 음성 인식",
+        localTts: "로컬 음성 합성",
+        openai: "OpenAI",
+        downloaded_one: "모델 {{count}}개 다운로드됨",
+        downloaded_other: "모델 {{count}}개 다운로드됨",
+        configured: "설정됨",
+        notConfigured: "설정 안 됨",
+      },
+    },
     general: {
       title: "일반",
       sending: "전송",

packages/app/src/i18n/resources/pt-BR.ts

@@ -2139,6 +2139,7 @@ export const ptBR: TranslationResources = {
       connections: "Conexões",
       agents: "Agentes",
       metadata: "Metadados",
+      voice: "Voz",
       workspaces: "Workspaces",
       providers: "Provedores",
       usage: "Uso",
@@ -2161,6 +2162,76 @@ export const ptBR: TranslationResources = {
       docs: "Documentação",
       saveError: "Não foi possível atualizar a geração de metadados",
     },
+    voice: {
+      offline: "Conecte-se a este host para configurar a voz.",
+      updateHost: "Atualize o host para configurar a voz.",
+      saveError: "Não foi possível atualizar as configurações de voz",
+      provider: "Provedor",
+      providers: {
+        local: "Local",
+        openai: "OpenAI",
+      },
+      sttModel: "Modelo de fala para texto",
+      ttsModel: "Modelo de voz",
+      voice: "Voz",
+      notDownloadedOption: "{{label}} (não baixado)",
+      save: "Salvar",
+      retry: "Tentar novamente",
+      dictation: {
+        title: "Ditado",
+        enabled: "Ditado",
+        enabledHint: "Fale na caixa de mensagem em vez de digitar",
+      },
+      voiceMode: {
+        title: "Modo de voz",
+        info: "O modo de voz transcreve o que você diz e lê em voz alta as respostas do agente.",
+        enabled: "Modo de voz",
+        enabledHint: "Converse com seus agentes sem usar as mãos",
+        sttProvider: "Fala para texto",
+        ttsProvider: "Texto para fala",
+      },
+      openai: {
+        apiKey: "Chave de API",
+        apiKeyHint: "Salva no host e nunca mostrada novamente.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "Nova chave",
+        removeKey: "Remover",
+        removeKeyTitle: "Remover a chave de API da OpenAI?",
+        removeKeyMessage:
+          "Os recursos configurados com a OpenAI param de funcionar até você adicionar uma chave.",
+        baseUrl: "URL base",
+        baseUrlHint: "Para servidores compatíveis com a OpenAI. Deixe vazio para usar a OpenAI.",
+        missingKeyWarning: "A OpenAI está selecionada, mas nenhuma chave de API foi definida.",
+      },
+      models: {
+        loading: "Carregando modelos...",
+        loadError: "Não foi possível carregar os modelos locais",
+        downloaded: "Baixado",
+        inUse: "Em uso",
+        recommended: "Recomendado",
+        download: "Baixar",
+        downloading: "Baixando...",
+        downloadingPercent: "Baixando {{percent}}%",
+        extracting: "Extraindo...",
+        delete: "Excluir",
+        deleteAction: "Excluir {{label}}",
+        deleteTitle: "Excluir {{label}}?",
+        deleteMessage: "Isso libera {{size}}. Você pode baixá-lo de novo depois.",
+        languages: "Idiomas do {{label}}",
+        moreLanguages: "{{languages}} e mais {{count}}",
+      },
+      providerSettings: {
+        title: "Provedores",
+        info: "Modelos e credenciais de cada provedor. Os modelos locais rodam neste host e mostram tamanho e idiomas antes do download.",
+        localStt: "Fala para texto local",
+        localTts: "Texto para fala local",
+        openai: "OpenAI",
+        downloaded_one: "{{count}} modelo baixado",
+        downloaded_other: "{{count}} modelos baixados",
+        configured: "Configurado",
+        notConfigured: "Não configurado",
+      },
+    },
     general: {
       title: "Geral",
       sending: "Envio",

packages/app/src/i18n/resources/ru.ts

@@ -2139,6 +2139,7 @@ export const ru: TranslationResources = {
       connections: "Подключения",
       agents: "Агенты",
       metadata: "Метаданные",
+      voice: "Голос",
       workspaces: "Рабочие пространства",
       providers: "Провайдеры",
       usage: "Использование",
@@ -2161,6 +2162,77 @@ export const ru: TranslationResources = {
       docs: "Документация",
       saveError: "Не удалось обновить настройки генерации метаданных",
     },
+    voice: {
+      offline: "Подключитесь к этому хосту, чтобы настроить голос.",
+      updateHost: "Обновите хост, чтобы настроить голос.",
+      saveError: "Не удалось обновить голосовые настройки",
+      provider: "Провайдер",
+      providers: {
+        local: "Локально",
+        openai: "OpenAI",
+      },
+      sttModel: "Модель распознавания речи",
+      ttsModel: "Модель голоса",
+      voice: "Голос",
+      notDownloadedOption: "{{label}} (не скачана)",
+      save: "Сохранить",
+      retry: "Повторить",
+      dictation: {
+        title: "Диктовка",
+        enabled: "Диктовка",
+        enabledHint: "Говорите в поле сообщения вместо набора текста",
+      },
+      voiceMode: {
+        title: "Голосовой режим",
+        info: "Голосовой режим расшифровывает вашу речь и зачитывает ответы агента вслух.",
+        enabled: "Голосовой режим",
+        enabledHint: "Общайтесь с агентами без рук",
+        sttProvider: "Распознавание речи",
+        ttsProvider: "Синтез речи",
+      },
+      openai: {
+        apiKey: "API-ключ",
+        apiKeyHint: "Хранится на хосте и больше не показывается.",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "Новый ключ",
+        removeKey: "Удалить",
+        removeKeyTitle: "Удалить API-ключ OpenAI?",
+        removeKeyMessage:
+          "Функции, настроенные на OpenAI, перестанут работать, пока вы не добавите ключ.",
+        baseUrl: "Базовый URL",
+        baseUrlHint:
+          "Для серверов, совместимых с OpenAI. Оставьте пустым, чтобы использовать OpenAI.",
+        missingKeyWarning: "Выбран OpenAI, но API-ключ не задан.",
+      },
+      models: {
+        loading: "Загрузка моделей...",
+        loadError: "Не удалось загрузить локальные модели",
+        downloaded: "Скачана",
+        inUse: "Используется",
+        recommended: "Рекомендуется",
+        download: "Скачать",
+        downloading: "Скачивание...",
+        downloadingPercent: "Скачивание {{percent}}%",
+        extracting: "Распаковка...",
+        delete: "Удалить",
+        deleteAction: "Удалить {{label}}",
+        deleteTitle: "Удалить {{label}}?",
+        deleteMessage: "Освободится {{size}}. Позже её можно скачать снова.",
+        languages: "Языки {{label}}",
+        moreLanguages: "{{languages}} и ещё {{count}}",
+      },
+      providerSettings: {
+        title: "Провайдеры",
+        info: "Модели и учётные данные каждого провайдера. Локальные модели работают на этом хосте; размер и языки видны до загрузки.",
+        localStt: "Локальное распознавание речи",
+        localTts: "Локальный синтез речи",
+        openai: "OpenAI",
+        downloaded_one: "Загружено моделей: {{count}}",
+        downloaded_other: "Загружено моделей: {{count}}",
+        configured: "Настроено",
+        notConfigured: "Не настроено",
+      },
+    },
     general: {
       title: "Основные",
       sending: "Отправка",

packages/app/src/i18n/resources/zh-CN.ts

@@ -2084,6 +2084,7 @@ export const zhCN: TranslationResources = {
       connections: "连接",
       agents: "Agents",
       metadata: "元数据",
+      voice: "语音",
       workspaces: "Workspaces",
       providers: "Providers",
       usage: "使用情况",
@@ -2105,6 +2106,75 @@ export const zhCN: TranslationResources = {
       docs: "文档",
       saveError: "无法更新元数据生成设置",
     },
+    voice: {
+      offline: "连接到此主机以配置语音。",
+      updateHost: "请更新主机以配置语音。",
+      saveError: "无法更新语音设置",
+      provider: "提供方",
+      providers: {
+        local: "本地",
+        openai: "OpenAI",
+      },
+      sttModel: "语音转文字模型",
+      ttsModel: "语音模型",
+      voice: "音色",
+      notDownloadedOption: "{{label}}（未下载）",
+      save: "保存",
+      retry: "重试",
+      dictation: {
+        title: "听写",
+        enabled: "听写",
+        enabledHint: "对着消息框说话，无需打字",
+      },
+      voiceMode: {
+        title: "语音模式",
+        info: "语音模式会转写你说的话，并朗读智能体的回复。",
+        enabled: "语音模式",
+        enabledHint: "免手动与智能体对话",
+        sttProvider: "语音转文字",
+        ttsProvider: "文字转语音",
+      },
+      openai: {
+        apiKey: "API 密钥",
+        apiKeyHint: "保存在主机上，不会再次显示。",
+        keyPlaceholder: "sk-...",
+        replaceKeyPlaceholder: "新密钥",
+        removeKey: "移除",
+        removeKeyTitle: "移除 OpenAI API 密钥？",
+        removeKeyMessage: "在添加密钥之前，设为 OpenAI 的功能将无法使用。",
+        baseUrl: "基础 URL",
+        baseUrlHint: "用于兼容 OpenAI 的服务器。留空则使用 OpenAI。",
+        missingKeyWarning: "已选择 OpenAI，但未设置 API 密钥。",
+      },
+      models: {
+        loading: "正在加载模型...",
+        loadError: "无法加载本地模型",
+        downloaded: "已下载",
+        inUse: "使用中",
+        recommended: "推荐",
+        download: "下载",
+        downloading: "正在下载...",
+        downloadingPercent: "正在下载 {{percent}}%",
+        extracting: "正在解压...",
+        delete: "删除",
+        deleteAction: "删除 {{label}}",
+        deleteTitle: "删除 {{label}}？",
+        deleteMessage: "这将释放 {{size}}。之后可以重新下载。",
+        languages: "{{label}} 支持的语言",
+        moreLanguages: "{{languages}} 等另外 {{count}} 种",
+      },
+      providerSettings: {
+        title: "提供方",
+        info: "各提供方的模型和凭据。本地模型在此主机上运行，下载前会显示大小和支持的语言。",
+        localStt: "本地语音转文字",
+        localTts: "本地文字转语音",
+        openai: "OpenAI",
+        downloaded_one: "已下载 {{count}} 个模型",
+        downloaded_other: "已下载 {{count}} 个模型",
+        configured: "已配置",
+        notConfigured: "未配置",
+      },
+    },
     general: {
       title: "通用",
       sending: "发送",

packages/app/src/screens/settings-screen.tsx

@@ -36,6 +36,7 @@ import {
   Code2,
   Smartphone,
   Sparkles,
+  Mic,
   Blocks,
   Globe,
   PanelLeft,
@@ -117,6 +118,7 @@ import { PluginSettingsContent } from "@/plugins/settings";
 import { useInstalledPlugins } from "@/plugins/registry";
 import { HostPluginsPage } from "@/screens/settings/plugins-page";
 import { MetadataGenerationPage } from "@/screens/settings/metadata-generation-page";
+import { HostVoicePage } from "@/screens/settings/voice/voice-page";
 import ProjectsScreen from "@/screens/projects-screen";
 import ProjectSettingsScreen from "@/screens/project-settings-screen";
 import { SETTINGS_DESKTOP_SIDEBAR_WIDTH, useIsCompactFormFactor } from "@/constants/layout";
@@ -234,6 +236,7 @@ const HOST_SECTION_ITEMS: HostSectionItem[] = [
   { id: "pair-device", labelKey: "openProject.tiles.pairDevice.title", icon: Smartphone },
   { id: "agents", labelKey: "settings.hostSections.agents", icon: Bot },
   { id: "metadata", labelKey: "settings.hostSections.metadata", icon: Sparkles },
+  { id: "voice", labelKey: "settings.hostSections.voice", icon: Mic },
   { id: "workspaces", labelKey: "settings.hostSections.workspaces", icon: FolderGit2 },
   { id: "providers", labelKey: "settings.hostSections.providers", icon: Boxes },
   { id: "usage", labelKey: "settings.hostSections.usage", icon: Gauge },
@@ -256,6 +259,8 @@ function renderHostSettingsContent(
       return <HostAgentsPage serverId={view.serverId} />;
     case "metadata":
       return <MetadataGenerationPage serverId={view.serverId} />;
+    case "voice":
+      return <HostVoicePage serverId={view.serverId} />;
     case "workspaces":
       return <HostWorkspacesPage serverId={view.serverId} />;
     case "providers":

packages/app/src/screens/settings/voice/use-local-speech-models.ts

@@ -0,0 +1,71 @@
+import { useCallback } from "react";
+import { useTranslation } from "react-i18next";
+import type { LocalSpeechModel } from "@getpaseo/protocol/speech/rpc-schemas";
+import { useFetchQuery } from "@/data/query";
+import { useHostRuntimeClient, useHostRuntimeIsConnected } from "@/runtime/host-runtime";
+import { isLocalModelBusy } from "./voice-settings";
+
+const DOWNLOAD_POLL_INTERVAL_MS = 1000;
+
+const localSpeechModelsQueryKey = (serverId: string) => ["speech-local-models", serverId] as const;
+
+export interface LocalSpeechModels {
+  models: LocalSpeechModel[];
+  isLoading: boolean;
+  error: Error | null;
+  refresh: () => void;
+  download: (modelId: string) => Promise<void>;
+  remove: (modelId: string) => Promise<void>;
+}
+
+// The daemon reports download progress through the list, so the list polls while any
+// model is downloading or extracting.
+export function useLocalSpeechModels(serverId: string): LocalSpeechModels {
+  const { t } = useTranslation();
+  const client = useHostRuntimeClient(serverId);
+  const isConnected = useHostRuntimeIsConnected(serverId);
+  const query = useFetchQuery({
+    queryKey: localSpeechModelsQueryKey(serverId),
+    enabled: Boolean(client && isConnected),
+    dataShape: "list",
+    staleTimeMs: 0,
+    queryFn: () => {
+      if (!client) throw new Error(t("workspace.terminal.hostDisconnected"));
+      return client.listLocalSpeechModels();
+    },
+    refetchInterval: (current) =>
+      current.state.data?.some(isLocalModelBusy) ? DOWNLOAD_POLL_INTERVAL_MS : false,
+  });
+  const { refetch } = query;
+
+  const refresh = useCallback(() => {
+    void refetch();
+  }, [refetch]);
+
+  const download = useCallback(
+    async (modelId: string) => {
+      if (!client) return;
+      await client.downloadLocalSpeechModel(modelId);
+      await refetch();
+    },
+    [client, refetch],
+  );
+
+  const remove = useCallback(
+    async (modelId: string) => {
+      if (!client) return;
+      await client.deleteLocalSpeechModel(modelId);
+      await refetch();
+    },
+    [client, refetch],
+  );
+
+  return {
+    models: query.data ?? [],
+    isLoading: query.isLoading,
+    error: query.error,
+    refresh,
+    download,
+    remove,
+  };
+}

packages/app/src/screens/settings/voice/voice-page.tsx

@@ -0,0 +1,703 @@
+import { useCallback, useMemo, useRef, useState } from "react";
+import { Alert as NativeAlert, Text, View } from "react-native";
+import { useTranslation } from "react-i18next";
+import type { TFunction } from "i18next";
+import { StyleSheet } from "react-native-unistyles";
+import { Download, Languages, Trash2 } from "lucide-react-native";
+import type {
+  LocalSpeechModel,
+  SpeechSettings,
+  SpeechSettingsPatch,
+} from "@getpaseo/protocol/speech/rpc-schemas";
+import {
+  SettingsCard,
+  SettingsCollapsibleRow,
+  SettingsInfoTip,
+  SettingsRow,
+  SettingsSection,
+  SettingsSelect,
+} from "@/components/settings";
+import { Alert } from "@/components/ui/alert";
+import { Button } from "@/components/ui/button";
+import { FormTextInput } from "@/components/ui/form-field";
+import { LoadingSpinner } from "@/components/ui/loading-spinner";
+import { StatusBadge } from "@/components/ui/status-badge";
+import { Switch } from "@/components/ui/switch";
+import type { EditingTextInputHandle } from "@/components/ui/text-input";
+import { useDaemonConfig } from "@/hooks/use-daemon-config";
+import { useHostFeature } from "@/runtime/host-features";
+import { useHostRuntimeIsConnected } from "@/runtime/host-runtime";
+import { confirmDialog } from "@/utils/confirm-dialog";
+import { useLocalSpeechModels, type LocalSpeechModels } from "./use-local-speech-models";
+import {
+  SPEECH_PROVIDERS,
+  buildModelOptions,
+  buildOpenAiVoiceOptions,
+  formatLanguages,
+  formatModelSize,
+  getLocalModelState,
+  resolveSelectedModel,
+  resolveSelectedVoice,
+  summarizeLocalModels,
+  toSpeechProvider,
+  usesOpenAi,
+  type SpeechModelKind,
+  type SpeechProvider,
+} from "./voice-settings";
+
+type SavePatch = (patch: SpeechSettingsPatch) => void;
+
+function errorMessage(error: unknown): string {
+  return error instanceof Error ? error.message : String(error);
+}
+
+export function HostVoicePage({ serverId }: { serverId: string }) {
+  const { t } = useTranslation();
+  const isConnected = useHostRuntimeIsConnected(serverId);
+  const supported = useHostFeature(serverId, "speechSettings");
+  const { config, patchConfig } = useDaemonConfig(serverId);
+  const localModels = useLocalSpeechModels(serverId);
+  const { refresh: refreshModels } = localModels;
+
+  const save = useCallback<SavePatch>(
+    (patch) => {
+      patchConfig({ speech: patch })
+        .then(refreshModels)
+        .catch((error: unknown) => {
+          NativeAlert.alert(t("settings.voice.saveError"), errorMessage(error));
+        });
+    },
+    [patchConfig, refreshModels, t],
+  );
+
+  if (!isConnected) {
+    return <Alert size="md" variant="warning" title={t("settings.voice.offline")} />;
+  }
+  if (!supported) {
+    return <Alert size="md" variant="warning" title={t("settings.voice.updateHost")} />;
+  }
+  const speech = config?.speech;
+  if (!speech) {
+    return (
+      <View style={styles.loading}>
+        <LoadingSpinner size="large" color={styles.spinnerColor.color} />
+      </View>
+    );
+  }
+
+  return (
+    <View testID="voice-settings">
+      <DictationSection speech={speech} localModels={localModels.models} save={save} />
+      <VoiceModeSection speech={speech} localModels={localModels.models} save={save} />
+      <ProvidersSection speech={speech} localModels={localModels} save={save} />
+    </View>
+  );
+}
+
+// ---------------------------------------------------------------------------
+// Feature sections
+// ---------------------------------------------------------------------------
+
+interface FeatureSectionProps {
+  speech: SpeechSettings;
+  localModels: LocalSpeechModel[];
+  save: SavePatch;
+}
+
+function DictationSection({ speech, localModels, save }: FeatureSectionProps) {
+  const { t } = useTranslation();
+  const { dictation } = speech;
+  const setEnabled = useCallback((enabled: boolean) => save({ dictation: { enabled } }), [save]);
+  const setProvider = useCallback(
+    (provider: SpeechProvider) => save({ dictation: { stt: { provider } } }),
+    [save],
+  );
+  const setModel = useCallback((model: string) => save({ dictation: { stt: { model } } }), [save]);
+
+  return (
+    <SettingsSection title={t("settings.voice.dictation.title")} testID="voice-dictation">
+      <SettingsCard>
+        <SettingsRow
+          label={t("settings.voice.dictation.enabled")}
+          hint={t("settings.voice.dictation.enabledHint")}
+        >
+          <Switch
+            value={dictation.enabled}
+            onValueChange={setEnabled}
+            accessibilityLabel={t("settings.voice.dictation.enabled")}
+          />
+        </SettingsRow>
+        {dictation.enabled ? (
+          <ProviderRow
+            label={t("settings.voice.provider")}
+            value={toSpeechProvider(dictation.stt.provider)}
+            onChange={setProvider}
+            testID="voice-dictation-provider"
+          />
+        ) : null}
+        {dictation.enabled ? (
+          <ModelRow
+            kind="stt"
+            provider={toSpeechProvider(dictation.stt.provider)}
+            model={dictation.stt.model}
+            localModels={localModels}
+            onChange={setModel}
+          />
+        ) : null}
+      </SettingsCard>
+    </SettingsSection>
+  );
+}
+
+function VoiceModeSection({ speech, localModels, save }: FeatureSectionProps) {
+  const { t } = useTranslation();
+  const { voiceMode } = speech;
+  const sttProvider = toSpeechProvider(voiceMode.stt.provider);
+  const ttsProvider = toSpeechProvider(voiceMode.tts.provider);
+  const setEnabled = useCallback((enabled: boolean) => save({ voiceMode: { enabled } }), [save]);
+  const setSttProvider = useCallback(
+    (provider: SpeechProvider) => save({ voiceMode: { stt: { provider } } }),
+    [save],
+  );
+  const setSttModel = useCallback(
+    (model: string) => save({ voiceMode: { stt: { model } } }),
+    [save],
+  );
+  const setTtsProvider = useCallback(
+    (provider: SpeechProvider) => save({ voiceMode: { tts: { provider } } }),
+    [save],
+  );
+  const setTtsModel = useCallback(
+    (model: string) => save({ voiceMode: { tts: { model } } }),
+    [save],
+  );
+  const setTtsVoice = useCallback(
+    (voice: string) => save({ voiceMode: { tts: { voice } } }),
+    [save],
+  );
+  const voiceOptions = useMemo(
+    () => buildOpenAiVoiceOptions(resolveSelectedVoice(voiceMode.tts.voice)),
+    [voiceMode.tts.voice],
+  );
+
+  return (
+    <SettingsSection
+      title={t("settings.voice.voiceMode.title")}
+      info={t("settings.voice.voiceMode.info")}
+      testID="voice-voice-mode"
+    >
+      <SettingsCard>
+        <SettingsRow
+          label={t("settings.voice.voiceMode.enabled")}
+          hint={t("settings.voice.voiceMode.enabledHint")}
+        >
+          <Switch
+            value={voiceMode.enabled}
+            onValueChange={setEnabled}
+            accessibilityLabel={t("settings.voice.voiceMode.enabled")}
+          />
+        </SettingsRow>
+        {voiceMode.enabled ? (
+          <ProviderRow
+            label={t("settings.voice.voiceMode.sttProvider")}
+            value={sttProvider}
+            onChange={setSttProvider}
+            testID="voice-mode-stt-provider"
+          />
+        ) : null}
+        {voiceMode.enabled ? (
+          <ModelRow
+            kind="stt"
+            provider={sttProvider}
+            model={voiceMode.stt.model}
+            localModels={localModels}
+            onChange={setSttModel}
+          />
+        ) : null}
+        {voiceMode.enabled ? (
+          <ProviderRow
+            label={t("settings.voice.voiceMode.ttsProvider")}
+            value={ttsProvider}
+            onChange={setTtsProvider}
+            testID="voice-mode-tts-provider"
+          />
+        ) : null}
+        {voiceMode.enabled ? (
+          <ModelRow
+            kind="tts"
+            provider={ttsProvider}
+            model={voiceMode.tts.model}
+            localModels={localModels}
+            onChange={setTtsModel}
+          />
+        ) : null}
+        {voiceMode.enabled && ttsProvider === "openai" ? (
+          <SettingsSelect
+            label={t("settings.voice.voice")}
+            value={resolveSelectedVoice(voiceMode.tts.voice)}
+            options={voiceOptions}
+            onValueChange={setTtsVoice}
+          />
+        ) : null}
+      </SettingsCard>
+    </SettingsSection>
+  );
+}
+
+function ProviderRow({
+  label,
+  value,
+  onChange,
+  testID,
+}: {
+  label: string;
+  value: SpeechProvider;
+  onChange: (provider: SpeechProvider) => void;
+  testID: string;
+}) {
+  const { t } = useTranslation();
+  const options = useMemo(
+    () =>
+      SPEECH_PROVIDERS.map((provider) => ({
+        value: provider,
+        label: t(`settings.voice.providers.${provider}`),
+      })),
+    [t],
+  );
+  return (
+    <SettingsSelect
+      label={label}
+      value={value}
+      options={options}
+      onValueChange={onChange}
+      testID={testID}
+    />
+  );
+}
+
+function ModelRow({
+  kind,
+  provider,
+  model,
+  localModels,
+  onChange,
+}: {
+  kind: SpeechModelKind;
+  provider: SpeechProvider;
+  model: string | undefined;
+  localModels: LocalSpeechModel[];
+  onChange: (model: string) => void;
+}) {
+  const { t } = useTranslation();
+  const selected = resolveSelectedModel({ kind, provider, model, localModels });
+  const options = useMemo(
+    () =>
+      buildModelOptions({
+        kind,
+        provider,
+        selected,
+        localModels,
+        notDownloadedLabel: (label) => t("settings.voice.notDownloadedOption", { label }),
+      }),
+    [kind, localModels, provider, selected, t],
+  );
+  return (
+    <SettingsSelect
+      label={kind === "stt" ? t("settings.voice.sttModel") : t("settings.voice.ttsModel")}
+      value={selected}
+      options={options}
+      onValueChange={onChange}
+    />
+  );
+}
+
+// ---------------------------------------------------------------------------
+// Providers: one collapsible row per provider, each with a one-line summary
+// ---------------------------------------------------------------------------
+
+function ProvidersSection({
+  speech,
+  localModels,
+  save,
+}: {
+  speech: SpeechSettings;
+  localModels: LocalSpeechModels;
+  save: SavePatch;
+}) {
+  const { t } = useTranslation();
+  const missingKey = usesOpenAi(speech) && !speech.openai.apiKeyConfigured;
+  return (
+    <SettingsSection
+      title={t("settings.voice.providerSettings.title")}
+      info={t("settings.voice.providerSettings.info")}
+      testID="voice-providers"
+    >
+      {missingKey ? (
+        <View style={styles.sectionAlert}>
+          <Alert size="sm" variant="warning" title={t("settings.voice.openai.missingKeyWarning")} />
+        </View>
+      ) : null}
+      <SettingsCard>
+        <LocalProviderRow kind="stt" localModels={localModels} />
+        <LocalProviderRow kind="tts" localModels={localModels} />
+        <OpenAiProviderRow speech={speech} save={save} />
+      </SettingsCard>
+    </SettingsSection>
+  );
+}
+
+function LocalProviderRow({
+  kind,
+  localModels,
+}: {
+  kind: SpeechModelKind;
+  localModels: LocalSpeechModels;
+}) {
+  const { t } = useTranslation();
+  const { models, isLoading, error, refresh, download, remove } = localModels;
+  const kindModels = useMemo(() => models.filter((model) => model.kind === kind), [kind, models]);
+  const label =
+    kind === "stt"
+      ? t("settings.voice.providerSettings.localStt")
+      : t("settings.voice.providerSettings.localTts");
+
+  if (error && kindModels.length === 0) {
+    return (
+      <SettingsCollapsibleRow
+        label={label}
+        summary={t("settings.voice.models.loadError")}
+        testID={`voice-provider-local-${kind}`}
+      >
+        <SettingsRow label={t("settings.voice.models.loadError")} hint={error.message}>
+          <Button variant="outline" onPress={refresh}>
+            {t("settings.voice.retry")}
+          </Button>
+        </SettingsRow>
+      </SettingsCollapsibleRow>
+    );
+  }
+  return (
+    <SettingsCollapsibleRow
+      label={label}
+      summary={isLoading ? t("settings.voice.models.loading") : localSummaryLabel(models, kind, t)}
+      testID={`voice-provider-local-${kind}`}
+    >
+      {kindModels.map((model) => (
+        <LocalModelRow key={model.id} model={model} onDownload={download} onDelete={remove} />
+      ))}
+    </SettingsCollapsibleRow>
+  );
+}
+
+function localSummaryLabel(
+  models: readonly LocalSpeechModel[],
+  kind: SpeechModelKind,
+  t: TFunction,
+): string {
+  const summary = summarizeLocalModels(models, kind);
+  switch (summary.kind) {
+    case "downloading":
+      return summary.percent === null
+        ? t("settings.voice.models.downloading")
+        : t("settings.voice.models.downloadingPercent", { percent: summary.percent });
+    case "extracting":
+      return t("settings.voice.models.extracting");
+    case "downloaded":
+      return t("settings.voice.providerSettings.downloaded", { count: summary.count });
+  }
+}
+
+function OpenAiProviderRow({ speech, save }: { speech: SpeechSettings; save: SavePatch }) {
+  const { t } = useTranslation();
+  const { apiKeyConfigured, baseUrl } = speech.openai;
+  const keyInput = useRef<EditingTextInputHandle>(null);
+  const [draftKey, setDraftKey] = useState("");
+  const [draftBaseUrl, setDraftBaseUrl] = useState<string | null>(null);
+
+  const saveKey = useCallback(() => {
+    save({ openai: { apiKey: draftKey } });
+    keyInput.current?.replaceText("");
+    setDraftKey("");
+  }, [draftKey, save]);
+  const removeKey = useCallback(() => {
+    void confirmDialog({
+      title: t("settings.voice.openai.removeKeyTitle"),
+      message: t("settings.voice.openai.removeKeyMessage"),
+      confirmLabel: t("settings.voice.openai.removeKey"),
+      destructive: true,
+    }).then((confirmed) => {
+      if (confirmed) save({ openai: { apiKey: null } });
+      return undefined;
+    });
+  }, [save, t]);
+  const saveBaseUrl = useCallback(() => {
+    if (draftBaseUrl === null) return;
+    save({ openai: { baseUrl: draftBaseUrl.trim() || null } });
+    setDraftBaseUrl(null);
+  }, [draftBaseUrl, save]);
+
+  const apiKeyInfo = useMemo(
+    () => (
+      <SettingsInfoTip
+        title={t("settings.voice.openai.apiKey")}
+        info={t("settings.voice.openai.apiKeyHint")}
+      />
+    ),
+    [t],
+  );
+  const baseUrlInfo = useMemo(
+    () => (
+      <SettingsInfoTip
+        title={t("settings.voice.openai.baseUrl")}
+        info={t("settings.voice.openai.baseUrlHint")}
+      />
+    ),
+    [t],
+  );
+
+  return (
+    <SettingsCollapsibleRow
+      label={t("settings.voice.providerSettings.openai")}
+      summary={
+        apiKeyConfigured
+          ? t("settings.voice.providerSettings.configured")
+          : t("settings.voice.providerSettings.notConfigured")
+      }
+      testID="voice-provider-openai"
+    >
+      <SettingsRow label={t("settings.voice.openai.apiKey")} labelAccessory={apiKeyInfo}>
+        <View style={styles.inputControls}>
+          <FormTextInput
+            ref={keyInput}
+            secureTextEntry
+            autoCapitalize="none"
+            autoCorrect={false}
+            placeholder={
+              apiKeyConfigured
+                ? t("settings.voice.openai.replaceKeyPlaceholder")
+                : t("settings.voice.openai.keyPlaceholder")
+            }
+            onChangeText={setDraftKey}
+            accessibilityLabel={t("settings.voice.openai.apiKey")}
+            style={styles.input}
+            testID="voice-openai-key-input"
+          />
+          <Button
+            variant="outline"
+            onPress={saveKey}
+            disabled={draftKey.trim().length === 0}
+            testID="voice-openai-key-save"
+          >
+            {t("settings.voice.save")}
+          </Button>
+          {apiKeyConfigured ? (
+            <Button variant="ghost" onPress={removeKey}>
+              {t("settings.voice.openai.removeKey")}
+            </Button>
+          ) : null}
+        </View>
+      </SettingsRow>
+      <SettingsRow label={t("settings.voice.openai.baseUrl")} labelAccessory={baseUrlInfo}>
+        <View style={styles.inputControls}>
+          <FormTextInput
+            autoCapitalize="none"
+            autoCorrect={false}
+            initialValue={baseUrl ?? ""}
+            placeholder="https://api.openai.com/v1"
+            onChangeText={setDraftBaseUrl}
+            accessibilityLabel={t("settings.voice.openai.baseUrl")}
+            style={styles.input}
+          />
+          <Button
+            variant="outline"
+            onPress={saveBaseUrl}
+            disabled={draftBaseUrl === null || draftBaseUrl.trim() === (baseUrl ?? "")}
+          >
+            {t("settings.voice.save")}
+          </Button>
+        </View>
+      </SettingsRow>
+    </SettingsCollapsibleRow>
+  );
+}
+
+function LocalModelRow({
+  model,
+  onDownload,
+  onDelete,
+}: {
+  model: LocalSpeechModel;
+  onDownload: (modelId: string) => Promise<void>;
+  onDelete: (modelId: string) => Promise<void>;
+}) {
+  const { t, i18n } = useTranslation();
+  const state = getLocalModelState(model);
+  const [actionError, setActionError] = useState<string | null>(null);
+
+  const download = useCallback(() => {
+    setActionError(null);
+    onDownload(model.id).catch((error: unknown) => setActionError(errorMessage(error)));
+  }, [model.id, onDownload]);
+  const remove = useCallback(() => {
+    void confirmDialog({
+      title: t("settings.voice.models.deleteTitle", { label: model.label }),
+      message: t("settings.voice.models.deleteMessage", {
+        size: formatModelSize(model.downloadSizeBytes),
+      }),
+      confirmLabel: t("settings.voice.models.delete"),
+      destructive: true,
+    })
+      .then((confirmed) => {
+        if (!confirmed) return undefined;
+        setActionError(null);
+        return onDelete(model.id);
+      })
+      .catch((error: unknown) => setActionError(errorMessage(error)));
+  }, [model.downloadSizeBytes, model.id, model.label, onDelete, t]);
+
+  const languages = formatLanguages({
+    languages: model.languages,
+    locale: i18n.language,
+    formatMore: (listed, count) =>
+      t("settings.voice.models.moreLanguages", { languages: listed, count }),
+  });
+  const details = useMemo(
+    () => (
+      <View style={styles.details}>
+        <SettingsInfoTip
+          title={model.label}
+          info={model.description}
+          testID={`voice-model-${model.id}-description`}
+        />
+        <SettingsInfoTip
+          title={model.label}
+          info={languages}
+          icon={Languages}
+          accessibilityLabel={t("settings.voice.models.languages", { label: model.label })}
+          testID={`voice-model-${model.id}-languages`}
+        />
+        <Text style={styles.modelSize}>{formatModelSize(model.downloadSizeBytes)}</Text>
+        {state.kind === "installed" ? (
+          <StatusBadge
+            size="xs"
+            variant="success"
+            label={
+              model.inUse ? t("settings.voice.models.inUse") : t("settings.voice.models.downloaded")
+            }
+          />
+        ) : null}
+        {model.isDefault ? (
+          <StatusBadge size="xs" label={t("settings.voice.models.recommended")} />
+        ) : null}
+      </View>
+    ),
+    [
+      languages,
+      model.description,
+      model.downloadSizeBytes,
+      model.id,
+      model.inUse,
+      model.isDefault,
+      model.label,
+      state.kind,
+      t,
+    ],
+  );
+
+  let control = null;
+  if (state.kind === "downloading") {
+    control = (
+      <View style={styles.progress}>
+        <LoadingSpinner size="small" color={styles.spinnerColor.color} />
+        <Text style={styles.progressText}>
+          {state.percent === null
+            ? t("settings.voice.models.downloading")
+            : t("settings.voice.models.downloadingPercent", { percent: state.percent })}
+        </Text>
+      </View>
+    );
+  } else if (state.kind === "extracting") {
+    control = (
+      <View style={styles.progress}>
+        <LoadingSpinner size="small" color={styles.spinnerColor.color} />
+        <Text style={styles.progressText}>{t("settings.voice.models.extracting")}</Text>
+      </View>
+    );
+  } else if (state.kind === "installed") {
+    control = model.inUse ? null : (
+      <Button
+        variant="ghost"
+        leftIcon={Trash2}
+        onPress={remove}
+        accessibilityLabel={t("settings.voice.models.deleteAction", { label: model.label })}
+        testID={`voice-model-delete-${model.id}`}
+      >
+        {t("settings.voice.models.delete")}
+      </Button>
+    );
+  } else {
+    control = (
+      <Button
+        variant="outline"
+        leftIcon={Download}
+        onPress={download}
+        testID={`voice-model-download-${model.id}`}
+      >
+        {state.kind === "failed" ? t("settings.voice.retry") : t("settings.voice.models.download")}
+      </Button>
+    );
+  }
+
+  return (
+    <SettingsRow
+      label={model.label}
+      labelAccessory={details}
+      error={actionError ?? (state.kind === "failed" ? state.error : null)}
+      testID={`voice-model-${model.id}`}
+    >
+      {control}
+    </SettingsRow>
+  );
+}
+
+const styles = StyleSheet.create((theme) => ({
+  loading: {
+    paddingVertical: theme.spacing[8],
+    alignItems: "center",
+  },
+  spinnerColor: {
+    color: theme.colors.foregroundMuted,
+  },
+  sectionAlert: {
+    marginBottom: theme.spacing[3],
+  },
+  inputControls: {
+    flexDirection: "row",
+    alignItems: "center",
+    flexWrap: "wrap",
+    gap: theme.spacing[2],
+  },
+  input: {
+    minWidth: 220,
+  },
+  details: {
+    flexDirection: "row",
+    alignItems: "center",
+    gap: theme.spacing[2],
+  },
+  modelSize: {
+    color: theme.colors.foregroundMuted,
+    fontSize: theme.fontSize.sm,
+    fontVariant: ["tabular-nums"],
+  },
+  progress: {
+    flexDirection: "row",
+    alignItems: "center",
+    gap: theme.spacing[2],
+  },
+  progressText: {
+    color: theme.colors.foregroundMuted,
+    fontSize: theme.fontSize.sm,
+    fontVariant: ["tabular-nums"],
+  },
+}));

packages/app/src/screens/settings/voice/voice-settings.test.ts

@@ -0,0 +1,126 @@
+import { describe, expect, it } from "vitest";
+import type { LocalSpeechModel } from "@getpaseo/protocol/speech/rpc-schemas";
+import {
+  buildModelOptions,
+  formatLanguages,
+  formatModelSize,
+  getLocalModelState,
+  resolveSelectedModel,
+  summarizeLocalModels,
+} from "./voice-settings";
+
+function model(overrides: Partial<LocalSpeechModel>): LocalSpeechModel {
+  return {
+    id: "parakeet-tdt-0.6b-v2-int8",
+    kind: "stt",
+    label: "Parakeet v2",
+    description: "Accurate English transcription.",
+    languages: ["en"],
+    downloadSizeBytes: 482_468_385,
+    isDefault: true,
+    inUse: true,
+    status: "installed",
+    ...overrides,
+  };
+}
+
+const catalog = [
+  model({}),
+  model({
+    id: "parakeet-tdt-110m-en-int8",
+    label: "Parakeet Small",
+    isDefault: false,
+    status: "not_installed",
+    inUse: false,
+  }),
+  model({ id: "kokoro-en-v0_19", kind: "tts", label: "Kokoro", inUse: false }),
+];
+
+describe("voice settings", () => {
+  it("falls back to the catalog default when no local model is saved", () => {
+    expect(
+      resolveSelectedModel({
+        kind: "stt",
+        provider: "local",
+        model: undefined,
+        localModels: catalog,
+      }),
+    ).toBe("parakeet-tdt-0.6b-v2-int8");
+    expect(
+      resolveSelectedModel({
+        kind: "tts",
+        provider: "openai",
+        model: undefined,
+        localModels: catalog,
+      }),
+    ).toBe("tts-1");
+  });
+
+  it("marks local models that still need a download", () => {
+    expect(
+      buildModelOptions({
+        kind: "stt",
+        provider: "local",
+        selected: "parakeet-tdt-0.6b-v2-int8",
+        localModels: catalog,
+        notDownloadedLabel: (label) => `${label} (not downloaded)`,
+      }),
+    ).toEqual([
+      { value: "parakeet-tdt-0.6b-v2-int8", label: "Parakeet v2" },
+      { value: "parakeet-tdt-110m-en-int8", label: "Parakeet Small (not downloaded)" },
+    ]);
+  });
+
+  it("keeps a custom OpenAI-compatible model id selectable", () => {
+    const options = buildModelOptions({
+      kind: "stt",
+      provider: "openai",
+      selected: "my-whisper",
+      localModels: catalog,
+      notDownloadedLabel: (label) => label,
+    });
+    expect(options.at(-1)).toEqual({ value: "my-whisper", label: "my-whisper" });
+  });
+
+  it("reports download progress as a percentage", () => {
+    expect(
+      getLocalModelState(model({ status: "downloading", receivedBytes: 241, totalBytes: 482 })),
+    ).toEqual({ kind: "downloading", percent: 50 });
+    expect(getLocalModelState(model({ status: "downloading" }))).toEqual({
+      kind: "downloading",
+      percent: null,
+    });
+  });
+
+  it("summarizes each local provider by its downloads", () => {
+    expect(summarizeLocalModels(catalog, "stt")).toEqual({ kind: "downloaded", count: 1 });
+    expect(summarizeLocalModels(catalog, "tts")).toEqual({ kind: "downloaded", count: 1 });
+    const downloading = [
+      ...catalog,
+      model({
+        id: "parakeet-tdt-0.6b-v3-int8",
+        status: "downloading",
+        receivedBytes: 1,
+        totalBytes: 4,
+      }),
+    ];
+    expect(summarizeLocalModels(downloading, "stt")).toEqual({ kind: "downloading", percent: 25 });
+    expect(summarizeLocalModels(downloading, "tts")).toEqual({ kind: "downloaded", count: 1 });
+  });
+
+  it("formats download sizes", () => {
+    expect(formatModelSize(482_468_385)).toBe("482 MB");
+    expect(formatModelSize(1_250_000_000)).toBe("1.3 GB");
+  });
+
+  it("names a short language list and counts the rest of a long one", () => {
+    const formatMore = (languages: string, count: number) => `${languages} and ${count} more`;
+    expect(formatLanguages({ languages: ["en", "de"], locale: "en", formatMore })).toBe(
+      "English, German",
+    );
+    const whisper = ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca"];
+    expect(formatLanguages({ languages: whisper, locale: "en", formatMore })).toBe(
+      "English, Chinese, German, Spanish, Russian, Korean, French, Japanese, Portuguese, Turkish and 2 more",
+    );
+  });
+});

packages/app/src/screens/settings/voice/voice-settings.ts

@@ -0,0 +1,173 @@
+import type { LocalSpeechModel, SpeechSettings } from "@getpaseo/protocol/speech/rpc-schemas";
+
+// What the Voice page needs to know about speech providers and models, kept free of React
+// so the option lists and model states are testable on their own.
+
+export type SpeechProvider = "local" | "openai";
+export type SpeechModelKind = "stt" | "tts";
+
+export const SPEECH_PROVIDERS: readonly SpeechProvider[] = ["local", "openai"];
+
+// OpenAI accepts free-form ids so self-hosted servers can use their own; these are the
+// ones the page offers. A saved id outside the list is still shown as an option.
+const OPENAI_MODELS: Record<SpeechModelKind, { ids: readonly string[]; defaultId: string }> = {
+  stt: {
+    ids: ["whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe"],
+    defaultId: "whisper-1",
+  },
+  tts: { ids: ["tts-1", "tts-1-hd", "gpt-4o-mini-tts"], defaultId: "tts-1" },
+};
+
+const OPENAI_VOICES = ["alloy", "ash", "coral", "echo", "fable", "nova", "onyx", "sage", "shimmer"];
+const DEFAULT_OPENAI_VOICE = "alloy";
+
+export interface SpeechModelOption {
+  value: string;
+  label: string;
+}
+
+export function toSpeechProvider(provider: string): SpeechProvider {
+  return provider === "openai" ? "openai" : "local";
+}
+
+export function resolveSelectedModel(input: {
+  kind: SpeechModelKind;
+  provider: SpeechProvider;
+  model: string | undefined;
+  localModels: readonly LocalSpeechModel[];
+}): string {
+  if (input.model) return input.model;
+  if (input.provider === "openai") return OPENAI_MODELS[input.kind].defaultId;
+  return input.localModels.find((m) => m.kind === input.kind && m.isDefault)?.id ?? "";
+}
+
+export function buildModelOptions(input: {
+  kind: SpeechModelKind;
+  provider: SpeechProvider;
+  selected: string;
+  localModels: readonly LocalSpeechModel[];
+  notDownloadedLabel: (label: string) => string;
+}): SpeechModelOption[] {
+  if (input.provider === "openai") {
+    return withSelected(
+      OPENAI_MODELS[input.kind].ids.map((id) => ({ value: id, label: id })),
+      input.selected,
+    );
+  }
+  return input.localModels
+    .filter((model) => model.kind === input.kind)
+    .map((model) => ({
+      value: model.id,
+      label: model.status === "installed" ? model.label : input.notDownloadedLabel(model.label),
+    }));
+}
+
+export function resolveSelectedVoice(voice: string | undefined): string {
+  return voice ?? DEFAULT_OPENAI_VOICE;
+}
+
+export function buildOpenAiVoiceOptions(selected: string): SpeechModelOption[] {
+  return withSelected(
+    OPENAI_VOICES.map((voice) => ({ value: voice, label: voice })),
+    selected,
+  );
+}
+
+function withSelected(options: SpeechModelOption[], selected: string): SpeechModelOption[] {
+  if (!selected || options.some((option) => option.value === selected)) return options;
+  return [...options, { value: selected, label: selected }];
+}
+
+export function usesOpenAi(settings: SpeechSettings): boolean {
+  return (
+    (settings.dictation.enabled && settings.dictation.stt.provider === "openai") ||
+    (settings.voiceMode.enabled &&
+      (settings.voiceMode.stt.provider === "openai" ||
+        settings.voiceMode.tts.provider === "openai"))
+  );
+}
+
+export type LocalModelState =
+  | { kind: "installed" }
+  | { kind: "not_installed" }
+  | { kind: "downloading"; percent: number | null }
+  | { kind: "extracting" }
+  | { kind: "failed"; error: string };
+
+export function getLocalModelState(model: LocalSpeechModel): LocalModelState {
+  switch (model.status) {
+    case "installed":
+      return { kind: "installed" };
+    case "downloading": {
+      const total = model.totalBytes ?? 0;
+      const received = model.receivedBytes ?? 0;
+      return {
+        kind: "downloading",
+        percent: total > 0 ? Math.min(100, Math.floor((received / total) * 100)) : null,
+      };
+    }
+    case "extracting":
+      return { kind: "extracting" };
+    case "failed":
+      return { kind: "failed", error: model.error ?? "" };
+    default:
+      return { kind: "not_installed" };
+  }
+}
+
+export function isLocalModelBusy(model: LocalSpeechModel): boolean {
+  return model.status === "downloading" || model.status === "extracting";
+}
+
+// What a collapsed local provider row says: an active download wins over the count.
+export type LocalModelsSummary =
+  | { kind: "downloading"; percent: number | null }
+  | { kind: "extracting" }
+  | { kind: "downloaded"; count: number };
+
+export function summarizeLocalModels(
+  models: readonly LocalSpeechModel[],
+  kind: SpeechModelKind,
+): LocalModelsSummary {
+  const kindModels = models.filter((model) => model.kind === kind);
+  const busy = kindModels.find(isLocalModelBusy);
+  if (busy) {
+    const state = getLocalModelState(busy);
+    if (state.kind === "downloading") return state;
+    return { kind: "extracting" };
+  }
+  return {
+    kind: "downloaded",
+    count: kindModels.filter((model) => model.status === "installed").length,
+  };
+}
+
+export function formatModelSize(bytes: number): string {
+  const megabytes = bytes / 1_000_000;
+  if (megabytes >= 1000) return `${(megabytes / 1000).toFixed(1)} GB`;
+  return `${Math.round(megabytes)} MB`;
+}
+
+// Multilingual models list close to a hundred languages; past this many the tooltip names
+// the first ones and counts the rest.
+const MAX_LISTED_LANGUAGES = 10;
+
+export function formatLanguages(input: {
+  languages: readonly string[];
+  locale: string;
+  formatMore: (languages: string, count: number) => string;
+}): string {
+  const names = languageNames(input.locale);
+  const listed = input.languages
+    .slice(0, MAX_LISTED_LANGUAGES)
+    .map((code) => names?.of(code) ?? code.toUpperCase())
+    .join(", ");
+  const hidden = input.languages.length - MAX_LISTED_LANGUAGES;
+  return hidden > 0 ? input.formatMore(listed, hidden) : listed;
+}
+
+// Hermes ships without Intl.DisplayNames; the language code is the fallback label there.
+function languageNames(locale: string): Intl.DisplayNames | null {
+  if (typeof Intl.DisplayNames !== "function") return null;
+  return new Intl.DisplayNames([locale], { type: "language" });
+}

packages/app/src/tool-calls/presentation.test.ts

@@ -1,9 +1,11 @@
+import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { ToolCallDetail } from "@getpaseo/protocol/agent-types";
 import { describe, expect, it } from "vitest";
 
 import { buildToolCallPresentation, type ToolCallPresentationIcon } from "./presentation";
 
 const fakeIcons = {
+  paseo: (() => null) as ToolCallPresentationIcon,
   brain: (() => null) as ToolCallPresentationIcon,
   eye: (() => null) as ToolCallPresentationIcon,
   wrench: (() => null) as ToolCallPresentationIcon,
@@ -12,7 +14,11 @@ const fakeIcons = {
 function fakeResolveIcon(
   toolName: string,
   detail: ToolCallDetail | undefined,
+  agentMessage: AgentMessage | undefined,
 ): ToolCallPresentationIcon {
+  if (agentMessage) {
+    return fakeIcons.paseo;
+  }
   if (detail?.type === "plan") {
     return fakeIcons.brain;
   }
@@ -94,32 +100,35 @@ describe("tool-call presentation", () => {
 });
 
 it.each([
-  ["message", "Message from QA messenger"],
-  ["finished", "QA messenger finished"],
-  ["errored", "QA messenger errored"],
-  ["permission-required", "QA messenger needs permission"],
-  ["closed", "QA messenger closed"],
-] as const)("presents %s from structured provenance without a second label", (event, heading) => {
-  const presentation = buildToolCallPresentation({
-    toolName: "internal_name_should_not_be_visible",
-    status: "completed",
-    error: null,
-    detail: { type: "plain_text", label: "legacy summary", text: "legacy body" },
-    agentMessage: {
-      event,
-      sender: { id: "server::sender", title: "QA messenger" },
-      text: "The delivered message.",
-    },
-    resolveIcon: fakeResolveIcon,
-  });
-  expect(presentation.displayName).toBe(heading);
-  expect(presentation.summary).toBeUndefined();
-  expect(presentation.detail).toEqual({
-    type: "plain_text",
-    icon: "bot",
-    text: "From agent: server::sender\n\nThe delivered message.",
-  });
-});
+  ["message", "Message received"],
+  ["finished", "Agent finished"],
+  ["errored", "Agent errored"],
+  ["permission-required", "Agent needs permission"],
+  ["closed", "Agent closed"],
+] as const)(
+  "presents %s with a fixed label, the sender as context, and the Paseo icon",
+  (event, heading) => {
+    const presentation = buildToolCallPresentation({
+      toolName: "internal_name_should_not_be_visible",
+      status: "completed",
+      error: null,
+      detail: { type: "plain_text", label: "legacy summary", text: "legacy body", icon: "bot" },
+      agentMessage: {
+        event,
+        sender: { id: "server::sender", title: "QA messenger" },
+        text: "The delivered message.",
+      },
+      resolveIcon: fakeResolveIcon,
+    });
+    expect(presentation.displayName).toBe(heading);
+    expect(presentation.summary).toBe("QA messenger");
+    expect(presentation.icon).toBe(fakeIcons.paseo);
+    expect(presentation.detail).toEqual({
+      type: "plain_text",
+      text: "From agent: server::sender\n\nThe delivered message.",
+    });
+  },
+);
 
 it("uses an opaque sender ID when no title is available", () => {
   const presentation = buildToolCallPresentation({
@@ -129,5 +138,19 @@ it("uses an opaque sender ID when no title is available", () => {
     agentMessage: { event: "message", sender: { id: "remote::worker" }, text: "Hello" },
     resolveIcon: fakeResolveIcon,
   });
-  expect(presentation.displayName).toBe("Message from remote::worker");
+  expect(presentation.displayName).toBe("Message received");
+  expect(presentation.summary).toBe("remote::worker");
+});
+
+it("shows the target agent title as context for Paseo agent tools", () => {
+  const presentation = buildToolCallPresentation({
+    toolName: "mcp__paseo__kill_agent",
+    status: "completed",
+    error: null,
+    detail: { type: "unknown", input: { agentId: "agt_1" }, output: null },
+    targetAgentTitle: "Reviewer",
+    resolveIcon: fakeResolveIcon,
+  });
+  expect(presentation.displayName).toBe("Kill agent");
+  expect(presentation.summary).toBe("Reviewer");
 });

packages/app/src/tool-calls/presentation.ts

@@ -1,5 +1,5 @@
 import type { AgentMessage } from "@getpaseo/protocol/agent-message";
-import { buildAgentMessageDisplay } from "@getpaseo/protocol/agent-message-display";
+import { buildAgentMessageDisplay } from "@getpaseo/protocol/paseo-tool-presentation/index";
 import type { PlanOutcome } from "@/components/plan-card";
 import type { ComponentType } from "react";
 import type { ToolCallDetail } from "@getpaseo/protocol/agent-types";
@@ -22,6 +22,7 @@ interface BuildToolCallPresentationInput {
   detail?: ToolCallDetail;
   cwd?: string;
   metadata?: Record<string, unknown>;
+  targetAgentTitle?: string;
   resolveIcon: ToolCallIconResolver;
 }
 
@@ -42,6 +43,7 @@ export interface ToolCallPresentation {
 export type ToolCallIconResolver = (
   toolName: string,
   detail: ToolCallDetail | undefined,
+  agentMessage: AgentMessage | undefined,
 ) => ToolCallPresentationIcon;
 
 function displayStatus(status: ToolCallStatus): ToolCallDisplayInput["status"] {
@@ -67,6 +69,7 @@ export function buildToolCallPresentation(
     detail: detailForDisplay,
     metadata: input.metadata,
     cwd: input.cwd,
+    targetAgentTitle: input.targetAgentTitle,
   });
   const isLoadingDetails = isPendingToolCallDetail({
     detail,
@@ -80,7 +83,7 @@ export function buildToolCallPresentation(
     displayName: displayModel.displayName,
     summary: displayModel.summary,
     errorText: displayModel.errorText,
-    icon: input.resolveIcon(input.toolName, detail),
+    icon: input.resolveIcon(input.toolName, detail, input.agentMessage),
     isLoadingDetails,
     hasDetails,
     canOpenDetails: hasDetails || isLoadingDetails,

packages/app/src/tool-calls/use-target-agent-title.ts

@@ -0,0 +1,19 @@
+import type { ToolCallDetail } from "@getpaseo/protocol/agent-types";
+import { getPaseoToolTargetAgentId } from "@getpaseo/protocol/paseo-tool-presentation/index";
+import { useSessionStore } from "@/stores/session-store";
+
+/** Title of the agent a Paseo tool call acts on, when this host knows it. */
+export function useTargetAgentTitle(input: {
+  serverId: string | undefined;
+  toolName: string;
+  detail: ToolCallDetail | undefined;
+}): string | undefined {
+  const agentId = getPaseoToolTargetAgentId(input.toolName, input.detail);
+  const { serverId } = input;
+  return useSessionStore((state) => {
+    if (!serverId || !agentId) return undefined;
+    const session = state.sessions[serverId];
+    const agent = session?.agents.get(agentId) ?? session?.agentDetails.get(agentId);
+    return agent?.title ?? undefined;
+  });
+}

packages/app/src/usage/balance-bar.tsx

@@ -41,11 +41,17 @@ function fillToneStyle(tone: UsageTone) {
   }
 }
 
-export function UsageBalanceBar({ balance }: { balance: UsageBalance }) {
+export function UsageBalanceBar({
+  balance,
+  retained = false,
+}: {
+  balance: UsageBalance;
+  retained?: boolean;
+}) {
   const { i18n } = useTranslation();
   const { amountText, usedPct } = resolveBalance(balance, i18n.language);
   const tone = balance.tone ?? "default";
-  const resetLabel = formatResetLabel(balance.resetsAt);
+  const resetLabel = formatResetLabel(balance.resetsAt, retained);
 
   const fillStyle = useMemo<StyleProp<ViewStyle>>(
     () => [styles.fill, fillToneStyle(tone), { width: `${clampPct(usedPct ?? 0)}%` }],

packages/app/src/usage/card.tsx

@@ -16,7 +16,7 @@ import { useCompactTimeAgo } from "@/hooks/use-time-ago";
 import { UsageBalanceBar } from "./balance-bar";
 import { usageCopy } from "./copy";
 import type { UsageDisplay } from "./display";
-import { formatUsageFreshness, type UsageRefresh } from "./model";
+import { formatUsageFreshness, resolveUsageReport, type UsageRefresh } from "./model";
 import { useReportRefresh } from "./queries";
 import { UsageSourceIcon } from "./source-icon";
 import type { UsageReport, UsageReportEntry, UsageWindow } from "./types";
@@ -27,31 +27,6 @@ function statusText(report: UsageReport): string | null {
   return report.status === "error" ? "Error" : "Unavailable";
 }
 
-function reportContent(report: UsageReport) {
-  if (report.status === "available")
-    return {
-      windows: report.windows,
-      balances: report.balances ?? [],
-      details: report.details ?? [],
-      message: undefined,
-    };
-  const message =
-    report.status === "unavailable" ? usageCopy.problem(report.problem) : report.error;
-  return { windows: [], balances: [], details: [], message };
-}
-
-function reportMessages(entry: UsageReportEntry): string[] {
-  if (entry.report.status === "available") return [];
-  if (entry.loginErrors)
-    return entry.loginErrors.map(
-      (login) => `${login.harness}: ${reportContent(login.report).message}`,
-    );
-  // COMPAT(usageLoginErrors): added in v0.11.0, remove after 2027-04-05 once daemon floor >= v0.11.0.
-  return [
-    entry.report.status === "error" ? entry.report.error : usageCopy.problem(entry.report.problem),
-  ];
-}
-
 const ThemedRotateCw = withUnistyles(RotateCw);
 const ThemedLoadingSpinner = withUnistyles(LoadingSpinner);
 
@@ -81,8 +56,8 @@ export function UsageCard({
   const usage = entry.report;
   const status = statusText(usage);
   const footer = entry.account.label ?? null;
-  const { windows, balances, details } = reportContent(usage);
-  const messages = reportMessages(entry);
+  const { windows, balances, details, planLabel, successfulAt, retained, messages } =
+    resolveUsageReport(entry);
 
   const containerStyle = useMemo(
     () => [styles.container, compact ? styles.containerCompact : styles.containerPadded],
@@ -104,9 +79,7 @@ export function UsageCard({
         <Text style={styles.name} numberOfLines={1}>
           {entry.sourceLabel}
         </Text>
-        {usage.status === "available" && usage.planLabel ? (
-          <StatusBadge label={usage.planLabel} variant="muted" size="xs" />
-        ) : null}
+        {planLabel ? <StatusBadge label={planLabel} variant="muted" size="xs" /> : null}
         <View style={styles.headerSpacer} />
         {status ? (
           <View style={styles.statusRow}>
@@ -117,7 +90,8 @@ export function UsageCard({
         {refreshable ? (
           <UsageRefreshButton
             sourceLabel={entry.sourceLabel}
-            fetchedAt={entry.fetchedAt}
+            successfulAt={successfulAt}
+            retained={retained}
             refreshState={refreshState}
             onRefresh={refresh}
             compact={isCompact}
@@ -138,12 +112,13 @@ export function UsageCard({
               key={window.id}
               entry={entry}
               window={window}
+              retained={retained}
               display={display}
               pinnable={pinnable}
             />
           ))}
           {balances.map((balance) => (
-            <UsageBalanceBar key={balance.id} balance={balance} />
+            <UsageBalanceBar key={balance.id} balance={balance} retained={retained} />
           ))}
         </View>
       ) : null}
@@ -170,7 +145,8 @@ export function UsageCard({
           </Text>
           {showsFreshnessInline ? (
             <UsageFreshness
-              fetchedAt={entry.fetchedAt}
+              successfulAt={successfulAt}
+              retained={retained}
               style={styles.freshness}
               testID="usage-freshness"
             />
@@ -192,7 +168,9 @@ function CardWindowBar({
   window,
   display,
   pinnable,
+  retained,
 }: {
+  retained: boolean;
   entry: UsageReportEntry;
   window: UsageWindow;
   display: UsageDisplay;
@@ -207,6 +185,7 @@ function CardWindowBar({
   return (
     <UsageWindowBar
       window={window}
+      retained={retained}
       displayAs={display.displayAs}
       pinnable={pinnable}
       pinned={display.isPinned(pin)}
@@ -220,13 +199,15 @@ function CardWindowBar({
 /** Refreshes this one report. Its tooltip says when the report on screen was fetched. */
 function UsageRefreshButton({
   sourceLabel,
-  fetchedAt,
+  successfulAt,
+  retained,
   refreshState,
   onRefresh,
   compact,
 }: {
   sourceLabel: string;
-  fetchedAt: string;
+  successfulAt: string | null;
+  retained: boolean;
   refreshState: UsageRefresh;
   onRefresh: () => void;
   compact: boolean;
@@ -236,12 +217,13 @@ function UsageRefreshButton({
   const freshness = useMemo(
     () => (
       <UsageFreshness
-        fetchedAt={fetchedAt}
+        successfulAt={successfulAt}
+        retained={retained}
         style={styles.tooltipText}
         testID="usage-freshness-tooltip"
       />
     ),
-    [fetchedAt],
+    [successfulAt, retained],
   );
   return (
     <ToolbarButton
@@ -265,18 +247,20 @@ function UsageRefreshButton({
 
 /** Its own component so the relative-time clock re-renders one `<Text>`, not the card. */
 function UsageFreshness({
-  fetchedAt,
+  successfulAt,
+  retained,
   style,
   testID,
 }: {
-  fetchedAt: string;
+  successfulAt: string | null;
+  retained: boolean;
   style: StyleProp<TextStyle>;
   testID: string;
 }) {
-  const elapsed = useCompactTimeAgo(new Date(fetchedAt));
+  const elapsed = useCompactTimeAgo(successfulAt ? new Date(successfulAt) : null);
   return (
     <Text style={style} numberOfLines={1} testID={testID}>
-      {formatUsageFreshness(elapsed)}
+      {successfulAt ? formatUsageFreshness(elapsed, retained) : "No successful update"}
     </Text>
   );
 }

packages/app/src/usage/format.test.ts

@@ -1,5 +1,5 @@
 import { describe, expect, it } from "vitest";
-import { formatAmount } from "./format";
+import { formatAmount, formatResetLabel } from "./format";
 
 describe("formatAmount", () => {
   it("groups thousands in the app's language", () => {
@@ -13,3 +13,10 @@ describe("formatAmount", () => {
     expect(formatAmount(1234.5, "usd", "fr").replace(/\s/g, " ")).toBe("1 234,50 $US");
   });
 });
+
+it("retained reset times that have passed do not claim the quota is resetting", () => {
+  const past = "2000-01-01T00:00:00.000Z";
+  expect(formatResetLabel(past, true)).toBe("Reset time passed");
+  expect(formatResetLabel(past)).toBe("resetting now");
+  expect(formatResetLabel(null, true)).toBeNull();
+});

packages/app/src/usage/format.ts

@@ -27,10 +27,11 @@ function relativeDuration(iso: string): string | null {
   return `${diffMinutes}m`;
 }
 
-export function formatResetLabel(iso: string | null | undefined): string | null {
+export function formatResetLabel(iso: string | null | undefined, retained = false): string | null {
   if (!iso) return null;
   const rel = relativeDuration(iso);
   if (!rel) return null;
+  if (rel === "now" && retained) return "Reset time passed";
   return rel === "now" ? "resetting now" : `resets ${rel}`;
 }
 

packages/app/src/usage/model.test.ts

@@ -1,5 +1,6 @@
 import { describe, expect, it } from "vitest";
 import {
+  resolveUsageReport,
   displayPercent,
   formatUsageFreshness,
   resolveAgentUsageView,
@@ -325,3 +326,72 @@ describe("resolveAgentUsageView", () => {
     ).toEqual({ kind: "error", message: "Unable to load usage: Unknown agent" });
   });
 });
+
+it("resolves retained usage and successful time without inventing old-daemon history", () => {
+  const success = entry({ windows: [{ id: "weekly", label: "Weekly", usedPct: 42 }] });
+  const failure: UsageReportEntry = {
+    ...success,
+    fetchedAt: "2026-01-01T00:06:00.000Z",
+    report: { status: "error", error: "Rate limited" },
+    lastSuccessful: {
+      fetchedAt: success.fetchedAt,
+      report: success.report as Extract<UsageReportEntry["report"], { status: "available" }>,
+    },
+  };
+  expect(resolveUsageReport(failure)).toEqual({
+    windows: success.report.status === "available" ? success.report.windows : [],
+    balances: [],
+    details: [],
+    planLabel: null,
+    successfulAt: success.fetchedAt,
+    retained: true,
+    messages: ["Rate limited"],
+  });
+  expect(resolveUsageReport({ ...failure, lastSuccessful: undefined })).toEqual({
+    windows: [],
+    balances: [],
+    details: [],
+    planLabel: null,
+    successfulAt: null,
+    retained: false,
+    messages: ["Rate limited"],
+  });
+  expect(resolveUsageReport(success)).toEqual({
+    windows: success.report.status === "available" ? success.report.windows : [],
+    balances: [],
+    details: [],
+    planLabel: null,
+    successfulAt: success.fetchedAt,
+    retained: false,
+    messages: [],
+  });
+});
+
+it("orders failed polls by attempt time even when successful data is older", () => {
+  const success = entry({});
+  if (success.report.status !== "available") throw new Error("fixture must be available");
+  const failure: UsageReportEntry = {
+    ...success,
+    fetchedAt: "2026-01-01T00:06:00.000Z",
+    report: { status: "error", error: "Rate limited" },
+    lastSuccessful: { fetchedAt: success.fetchedAt, report: success.report },
+  };
+  expect(upsertReport([failure], success)).toEqual([failure]);
+  expect(settleReports([failure], [success])).toEqual([failure]);
+  expect(upsertReport([success], failure)).toEqual([failure]);
+});
+
+it("available and retained usage show the same successful completion time", () => {
+  const success: UsageReportEntry = { ...entry({}), successfulAt: "2026-01-01T00:00:15.000Z" };
+  if (success.report.status !== "available") throw new Error("fixture must be available");
+  expect(resolveUsageReport(success).successfulAt).toBe("2026-01-01T00:00:15.000Z");
+  const failure: UsageReportEntry = {
+    ...success,
+    successfulAt: undefined,
+    fetchedAt: "2026-01-01T00:06:00.000Z",
+    report: { status: "error", error: "Rate limited" },
+    lastSuccessful: { fetchedAt: success.successfulAt!, report: success.report },
+  };
+  expect(resolveUsageReport(failure).successfulAt).toBe(resolveUsageReport(success).successfulAt);
+  expect(upsertReport([failure], success)).toEqual([failure]);
+});

packages/app/src/usage/model.ts

@@ -1,7 +1,7 @@
 import { formatCompactTimeAgoAsProse } from "@/utils/time";
 import { usageCopy } from "./copy";
 import type { UsageDisplayAs } from "./preferences";
-import type { UsageReportEntry, UsageView, UsageWindow } from "./types";
+import type { UsageReport, UsageReportEntry, UsageView, UsageWindow } from "./types";
 
 export function usedPercent(window: UsageWindow): number | null {
   if (window.usedPct != null) return window.usedPct;
@@ -32,8 +32,8 @@ export function usageWindowRowLabel(input: {
 }
 
 /** When a report was fetched, from its compact relative time: "Updated 3m ago". */
-export function formatUsageFreshness(compactTimeAgo: string): string {
-  return `${usageCopy.updated} ${formatCompactTimeAgoAsProse(compactTimeAgo)}`;
+export function formatUsageFreshness(compactTimeAgo: string, retained = false): string {
+  return `${retained ? "Last updated" : usageCopy.updated} ${formatCompactTimeAgoAsProse(compactTimeAgo)}`;
 }
 
 /** A user-requested refresh of one report. The previous report stays on screen throughout. */
@@ -192,3 +192,40 @@ export function resolveUsageModalHostId(choice: UsageHostChoice): string | null
   const picked = connected.find((host) => host.serverId === choice.pickedServerId);
   return picked?.serverId ?? resolveUsageHostId(choice) ?? connected[0]?.serverId ?? null;
 }
+
+/** Current outcome owns messages; only a successful poll owns values and freshness. */
+export function resolveUsageReport(entry: UsageReportEntry) {
+  const available = entry.report.status === "available";
+  // COMPAT(usageLastSuccessful): added in v0.12.0, remove after 2027-04-17 once daemon floor >= v0.12.0.
+  // Older daemons cannot provide history; a failed attempt is never a successful update.
+  const snapshot = available ? null : (entry.lastSuccessful ?? null);
+  const content = entry.report.status === "available" ? entry.report : (snapshot?.report ?? null);
+  const messages: string[] = [];
+  if (!available) {
+    if (entry.loginErrors)
+      messages.push(
+        ...entry.loginErrors.map((login) => `${login.harness}: ${usageProblemText(login.report)}`),
+      );
+    // COMPAT(usageLoginErrors): added in v0.11.0, remove after 2027-04-05 once daemon floor >= v0.11.0.
+    else messages.push(usageProblemText(entry.report));
+  }
+  return {
+    windows: content?.windows ?? [],
+    balances: content?.balances ?? [],
+    details: content?.details ?? [],
+    planLabel: content?.planLabel ?? null,
+    // COMPAT(usageSuccessfulAt): added in v0.12.0, remove after 2027-04-17 once daemon floor >= v0.12.0.
+    // Old daemons expose only attempt time for available reports, never for failures.
+    successfulAt: available
+      ? (entry.successfulAt ?? entry.fetchedAt)
+      : (snapshot?.fetchedAt ?? null),
+    retained: snapshot !== null,
+    messages,
+  };
+}
+
+function usageProblemText(report: UsageReport): string {
+  if (report.status === "error") return report.error;
+  if (report.status === "unavailable") return usageCopy.problem(report.problem);
+  return "";
+}

packages/app/src/usage/pinned.test.ts

@@ -257,9 +257,12 @@ describe("resolvePinnedUsage", () => {
   });
 });
 
-it("keeps unavailable and error reports out of the sidebar summary", () => {
+it("keeps unavailable and error reports out of the sidebar summary even with retained data", () => {
+  if (claude.report.status !== "available" || codex.report.status !== "available")
+    throw new Error("fixtures must be available");
   const expired: UsageReportEntry = {
     ...claude,
+    lastSuccessful: { fetchedAt: claude.fetchedAt, report: claude.report },
     report: {
       status: "unavailable",
       problem: { kind: "expired", expiresAt: "2026-10-01T00:00:00.000Z", refreshedBy: "claude" },
@@ -267,6 +270,7 @@ it("keeps unavailable and error reports out of the sidebar summary", () => {
   };
   const failed: UsageReportEntry = {
     ...codex,
+    lastSuccessful: { fetchedAt: codex.fetchedAt, report: codex.report },
     report: { status: "error", error: "Store deleted" },
   };
   expect(resolvePinnedUsage([expired, failed], preferences(null))).toEqual([]);

packages/app/src/usage/window-bar.tsx

@@ -26,7 +26,9 @@ export function UsageWindowBar({
   onTogglePin,
   pinLabel,
   pinTestID,
+  retained = false,
 }: {
+  retained?: boolean;
   window: UsageWindow;
   displayAs: UsageDisplayAs;
   /** Whether the row pins the window to the sidebar. When false the row is a plain bar. */
@@ -40,10 +42,13 @@ export function UsageWindowBar({
   const shownPct = displayPercent(window, displayAs);
   const tone = windowTone(window);
 
-  const isAtRisk = window.runsOutAt != null && window.shortfallPct != null;
+  const isAtRisk =
+    window.runsOutAt != null &&
+    window.shortfallPct != null &&
+    (!retained || Date.parse(window.runsOutAt) > Date.now());
   const trailing = isAtRisk
     ? `runs out ${formatResetLabel(window.runsOutAt)?.replace("resets ", "") ?? ""}`.trim()
-    : formatResetLabel(window.resetsAt);
+    : formatResetLabel(window.resetsAt, retained);
 
   const value = shownPct != null ? formatDisplayPct(shownPct, displayAs) : "—";
   const accessibilityState = useMemo(() => ({ checked: pinned }), [pinned]);

packages/app/src/utils/host-routes.ts

@@ -517,6 +517,7 @@ export const HOST_SECTION_SLUGS = [
   "pair-device",
   "agents",
   "metadata",
+  "voice",
   "workspaces",
   "providers",
   "usage",

packages/app/src/utils/tool-call-icon-name.test.ts

@@ -53,4 +53,14 @@ describe("resolveToolCallIconName", () => {
 
     expect(icon).toBe("wrench");
   });
+
+  it("uses the Paseo icon for agent messages despite the legacy bot detail icon", () => {
+    const icon = resolveToolCallIconName(
+      "agent_message",
+      { type: "plain_text", text: "Done.", icon: "bot" },
+      { event: "finished", sender: { id: "agt_1" }, text: "Done." },
+    );
+
+    expect(icon).toBe("paseo");
+  });
 });

packages/app/src/utils/tool-call-icon-name.ts

@@ -1,3 +1,4 @@
+import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { ToolCallDetail, ToolCallIconName } from "@getpaseo/protocol/agent-types";
 import { isPaseoToolName } from "@getpaseo/protocol/tool-name-normalization";
 
@@ -17,7 +18,15 @@ const TOOL_DETAIL_ICON_NAMES: Record<ToolCallDetail["type"], ToolCallIcon> = {
   unknown: "wrench",
 };
 
-export function resolveToolCallIconName(toolName: string, detail?: ToolCallDetail): ToolCallIcon {
+export function resolveToolCallIconName(
+  toolName: string,
+  detail?: ToolCallDetail,
+  agentMessage?: AgentMessage,
+): ToolCallIcon {
+  // Agent messages are Paseo deliveries; the wire detail's legacy "bot" icon is for old clients.
+  if (agentMessage) {
+    return "paseo";
+  }
   const lowerName = toolName.trim().toLowerCase();
 
   if (detail?.type === "plain_text" && detail.icon) {

packages/app/src/utils/tool-call-icon.ts

@@ -10,6 +10,7 @@ import {
   SquareTerminal,
   Wrench,
 } from "lucide-react-native";
+import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { ToolCallDetail } from "@getpaseo/protocol/agent-types";
 import { PaseoLogo } from "@/components/icons/paseo-logo";
 import { resolveToolCallIconName, type ToolCallIcon } from "./tool-call-icon-name";
@@ -36,6 +37,7 @@ export function componentForToolCallIcon(name: ToolCallIcon): ToolCallIconCompon
 export function resolveToolCallIcon(
   toolName: string,
   detail?: ToolCallDetail,
+  agentMessage?: AgentMessage,
 ): ToolCallIconComponent {
-  return componentForToolCallIcon(resolveToolCallIconName(toolName, detail));
+  return componentForToolCallIcon(resolveToolCallIconName(toolName, detail, agentMessage));
 }

packages/app/vitest.config.ts

@@ -82,6 +82,7 @@ export default defineConfig({
     // Bundle the CJS dependencies of the excluded gesture-handler package for the browser.
     include: [
       "react/jsx-runtime",
+      "react/jsx-dev-runtime",
       "react-native-gesture-handler > hoist-non-react-statics",
       "react-native-gesture-handler > invariant",
     ],
@@ -91,6 +92,8 @@ export default defineConfig({
       "react-native-keyboard-controller",
     ],
   },
+  // babel-preset-expo compiles JSX with the automatic runtime, so app modules don't import React.
+  esbuild: { jsx: "automatic" },
   // The globals a React Native bundler defines, which esbuild is no longer there to supply for
   // the package excluded above.
   define: {

packages/cli/src/commands/usage/index.test.ts

@@ -277,3 +277,40 @@ describe("usage CLI registration", () => {
     expect(usage.commands[1]!.helpInformation()).toContain("<report-id>");
   });
 });
+
+it("shows retained values with current failures and separates successful time from latest attempt", async () => {
+  const success: UsageReportEntry = { ...reports[0]!, successfulAt: "2026-10-09T12:00:15Z" };
+  const current = await runUsageCommand(
+    options,
+    { kind: "inspect", id: success.id },
+    host([success]).connect,
+  );
+  expect(render(current)).toContain("Latest attempt: 2026-10-09T12:00:00Z");
+  expect(render(current)).toContain("Last successful: 2026-10-09T12:00:15Z");
+  const currentList = await runUsageCommand(options, { kind: "list" }, host([success]).connect);
+  expect(render(currentList)).toContain("Last successful: 2026-10-09T12:00:15Z");
+  if (success.report.status !== "available") throw new Error("fixture must be available");
+  const retained: UsageReportEntry = {
+    ...success,
+    fetchedAt: "2026-10-09T12:06:00Z",
+    report: { status: "error", error: "Rate limited" },
+    successfulAt: undefined,
+    lastSuccessful: { fetchedAt: success.successfulAt!, report: success.report },
+  };
+  const daemon = host([retained]);
+  const listed = await runUsageCommand(options, { kind: "list" }, daemon.connect);
+  expect(render(listed)).toContain("Retained: Five hours: 12.5% used");
+  expect(render(listed)).toContain("Last successful: 2026-10-09T12:00:15Z");
+  expect(render(listed)).toContain("Rate limited");
+  expect(JSON.parse(render(listed, { format: "json" }))).toEqual([retained]);
+  const inspected = await runUsageCommand(
+    options,
+    { kind: "inspect", id: retained.id },
+    daemon.connect,
+  );
+  expect(render(inspected)).toContain("Latest attempt: 2026-10-09T12:06:00Z");
+  expect(render(inspected)).toContain("Last successful: 2026-10-09T12:00:15Z");
+  expect(render(inspected)).toContain("Retained usage:");
+  expect(render(inspected)).toContain("Five hours: 12.5% used");
+  expect(render(inspected)).toContain("Reason: Rate limited");
+});

packages/cli/src/commands/usage/presentation.ts

@@ -44,8 +44,18 @@ function summary(entry: UsageReportEntry): string[] {
     const lines = [failureText(report)];
     for (const login of entry.loginErrors ?? [])
       lines.push(`${login.harness}: ${failureText(login.report)}`);
+    if (entry.lastSuccessful) {
+      lines.push(`Last successful: ${entry.lastSuccessful.fetchedAt}`);
+      lines.push(
+        ...availableSummary(entry.lastSuccessful.report).map((line) => `Retained: ${line}`),
+      );
+    } else lines.push("No successful update");
     return lines;
   }
+  return [...availableSummary(report), `Last successful: ${successfulTime(entry)}`];
+}
+
+function availableSummary(report: Extract<UsageReport, { status: "available" }>): string[] {
   const lines = report.windows.map(windowText);
   lines.push(...(report.balances ?? []).map(balanceText));
   return lines.length ? lines : ["-"];
@@ -68,7 +78,7 @@ const summarySchema: OutputSchema<SummaryRow> = {
     { header: "ACCOUNT", field: "account" },
     { header: "STATUS", field: "status" },
     { header: "USAGE", field: "usage" },
-    { header: "FETCHED", field: "fetched" },
+    { header: "FETCHED (LATEST ATTEMPT)", field: "fetched" },
   ],
 };
 
@@ -79,30 +89,15 @@ function inspect(entry: UsageReportEntry): string {
     `Source ID: ${entry.sourceId}`,
     `Account: ${value(entry.account.label)}`,
     `Status: ${entry.report.status}`,
-    `Fetched: ${value(entry.fetchedAt)}`,
+    `Latest attempt: ${value(entry.fetchedAt)}`,
   ];
-  const { report } = entry;
-  if (report.status === "available") {
-    lines.push(`Plan: ${value(report.planLabel)}`, "Windows:");
-    if (!report.windows.length) lines.push("  -");
-    for (const window of report.windows) {
-      lines.push(`  ${windowText(window)} [${window.id}]`, `    Resets: ${value(window.resetsAt)}`);
-      if (window.runsOutAt != null) lines.push(`    Runs out: ${window.runsOutAt}`);
-      if (window.shortfallPct != null) lines.push(`    Shortfall: ${percent(window.shortfallPct)}`);
-    }
-    lines.push("Balances:");
-    if (!report.balances?.length) lines.push("  -");
-    for (const balance of report.balances ?? []) {
-      lines.push(
-        `  ${balanceText(balance)} [${balance.id}]`,
-        `    Resets: ${value(balance.resetsAt)}`,
-      );
-    }
-    lines.push("Details:");
-    if (!report.details?.length) lines.push("  -");
-    for (const detail of report.details ?? []) lines.push(`  ${detail.label}: ${detail.value}`);
-  } else {
-    lines.push(`Reason: ${failureText(report)}`);
+  const report = entry.report.status === "available" ? entry.report : entry.lastSuccessful?.report;
+  const successfulAt = successfulTime(entry);
+  lines.push(successfulAt ? `Last successful: ${successfulAt}` : "No successful update");
+  if (entry.report.status !== "available") lines.push(`Reason: ${failureText(entry.report)}`);
+  if (report) {
+    if (entry.report.status !== "available") lines.push("Retained usage:");
+    lines.push(...availableDetails(report));
   }
   if (entry.loginErrors?.length) {
     lines.push("Login failures:");
@@ -135,3 +130,33 @@ export const usageSchema: OutputSchema<UsageReportEntry> = {
     return renderTable<SummaryRow>({ type: "list", data: rows, schema: summarySchema }, options);
   },
 };
+
+function availableDetails(report: Extract<UsageReport, { status: "available" }>): string[] {
+  const lines: string[] = [];
+  lines.push(`Plan: ${value(report.planLabel)}`, "Windows:");
+  if (!report.windows.length) lines.push("  -");
+  for (const window of report.windows) {
+    lines.push(`  ${windowText(window)} [${window.id}]`, `    Resets: ${value(window.resetsAt)}`);
+    if (window.runsOutAt != null) lines.push(`    Runs out: ${window.runsOutAt}`);
+    if (window.shortfallPct != null) lines.push(`    Shortfall: ${percent(window.shortfallPct)}`);
+  }
+  lines.push("Balances:");
+  if (!report.balances?.length) lines.push("  -");
+  for (const balance of report.balances ?? []) {
+    lines.push(
+      `  ${balanceText(balance)} [${balance.id}]`,
+      `    Resets: ${value(balance.resetsAt)}`,
+    );
+  }
+  lines.push("Details:");
+  if (!report.details?.length) lines.push("  -");
+  for (const detail of report.details ?? []) lines.push(`  ${detail.label}: ${detail.value}`);
+  return lines;
+}
+
+function successfulTime(entry: UsageReportEntry): string | undefined {
+  // COMPAT(usageSuccessfulAt): added in v0.12.0, remove after 2027-04-17 once daemon floor >= v0.12.0.
+  // Only available reports from older daemons can use their attempt timestamp as freshness.
+  if (entry.report.status === "available") return entry.successfulAt ?? entry.fetchedAt;
+  return entry.lastSuccessful?.fetchedAt;
+}

packages/client/src/daemon-client.ts

@@ -12,6 +12,7 @@ import { CreationClient } from "./creation/index.js";
 import type { CreationSnapshot } from "@getpaseo/protocol/messages";
 import type { z } from "zod";
 import type { SessionEventSubscription } from "@getpaseo/protocol/messages";
+import type { LocalSpeechModel } from "@getpaseo/protocol/speech/rpc-schemas";
 import type { ClientCapability } from "@getpaseo/protocol/client-capabilities";
 import type { AgentAttentionNotificationPayload } from "@getpaseo/protocol/agent-attention-notification";
 import { MAX_WEBSOCKET_MESSAGE_BYTES } from "@getpaseo/protocol/websocket-message-limit";
@@ -5264,6 +5265,34 @@ export class DaemonClient {
     });
   }
 
+  async listLocalSpeechModels(requestId?: string): Promise<LocalSpeechModel[]> {
+    const payload = await this.sendCorrelatedSessionRequest({
+      requestId,
+      message: { type: "speech.local_models.list.request" },
+      responseType: "speech.local_models.list.response",
+    });
+    if (payload.error) throw new Error(payload.error);
+    return payload.models;
+  }
+
+  async downloadLocalSpeechModel(modelId: string, requestId?: string): Promise<void> {
+    const payload = await this.sendCorrelatedSessionRequest({
+      requestId,
+      message: { type: "speech.local_models.download.request", modelId },
+      responseType: "speech.local_models.download.response",
+    });
+    if (payload.error) throw new Error(payload.error);
+  }
+
+  async deleteLocalSpeechModel(modelId: string, requestId?: string): Promise<void> {
+    const payload = await this.sendCorrelatedSessionRequest({
+      requestId,
+      message: { type: "speech.local_models.delete.request", modelId },
+      responseType: "speech.local_models.delete.response",
+    });
+    if (payload.error) throw new Error(payload.error);
+  }
+
   sendBrowserAutomationExecuteResponse(response: BrowserAutomationExecuteResponse): void {
     this.sendSessionMessageStrict(response);
   }

packages/desktop/e2e/workspace-restart.spec.ts

@@ -232,17 +232,18 @@ test("scrolled chat does not exclude the workspace titlebar from dragging", asyn
     }
     await page.getByRole("button", { name: "Close Find", exact: true }).click();
     await expect(find).toBeHidden();
+    // Closing Find returns keyboard scrolling to the chat viewport, which emits no window region.
     await expect
-      .poll(() =>
-        chat.evaluate((scroll) => ({
-          focusReturned: document.activeElement?.contains(scroll),
-          tabindex: document.activeElement?.getAttribute("tabindex"),
-          appRegion: getComputedStyle(document.activeElement!).getPropertyValue(
-            "-webkit-app-region",
-          ),
-        })),
-      )
-      .toEqual({ focusReturned: true, tabindex: "-1", appRegion: "no-drag" });
+      .poll(() => chat.evaluate((scroll) => document.activeElement === scroll))
+      .toBe(true);
+    await expect
+      .poll(() => chat.evaluate(inspectChatDragExclusions))
+      .toEqual({
+        contentCrossesHeader: true,
+        contentCrossesTabRow: true,
+        focusScopeRegion: "no-drag",
+        exclusions: 0,
+      });
     await page.screenshot({ path: testInfo.outputPath("scrolled-chat-titlebar.png") });
   } finally {
     await agent.cleanup();

packages/protocol/src/agent-message-display.ts

@@ -1,25 +0,0 @@
-import type { AgentMessage } from "./agent-message.js";
-import type { ToolCallDetail } from "./agent-types.js";
-
-/** Presentation shared by clients; never used to encode provider prompts. */
-export function buildAgentMessageDisplay(message: AgentMessage): {
-  displayName: string;
-  detail: ToolCallDetail;
-} {
-  const sender = message.sender.title ?? message.sender.id;
-  const headings: Record<AgentMessage["event"], string> = {
-    message: `Message from ${sender}`,
-    finished: `${sender} finished`,
-    errored: `${sender} errored`,
-    "permission-required": `${sender} needs permission`,
-    closed: `${sender} closed`,
-  };
-  return {
-    displayName: headings[message.event],
-    detail: {
-      type: "plain_text",
-      icon: "bot",
-      text: `From agent: ${message.sender.id}\n\n${message.text}`,
-    },
-  };
-}

packages/protocol/src/messages.ts

@@ -63,6 +63,16 @@ import {
   ScheduleRunOnceResponseSchema,
   ScheduleUpdateResponseSchema,
 } from "./schedule/rpc-schemas.js";
+import {
+  SpeechLocalModelsDeleteRequestSchema,
+  SpeechLocalModelsDeleteResponseSchema,
+  SpeechLocalModelsDownloadRequestSchema,
+  SpeechLocalModelsDownloadResponseSchema,
+  SpeechLocalModelsListRequestSchema,
+  SpeechLocalModelsListResponseSchema,
+  SpeechSettingsPatchSchema,
+  SpeechSettingsSchema,
+} from "./speech/rpc-schemas.js";
 import {
   LoopRunRequestSchema,
   LoopListRequestSchema,
@@ -208,6 +218,8 @@ export const MutableDaemonConfigSchema = z
     skills: z.object({ selection: AgentSkillSelectionSchema.optional() }).strict().optional(),
     pluginsEnabled: z.boolean().optional(),
     plugins: z.record(PluginIdSchema, PluginSourceSchema).optional(),
+    // COMPAT(speechSettings): added in v0.12.0, optional because older daemons omit it.
+    speech: SpeechSettingsSchema.optional(),
   })
   .passthrough();
 
@@ -228,6 +240,7 @@ export const MutableDaemonConfigPatchSchema = z
     agentProfiles: z.array(AgentProfileSchema).optional(),
     pluginsEnabled: z.boolean().optional(),
     plugins: z.record(PluginIdSchema, PluginSourceSchema).optional(),
+    speech: SpeechSettingsPatchSchema.optional(),
   })
   .partial()
   .passthrough();
@@ -3390,6 +3403,9 @@ export const SessionInboundMessageSchema = z.discriminatedUnion("type", [
   ChatWaitRequestSchema,
   ScheduleCreateRequestSchema,
   ScheduleListRequestSchema,
+  SpeechLocalModelsListRequestSchema,
+  SpeechLocalModelsDownloadRequestSchema,
+  SpeechLocalModelsDeleteRequestSchema,
   ScheduleInspectRequestSchema,
   ScheduleLogsRequestSchema,
   SchedulePauseRequestSchema,
@@ -3620,6 +3636,8 @@ export const ServerInfoStatusPayloadSchema = z
         daemonStatusRpc: z.boolean().optional(),
         // COMPAT(daemonConfigReload): added in v0.4.0, remove gate after 2027-02-14.
         daemonConfigReload: z.boolean().optional(),
+        // COMPAT(speechSettings): added in v0.12.0, remove gate after 2027-04-18.
+        speechSettings: z.boolean().optional(),
         // COMPAT(relayConfig): added in v0.2.6, remove gate after 2027-01-31.
         relayConfig: z.boolean().optional(),
         // COMPAT(pushTokenRevocation): added in v0.3.2, remove gate after 2027-02-10.
@@ -6306,14 +6324,15 @@ export const UsageProblemSchema = z.discriminatedUnion("kind", [
   }),
   z.object({ kind: z.literal("no_quota"), detail: z.string() }),
 ]);
+const AvailableUsageReportSchema = z.object({
+  status: z.literal("available"),
+  planLabel: z.string().optional(),
+  windows: z.array(ProviderUsageWindowSchema),
+  balances: z.array(ProviderUsageBalanceSchema).optional(),
+  details: z.array(ProviderUsageDetailSchema).optional(),
+});
 export const UsageReportSchema = z.discriminatedUnion("status", [
-  z.object({
-    status: z.literal("available"),
-    planLabel: z.string().optional(),
-    windows: z.array(ProviderUsageWindowSchema),
-    balances: z.array(ProviderUsageBalanceSchema).optional(),
-    details: z.array(ProviderUsageDetailSchema).optional(),
-  }),
+  AvailableUsageReportSchema,
   z.object({ status: z.literal("unavailable"), problem: UsageProblemSchema }),
   z.object({ status: z.literal("error"), error: z.string() }),
 ]);
@@ -6325,6 +6344,11 @@ export const UsageReportEntrySchema = z.object({
   sourceLabel: z.string(),
   icon: z.string().optional(),
   report: UsageReportSchema,
+  // Successful completion time; fetchedAt remains the attempt timestamp for ordering.
+  successfulAt: z.string().optional(),
+  lastSuccessful: z
+    .object({ fetchedAt: z.string(), report: AvailableUsageReportSchema })
+    .optional(),
   loginErrors: z
     .array(
       z.object({
@@ -7055,6 +7079,9 @@ export const SessionOutboundMessageSchema = z.discriminatedUnion("type", [
   ChatWaitResponseSchema,
   ScheduleCreateResponseSchema,
   ScheduleListResponseSchema,
+  SpeechLocalModelsListResponseSchema,
+  SpeechLocalModelsDownloadResponseSchema,
+  SpeechLocalModelsDeleteResponseSchema,
   ScheduleInspectResponseSchema,
   ScheduleLogsResponseSchema,
   SchedulePauseResponseSchema,

packages/protocol/src/messages.wire-compat.test.ts

@@ -1,6 +1,7 @@
 import { describe, expect, test } from "vitest";
 import { z } from "zod";
 import {
+  UsageReportEntrySchema,
   AgentSnapshotPayloadSchema,
   AgentTimelineItemPayloadSchema,
   ServerInfoStatusPayloadSchema,
@@ -436,3 +437,40 @@ test("usage login errors are additive and older reports still parse", () => {
   expect(SessionOutboundMessageSchema.parse(newMessage)).toEqual(newMessage);
   expect(legacy.parse(newMessage)).toEqual(oldMessage);
 });
+
+test("usage entries accept older failures and additive successful snapshots", () => {
+  const oldEntry = {
+    id: "source:account",
+    sourceId: "source",
+    sourceLabel: "Source",
+    account: {},
+    fetchedAt: "2026-10-17T10:06:00Z",
+    report: { status: "error", error: "Rate limited" },
+  };
+  expect(UsageReportEntrySchema.parse(oldEntry)).toEqual(oldEntry);
+  const retained = {
+    ...oldEntry,
+    lastSuccessful: {
+      fetchedAt: "2026-10-17T10:00:00Z",
+      report: { status: "available", windows: [{ id: "weekly", label: "Weekly", usedPct: 42 }] },
+    },
+  };
+  expect(UsageReportEntrySchema.parse(retained)).toEqual(retained);
+  const available = {
+    ...oldEntry,
+    report: retained.lastSuccessful.report,
+    successfulAt: "2026-10-17T10:00:15Z",
+  };
+  expect(UsageReportEntrySchema.parse(available)).toEqual(available);
+  expect(
+    UsageReportEntrySchema.omit({ lastSuccessful: true, successfulAt: true }).parse(available),
+  ).toEqual({ ...oldEntry, report: available.report });
+  // An older client's entry shape strips the additive snapshot and still sees the failure.
+  expect(UsageReportEntrySchema.omit({ lastSuccessful: true }).parse(retained)).toEqual(oldEntry);
+  expect(
+    UsageReportEntrySchema.safeParse({
+      ...oldEntry,
+      lastSuccessful: { fetchedAt: oldEntry.fetchedAt, report: oldEntry.report },
+    }).success,
+  ).toBe(false);
+});

packages/protocol/src/paseo-tool-presentation/agent-message.ts

@@ -0,0 +1,31 @@
+import type { AgentMessage } from "../agent-message.js";
+import type { ToolCallDetail } from "../agent-types.js";
+import { toSummaryText } from "./summary-text.js";
+
+export interface AgentMessageDisplay {
+  displayName: string;
+  summary?: string;
+  detail: ToolCallDetail;
+}
+
+/** Events read noun-first ("Agent finished"); the sender goes in the summary. */
+const EVENT_LABELS: Record<AgentMessage["event"], string> = {
+  message: "Message received",
+  finished: "Agent finished",
+  errored: "Agent errored",
+  "permission-required": "Agent needs permission",
+  closed: "Agent closed",
+};
+
+/** Presentation shared by clients; never used to encode provider prompts. */
+export function buildAgentMessageDisplay(message: AgentMessage): AgentMessageDisplay {
+  const summary = toSummaryText(message.sender.title ?? message.sender.id);
+  return {
+    displayName: EVENT_LABELS[message.event],
+    ...(summary ? { summary } : {}),
+    detail: {
+      type: "plain_text",
+      text: `From agent: ${message.sender.id}\n\n${message.text}`,
+    },
+  };
+}

packages/protocol/src/paseo-tool-presentation/catalog.ts

@@ -0,0 +1,349 @@
+/**
+ * One entry per Paseo MCP tool: the timeline label, the context shown after it,
+ * and how the expanded details lay out the call.
+ *
+ * Labels are fixed text so truncation never hides them. Actions read verb-first
+ * ("Send message"); the context goes in the summary.
+ */
+
+type ToolInput = Readonly<Record<string, unknown>>;
+
+/** `targetAgent` is the target agent's title when known, else its ID. */
+export type PaseoToolContext = (input: ToolInput, targetAgent: string | undefined) => unknown;
+
+export interface PaseoToolDetailSpec {
+  promptField?: string;
+  inputOrder?: readonly string[];
+  outputFields?: readonly string[];
+}
+
+export interface PaseoToolEntry {
+  label: string;
+  context?: PaseoToolContext;
+  detail?: PaseoToolDetailSpec;
+}
+
+const WORKSPACE_FIELDS = [
+  "title",
+  "workspaceId",
+  "projectId",
+  "isolation",
+  "path",
+  "mode",
+  "worktreeSlug",
+  "branchName",
+  "baseBranch",
+  "branch",
+  "prNumber",
+  "forge",
+] as const;
+const AGENT_FIELDS = [
+  "title",
+  "agentId",
+  "provider",
+  "workspaceId",
+  "cwd",
+  "sessionMode",
+  "modeId",
+  "background",
+  "notifyOnFinish",
+  "internal",
+  "settings",
+  "labels",
+] as const;
+const AUTOMATION_FIELDS = [
+  "name",
+  "id",
+  "cron",
+  "timezone",
+  "provider",
+  "cwd",
+  "isolation",
+  "maxRuns",
+  "expiresIn",
+  "clearExpires",
+] as const;
+const BROWSER_FIELDS = [
+  "browserId",
+  "url",
+  "ref",
+  "sourceRef",
+  "targetRef",
+  "value",
+  "text",
+  "key",
+  "button",
+  "doubleClick",
+  "modifiers",
+  "filePaths",
+  "fullPage",
+  "maxEntries",
+  "timeoutMs",
+  "deltaX",
+  "deltaY",
+  "width",
+  "height",
+  "function",
+] as const;
+
+const AUTOMATION_OUTPUT = ["id", "status", "nextRunAt", "expiresAt"] as const;
+
+function field(...keys: string[]): PaseoToolContext {
+  return (input) => keys.map((key) => input[key]).find(isPresent);
+}
+
+function targetAgent(): PaseoToolContext {
+  return (_input, agent) => agent;
+}
+
+function fieldOrTargetAgent(key: string): PaseoToolContext {
+  return (input, agent) => (isPresent(input[key]) ? input[key] : agent);
+}
+
+function workspaceContext(): PaseoToolContext {
+  return (input) =>
+    [input.title, input.branchName, input.branch, baseName(input.path)].find(isPresent);
+}
+
+function viewportContext(): PaseoToolContext {
+  return (input) =>
+    typeof input.width === "number" && typeof input.height === "number"
+      ? `${input.width}×${input.height}`
+      : undefined;
+}
+
+function isPresent(value: unknown): boolean {
+  if (typeof value === "string") return value.trim().length > 0;
+  if (Array.isArray(value)) return value.length > 0;
+  return typeof value === "number";
+}
+
+function baseName(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  return value.split(/[\\/]/).findLast((segment) => segment.length > 0);
+}
+
+function browser(label: string, context?: PaseoToolContext): PaseoToolEntry {
+  return { label, ...(context ? { context } : {}), detail: { inputOrder: BROWSER_FIELDS } };
+}
+
+export const PASEO_TOOL_CATALOG = {
+  // Agents
+  create_agent: {
+    label: "Create agent",
+    context: field("title", "initialPrompt"),
+    detail: {
+      promptField: "initialPrompt",
+      inputOrder: AGENT_FIELDS,
+      outputFields: ["agentId", "status", "currentModeId", "cwd"],
+    },
+  },
+  send_agent_prompt: {
+    label: "Send message",
+    context: field("prompt"),
+    detail: {
+      promptField: "prompt",
+      inputOrder: AGENT_FIELDS,
+      outputFields: ["status", "lastMessage", "permission"],
+    },
+  },
+  get_agent_status: {
+    label: "Check agent",
+    context: targetAgent(),
+    detail: { inputOrder: ["agentId"] },
+  },
+  get_agent_activity: {
+    label: "Read agent activity",
+    context: targetAgent(),
+    detail: { inputOrder: ["agentId", "limit"] },
+  },
+  list_agents: {
+    label: "List agents",
+    detail: { inputOrder: ["cwd", "statuses", "sinceHours", "limit", "includeArchived"] },
+  },
+  update_agent: {
+    label: "Update agent",
+    context: fieldOrTargetAgent("name"),
+    detail: { inputOrder: AGENT_FIELDS },
+  },
+  set_agent_mode: {
+    label: "Set agent mode",
+    context: field("modeId"),
+    detail: { inputOrder: ["agentId", "modeId"] },
+  },
+  cancel_agent: {
+    label: "Cancel agent",
+    context: targetAgent(),
+    detail: { inputOrder: ["agentId"] },
+  },
+  archive_agent: {
+    label: "Archive agent",
+    context: targetAgent(),
+    detail: { inputOrder: ["agentId"] },
+  },
+  kill_agent: { label: "Kill agent", context: targetAgent(), detail: { inputOrder: ["agentId"] } },
+  list_pending_permissions: { label: "List permissions" },
+  respond_to_permission: {
+    label: "Respond to permission",
+    context: targetAgent(),
+    detail: { inputOrder: ["agentId", "requestId", "response"] },
+  },
+
+  // Workspaces and scripts
+  create_workspace: {
+    label: "Create workspace",
+    context: workspaceContext(),
+    detail: { inputOrder: WORKSPACE_FIELDS, outputFields: ["workspaceId", "projectId"] },
+  },
+  list_workspaces: { label: "List workspaces" },
+  rename_workspace: {
+    label: "Rename workspace",
+    context: field("title"),
+    detail: { inputOrder: ["title", "workspaceId"] },
+  },
+  archive_workspace: {
+    label: "Archive workspace",
+    context: field("workspaceId"),
+    detail: {
+      inputOrder: ["workspaceId"],
+      outputFields: ["workspaceId", "archivedAgentIds", "removedDirectory"],
+    },
+  },
+  list_workspace_scripts: { label: "List scripts", detail: { inputOrder: ["workspaceId"] } },
+  start_workspace_script: {
+    label: "Start script",
+    context: field("scriptName"),
+    detail: { inputOrder: ["workspaceId", "scriptName"] },
+  },
+  stop_workspace_script: {
+    label: "Stop script",
+    context: field("scriptName"),
+    detail: { inputOrder: ["workspaceId", "scriptName"] },
+  },
+
+  // Terminals
+  create_terminal: {
+    label: "Create terminal",
+    context: field("name", "command"),
+    detail: { inputOrder: ["cwd", "workspaceId", "name", "command"] },
+  },
+  list_terminals: { label: "List terminals", detail: { inputOrder: ["cwd", "all"] } },
+  capture_terminal: {
+    label: "Read terminal",
+    context: field("terminalId"),
+    detail: { inputOrder: ["terminalId", "lines"] },
+  },
+  send_terminal_keys: {
+    label: "Send keys",
+    context: field("keys"),
+    detail: { inputOrder: ["terminalId", "keys", "literal"] },
+  },
+  kill_terminal: {
+    label: "Kill terminal",
+    context: field("terminalId"),
+    detail: { inputOrder: ["terminalId"] },
+  },
+
+  // Schedules and heartbeats
+  create_schedule: {
+    label: "Create schedule",
+    context: field("name", "cron"),
+    detail: {
+      promptField: "prompt",
+      inputOrder: AUTOMATION_FIELDS,
+      outputFields: AUTOMATION_OUTPUT,
+    },
+  },
+  create_heartbeat: {
+    label: "Create heartbeat",
+    context: field("name", "cron"),
+    detail: {
+      promptField: "prompt",
+      inputOrder: AUTOMATION_FIELDS,
+      outputFields: AUTOMATION_OUTPUT,
+    },
+  },
+  update_schedule: {
+    label: "Update schedule",
+    context: field("name", "id"),
+    detail: { promptField: "prompt", inputOrder: AUTOMATION_FIELDS },
+  },
+  list_schedules: { label: "List schedules" },
+  inspect_schedule: {
+    label: "Inspect schedule",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+  schedule_logs: {
+    label: "Read schedule logs",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+  run_schedule_once: {
+    label: "Run schedule",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+  pause_schedule: { label: "Pause schedule", context: field("id"), detail: { inputOrder: ["id"] } },
+  resume_schedule: {
+    label: "Resume schedule",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+  delete_schedule: {
+    label: "Delete schedule",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+  delete_heartbeat: {
+    label: "Delete heartbeat",
+    context: field("id"),
+    detail: { inputOrder: ["id"] },
+  },
+
+  // Providers
+  list_providers: { label: "List providers" },
+  list_models: {
+    label: "List models",
+    context: field("provider"),
+    detail: { inputOrder: ["provider"] },
+  },
+  list_profiles: { label: "List profiles" },
+  inspect_provider: {
+    label: "Inspect provider",
+    context: field("provider"),
+    detail: { inputOrder: ["provider", "cwd", "settings"] },
+  },
+
+  // Browser
+  browser_list_tabs: browser("List browser tabs"),
+  browser_new_tab: browser("Open browser tab", field("url")),
+  browser_close_tab: browser("Close browser tab", field("browserId")),
+  browser_navigate: browser("Navigate", field("url")),
+  browser_back: browser("Go back"),
+  browser_forward: browser("Go forward"),
+  browser_reload: browser("Reload page"),
+  browser_snapshot: browser("Snapshot page"),
+  browser_screenshot: browser("Take screenshot"),
+  browser_click: browser("Click element", field("ref")),
+  browser_hover: browser("Hover element", field("ref")),
+  browser_drag: browser("Drag element", field("sourceRef")),
+  browser_fill: browser("Fill field", field("ref")),
+  browser_select: browser("Select option", field("value", "ref")),
+  browser_type: browser("Type text", field("text")),
+  browser_keypress: browser("Press key", field("key")),
+  browser_upload: browser("Upload files", field("filePaths")),
+  browser_wait: browser("Wait for page", field("text", "url")),
+  browser_scroll: browser("Scroll page"),
+  browser_resize: browser("Resize browser", viewportContext()),
+  browser_logs: browser("Read browser logs"),
+  browser_evaluate: browser("Run JavaScript", field("function")),
+} satisfies Record<string, PaseoToolEntry>;
+
+export type PaseoToolName = keyof typeof PASEO_TOOL_CATALOG;
+
+export function getPaseoToolEntry(leafName: string): PaseoToolEntry | undefined {
+  return Object.prototype.hasOwnProperty.call(PASEO_TOOL_CATALOG, leafName)
+    ? PASEO_TOOL_CATALOG[leafName as PaseoToolName]
+    : undefined;
+}

packages/protocol/src/paseo-tool-presentation/detail-sections.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from "vitest";
 
-import { buildPaseoToolDetailSections } from "./paseo-tool-call-detail.js";
+import { buildPaseoToolDetailSections } from "./index.js";
 
 describe("Paseo tool-call detail presentation", () => {
   it.each(["mcp__paseo__create_agent", "paseo.create_agent", "paseo_remote.create_agent"])(

packages/protocol/src/paseo-tool-presentation/detail-sections.ts

@@ -1,4 +1,5 @@
-import { getPaseoToolLeafName } from "./tool-name-normalization.js";
+import { getPaseoToolLeafName } from "../tool-name-normalization.js";
+import { getPaseoToolEntry, type PaseoToolDetailSpec } from "./catalog.js";
 
 export interface PaseoToolDetailField {
   label: string;
@@ -17,161 +18,6 @@ export type PaseoToolDetailSection =
       fields: PaseoToolDetailField[];
     };
 
-interface ToolDetailSpec {
-  promptField?: string;
-  inputOrder?: readonly string[];
-  outputFields?: readonly string[];
-}
-
-const WORKSPACE_FIELDS = [
-  "title",
-  "workspaceId",
-  "projectId",
-  "isolation",
-  "path",
-  "mode",
-  "worktreeSlug",
-  "branchName",
-  "baseBranch",
-  "branch",
-  "prNumber",
-  "forge",
-] as const;
-const AGENT_FIELDS = [
-  "title",
-  "agentId",
-  "provider",
-  "workspaceId",
-  "cwd",
-  "sessionMode",
-  "modeId",
-  "background",
-  "notifyOnFinish",
-  "internal",
-  "settings",
-  "labels",
-] as const;
-const AUTOMATION_FIELDS = [
-  "name",
-  "id",
-  "cron",
-  "timezone",
-  "provider",
-  "cwd",
-  "isolation",
-  "maxRuns",
-  "expiresIn",
-  "clearExpires",
-] as const;
-const BROWSER_FIELDS = [
-  "browserId",
-  "url",
-  "ref",
-  "sourceRef",
-  "targetRef",
-  "value",
-  "text",
-  "key",
-  "button",
-  "doubleClick",
-  "modifiers",
-  "filePaths",
-  "fullPage",
-  "maxEntries",
-  "timeoutMs",
-  "deltaX",
-  "deltaY",
-  "width",
-  "height",
-  "function",
-] as const;
-
-const TOOL_SPECS: Readonly<Record<string, ToolDetailSpec>> = {
-  create_workspace: {
-    inputOrder: WORKSPACE_FIELDS,
-    outputFields: ["workspaceId", "projectId"],
-  },
-  list_workspaces: {},
-  archive_workspace: {
-    inputOrder: ["workspaceId"],
-    outputFields: ["workspaceId", "archivedAgentIds", "removedDirectory"],
-  },
-  rename_workspace: { inputOrder: ["title", "workspaceId"] },
-  create_agent: {
-    promptField: "initialPrompt",
-    inputOrder: AGENT_FIELDS,
-    outputFields: ["agentId", "status", "currentModeId", "cwd"],
-  },
-  send_agent_prompt: {
-    promptField: "prompt",
-    inputOrder: AGENT_FIELDS,
-    outputFields: ["status", "lastMessage", "permission"],
-  },
-  get_agent_status: { inputOrder: ["agentId"] },
-  list_agents: { inputOrder: ["cwd", "statuses", "sinceHours", "limit", "includeArchived"] },
-  cancel_agent: { inputOrder: ["agentId"] },
-  archive_agent: { inputOrder: ["agentId"] },
-  kill_agent: { inputOrder: ["agentId"] },
-  update_agent: { inputOrder: AGENT_FIELDS },
-  get_agent_activity: { inputOrder: ["agentId", "limit"] },
-  set_agent_mode: { inputOrder: ["agentId", "modeId"] },
-  list_workspace_scripts: { inputOrder: ["workspaceId"] },
-  start_workspace_script: { inputOrder: ["workspaceId", "scriptName"] },
-  stop_workspace_script: { inputOrder: ["workspaceId", "scriptName"] },
-  list_terminals: { inputOrder: ["cwd", "all"] },
-  create_terminal: { inputOrder: ["cwd", "workspaceId", "name", "command"] },
-  kill_terminal: { inputOrder: ["terminalId"] },
-  capture_terminal: { inputOrder: ["terminalId", "lines"] },
-  send_terminal_keys: { inputOrder: ["terminalId", "keys", "literal"] },
-  create_schedule: {
-    promptField: "prompt",
-    inputOrder: AUTOMATION_FIELDS,
-    outputFields: ["id", "status", "nextRunAt", "expiresAt"],
-  },
-  create_heartbeat: {
-    promptField: "prompt",
-    inputOrder: AUTOMATION_FIELDS,
-    outputFields: ["id", "status", "nextRunAt", "expiresAt"],
-  },
-  delete_heartbeat: { inputOrder: ["id"] },
-  list_schedules: {},
-  inspect_schedule: { inputOrder: ["id"] },
-  pause_schedule: { inputOrder: ["id"] },
-  resume_schedule: { inputOrder: ["id"] },
-  delete_schedule: { inputOrder: ["id"] },
-  update_schedule: { promptField: "prompt", inputOrder: AUTOMATION_FIELDS },
-  schedule_logs: { inputOrder: ["id"] },
-  run_schedule_once: { inputOrder: ["id"] },
-  list_providers: {},
-  list_models: { inputOrder: ["provider"] },
-  list_profiles: {},
-  inspect_provider: { inputOrder: ["provider", "cwd", "settings"] },
-  list_pending_permissions: {},
-  respond_to_permission: { inputOrder: ["agentId", "requestId", "response"] },
-  browser_list_tabs: {},
-  browser_new_tab: { inputOrder: BROWSER_FIELDS },
-  browser_snapshot: { inputOrder: BROWSER_FIELDS },
-  browser_click: { inputOrder: BROWSER_FIELDS },
-  browser_fill: { inputOrder: BROWSER_FIELDS },
-  browser_wait: { inputOrder: BROWSER_FIELDS },
-  browser_type: { inputOrder: BROWSER_FIELDS },
-  browser_keypress: { inputOrder: BROWSER_FIELDS },
-  browser_navigate: { inputOrder: BROWSER_FIELDS },
-  browser_back: { inputOrder: BROWSER_FIELDS },
-  browser_forward: { inputOrder: BROWSER_FIELDS },
-  browser_reload: { inputOrder: BROWSER_FIELDS },
-  browser_screenshot: { inputOrder: BROWSER_FIELDS },
-  browser_upload: { inputOrder: BROWSER_FIELDS },
-  browser_hover: { inputOrder: BROWSER_FIELDS },
-  browser_select: { inputOrder: BROWSER_FIELDS },
-  browser_drag: { inputOrder: BROWSER_FIELDS },
-  browser_logs: { inputOrder: BROWSER_FIELDS },
-  browser_evaluate: { inputOrder: BROWSER_FIELDS },
-  browser_scroll: { inputOrder: BROWSER_FIELDS },
-  browser_resize: { inputOrder: BROWSER_FIELDS },
-  browser_close_tab: { inputOrder: BROWSER_FIELDS },
-};
-
 const FIELD_LABELS: Readonly<Record<string, string>> = {
   agentId: "Agent",
   archivedAgentIds: "Archived agents",
@@ -330,7 +176,7 @@ export function buildPaseoToolDetailSections(
   const leafName = getPaseoToolLeafName(toolName);
   if (!leafName) return null;
 
-  const spec = TOOL_SPECS[leafName] ?? {};
+  const spec: PaseoToolDetailSpec = getPaseoToolEntry(leafName)?.detail ?? {};
   const sections: PaseoToolDetailSection[] = [];
   if (spec.promptField && isRecord(input)) {
     const prompt = input[spec.promptField];

packages/protocol/src/paseo-tool-presentation/index.test.ts

@@ -0,0 +1,141 @@
+import { describe, expect, it } from "vitest";
+
+import {
+  buildAgentMessageDisplay,
+  buildPaseoToolDisplay,
+  getPaseoToolTargetAgentId,
+  MAX_SUMMARY_CHARS,
+  PASEO_TOOL_NAMES,
+} from "./index.js";
+
+function display(toolName: string, input: unknown, targetAgentTitle?: string) {
+  return buildPaseoToolDisplay({
+    toolName,
+    detail: { type: "unknown", input, output: null },
+    ...(targetAgentTitle ? { targetAgentTitle } : {}),
+  });
+}
+
+describe("Paseo tool display", () => {
+  it.each([
+    [
+      "send_agent_prompt",
+      { agentId: "agt_1", prompt: "Fix the failing test" },
+      "Send message",
+      "Fix the failing test",
+    ],
+    ["create_agent", { title: "Reviewer", initialPrompt: "Review it" }, "Create agent", "Reviewer"],
+    ["create_agent", { initialPrompt: "Review it" }, "Create agent", "Review it"],
+    ["get_agent_status", { agentId: "agt_1" }, "Check agent", "agt_1"],
+    ["update_agent", { agentId: "agt_1", name: "Renamed" }, "Update agent", "Renamed"],
+    ["create_workspace", { path: "/tmp/repo/feature-x" }, "Create workspace", "feature-x"],
+    ["create_workspace", { title: "Docs", branchName: "docs" }, "Create workspace", "Docs"],
+    ["start_workspace_script", { scriptName: "web" }, "Start script", "web"],
+    ["send_terminal_keys", { terminalId: "t1", keys: "npm test" }, "Send keys", "npm test"],
+    ["create_schedule", { prompt: "Check CI", cron: "0 9 * * 1" }, "Create schedule", "0 9 * * 1"],
+    ["browser_navigate", { url: "https://paseo.sh" }, "Navigate", "https://paseo.sh"],
+    [
+      "browser_upload",
+      { ref: "@e1", filePaths: ["/a.png", "/b.png"] },
+      "Upload files",
+      "/a.png +1",
+    ],
+    ["browser_resize", { width: 800, height: 600 }, "Resize browser", "800×600"],
+  ])("presents %s with a fixed label and its context", (tool, input, label, summary) => {
+    expect(display(`mcp__paseo__${tool}`, input)).toEqual({ displayName: label, summary });
+  });
+
+  it("omits the summary when a call has no context", () => {
+    expect(display("mcp__paseo__list_agents", {})).toEqual({ displayName: "List agents" });
+  });
+
+  it("recognizes every Paseo namespace format", () => {
+    for (const name of ["mcp__paseo__kill_agent", "paseo.kill_agent", "paseo_remote.kill_agent"]) {
+      expect(display(name, { agentId: "agt_1" })?.displayName).toBe("Kill agent");
+    }
+  });
+
+  it("returns null outside the Paseo namespace, including speak", () => {
+    expect(display("Bash", {})).toBeNull();
+    expect(display("mcp__paseo__speak", { text: "hi" })).toBeNull();
+  });
+
+  it("humanizes a Paseo tool that has no catalog entry", () => {
+    expect(display("mcp__paseo__brand_new_tool", {})).toEqual({ displayName: "Brand new tool" });
+  });
+
+  it("prefers the known agent title over the agent ID", () => {
+    expect(display("mcp__paseo__cancel_agent", { agentId: "agt_1" }, "Reviewer")).toEqual({
+      displayName: "Cancel agent",
+      summary: "Reviewer",
+    });
+    expect(
+      getPaseoToolTargetAgentId("mcp__paseo__cancel_agent", {
+        type: "unknown",
+        input: { agentId: "agt_1" },
+        output: null,
+      }),
+    ).toBe("agt_1");
+    expect(
+      getPaseoToolTargetAgentId("Bash", { type: "unknown", input: { agentId: "x" }, output: null }),
+    ).toBeNull();
+  });
+
+  it("truncates a massive single-line prompt and collapses whitespace", () => {
+    const prompt = `Line one\n\n   line two ${"x".repeat(1_000_000)}`;
+    const summary = display("mcp__paseo__send_agent_prompt", { agentId: "a", prompt })?.summary;
+    expect(summary).toHaveLength(MAX_SUMMARY_CHARS);
+    expect(summary?.startsWith("Line one line two xxx")).toBe(true);
+    expect(summary?.endsWith("…")).toBe(true);
+  });
+
+  it("bounds the scan even when the prompt opens with a wall of whitespace", () => {
+    const prompt = `${" ".repeat(10_000)}hidden`;
+    const summary = display("mcp__paseo__send_agent_prompt", { agentId: "a", prompt })?.summary;
+    expect(summary).toBeUndefined();
+  });
+
+  it("keeps a short prompt intact", () => {
+    expect(
+      display("mcp__paseo__send_agent_prompt", { agentId: "a", prompt: " hi\nthere " })?.summary,
+    ).toBe("hi there");
+  });
+
+  it("catalogs tool names as lowercase leaf names", () => {
+    for (const name of PASEO_TOOL_NAMES) {
+      expect(name).toMatch(/^[a-z_]+$/);
+    }
+  });
+});
+
+describe("agent message display", () => {
+  it.each([
+    ["message", "Message received"],
+    ["finished", "Agent finished"],
+    ["errored", "Agent errored"],
+    ["permission-required", "Agent needs permission"],
+    ["closed", "Agent closed"],
+  ] as const)("labels %s noun-first with the sender as context", (event, label) => {
+    const result = buildAgentMessageDisplay({
+      event,
+      sender: { id: "srv::agt_1", title: "QA messenger" },
+      text: "Done.",
+    });
+    expect(result.displayName).toBe(label);
+    expect(result.summary).toBe("QA messenger");
+    expect(result.detail).toEqual({ type: "plain_text", text: "From agent: srv::agt_1\n\nDone." });
+  });
+
+  it("falls back to the sender ID and truncates a long title", () => {
+    expect(
+      buildAgentMessageDisplay({ event: "finished", sender: { id: "srv::agt_1" }, text: "" })
+        .summary,
+    ).toBe("srv::agt_1");
+    const summary = buildAgentMessageDisplay({
+      event: "finished",
+      sender: { id: "a", title: "t".repeat(500) },
+      text: "",
+    }).summary;
+    expect(summary).toHaveLength(MAX_SUMMARY_CHARS);
+  });
+});

packages/protocol/src/paseo-tool-presentation/index.ts

@@ -0,0 +1,85 @@
+import type { ToolCallDetail } from "../agent-types.js";
+import { getPaseoToolLeafName, isPaseoToolName } from "../tool-name-normalization.js";
+import { getPaseoToolEntry, PASEO_TOOL_CATALOG, type PaseoToolName } from "./catalog.js";
+import { toSummaryText } from "./summary-text.js";
+
+export { buildAgentMessageDisplay, type AgentMessageDisplay } from "./agent-message.js";
+export {
+  buildPaseoToolDetailSections,
+  type PaseoToolDetailField,
+  type PaseoToolDetailSection,
+} from "./detail-sections.js";
+export { MAX_SUMMARY_CHARS } from "./summary-text.js";
+export type { PaseoToolName };
+
+export interface PaseoToolDisplayInput {
+  toolName: string;
+  detail: ToolCallDetail;
+  /** Title of the agent named by the call's `agentId`, when the caller knows it. */
+  targetAgentTitle?: string;
+}
+
+export interface PaseoToolDisplay {
+  displayName: string;
+  summary?: string;
+}
+
+export const PASEO_TOOL_NAMES = Object.keys(PASEO_TOOL_CATALOG) as readonly PaseoToolName[];
+
+/** Returns null for tools outside the Paseo namespace. */
+export function buildPaseoToolDisplay(input: PaseoToolDisplayInput): PaseoToolDisplay | null {
+  const leafName = paseoLeafName(input.toolName);
+  if (!leafName) return null;
+  const entry = getPaseoToolEntry(leafName);
+  if (!entry) return { displayName: humanizeLeafName(leafName) };
+
+  const toolInput = readToolInput(input.detail);
+  const targetAgent = input.targetAgentTitle ?? readString(toolInput.agentId);
+  const summary = formatContext(entry.context?.(toolInput, targetAgent));
+  return { displayName: entry.label, ...(summary ? { summary } : {}) };
+}
+
+/** The agent a Paseo call acts on, so callers can resolve its title. */
+export function getPaseoToolTargetAgentId(
+  toolName: string,
+  detail: ToolCallDetail | undefined,
+): string | null {
+  if (!detail || !paseoLeafName(toolName)) return null;
+  return readString(readToolInput(detail).agentId) ?? null;
+}
+
+function paseoLeafName(toolName: string): string | null {
+  return isPaseoToolName(toolName) ? getPaseoToolLeafName(toolName) : null;
+}
+
+function readToolInput(detail: ToolCallDetail): Readonly<Record<string, unknown>> {
+  if (detail.type !== "unknown") return {};
+  const value = detail.input;
+  return typeof value === "object" && value !== null && !Array.isArray(value)
+    ? (value as Record<string, unknown>)
+    : {};
+}
+
+function readString(value: unknown): string | undefined {
+  return typeof value === "string" && value.length > 0 ? value : undefined;
+}
+
+function formatContext(value: unknown): string | undefined {
+  if (typeof value === "string") return toSummaryText(value);
+  if (typeof value === "number") return String(value);
+  if (Array.isArray(value)) {
+    const [first, ...rest] = value;
+    const head = typeof first === "string" ? toSummaryText(first) : undefined;
+    if (!head) return undefined;
+    return rest.length > 0 ? `${head} +${rest.length}` : head;
+  }
+  return undefined;
+}
+
+function humanizeLeafName(leafName: string): string {
+  const sentence = leafName
+    .replace(/[._-]+/g, " ")
+    .trim()
+    .toLowerCase();
+  return `${sentence[0]?.toUpperCase() ?? ""}${sentence.slice(1)}`;
+}

packages/protocol/src/paseo-tool-presentation/summary-text.ts

@@ -0,0 +1,21 @@
+/**
+ * Prompts and results can be one enormous line. Summaries are capped here so no
+ * consumer relies on its renderer to clip them.
+ */
+export const MAX_SUMMARY_CHARS = 120;
+// Bounds the whitespace scan: inputs can be megabytes.
+const SCAN_WINDOW_CHARS = MAX_SUMMARY_CHARS * 4;
+
+export function toSummaryText(value: string): string | undefined {
+  const isPartial = value.length > SCAN_WINDOW_CHARS;
+  const collapsed = value.slice(0, SCAN_WINDOW_CHARS).replace(/\s+/g, " ").trim();
+  if (!collapsed) return undefined;
+  if (collapsed.length <= MAX_SUMMARY_CHARS && !isPartial) return collapsed;
+  const kept = dropTrailingHighSurrogate(collapsed.slice(0, MAX_SUMMARY_CHARS - 1)).trimEnd();
+  return `${kept}…`;
+}
+
+function dropTrailingHighSurrogate(text: string): string {
+  const last = text.charCodeAt(text.length - 1);
+  return last >= 0xd800 && last <= 0xdbff ? text.slice(0, -1) : text;
+}

packages/protocol/src/speech/rpc-schemas.ts

@@ -0,0 +1,165 @@
+import { z } from "zod";
+
+// ---------------------------------------------------------------------------
+// Speech settings: the `speech` section of the mutable daemon config.
+// ---------------------------------------------------------------------------
+
+// Provider ids stay plain strings so an old client can parse a daemon that adds one.
+const SpeechSttSettingsSchema = z
+  .object({
+    provider: z.string(),
+    // Omitted means the provider's default model.
+    model: z.string().optional(),
+    language: z.string().optional(),
+  })
+  .passthrough();
+
+const SpeechTtsSettingsSchema = z
+  .object({
+    provider: z.string(),
+    model: z.string().optional(),
+    voice: z.string().optional(),
+  })
+  .passthrough();
+
+export const SpeechSettingsSchema = z
+  .object({
+    dictation: z
+      .object({
+        enabled: z.boolean(),
+        stt: SpeechSttSettingsSchema,
+      })
+      .passthrough(),
+    voiceMode: z
+      .object({
+        enabled: z.boolean(),
+        stt: SpeechSttSettingsSchema,
+        tts: SpeechTtsSettingsSchema,
+      })
+      .passthrough(),
+    openai: z
+      .object({
+        // The key itself is write-only; readers only learn whether one is set.
+        apiKeyConfigured: z.boolean(),
+        baseUrl: z.string().optional(),
+      })
+      .passthrough(),
+  })
+  .passthrough();
+
+// null clears a field back to its default. Changing `provider` without `model` clears
+// the model, because model ids belong to one provider.
+const SpeechSttSettingsPatchSchema = z
+  .object({
+    provider: z.string().optional(),
+    model: z.string().nullable().optional(),
+    language: z.string().nullable().optional(),
+  })
+  .passthrough();
+
+const SpeechTtsSettingsPatchSchema = z
+  .object({
+    provider: z.string().optional(),
+    model: z.string().nullable().optional(),
+    voice: z.string().nullable().optional(),
+  })
+  .passthrough();
+
+export const SpeechSettingsPatchSchema = z
+  .object({
+    dictation: z
+      .object({
+        enabled: z.boolean().optional(),
+        stt: SpeechSttSettingsPatchSchema.optional(),
+      })
+      .passthrough()
+      .optional(),
+    voiceMode: z
+      .object({
+        enabled: z.boolean().optional(),
+        stt: SpeechSttSettingsPatchSchema.optional(),
+        tts: SpeechTtsSettingsPatchSchema.optional(),
+      })
+      .passthrough()
+      .optional(),
+    openai: z
+      .object({
+        apiKey: z.string().nullable().optional(),
+        baseUrl: z.string().nullable().optional(),
+      })
+      .passthrough()
+      .optional(),
+  })
+  .passthrough();
+
+export type SpeechSettings = z.infer<typeof SpeechSettingsSchema>;
+export type SpeechSettingsPatch = z.infer<typeof SpeechSettingsPatchSchema>;
+
+// ---------------------------------------------------------------------------
+// Local speech models: catalog, install state, download, delete.
+// ---------------------------------------------------------------------------
+
+export const LocalSpeechModelSchema = z
+  .object({
+    id: z.string(),
+    // "stt" or "tts".
+    kind: z.string(),
+    label: z.string(),
+    description: z.string(),
+    languages: z.array(z.string()),
+    downloadSizeBytes: z.number(),
+    isDefault: z.boolean(),
+    // Selected by an enabled feature; the daemon keeps it installed.
+    inUse: z.boolean(),
+    // "installed" | "not_installed" | "downloading" | "extracting" | "failed".
+    status: z.string(),
+    receivedBytes: z.number().optional(),
+    totalBytes: z.number().optional(),
+    error: z.string().optional(),
+  })
+  .passthrough();
+
+export type LocalSpeechModel = z.infer<typeof LocalSpeechModelSchema>;
+
+export const SpeechLocalModelsListRequestSchema = z.object({
+  type: z.literal("speech.local_models.list.request"),
+  requestId: z.string(),
+});
+
+export const SpeechLocalModelsDownloadRequestSchema = z.object({
+  type: z.literal("speech.local_models.download.request"),
+  requestId: z.string(),
+  modelId: z.string(),
+});
+
+export const SpeechLocalModelsDeleteRequestSchema = z.object({
+  type: z.literal("speech.local_models.delete.request"),
+  requestId: z.string(),
+  modelId: z.string(),
+});
+
+export const SpeechLocalModelsListResponseSchema = z.object({
+  type: z.literal("speech.local_models.list.response"),
+  payload: z.object({
+    requestId: z.string(),
+    models: z.array(LocalSpeechModelSchema),
+    error: z.string().nullable(),
+  }),
+});
+
+// Resolves once the download starts; poll the list for progress.
+export const SpeechLocalModelsDownloadResponseSchema = z.object({
+  type: z.literal("speech.local_models.download.response"),
+  payload: z.object({
+    requestId: z.string(),
+    error: z.string().nullable(),
+  }),
+});
+
+export const SpeechLocalModelsDeleteResponseSchema = z.object({
+  type: z.literal("speech.local_models.delete.response"),
+  payload: z.object({
+    requestId: z.string(),
+    error: z.string().nullable(),
+  }),
+});

packages/protocol/src/tool-call-display.ts

@@ -1,6 +1,8 @@
-import { buildAgentMessageDisplay } from "./agent-message-display.js";
 import type { ToolCallTimelineItem } from "./agent-types.js";
-import { getPaseoToolLeafName, isPaseoToolName } from "./tool-name-normalization.js";
+import {
+  buildAgentMessageDisplay,
+  buildPaseoToolDisplay,
+} from "./paseo-tool-presentation/index.js";
 import { stripCwdPrefix } from "./path-utils.js";
 
 export type ToolCallDisplayInput = Pick<
@@ -8,6 +10,8 @@ export type ToolCallDisplayInput = Pick<
   "name" | "status" | "error" | "metadata" | "detail" | "agentMessage"
 > & {
   cwd?: string;
+  /** Title of the agent a Paseo call targets, when the caller knows it. */
+  targetAgentTitle?: string;
 };
 
 export interface ToolCallDisplayModel {
@@ -34,12 +38,6 @@ function humanizeToolName(name: string): string {
   if (!trimmed) {
     return name;
   }
-  if (isPaseoToolName(trimmed)) {
-    const leaf = getPaseoToolLeafName(trimmed);
-    if (leaf) {
-      return humanizeToolName(leaf);
-    }
-  }
   if (/[:./]/.test(trimmed) || trimmed.includes("__")) {
     return trimmed;
   }
@@ -152,8 +150,20 @@ function buildUnknownDetailOverride(input: ToolCallDisplayInput): DetailDisplay
 }
 
 export function buildToolCallDisplayModel(input: ToolCallDisplayInput): ToolCallDisplayModel {
-  if (input.agentMessage) {
-    return { displayName: buildAgentMessageDisplay(input.agentMessage).displayName };
+  const errorText = input.status === "failed" ? formatErrorText(input.error) : undefined;
+  const paseoDisplay = input.agentMessage
+    ? buildAgentMessageDisplay(input.agentMessage)
+    : buildPaseoToolDisplay({
+        toolName: input.name,
+        detail: input.detail,
+        targetAgentTitle: input.targetAgentTitle,
+      });
+  if (paseoDisplay) {
+    return {
+      displayName: paseoDisplay.displayName,
+      ...(paseoDisplay.summary ? { summary: paseoDisplay.summary } : {}),
+      ...(errorText ? { errorText } : {}),
+    };
   }
   const canonicalDisplay = buildCanonicalDetailDisplay(input);
   const unknownDetailOverride = buildUnknownDetailOverride(input);
@@ -162,7 +172,6 @@ export function buildToolCallDisplayModel(input: ToolCallDisplayInput): ToolCall
     canonicalDisplay.displayName ??
     humanizeToolName(input.name);
   const summary = unknownDetailOverride.summary ?? canonicalDisplay.summary;
-  const errorText = input.status === "failed" ? formatErrorText(input.error) : undefined;
 
   return {
     displayName,

packages/server/package.json

@@ -89,7 +89,7 @@
     "speech:transcribe:local": "tsx scripts/transcribe-local-wav.ts",
     "test": "npm run test:unit && npm run test:integration",
     "test:unit": "vitest run --fileParallelism --exclude \"**/*.e2e.test.ts\"",
-    "test:integration": "vitest run --maxWorkers=1 src/server/git-filename-diffs.e2e.test.ts src/server/daemon-e2e/checkout-diff-content.e2e.test.ts src/server/daemon-e2e/filesystem.e2e.test.ts src/server/daemon-e2e/file-download.e2e.test.ts src/server/daemon-e2e/cli-logs-follow.e2e.test.ts src/server/creation/creation.e2e.test.ts src/server/daemon-e2e/terminal-workspace-sdk.e2e.test.ts src/server/workspace-create-worktree-source.e2e.test.ts src/server/daemon-e2e/models.e2e.test.ts src/server/daemon-e2e/live-preferences.e2e.test.ts src/server/daemon-e2e/oversized-message.e2e.test.ts src/server/agent/model-catalog.e2e.test.ts src/server/plugins/plugin-paseo-api.e2e.test.ts && vitest run --maxWorkers=1 src/server/daemon-e2e/git-operations.e2e.test.ts -t \"merges into\" && vitest run --maxWorkers=1 src/server/session.create-agent-worktree-autoarchive.e2e.test.ts -t \"creates a worktree and auto-archives both\" && vitest run --maxWorkers=1 src/server/agent/providers/opencode-bridge.local.e2e.test.ts -t \"versioned runtime\" && vitest run --maxWorkers=1 src/server/daemon-e2e/relay-transport.e2e.test.ts -t \"oversized attachments\"",
+    "test:integration": "vitest run --maxWorkers=1 src/server/git-filename-diffs.e2e.test.ts src/server/daemon-e2e/checkout-diff-content.e2e.test.ts src/server/daemon-e2e/filesystem.e2e.test.ts src/server/daemon-e2e/file-download.e2e.test.ts src/server/daemon-e2e/cli-logs-follow.e2e.test.ts src/server/creation/creation.e2e.test.ts src/server/daemon-e2e/terminal-workspace-sdk.e2e.test.ts src/server/workspace-create-worktree-source.e2e.test.ts src/server/daemon-e2e/models.e2e.test.ts src/server/daemon-e2e/live-preferences.e2e.test.ts src/server/daemon-e2e/oversized-message.e2e.test.ts src/server/agent/model-catalog.e2e.test.ts src/server/plugins/plugin-paseo-api.e2e.test.ts && vitest run --maxWorkers=1 src/server/daemon-e2e/git-operations.e2e.test.ts src/server/session.create-agent-worktree-autoarchive.e2e.test.ts src/server/agent/providers/opencode-bridge.local.e2e.test.ts src/server/daemon-e2e/relay-transport.e2e.test.ts -t \"merges into|creates a worktree and auto-archives both|versioned runtime|oversized attachments\"",
     "test:hub-cli-contract": "vitest run --maxWorkers=1 src/server/hub/hub-cli-contract.test.ts",
     "test:integration:all": "npm run test:e2e",
     "test:integration:real": "vitest run real.e2e.test.ts",

packages/server/src/server/agent/activity-curator.test.ts

@@ -2,6 +2,7 @@ import { describe, expect, it } from "vitest";
 import { buildAgentForkContextAttachment, curateAgentActivity } from "./activity-curator.js";
 import type { AgentTimelineItem } from "./agent-sdk-types.js";
 import type { AgentTimelineRow } from "./agent-timeline-store-types.js";
+import { formatAgentMessage, projectAgentMessage } from "./agent-messages/index.js";
 
 function toolCallItem(params: {
   callId: string;
@@ -78,6 +79,28 @@ describe("curateAgentActivity", () => {
     );
   });
 
+  it("renders delivered agent messages with their event, sender, and body", () => {
+    const delivered = (source: Parameters<typeof formatAgentMessage>[0]["source"], text: string) =>
+      projectAgentMessage({
+        type: "user_message",
+        text: formatAgentMessage({ id: `msg-${text.length}`, source, text }),
+      })!;
+    const timeline: AgentTimelineItem[] = [
+      delivered(
+        { kind: "agent-message", agentId: "agt_lead", title: "CI lead" },
+        "Take ownership.\nRead the handoff.",
+      ),
+      delivered(
+        { kind: "agent-notification", agentId: "agt_child", event: "finished" },
+        "Child is done.",
+      ),
+    ];
+
+    expect(curateAgentActivity(timeline)).toBe(
+      "[Message received] CI lead\nTake ownership.\nRead the handoff.\n[Agent finished] agt_child\nChild is done.",
+    );
+  });
+
   it("renders user/assistant/reasoning entries", () => {
     const timeline: AgentTimelineItem[] = [
       { type: "user_message", text: "Hello" },

packages/server/src/server/agent/activity-curator.ts

@@ -1,7 +1,9 @@
 import type { AgentTimelineItem } from "./agent-sdk-types.js";
+import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { AgentAttachment } from "@getpaseo/protocol/messages";
 import type { AgentTimelineRow } from "./agent-timeline-store-types.js";
 import { isLikelyExternalToolName } from "@getpaseo/protocol/tool-name-normalization";
+import { buildAgentMessageDisplay } from "@getpaseo/protocol/paseo-tool-presentation/index";
 import { buildToolCallDisplayModel } from "@getpaseo/protocol/tool-call-display";
 import { projectTimelineRows } from "./timeline-projection.js";
 
@@ -119,6 +121,17 @@ function formatToolCallEntry(
   return activityEntry(summary ? `[${displayName}] ${summary}` : `[${displayName}]`);
 }
 
+function appendAgentMessageEntries(entries: ActivityEntry[], message: AgentMessage) {
+  const display = buildAgentMessageDisplay(message);
+  entries.push(
+    activityEntry(
+      display.summary ? `[${display.displayName}] ${display.summary}` : `[${display.displayName}]`,
+    ),
+  );
+  const body = message.text.trim();
+  if (body) entries.push(activityEntry(body));
+}
+
 function curateProjectedActivityEntries(
   items: readonly AgentTimelineItem[],
   options?: ActivityCuratorOptions,
@@ -146,6 +159,10 @@ function curateProjectedActivityEntries(
         appendTextEntry(entries, item, options);
         break;
       case "tool_call": {
+        if (item.agentMessage) {
+          appendAgentMessageEntries(entries, item.agentMessage);
+          break;
+        }
         entries.push(formatToolCallEntry(item, options));
         if (item.detail.type === "sub_agent" && item.detail.log.trim()) {
           entries.push(activityEntry(item.detail.log.trim()));

packages/server/src/server/agent/agent-sdk-types.ts

@@ -8,6 +8,7 @@ import type {
   ProviderOptions,
   ToolPolicy,
 } from "@getpaseo/protocol/agent-types";
+import type { AgentMessage } from "@getpaseo/protocol/agent-message";
 import type { AgentAttachment } from "@getpaseo/protocol/messages";
 import type { PaseoToolCatalog } from "./tools/types.js";
 
@@ -342,6 +343,8 @@ interface ToolCallBase {
   name: string;
   detail: ToolCallDetail;
   metadata?: Record<string, unknown>;
+  /** Set when the row is a delivered agent message rather than a provider tool call. */
+  agentMessage?: AgentMessage;
 }
 
 type ToolCallRunningTimelineItem = ToolCallBase & {

packages/server/src/server/agent/mcp-server.test.ts

@@ -66,6 +66,7 @@ import type { ForgeService } from "../../services/forge-service.js";
 import { areEquivalentPaths } from "../../utils/path.js";
 import type { TerminalManager } from "../../terminal/terminal-manager.js";
 import { PARENT_AGENT_ID_LABEL } from "@getpaseo/protocol/agent-labels";
+import { PASEO_TOOL_NAMES } from "@getpaseo/protocol/paseo-tool-presentation/index";
 import { MutableDaemonConfigSchema, type AgentProfile } from "@getpaseo/protocol/messages";
 import type { DaemonConfigStore } from "../daemon-config-store.js";
 import type { BrowserToolsBroker, BrowserToolsExecuteInput } from "../browser-tools/broker.js";
@@ -888,6 +889,40 @@ describe("bundled Paseo skill", () => {
   });
 });
 
+describe("Paseo tool timeline presentation", () => {
+  it("catalogs a timeline label for every advertised tool", async () => {
+    const server = await createAgentMcpServer({
+      agentManager: new BoundaryAgentManagerFake() as AgentManager,
+      agentStorage: new BoundaryAgentStorageFake() as AgentStorage,
+      providerSnapshotManager:
+        new BoundaryProviderSnapshotManagerFake() as unknown as ProviderSnapshotManager,
+      browserToolsEnabled: true,
+      browserToolsBroker: new FakeBrowserToolsBroker({
+        requestId: "req-catalog",
+        ok: true,
+        result: { command: "list_tabs", tabs: [] },
+      }) as BrowserToolsBroker,
+      callerAgentId: "agent-1",
+      logger: createTestLogger(),
+    });
+    const client = await connectInMemoryMcpClient(server);
+
+    try {
+      const { tools } = await client.listTools();
+      const cataloged = new Set<string>(PASEO_TOOL_NAMES);
+      // speak renders as a voice message, not a tool call row.
+      const uncataloged = tools
+        .map((tool) => tool.name)
+        .filter((name) => name !== "speak" && !cataloged.has(name));
+      expect(tools.length).toBeGreaterThan(40);
+      expect(uncataloged).toEqual([]);
+    } finally {
+      await client.close();
+      await server.close();
+    }
+  });
+});
+
 describe("browser MCP tools", () => {
   const logger = createTestLogger();
 

packages/server/src/server/agent/plugin-provider.test.ts

@@ -761,6 +761,72 @@ describe("PluginAgentClientRegistry", () => {
     await expect.poll(harness.closeCount).toBe(1);
     expect(harness.inputs.map((input) => input.type)).toContain("session.close");
   });
+
+  test("delivers a supported steer to the active turn", async () => {
+    const harness = createProviderHarness({
+      capabilities: [...CAPABILITIES, "prompt.steer"],
+      handleInput: async (input, emit) => {
+        if (input.type !== "session.prompt") return false;
+        emit({
+          type: "session.prompt_result",
+          sessionId: input.sessionId,
+          clientMessageId: input.prompt.clientMessageId,
+          result: { type: "steer", turnId: "turn-1" },
+        });
+        return true;
+      },
+    });
+    const registry = new PluginAgentClientRegistry(createTestLogger());
+    registry.replace([harness.registration]);
+    const client = registry.clients()[harness.registration.id]!;
+    const session = await client.createSession({ provider: harness.registration.id, cwd: "/tmp" });
+    try {
+      await expect(
+        session.steerActiveTurn!("follow up", {
+          expectedTurnId: "turn-1",
+          clientMessageId: "steer-1",
+          clearPendingPermissions: true,
+        }),
+      ).resolves.toEqual({ status: "accepted" });
+      expect(harness.inputs.find((input) => input.type === "session.prompt")).toMatchObject({
+        prompt: {
+          delivery: "steer",
+          clientMessageId: "steer-1",
+          input: { type: "message", content: [{ type: "text", text: "follow up" }] },
+          clearPendingPermissions: true,
+        },
+      });
+    } finally {
+      await session.close();
+      registry.replace([]);
+    }
+  });
+
+  test("returns unavailable when steering a provider without prompt.steer capability", async () => {
+    const harness = createProviderHarness({
+      capabilities: [
+        "prompt.message",
+        "session.configure",
+        "session.persistence",
+        "session.subsession",
+        "permission",
+      ],
+    });
+    const registry = new PluginAgentClientRegistry(createTestLogger());
+    registry.replace([harness.registration]);
+    const session = await registry.clients()[harness.registration.id]!.createSession({
+      provider: harness.registration.id,
+      cwd: "/workspace",
+    });
+    try {
+      const result = await session.steerActiveTurn!("hello", { expectedTurnId: "turn-1" });
+      expect(result).toEqual({ status: "unavailable" });
+      expect(harness.inputs.filter((input) => input.type === "session.prompt")).toHaveLength(0);
+    } finally {
+      await session.close();
+      registry.replace([]);
+    }
+  });
 });
 
 type RequestKind = "session.open" | "catalog" | "session.configure" | "session.prompt";

packages/server/src/server/agent/plugin-provider.ts

@@ -1175,6 +1175,9 @@ class PluginAgentSession implements AgentSession {
     prompt: AgentPromptInput,
     options: SteerActiveTurnOptions,
   ): Promise<SteerResult> {
+    if (!this.bridge.negotiatedCapabilities.includes("prompt.steer")) {
+      return { status: "unavailable" };
+    }
     const result = await this.bridge.prompt({
       clientMessageId: options.clientMessageId ?? randomUUID(),
       delivery: "steer",

packages/server/src/server/authorization/operation-permissions.ts

@@ -174,6 +174,9 @@ const INBOUND_PERMISSION = {
   set_agent_model_request: "workspace.write",
   set_agent_thinking_request: "workspace.write",
   set_daemon_config_request: "daemon.manage",
+  "speech.local_models.list.request": "daemon.read",
+  "speech.local_models.download.request": "daemon.manage",
+  "speech.local_models.delete.request": "daemon.manage",
   set_voice_mode: "workspace.write",
   shutdown_server_request: "daemon.manage",
   start_workspace_script_request: "workspace.write",
@@ -399,6 +402,9 @@ const OUTBOUND_PERMISSION = {
   set_agent_model_response: "workspace.write",
   set_agent_thinking_response: "workspace.write",
   set_daemon_config_response: "daemon.manage",
+  "speech.local_models.list.response": "daemon.read",
+  "speech.local_models.download.response": "daemon.manage",
+  "speech.local_models.delete.response": "daemon.manage",
   set_voice_mode_response: "workspace.write",
   start_workspace_script_response: "workspace.write",
   stash_list_response: "workspace.read",

packages/server/src/server/bootstrap.ts

@@ -131,6 +131,7 @@ import type { OpenAiSpeechProviderConfig } from "./speech/providers/openai/confi
 import type { LocalSpeechProviderConfig } from "./speech/providers/local/config.js";
 import type { RequestedSpeechProviders } from "./speech/speech-types.js";
 import { createSpeechService } from "./speech/speech-runtime.js";
+import { createSpeechSettingsOwner } from "./speech/speech-settings.js";
 import { AgentManager } from "./agent/agent-manager.js";
 import { AgentStorage } from "./agent/agent-storage.js";
 import { attachAgentStoragePersistence } from "./persistence-hooks.js";
@@ -370,6 +371,8 @@ export interface PaseoSpeechSttLanguages {
 
 export interface PaseoSpeechConfig {
   providers: RequestedSpeechProviders;
+  // Where local models live, whether or not a feature currently uses the local provider.
+  localModelsDir: string;
   sttLanguages?: PaseoSpeechSttLanguages;
   local?: PaseoLocalSpeechConfig;
 }
@@ -537,6 +540,10 @@ function resolveExpressTrustProxySetting(config: PaseoDaemonConfig): true | stri
   return config.trustedProxies ?? ["loopback"];
 }
 
+function resolveReloadEnv(config: PaseoDaemonConfig): NodeJS.ProcessEnv {
+  return config.configReload?.env ?? process.env;
+}
+
 function createInitialMutableDaemonConfig(config: PaseoDaemonConfig): MutableDaemonConfig {
   const providers = config.providerOverrides ?? {};
 
@@ -596,13 +603,24 @@ export async function createPaseoDaemon(
   const elapsed = () => `${(performance.now() - bootstrapStart).toFixed(0)}ms`;
   const daemonVersion = config.daemonVersion ?? resolveDaemonVersion(import.meta.url);
   const initialMutableConfig = createInitialMutableDaemonConfig(config);
+  const speechService = createSpeechService({
+    logger,
+    openaiConfig: config.openai,
+    speechConfig: config.speech,
+  });
+  logger.info({ elapsed: elapsed() }, "Speech service created");
   const daemonConfigStore = new DaemonConfigStore(config.paseoHome, initialMutableConfig, logger, {
     relayEnabledMutable: config.relayEnabledMutable ?? true,
     startupPersisted: config.configReload?.startupPersisted,
+    speech: createSpeechSettingsOwner({
+      paseoHome: config.paseoHome,
+      env: resolveReloadEnv(config),
+      speechService,
+    }),
     reloadSource: {
       resolve: (persisted) => {
         const reloaded = resolveConfigFromPersisted(config.paseoHome, persisted, {
-          env: config.configReload?.env ?? process.env,
+          env: resolveReloadEnv(config),
           cli: config.configReload?.cli,
           relayEnabledFallback: config.configReload?.relayEnabledFallback,
         });
@@ -1591,13 +1609,6 @@ export async function createPaseoDaemon(
     logger.info({ route: agentMcpRoute, enabled: mcpEnabled }, "Agent MCP route mounted");
   }
 
-  const speechService = createSpeechService({
-    logger,
-    openaiConfig: config.openai,
-    speechConfig: config.speech,
-  });
-  logger.info({ elapsed: elapsed() }, "Speech service created");
-
   logger.info({ elapsed: elapsed() }, "Bootstrap complete, ready to start listening");
 
   const start = async () => {

packages/server/src/server/daemon-client.e2e.test.ts

@@ -1318,9 +1318,9 @@ test("emits disabled voice capability reasons on fresh daemon startup", async ()
     expect(voice).toBeTruthy();
 
     expect(voice?.dictation.enabled).toBe(false);
-    expect(voice?.dictation.reason).toBe("Dictation is disabled in daemon config.");
+    expect(voice?.dictation.reason).toBe("Dictation is off. Turn it on in Settings > Voice.");
     expect(voice?.voice.enabled).toBe(false);
-    expect(voice?.voice.reason).toBe("Realtime voice is disabled in daemon config.");
+    expect(voice?.voice.reason).toBe("Voice mode is off. Turn it on in Settings > Voice.");
   } finally {
     await client.close().catch(() => undefined);
     await isolatedCtx.cleanup();

packages/server/src/server/daemon-config-store.test.ts

@@ -5,6 +5,7 @@ import { afterEach, describe, expect, test } from "vitest";
 
 import { DaemonConfigStore, applyMutableProviderConfigToOverrides } from "./daemon-config-store.js";
 import { loadPersistedConfig } from "./persisted-config.js";
+import { readSpeechSettings } from "./speech/speech-settings.js";
 import type { PersistedConfig } from "./persisted-config.js";
 import type { MutableDaemonConfig } from "@getpaseo/protocol/messages";
 
@@ -1193,3 +1194,110 @@ describe("DaemonConfigStore reload", () => {
     });
   });
 });
+
+describe("DaemonConfigStore speech settings", () => {
+  const tempDirs: string[] = [];
+
+  afterEach(() => {
+    for (const dir of tempDirs) rmSync(dir, { recursive: true, force: true });
+  });
+
+  function createSpeechStore(initialPersisted?: PersistedConfig) {
+    const paseoHome = mkdtempSync(path.join(tmpdir(), "paseo-daemon-config-speech-"));
+    tempDirs.push(paseoHome);
+    if (initialPersisted) {
+      writeFileSync(
+        path.join(paseoHome, "config.json"),
+        `${JSON.stringify(initialPersisted, null, 2)}\n`,
+      );
+    }
+    const persisted = loadPersistedConfig(paseoHome);
+    const applied: PersistedConfig[] = [];
+    const speech = {
+      read: (next: PersistedConfig) => readSpeechSettings(next, {}),
+      apply: (next: PersistedConfig) => applied.push(next),
+    };
+    const store = new DaemonConfigStore(paseoHome, reloadableConfig(persisted), undefined, {
+      speech,
+      reloadSource: {
+        resolve: (next) => ({ mutable: reloadableConfig(next), overrideControlledPaths: [] }),
+      },
+    });
+    return { paseoHome, store, applied, persisted };
+  }
+
+  test("keeps voice mode off until it is turned on", () => {
+    const { paseoHome, store } = createSpeechStore();
+
+    expect(store.get().speech?.dictation.enabled).toBe(true);
+    expect(store.get().speech?.voiceMode.enabled).toBe(false);
+
+    const result = store.patch({ speech: { voiceMode: { enabled: true } } });
+
+    expect(result.speech?.voiceMode.enabled).toBe(true);
+    expect(loadPersistedConfig(paseoHome).features?.voiceMode?.enabled).toBe(true);
+  });
+
+  test("stores the OpenAI key without ever returning it", () => {
+    const { paseoHome, store, applied } = createSpeechStore();
+
+    const result = store.patch({
+      speech: { dictation: { stt: { provider: "openai" } }, openai: { apiKey: " sk-test " } },
+    });
+
+    expect(result.speech?.openai).toEqual({ apiKeyConfigured: true });
+    expect(JSON.stringify(result)).not.toContain("sk-test");
+    expect(loadPersistedConfig(paseoHome).providers?.openai?.apiKey).toBe("sk-test");
+    expect(applied).toHaveLength(1);
+  });
+
+  test("applies a replaced key even though the visible settings do not change", () => {
+    const { store, applied } = createSpeechStore({
+      version: 1,
+      providers: { openai: { apiKey: "sk-old" } },
+    });
+
+    store.patch({ speech: { openai: { apiKey: "sk-new" } } });
+
+    expect(applied.map((next) => next.providers?.openai?.apiKey)).toEqual(["sk-new"]);
+  });
+
+  test("switching provider clears the previous provider's model", () => {
+    const { paseoHome, store } = createSpeechStore({
+      version: 1,
+      features: { dictation: { stt: { provider: "local", model: "parakeet-tdt-0.6b-v3-int8" } } },
+    });
+
+    const result = store.patch({ speech: { dictation: { stt: { provider: "openai" } } } });
+
+    expect(result.speech?.dictation.stt).toEqual({ provider: "openai" });
+    expect(loadPersistedConfig(paseoHome).features?.dictation?.stt).toEqual({
+      provider: "openai",
+    });
+  });
+
+  test("rejects a local model id outside the catalog without persisting it", () => {
+    const { paseoHome, store, applied } = createSpeechStore();
+
+    expect(() =>
+      store.patch({ speech: { voiceMode: { tts: { provider: "local", model: "nope" } } } }),
+    ).toThrow("Unknown local voice model: nope");
+    expect(loadPersistedConfig(paseoHome).features?.voiceMode).toBeUndefined();
+    expect(applied).toEqual([]);
+  });
+
+  test("reload applies hand-edited speech settings without a restart", () => {
+    const { paseoHome, store, applied, persisted } = createSpeechStore();
+    writeFileSync(
+      path.join(paseoHome, "config.json"),
+      `${JSON.stringify({ ...persisted, features: { voiceMode: { enabled: false } } }, null, 2)}\n`,
+    );
+
+    const result = store.reload();
+
+    expect(result.appliedPaths).toContain("features.voiceMode");
+    expect(result.restartRequiredPaths).toEqual([]);
+    expect(store.get().speech?.voiceMode.enabled).toBe(false);
+    expect(applied).toHaveLength(1);
+  });
+});

packages/server/src/server/daemon-config-store.ts

@@ -9,6 +9,8 @@ import {
   MutableDaemonConfigPatchSchema,
 } from "@getpaseo/protocol/messages";
 import type { AgentSkillSelection } from "@getpaseo/protocol/messages";
+import type { SpeechSettings, SpeechSettingsPatch } from "@getpaseo/protocol/speech/rpc-schemas";
+import { mergeSpeechSettingsPatch, type SpeechSettingsOwner } from "./speech/speech-settings.js";
 
 export type { MutableDaemonConfig, MutableDaemonConfigPatch } from "@getpaseo/protocol/messages";
 
@@ -31,8 +33,11 @@ interface SupportedMutableConfigPatch {
   skills?: MutableDaemonConfig["skills"];
   pluginsEnabled?: boolean;
   plugins?: MutableDaemonConfig["plugins"];
+  speech?: SpeechSettingsPatch;
 }
 
+const SPEECH_PERSISTED_PATHS = ["features.dictation", "features.voiceMode", "providers.openai"];
+
 interface LoggerLike {
   child(bindings: Record<string, unknown>): LoggerLike;
   info(...args: unknown[]): void;
@@ -276,6 +281,7 @@ function pickSupportedPatchFields(patch: MutableDaemonConfigPatch): SupportedMut
     ...(patch.agentProfiles !== undefined ? { agentProfiles: patch.agentProfiles } : {}),
     ...(patch.pluginsEnabled !== undefined ? { pluginsEnabled: patch.pluginsEnabled } : {}),
     ...(patch.plugins !== undefined ? { plugins: patch.plugins } : {}),
+    ...(patch.speech !== undefined ? { speech: patch.speech } : {}),
   };
 }
 
@@ -318,6 +324,7 @@ export class DaemonConfigStore {
   private readonly relayEnabledMutable: boolean;
   private readonly reloadSource: DaemonConfigReloadSource | undefined;
   private readonly startupPersisted: PersistedConfig;
+  private readonly speechOwner: SpeechSettingsOwner | undefined;
   private lastKnownPersisted: PersistedConfig;
 
   constructor(
@@ -328,18 +335,21 @@ export class DaemonConfigStore {
       relayEnabledMutable?: boolean;
       reloadSource?: DaemonConfigReloadSource;
       startupPersisted?: PersistedConfig;
+      speech?: SpeechSettingsOwner;
     } = {},
   ) {
     this.paseoHome = paseoHome;
     this.logger = getLogger(logger);
+    this.relayEnabledMutable = options.relayEnabledMutable ?? true;
+    this.reloadSource = options.reloadSource;
+    this.speechOwner = options.speech;
+    this.startupPersisted = options.startupPersisted ?? loadPersistedConfig(paseoHome, this.logger);
+    this.lastKnownPersisted = this.startupPersisted;
     this.current = MutableDaemonConfigSchema.parse({
       ...initial,
       relay: initial.relay ?? { enabled: true },
+      ...this.readSpeech(this.startupPersisted),
     });
-    this.relayEnabledMutable = options.relayEnabledMutable ?? true;
-    this.reloadSource = options.reloadSource;
-    this.startupPersisted = options.startupPersisted ?? loadPersistedConfig(paseoHome, this.logger);
-    this.lastKnownPersisted = this.startupPersisted;
   }
 
   public get(): MutableDaemonConfig {
@@ -361,9 +371,11 @@ export class DaemonConfigStore {
         "Relay is controlled by a daemon launch override. Remove PASEO_RELAY_ENABLED or the relay CLI flag before changing it here.",
       );
     }
-    const { removeProviders = [], ...configPatch } = parsedPatch;
+    const { removeProviders = [], ...patch } = parsedPatch;
+    const { speech: speechPatch, ...configPatch } = patch;
     const removedProviders = Array.from(new Set(removeProviders));
     const merged = deepMerge(this.current, configPatch);
+    if (speechPatch !== undefined) merged.speech = this.readPatchedSpeech(speechPatch);
     if (parsedPatch.skills?.selection !== undefined) {
       merged.skills = { selection: parsedPatch.skills.selection };
     }
@@ -377,30 +389,47 @@ export class DaemonConfigStore {
 
     const configChanged = !isEqualValue(this.current, next);
 
-    if (!configChanged && removedProviders.length === 0) {
+    // A replaced API key leaves the speech view unchanged, so a speech patch always persists.
+    if (!configChanged && removedProviders.length === 0 && speechPatch === undefined) {
       return this.current;
     }
 
     const { previous: persistedBeforePatch, knownNext } = this.persistConfig(
-      configPatch,
+      patch,
       removedProviders,
     );
-    if (!configChanged) {
-      this.lastKnownPersisted = knownNext;
-      return this.current;
-    }
-
-    try {
-      this.applyReplacement(next, { removedProviders });
-      this.lastKnownPersisted = knownNext;
-    } catch (error) {
-      savePersistedConfig(this.paseoHome, persistedBeforePatch, this.logger);
-      throw error;
+    const speechChanged = this.speechPersistedChanged(this.lastKnownPersisted, knownNext);
+    if (configChanged) {
+      try {
+        this.applyReplacement(next, { removedProviders });
+      } catch (error) {
+        savePersistedConfig(this.paseoHome, persistedBeforePatch, this.logger);
+        throw error;
+      }
     }
+    this.lastKnownPersisted = knownNext;
+    if (speechChanged) this.speechOwner?.apply(knownNext);
 
     return this.current;
   }
 
+  private readSpeech(persisted: PersistedConfig): Pick<MutableDaemonConfig, "speech"> {
+    return this.speechOwner ? { speech: this.speechOwner.read(persisted) } : {};
+  }
+
+  private readPatchedSpeech(speechPatch: SpeechSettingsPatch): SpeechSettings {
+    if (!this.speechOwner) {
+      throw new Error("Speech settings are unavailable for this daemon instance");
+    }
+    return this.speechOwner.read(mergeSpeechSettingsPatch(this.lastKnownPersisted, speechPatch));
+  }
+
+  private speechPersistedChanged(previous: PersistedConfig, next: PersistedConfig): boolean {
+    return diffPaths(previous, next).some((path) =>
+      SPEECH_PERSISTED_PATHS.some((owner) => pathBelongsTo(path, owner)),
+    );
+  }
+
   public reload(): DaemonConfigReloadResult {
     if (!this.reloadSource) {
       throw new Error("Daemon config reload is unavailable for this daemon instance");
@@ -413,6 +442,7 @@ export class DaemonConfigStore {
     const desired = MutableDaemonConfigSchema.parse({
       ...resolved.mutable,
       plugins: this.current.plugins,
+      ...this.readSpeech(persisted),
     });
     const changedSinceLastApply = diffPaths(this.lastKnownPersisted, persisted);
     const overrideControlledPaths = compactOwnedPaths(
@@ -421,7 +451,7 @@ export class DaemonConfigStore {
       ),
       resolved.overrideControlledPaths,
     );
-    const appliedPaths = RELOADABLE_PATHS.filter((persistedPath) => {
+    const appliedPaths: string[] = RELOADABLE_PATHS.filter((persistedPath) => {
       if (resolved.overrideControlledPaths.some((owner) => pathBelongsTo(persistedPath, owner))) {
         return false;
       }
@@ -438,6 +468,8 @@ export class DaemonConfigStore {
       diffPaths(this.startupPersisted, persisted).filter((path) => {
         if (path === "$schema" || path === "version") return false;
         if (RELOADABLE_PATHS.some((owner) => pathBelongsTo(path, owner))) return false;
+        if (this.speechOwner && SPEECH_PERSISTED_PATHS.some((owner) => pathBelongsTo(path, owner)))
+          return false;
         return !resolved.overrideControlledPaths.some((owner) => pathBelongsTo(path, owner));
       }),
       [],
@@ -446,8 +478,17 @@ export class DaemonConfigStore {
     const removedProviders = Object.keys(this.current.providers).filter(
       (provider) => !(provider in desired.providers),
     );
+    const speechChanged = this.speechPersistedChanged(this.lastKnownPersisted, persisted);
     this.applyReplacement(desired, { removedProviders });
     this.lastKnownPersisted = persisted;
+    if (speechChanged && this.speechOwner) {
+      this.speechOwner.apply(persisted);
+      appliedPaths.push(
+        ...SPEECH_PERSISTED_PATHS.filter((owner) =>
+          changedSinceLastApply.some((path) => pathBelongsTo(path, owner)),
+        ),
+      );
+    }
 
     return {
       appliedPaths: [...appliedPaths].sort(),
@@ -584,8 +625,9 @@ function mergeMutablePatchIntoPersistedConfig(params: {
   const { persisted, patch, removeProviders, persistRelayEnabled } = params;
   const daemon = mergeMutableDaemonPatch(persisted.daemon, patch, persistRelayEnabled);
   const agents = mergeMutableAgentPatch(persisted.agents, patch, removeProviders);
+  const withSpeech = patch.speech ? mergeSpeechSettingsPatch(persisted, patch.speech) : persisted;
   return {
-    ...persisted,
+    ...withSpeech,
     ...(patch.pluginsEnabled !== undefined ? { pluginsEnabled: patch.pluginsEnabled } : {}),
     ...(patch.plugins !== undefined ? { plugins: patch.plugins } : {}),
     ...(daemon ? { daemon } : { daemon: undefined }),

packages/server/src/server/plugins/usage-sources/index.test.ts

@@ -556,3 +556,208 @@ test("a hung login records its own timeout and still tries the next login", asyn
     { harness: "OpenCode", report: { status: "error", error: "Login rejected" } },
   ]);
 });
+
+test("retains the last successful poll across failures, cache expiry, and recovery", async () => {
+  let now = 0;
+  let report: unknown = {
+    status: "available",
+    windows: [{ id: "week", label: "Weekly", usedPct: 42 }],
+  };
+  const registry = new UsageSourceRegistry(() => now);
+  registry.register(
+    source({
+      id: "quota",
+      discover: async () => [{ key: "account", input: {} }],
+      fetch: async () => report,
+    }),
+  );
+  registry.register(source({ id: "other", discover: async () => [{ key: "account", input: {} }] }));
+  const [success] = await registry.listReports();
+  now = 360_000;
+  // An unrelated write evicts the expired fetch result, but must not discard its snapshot.
+  await registry.listReports({ reportIds: ["other:account"], forceRefresh: true });
+  report = { status: "error", error: "Rate limited" };
+  const [failure] = await registry.listReports({ reportIds: ["quota:account"] });
+  expect(failure).toMatchObject({
+    fetchedAt: new Date(now).toISOString(),
+    report,
+    lastSuccessful: { fetchedAt: success!.fetchedAt, report: success!.report },
+  });
+  now += 360_000;
+  const [repeated] = await registry.listReports({ reportIds: ["quota:account"] });
+  expect(repeated?.lastSuccessful).toEqual(failure?.lastSuccessful);
+  report = { status: "unavailable", problem: { kind: "no_quota", detail: "No quota" } };
+  const [unavailable] = await registry.listReports({
+    reportIds: ["quota:account"],
+    forceRefresh: true,
+  });
+  expect(unavailable?.lastSuccessful).toEqual(failure?.lastSuccessful);
+  now += 1000;
+  report = { status: "available", windows: [{ id: "week", label: "Weekly", usedPct: 43 }] };
+  const [recovered] = await registry.listReports({
+    reportIds: ["quota:account"],
+    forceRefresh: true,
+  });
+  expect(recovered?.report).toEqual(report);
+  expect(recovered?.lastSuccessful).toBeUndefined();
+  expect(recovered?.fetchedAt).toBe(new Date(now).toISOString());
+});
+
+test("successful history is isolated by login set and pruned when identities retire", async () => {
+  let login = "old";
+  let present = true;
+  let available = true;
+  const registry = new UsageSourceRegistry();
+  const fixture = source({
+    id: "source",
+    discover: async () => (present ? [{ key: "same", input: login }] : []),
+    fetch: async () =>
+      available ? { status: "available", windows: [] } : { status: "error", error: "failed" },
+  });
+  registry.register(fixture);
+  await registry.listReports();
+  available = false;
+  login = "new";
+  expect((await registry.listReports({ forceRefresh: true }))[0]?.lastSuccessful).toBeUndefined();
+  login = "old";
+  expect((await registry.listReports({ forceRefresh: true }))[0]?.lastSuccessful).toBeUndefined();
+  available = true;
+  await registry.listReports({ forceRefresh: true });
+  present = false;
+  expect(await registry.listReports()).toEqual([]);
+  present = true;
+  available = false;
+  expect((await registry.listReports())[0]?.lastSuccessful).toBeUndefined();
+  available = true;
+  await registry.listReports({ forceRefresh: true });
+  registry.unregister("source");
+  registry.register(fixture);
+  available = false;
+  expect((await registry.listReports())[0]?.lastSuccessful).toBeUndefined();
+});
+
+test("host fallback history never supplies an agent's failed login, and removed agents lose history", async () => {
+  const sessions = new Map([["agent", { provider: "codex", env: {}, sessionKey: "one" }]]);
+  let available = true;
+  const registry = new UsageSourceRegistry(Date.now, 300_000, undefined, {
+    hasAgent: (id) => sessions.has(id),
+    usageSession: (id) => sessions.get(id) ?? null,
+  });
+  registry.register({
+    id: "source",
+    label: "Source",
+    discover: async (scope) =>
+      (scope.kind === "global" ? ["host", "agent"] : ["agent"]).map((input) => ({
+        key: "same",
+        input,
+      })),
+    fetch: async () =>
+      available ? { status: "available", windows: [] } : { status: "error", error: "failed" },
+  });
+  await registry.listReports();
+  available = false;
+  expect((await registry.listReports({ agentId: "agent" }))[0]?.lastSuccessful).toBeUndefined();
+  available = true;
+  const [success] = await registry.listReports({ agentId: "agent", forceRefresh: true });
+  available = false;
+  expect(
+    (await registry.listReports({ agentId: "agent", forceRefresh: true }))[0]?.lastSuccessful
+      ?.report,
+  ).toEqual(success?.report);
+  sessions.delete("agent");
+  await registry.listReports();
+  sessions.set("agent", { provider: "codex", env: {}, sessionKey: "two" });
+  expect((await registry.listReports({ agentId: "agent" }))[0]?.lastSuccessful).toBeUndefined();
+});
+
+test("a timed out poll retains successful values and late completion cannot replace the failure", async () => {
+  let now = 1000;
+  let finish!: (value: unknown) => void;
+  let slow = false;
+  const registry = new UsageSourceRegistry(() => now, 300_000, undefined, undefined, 10);
+  registry.register(
+    source({
+      id: "source",
+      discover: async () => [{ key: "same", input: {} }],
+      fetch: async () =>
+        slow
+          ? new Promise((resolve) => {
+              finish = resolve;
+            })
+          : { status: "available", windows: [] },
+    }),
+  );
+  const [success] = await registry.listReports();
+  now = 2000;
+  slow = true;
+  const [failure] = await registry.listReports({ forceRefresh: true });
+  expect(failure?.report).toEqual({ status: "error", error: "Usage fetch timed out" });
+  expect(failure?.lastSuccessful).toEqual({
+    fetchedAt: success?.fetchedAt,
+    report: success?.report,
+  });
+  finish({ status: "available", windows: [{ id: "late", label: "Late" }] });
+  expect((await registry.listReports())[0]).toEqual(failure);
+});
+
+test("attempt ordering keeps its timestamp while retained freshness records successful completion", async () => {
+  let now = 1000;
+  let available = true;
+  const registry = new UsageSourceRegistry(() => now);
+  registry.register(
+    source({
+      id: "source",
+      discover: async () => [{ key: "same", input: {} }],
+      fetch: async () => {
+        if (available) now = 2000;
+        return available
+          ? { status: "available", windows: [] }
+          : { status: "error", error: "failed" };
+      },
+    }),
+  );
+  const [success] = await registry.listReports();
+  expect(success?.fetchedAt).toBe(new Date(1000).toISOString());
+  expect(success?.successfulAt).toBe(new Date(2000).toISOString());
+  available = false;
+  now = 3000;
+  const [failure] = await registry.listReports({ forceRefresh: true });
+  expect(failure?.fetchedAt).toBe(new Date(3000).toISOString());
+  expect(failure?.lastSuccessful?.fetchedAt).toBe(success?.successfulAt);
+});
+
+test("failed discovery preserves history until discovery confirms account removal", async () => {
+  let discoveryFails = false;
+  let present = true;
+  let available = true;
+  const registry = new UsageSourceRegistry(() => 1000, 300_000, { warn: () => {} });
+  registry.register(
+    source({
+      id: "source",
+      discover: async () => {
+        if (discoveryFails) throw new Error("Login store temporarily unavailable");
+        return present ? [{ key: "account", input: {} }] : [];
+      },
+      fetch: async () =>
+        available
+          ? { status: "available", windows: [{ id: "weekly", label: "Weekly", usedPct: 42 }] }
+          : { status: "error", error: "Rate limited" },
+    }),
+  );
+  const [success] = await registry.listReports();
+  available = false;
+  discoveryFails = true;
+  const [duringDiscoveryFailure] = await registry.listReports({ forceRefresh: true });
+  expect(duringDiscoveryFailure?.lastSuccessful).toEqual({
+    fetchedAt: success?.successfulAt,
+    report: success?.report,
+  });
+  discoveryFails = false;
+  const [afterDiscoveryRecovery] = await registry.listReports({ forceRefresh: true });
+  expect(afterDiscoveryRecovery?.lastSuccessful).toEqual(duringDiscoveryFailure?.lastSuccessful);
+  expect(afterDiscoveryRecovery?.report).toEqual({ status: "error", error: "Rate limited" });
+  present = false;
+  expect(await registry.listReports()).toEqual([]);
+  present = true;
+  expect((await registry.listReports())[0]?.lastSuccessful).toBeUndefined();
+});

packages/server/src/server/plugins/usage-sources/index.ts

@@ -56,6 +56,7 @@ export class UsageSourceRegistry {
   private defaults = new Map<string, KnownReport>();
   private readonly byAgent = new Map<string, AgentReports>();
   private readonly cache = new Map<string, { at: number; entry: UsageReportEntry }>();
+  private readonly successful = new Map<string, NonNullable<UsageReportEntry["lastSuccessful"]>>();
   private readonly pending = new Map<string, Promise<UsageReportEntry>>();
 
   constructor(
@@ -81,6 +82,8 @@ export class UsageSourceRegistry {
     }
     for (const key of this.known.keys()) if (key.startsWith(`${id}:`)) this.known.delete(key);
     for (const key of this.cache.keys()) if (key.startsWith(`${id}:`)) this.cache.delete(key);
+    for (const key of this.successful.keys())
+      if (key.startsWith(`${id}:`)) this.successful.delete(key);
     for (const key of this.pending.keys()) if (key.startsWith(`${id}:`)) this.pending.delete(key);
   }
 
@@ -96,7 +99,7 @@ export class UsageSourceRegistry {
     } else if (options.reportIds !== undefined) {
       ids = options.reportIds;
     } else {
-      this.defaults = await this.discover({ kind: "global" });
+      this.defaults = await this.discover({ kind: "global" }, this.defaults);
       this.mergeKnown();
       ids = [...this.known.keys()];
     }
@@ -124,7 +127,11 @@ export class UsageSourceRegistry {
   private async discoverAgent(agentId: string): Promise<string[]> {
     if (!this.agents.hasAgent(agentId)) throw new Error(`Unknown agent: ${agentId}`);
     const session = this.agents.usageSession(agentId);
-    if (!session) return [];
+    if (!session) {
+      this.byAgent.delete(agentId);
+      this.mergeKnown();
+      return [];
+    }
     const previous = this.byAgent.get(agentId);
     const sameScope =
       previous?.sessionKey === session.sessionKey &&
@@ -168,9 +175,26 @@ export class UsageSourceRegistry {
         }
       }
     }
+    // Fetch freshness expires independently of successful snapshots. Retain only live identities.
+    const active = this.activeCacheKeys();
+    for (const key of this.successful.keys()) if (!active.has(key)) this.successful.delete(key);
+    for (const key of this.cache.keys()) if (!active.has(key)) this.cache.delete(key);
   }
 
-  private async discover(scope: UsageScope): Promise<Map<string, KnownReport>> {
+  private activeCacheKeys(): Set<string> {
+    return new Set(
+      [
+        this.known,
+        this.defaults,
+        ...[...this.byAgent.values()].map((agent) => agent.reports),
+      ].flatMap((reports) => [...reports].map(([id, report]) => cacheIdentity(id, report))),
+    );
+  }
+
+  private async discover(
+    scope: UsageScope,
+    previous: ReadonlyMap<string, KnownReport> = new Map(),
+  ): Promise<Map<string, KnownReport>> {
     const discovered = await Promise.all(
       [...this.sources.values()].map(async (source) => {
         const reports = new Map<string, KnownReport>();
@@ -197,6 +221,11 @@ export class UsageSourceRegistry {
           }
         } catch (error) {
           this.logger.warn({ sourceId: source.id, err: error }, "Usage source discovery failed");
+          // A failed store read does not confirm removal. Session discovery has no previous
+          // mapping because a resumed agent may use a different launch environment.
+          for (const [id, report] of previous) {
+            if (report.source === source) reports.set(id, report);
+          }
         }
         return reports;
       }),
@@ -235,25 +264,42 @@ export class UsageSourceRegistry {
 
   private fetchId(id: string, known: KnownReport, forceRefresh = false): Promise<UsageReportEntry> {
     // Account identity groups cards; the ordered login set identifies a fetch result.
-    const cacheKey = `${id}:${createHash("sha256")
-      .update(JSON.stringify([known.label, known.logins.map(loginKey)]))
-      .digest("hex")}`;
+    const cacheKey = cacheIdentity(id, known);
     const cached = this.cache.get(cacheKey);
     if (!forceRefresh && cached && this.now() - cached.at < this.ttlMs)
       return Promise.resolve(cached.entry);
     const pending = this.pending.get(cacheKey);
     if (pending) return pending;
     const request = (async () => {
+      const fetchedAt = new Date(this.now()).toISOString();
+      const outcome = await this.fetchWithFallback(known);
+      const completedAt = new Date(this.now()).toISOString();
       const entry: UsageReportEntry = {
         id,
         sourceId: known.source.id,
         sourceLabel: known.source.label,
         icon: known.source.icon,
         account: { label: known.label },
-        fetchedAt: new Date(this.now()).toISOString(),
-        ...(await this.fetchWithFallback(known)),
+        fetchedAt,
+        ...outcome,
       };
-      if (this.sources.get(known.source.id) === known.source) this.writeCache(cacheKey, entry);
+      if (entry.report.status === "available") {
+        entry.successfulAt = completedAt;
+      } else {
+        entry.lastSuccessful = this.successful.get(cacheKey);
+      }
+      if (
+        this.sources.get(known.source.id) === known.source &&
+        this.activeCacheKeys().has(cacheKey)
+      ) {
+        if (entry.report.status === "available") {
+          this.successful.set(cacheKey, {
+            fetchedAt: completedAt,
+            report: entry.report,
+          });
+        }
+        this.writeCache(cacheKey, entry);
+      }
       return entry;
     })();
     this.pending.set(cacheKey, request);
@@ -346,3 +392,9 @@ function loginKey(login: Login): string {
       : value,
   );
 }
+
+function cacheIdentity(id: string, known: KnownReport): string {
+  return `${id}:${createHash("sha256")
+    .update(JSON.stringify([known.label, known.logins.map(loginKey)]))
+    .digest("hex")}`;
+}

packages/server/src/server/session.ts

@@ -182,6 +182,10 @@ import {
 import { ScheduleSession } from "./session/schedule/schedule-session.js";
 import { ProviderCatalogSession } from "./session/provider/provider-catalog-session.js";
 import { UsageSession } from "./session/usage/usage-session.js";
+import {
+  SpeechModelsSession,
+  type SpeechModelsSessionOptions,
+} from "./session/speech/speech-models-session.js";
 import { WorkspaceFilesSession } from "./session/files/workspace-files-session.js";
 import { AgentConfigSession } from "./session/agent-config/agent-config-session.js";
 import { ProjectConfigSession } from "./session/project-config/project-config-session.js";
@@ -525,6 +529,7 @@ export interface SessionOptions {
   stt: Resolvable<SpeechToTextProvider | null>;
   sttLanguage?: string;
   tts: Resolvable<TextToSpeechProvider | null>;
+  speechModels?: SpeechModelsSessionOptions["runtime"];
   terminalManager: TerminalManager | null;
   providerSnapshotManager: ProviderSnapshotManager;
   hubExecutionAgents?: HubExecutionAgents;
@@ -792,6 +797,7 @@ export class Session {
   private readonly scheduleSession: ScheduleSession;
   private readonly providerCatalogSession: ProviderCatalogSession;
   private readonly usageSession: UsageSession;
+  private readonly speechModelsSession: SpeechModelsSession;
   private readonly workspaceFilesSession: WorkspaceFilesSession;
   private readonly agentConfigSession: AgentConfigSession;
   private readonly projectConfigSession: ProjectConfigSession;
@@ -840,6 +846,7 @@ export class Session {
       stt,
       sttLanguage,
       tts,
+      speechModels,
       terminalManager,
       providerSnapshotManager,
       serviceProxy,
@@ -1005,6 +1012,10 @@ export class Session {
       runtime: pluginRuntime,
       logger: this.sessionLogger,
     });
+    this.speechModelsSession = new SpeechModelsSession({
+      emit: (msg) => this.emit(msg),
+      runtime: speechModels,
+    });
     this.agentConfigSession = new AgentConfigSession({
       host: {
         emit: (msg) => this.emit(msg),
@@ -2336,12 +2347,19 @@ export class Session {
       this.dispatchOrchestrationSkillsMessage(msg) ??
       this.dispatchPluginDirectoryMessage(msg) ??
       this.dispatchPluginMessage(msg) ??
-      this.dispatchTerminalMessage(msg) ??
-      this.dispatchScheduleMessage(msg) ??
+      this.dispatchHostServiceMessage(msg) ??
       this.dispatchMiscMessage(msg);
     if (promise) await promise;
   }
 
+  private dispatchHostServiceMessage(msg: SessionInboundMessage): Promise<void> | undefined {
+    return (
+      this.dispatchTerminalMessage(msg) ??
+      this.dispatchScheduleMessage(msg) ??
+      this.speechModelsSession.dispatch(msg)
+    );
+  }
+
   private dispatchWorkspaceLifecycleMessage(msg: SessionInboundMessage): Promise<void> | undefined {
     return (
       this.dispatchWorkspaceStateMessage(msg) ??

packages/server/src/server/session/speech/speech-models-session.test.ts

@@ -0,0 +1,106 @@
+import { describe, expect, test } from "vitest";
+
+import type { SessionOutboundMessage } from "../../messages.js";
+import {
+  listLocalSpeechModels,
+  type LocalSpeechModelId,
+} from "../../speech/providers/local/models.js";
+import {
+  LocalSpeechModelInUseError,
+  type LocalSpeechModelStatus,
+} from "../../speech/speech-runtime.js";
+import { SpeechModelsSession } from "./speech-models-session.js";
+
+const [firstModel] = listLocalSpeechModels();
+
+function createSession(models: LocalSpeechModelStatus[], inUse: LocalSpeechModelId[] = []) {
+  const emitted: SessionOutboundMessage[] = [];
+  const downloads: LocalSpeechModelId[] = [];
+  const session = new SpeechModelsSession({
+    emit: (message) => emitted.push(message),
+    runtime: {
+      listLocalModels: async () => models,
+      downloadLocalModel: (modelId) => {
+        downloads.push(modelId);
+      },
+      deleteLocalModel: async (modelId) => {
+        if (inUse.includes(modelId)) throw new LocalSpeechModelInUseError(modelId);
+      },
+    },
+  });
+  return { session, emitted, downloads };
+}
+
+describe("SpeechModelsSession", () => {
+  test("lists catalog details and download progress before anything is installed", async () => {
+    const { session, emitted } = createSession([
+      {
+        spec: firstModel,
+        state: { status: "downloading", receivedBytes: 10, totalBytes: 40 },
+        inUse: true,
+      },
+    ]);
+
+    await session.dispatch({ type: "speech.local_models.list.request", requestId: "r1" });
+
+    expect(emitted).toEqual([
+      {
+        type: "speech.local_models.list.response",
+        payload: {
+          requestId: "r1",
+          error: null,
+          models: [
+            {
+              id: firstModel.id,
+              kind: "stt",
+              label: firstModel.label,
+              description: firstModel.description,
+              languages: [...firstModel.languages],
+              downloadSizeBytes: firstModel.downloadSizeBytes,
+              isDefault: true,
+              inUse: true,
+              status: "downloading",
+              receivedBytes: 10,
+              totalBytes: 40,
+            },
+          ],
+        },
+      },
+    ]);
+  });
+
+  test("rejects a model id outside the catalog without starting a download", () => {
+    const { session, emitted, downloads } = createSession([]);
+
+    void session.dispatch({
+      type: "speech.local_models.download.request",
+      requestId: "r2",
+      modelId: "../../etc",
+    });
+
+    expect(downloads).toEqual([]);
+    expect(emitted).toEqual([
+      {
+        type: "speech.local_models.download.response",
+        payload: { requestId: "r2", error: "Unknown local speech model: ../../etc" },
+      },
+    ]);
+  });
+
+  test("reports why an in-use model cannot be deleted", async () => {
+    const { session, emitted } = createSession([], [firstModel.id]);
+
+    await session.dispatch({
+      type: "speech.local_models.delete.request",
+      requestId: "r3",
+      modelId: firstModel.id,
+    });
+
+    expect(emitted).toEqual([
+      {
+        type: "speech.local_models.delete.response",
+        payload: { requestId: "r3", error: new LocalSpeechModelInUseError(firstModel.id).message },
+      },
+    ]);
+  });
+});

packages/server/src/server/session/speech/speech-models-session.ts

@@ -0,0 +1,124 @@
+import type { LocalSpeechModel } from "@getpaseo/protocol/speech/rpc-schemas";
+
+import type { SessionInboundMessage, SessionOutboundMessage } from "../../messages.js";
+import { LocalSpeechModelIdSchema } from "../../speech/providers/local/models.js";
+import type { LocalSpeechModelStatus, SpeechService } from "../../speech/speech-runtime.js";
+
+type SpeechModelsRuntime = Pick<
+  SpeechService,
+  "listLocalModels" | "downloadLocalModel" | "deleteLocalModel"
+>;
+
+export interface SpeechModelsSessionOptions {
+  emit(message: SessionOutboundMessage): void;
+  // Absent when the daemon runs without speech.
+  runtime?: SpeechModelsRuntime | null;
+}
+
+export class SpeechModelsSession {
+  constructor(private readonly options: SpeechModelsSessionOptions) {}
+
+  // Handles the speech.local_models.* requests; returns undefined for any other message.
+  dispatch(msg: SessionInboundMessage): Promise<void> | undefined {
+    switch (msg.type) {
+      case "speech.local_models.list.request":
+        return this.handleList(msg);
+      case "speech.local_models.download.request":
+        this.handleDownload(msg);
+        return Promise.resolve();
+      case "speech.local_models.delete.request":
+        return this.handleDelete(msg);
+      default:
+        return undefined;
+    }
+  }
+
+  private async handleList(
+    msg: Extract<SessionInboundMessage, { type: "speech.local_models.list.request" }>,
+  ): Promise<void> {
+    try {
+      const models = await this.requireRuntime().listLocalModels();
+      this.options.emit({
+        type: "speech.local_models.list.response",
+        payload: { requestId: msg.requestId, models: models.map(toWireModel), error: null },
+      });
+    } catch (error) {
+      this.options.emit({
+        type: "speech.local_models.list.response",
+        payload: { requestId: msg.requestId, models: [], error: describeError(error) },
+      });
+    }
+  }
+
+  private handleDownload(
+    msg: Extract<SessionInboundMessage, { type: "speech.local_models.download.request" }>,
+  ): void {
+    try {
+      this.requireRuntime().downloadLocalModel(parseModelId(msg.modelId));
+      this.options.emit({
+        type: "speech.local_models.download.response",
+        payload: { requestId: msg.requestId, error: null },
+      });
+    } catch (error) {
+      this.options.emit({
+        type: "speech.local_models.download.response",
+        payload: { requestId: msg.requestId, error: describeError(error) },
+      });
+    }
+  }
+
+  private async handleDelete(
+    msg: Extract<SessionInboundMessage, { type: "speech.local_models.delete.request" }>,
+  ): Promise<void> {
+    try {
+      await this.requireRuntime().deleteLocalModel(parseModelId(msg.modelId));
+      this.options.emit({
+        type: "speech.local_models.delete.response",
+        payload: { requestId: msg.requestId, error: null },
+      });
+    } catch (error) {
+      this.options.emit({
+        type: "speech.local_models.delete.response",
+        payload: { requestId: msg.requestId, error: describeError(error) },
+      });
+    }
+  }
+
+  private requireRuntime(): SpeechModelsRuntime {
+    if (!this.options.runtime) {
+      throw new Error("Speech is unavailable on this daemon");
+    }
+    return this.options.runtime;
+  }
+}
+
+function parseModelId(modelId: string) {
+  const parsed = LocalSpeechModelIdSchema.safeParse(modelId);
+  if (!parsed.success) {
+    throw new Error(`Unknown local speech model: ${modelId}`);
+  }
+  return parsed.data;
+}
+
+function toWireModel(model: LocalSpeechModelStatus): LocalSpeechModel {
+  const { spec, state, inUse } = model;
+  return {
+    id: spec.id,
+    kind: spec.kind === "tts" ? "tts" : "stt",
+    label: spec.label,
+    description: spec.description,
+    languages: [...spec.languages],
+    downloadSizeBytes: spec.downloadSizeBytes,
+    isDefault: spec.defaultFor !== undefined,
+    inUse,
+    status: state.status,
+    ...(state.status === "downloading"
+      ? { receivedBytes: state.receivedBytes, totalBytes: state.totalBytes }
+      : {}),
+    ...(state.status === "failed" ? { error: state.error } : {}),
+  };
+}
+
+function describeError(error: unknown): string {
+  return error instanceof Error ? error.message : String(error);
+}

packages/server/src/server/speech/providers/local/config.ts

@@ -29,6 +29,7 @@ export interface LocalSpeechProviderConfig {
 
 export interface ResolvedLocalSpeechConfig {
   local: LocalSpeechProviderConfig | undefined;
+  modelsDir: string;
   sttLanguages: LocalSpeechSttLanguageConfig;
 }
 
@@ -200,11 +201,10 @@ export function resolveLocalSpeechConfig(params: {
     buildLocalSpeechResolutionInput({ ...params, includeProviderConfig }),
   );
 
-  const resolvedVoiceTtsSpeakerId =
-    parsed.voiceLocalTtsSpeakerId ??
-    (parsed.voiceLocalTtsModel === "kokoro-en-v0_19" ? 0 : undefined);
+  const resolvedVoiceTtsSpeakerId = parsed.voiceLocalTtsSpeakerId ?? 0;
 
   return {
+    modelsDir: parsed.modelsDir,
     sttLanguages: {
       dictation: parsed.dictationLanguage,
       voice: parsed.voiceLanguage,

packages/server/src/server/speech/providers/local/model-library.ts

@@ -0,0 +1,137 @@
+import type { Logger } from "pino";
+
+import {
+  deleteSherpaOnnxModel,
+  ensureSherpaOnnxModel,
+  isSherpaOnnxModelInstalled,
+} from "./sherpa/model-downloader.js";
+import {
+  listLocalSpeechModels,
+  type LocalSpeechModelId,
+  type LocalSpeechModelSpec,
+} from "./models.js";
+
+export type LocalSpeechModelInstallState =
+  | { status: "installed" }
+  | { status: "not_installed" }
+  | { status: "downloading"; receivedBytes: number; totalBytes: number }
+  | { status: "extracting" }
+  | { status: "failed"; error: string };
+
+export interface LocalSpeechModelEntry {
+  spec: LocalSpeechModelSpec;
+  state: LocalSpeechModelInstallState;
+}
+
+type InFlightState = Extract<
+  LocalSpeechModelInstallState,
+  { status: "downloading" | "extracting" }
+>;
+
+interface InFlightDownload {
+  promise: Promise<string>;
+  state: InFlightState;
+}
+
+export class LocalSpeechModelBusyError extends Error {
+  constructor(public readonly modelId: LocalSpeechModelId) {
+    super(`${modelId} is downloading. Wait for the download to finish before deleting it.`);
+    this.name = "LocalSpeechModelBusyError";
+  }
+}
+
+// Owns the models directory: which catalog models are installed, which are downloading,
+// and the last failure per model. Concurrent downloads of one model share a single transfer.
+export class LocalSpeechModelLibrary {
+  private readonly inFlight = new Map<LocalSpeechModelId, InFlightDownload>();
+  private readonly failures = new Map<LocalSpeechModelId, string>();
+  private readonly abortController = new AbortController();
+  private readonly logger: Logger;
+
+  constructor(
+    private readonly modelsDir: string,
+    logger: Logger,
+  ) {
+    this.logger = logger.child({ module: "speech", component: "local-model-library" });
+  }
+
+  getModelsDir(): string {
+    return this.modelsDir;
+  }
+
+  async list(): Promise<LocalSpeechModelEntry[]> {
+    return Promise.all(
+      listLocalSpeechModels().map(async (spec) => ({ spec, state: await this.getState(spec.id) })),
+    );
+  }
+
+  async listMissing(modelIds: LocalSpeechModelId[]): Promise<LocalSpeechModelId[]> {
+    const installed = await Promise.all(
+      modelIds.map((modelId) => isSherpaOnnxModelInstalled(this.modelsDir, modelId)),
+    );
+    return modelIds.filter((_modelId, index) => !installed[index]);
+  }
+
+  download(modelId: LocalSpeechModelId): Promise<string> {
+    const existing = this.inFlight.get(modelId);
+    if (existing) {
+      return existing.promise;
+    }
+    this.failures.delete(modelId);
+    const entry: InFlightDownload = {
+      state: { status: "downloading", receivedBytes: 0, totalBytes: 0 },
+      promise: Promise.resolve(""),
+    };
+    entry.promise = ensureSherpaOnnxModel({
+      modelsDir: this.modelsDir,
+      modelId,
+      logger: this.logger,
+      signal: this.abortController.signal,
+      onProgress: (progress) => {
+        entry.state =
+          progress.phase === "downloading"
+            ? {
+                status: "downloading",
+                receivedBytes: progress.receivedBytes,
+                totalBytes: progress.totalBytes,
+              }
+            : { status: "extracting" };
+      },
+    })
+      .catch((error: unknown) => {
+        this.failures.set(modelId, error instanceof Error ? error.message : String(error));
+        throw error;
+      })
+      .finally(() => {
+        this.inFlight.delete(modelId);
+      });
+    this.inFlight.set(modelId, entry);
+    return entry.promise;
+  }
+
+  async delete(modelId: LocalSpeechModelId): Promise<void> {
+    if (this.inFlight.has(modelId)) {
+      throw new LocalSpeechModelBusyError(modelId);
+    }
+    this.failures.delete(modelId);
+    await deleteSherpaOnnxModel(this.modelsDir, modelId);
+    this.logger.info({ modelId }, "Deleted local speech model");
+  }
+
+  async stop(): Promise<void> {
+    this.abortController.abort();
+    await Promise.allSettled(Array.from(this.inFlight.values(), (entry) => entry.promise));
+  }
+
+  private async getState(modelId: LocalSpeechModelId): Promise<LocalSpeechModelInstallState> {
+    const inFlight = this.inFlight.get(modelId);
+    if (inFlight) {
+      return inFlight.state;
+    }
+    if (await isSherpaOnnxModelInstalled(this.modelsDir, modelId)) {
+      return { status: "installed" };
+    }
+    const failure = this.failures.get(modelId);
+    return failure ? { status: "failed", error: failure } : { status: "not_installed" };
+  }
+}

packages/server/src/server/speech/providers/local/models.test.ts

@@ -13,12 +13,8 @@ import path from "node:path";
 import pino from "pino";
 import { describe, expect, onTestFinished, test } from "vitest";
 
-import {
-  ensureLocalSpeechModels,
-  getLocalSpeechModelDir,
-  listLocalSpeechModels,
-  listMissingLocalSpeechModels,
-} from "./models.js";
+import { LocalSpeechModelLibrary } from "./model-library.js";
+import { getLocalSpeechModelDir, listLocalSpeechModels } from "./models.js";
 
 const logger = pino({ level: "silent" });
 const modelId = "parakeet-tdt-0.6b-v2-int8";
@@ -55,16 +51,31 @@ describe("local speech models", () => {
     const encoder = path.join(modelDir, spec.requiredFiles[0]);
     truncateSync(encoder, 1_000);
 
-    expect(await listMissingLocalSpeechModels({ modelsDir, modelIds: [modelId] })).toEqual([
-      modelId,
-    ]);
+    const library = new LocalSpeechModelLibrary(modelsDir, logger);
+    expect(await library.listMissing([modelId])).toEqual([modelId]);
 
-    await ensureLocalSpeechModels({ modelsDir, modelIds: [modelId], logger });
+    await library.download(modelId);
 
     expect(readFileSync(encoder, "utf8")).toBe(
       `complete ${spec.requiredFiles[0]}`.padEnd(64_000, "."),
     );
     expect(existsSync(archive)).toBe(false);
-    expect(await listMissingLocalSpeechModels({ modelsDir, modelIds: [modelId] })).toEqual([]);
+    expect(await library.listMissing([modelId])).toEqual([]);
+  });
+
+  test("lists install state and deletes an installed model", async () => {
+    const { modelsDir } = setupModelsDirWithArchive();
+    const library = new LocalSpeechModelLibrary(modelsDir, logger);
+    const stateOf = async () =>
+      (await library.list()).find((entry) => entry.spec.id === modelId)?.state;
+
+    expect(await stateOf()).toEqual({ status: "not_installed" });
+    await library.download(modelId);
+    expect(await stateOf()).toEqual({ status: "installed" });
+
+    await library.delete(modelId);
+
+    expect(await stateOf()).toEqual({ status: "not_installed" });
+    expect(existsSync(getLocalSpeechModelDir(modelsDir, modelId))).toBe(false);
   });
 });

packages/server/src/server/speech/providers/local/models.ts

@@ -1,11 +1,8 @@
-import {
-  ensureSherpaOnnxModels,
-  getSherpaOnnxModelDir,
-  isSherpaOnnxModelInstalled,
-} from "./sherpa/model-downloader.js";
+import { ensureSherpaOnnxModels, getSherpaOnnxModelDir } from "./sherpa/model-downloader.js";
 import {
   DEFAULT_LOCAL_STT_MODEL,
   DEFAULT_LOCAL_TTS_MODEL,
+  LocalSpeechModelIdSchema,
   LocalSttModelIdSchema,
   LocalTtsModelIdSchema,
   listSherpaOnnxModels,
@@ -17,6 +14,7 @@ import {
 export {
   DEFAULT_LOCAL_STT_MODEL,
   DEFAULT_LOCAL_TTS_MODEL,
+  LocalSpeechModelIdSchema,
   LocalSttModelIdSchema,
   LocalTtsModelIdSchema,
   type LocalSpeechModelId,
@@ -34,16 +32,6 @@ export function getLocalSpeechModelDir(modelsDir: string, modelId: LocalSpeechMo
   return getSherpaOnnxModelDir(modelsDir, modelId);
 }
 
-export async function listMissingLocalSpeechModels(options: {
-  modelsDir: string;
-  modelIds: LocalSpeechModelId[];
-}): Promise<LocalSpeechModelId[]> {
-  const installed = await Promise.all(
-    options.modelIds.map((modelId) => isSherpaOnnxModelInstalled(options.modelsDir, modelId)),
-  );
-  return options.modelIds.filter((_modelId, index) => !installed[index]);
-}
-
 export async function ensureLocalSpeechModels(options: {
   modelsDir: string;
   modelIds: LocalSpeechModelId[];

packages/server/src/server/speech/providers/local/sherpa/model-catalog.ts

@@ -4,43 +4,467 @@ export type SherpaOnnxModelKind = "stt-offline" | "tts";
 
 type DefaultModelRole = "stt" | "tts";
 
-interface SherpaOnnxCatalogEntry {
-  kind: SherpaOnnxModelKind;
+// How sherpa-onnx loads a model, with file names relative to the extracted directory.
+export type SttEngine =
+  | { family: "transducer"; encoder: string; decoder: string; joiner: string; tokens: string }
+  | { family: "whisper"; encoder: string; decoder: string; tokens: string }
+  | { family: "sense_voice"; model: string; tokens: string }
+  | { family: "dolphin"; model: string; tokens: string }
+  | { family: "nemo_ctc"; model: string; tokens: string };
+
+export type TtsEngine =
+  | {
+      family: "kokoro";
+      model: string;
+      voices: string;
+      tokens: string;
+      dataDir: string;
+      // Multi-language Kokoro models read pronunciations from these instead of espeak alone.
+      lexicons?: readonly string[];
+      dictDir?: string;
+      ruleFsts?: readonly string[];
+    }
+  | { family: "kitten"; model: string; voices: string; tokens: string; dataDir: string }
+  | { family: "vits"; model: string; tokens: string; dataDir: string };
+
+interface SherpaOnnxCatalogEntryBase {
+  label: string;
+  // One user-facing sentence shown before download.
+  description: string;
+  // BCP 47 language tags the model transcribes or speaks.
+  languages: readonly string[];
+  // Exact size of the release archive. The downloader rejects any other size.
+  downloadSizeBytes: number;
   archiveUrl: string;
   extractedDir: string;
-  requiredFiles: string[];
-  description: string;
   defaultFor?: DefaultModelRole;
 }
 
+type SherpaOnnxCatalogEntry =
+  | (SherpaOnnxCatalogEntryBase & { kind: "stt-offline"; engine: SttEngine })
+  | (SherpaOnnxCatalogEntryBase & { kind: "tts"; engine: TtsEngine });
+
+// Every sherpa-onnx release archive extracts to a directory named after the archive.
+function releaseArchive(tag: "asr-models" | "tts-models", name: string) {
+  return {
+    archiveUrl: `https://github.com/k2-fsa/sherpa-onnx/releases/download/${tag}/${name}.tar.bz2`,
+    extractedDir: name,
+  };
+}
+
+const PARAKEET_INT8_ENGINE = {
+  family: "transducer",
+  encoder: "encoder.int8.onnx",
+  decoder: "decoder.int8.onnx",
+  joiner: "joiner.int8.onnx",
+  tokens: "tokens.txt",
+} as const satisfies SttEngine;
+
+function whisperEngine(size: string): SttEngine {
+  return {
+    family: "whisper",
+    encoder: `${size}-encoder.int8.onnx`,
+    decoder: `${size}-decoder.int8.onnx`,
+    tokens: `${size}-tokens.txt`,
+  };
+}
+
+function piperEngine(voice: string): TtsEngine {
+  return {
+    family: "vits",
+    model: `${voice}.onnx`,
+    tokens: "tokens.txt",
+    dataDir: "espeak-ng-data",
+  };
+}
+
+// Parakeet TDT v3 transcribes these 25 European languages and detects which one is spoken.
+const PARAKEET_V3_LANGUAGES = [
+  "bg",
+  "hr",
+  "cs",
+  "da",
+  "nl",
+  "en",
+  "et",
+  "fi",
+  "fr",
+  "de",
+  "el",
+  "hu",
+  "it",
+  "lv",
+  "lt",
+  "mt",
+  "pl",
+  "pt",
+  "ro",
+  "sk",
+  "sl",
+  "es",
+  "sv",
+  "ru",
+  "uk",
+] as const;
+
+// The 99 languages multilingual Whisper models transcribe, detecting which one is spoken.
+const WHISPER_LANGUAGES = [
+  "en",
+  "zh",
+  "de",
+  "es",
+  "ru",
+  "ko",
+  "fr",
+  "ja",
+  "pt",
+  "tr",
+  "pl",
+  "ca",
+  "nl",
+  "ar",
+  "sv",
+  "it",
+  "id",
+  "hi",
+  "fi",
+  "vi",
+  "he",
+  "uk",
+  "el",
+  "ms",
+  "cs",
+  "ro",
+  "da",
+  "hu",
+  "ta",
+  "no",
+  "th",
+  "ur",
+  "hr",
+  "bg",
+  "lt",
+  "la",
+  "mi",
+  "ml",
+  "cy",
+  "sk",
+  "te",
+  "fa",
+  "lv",
+  "bn",
+  "sr",
+  "az",
+  "sl",
+  "kn",
+  "et",
+  "mk",
+  "br",
+  "eu",
+  "is",
+  "hy",
+  "ne",
+  "mn",
+  "bs",
+  "kk",
+  "sq",
+  "sw",
+  "gl",
+  "mr",
+  "pa",
+  "si",
+  "km",
+  "sn",
+  "yo",
+  "so",
+  "af",
+  "oc",
+  "ka",
+  "be",
+  "tg",
+  "sd",
+  "gu",
+  "am",
+  "yi",
+  "lo",
+  "uz",
+  "fo",
+  "ht",
+  "ps",
+  "tk",
+  "nn",
+  "mt",
+  "sa",
+  "lb",
+  "my",
+  "bo",
+  "tl",
+  "mg",
+  "as",
+  "tt",
+  "haw",
+  "ln",
+  "ha",
+  "ba",
+  "jv",
+  "su",
+] as const;
+
+// Dolphin's 40 Eastern languages. It also covers 22 Chinese dialects under "zh".
+const DOLPHIN_LANGUAGES = [
+  "zh",
+  "ja",
+  "th",
+  "ru",
+  "ko",
+  "id",
+  "vi",
+  "yue",
+  "hi",
+  "ur",
+  "ms",
+  "uz",
+  "ar",
+  "fa",
+  "bn",
+  "ta",
+  "te",
+  "ug",
+  "gu",
+  "my",
+  "tl",
+  "kk",
+  "or",
+  "ne",
+  "mn",
+  "km",
+  "jv",
+  "lo",
+  "si",
+  "fil",
+  "ps",
+  "pa",
+  "kab",
+  "ba",
+  "ks",
+  "tg",
+  "su",
+  "mr",
+  "ky",
+  "az",
+] as const;
+
 export const SHERPA_ONNX_MODEL_CATALOG = {
   "parakeet-tdt-0.6b-v2-int8": {
     kind: "stt-offline",
-    archiveUrl:
-      "https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8.tar.bz2",
-    extractedDir: "sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8",
-    requiredFiles: ["encoder.int8.onnx", "decoder.int8.onnx", "joiner.int8.onnx", "tokens.txt"],
-    description: "NVIDIA Parakeet TDT v2 (offline NeMo transducer, English).",
+    label: "Parakeet v2",
+    description: "Accurate English transcription that runs well on a laptop CPU.",
+    languages: ["en"],
+    downloadSizeBytes: 482_468_385,
+    ...releaseArchive("asr-models", "sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8"),
+    engine: PARAKEET_INT8_ENGINE,
     defaultFor: "stt",
   },
+  "parakeet-tdt-110m-en-int8": {
+    kind: "stt-offline",
+    label: "Parakeet Small",
+    description: "Small, fast English model with punctuation. A quick download for any laptop.",
+    languages: ["en"],
+    downloadSizeBytes: 108_035_095,
+    ...releaseArchive("asr-models", "sherpa-onnx-nemo-parakeet_tdt_transducer_110m-en-36000-int8"),
+    engine: PARAKEET_INT8_ENGINE,
+  },
   "parakeet-tdt-0.6b-v3-int8": {
     kind: "stt-offline",
-    archiveUrl:
-      "https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8.tar.bz2",
-    extractedDir: "sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8",
-    requiredFiles: ["encoder.int8.onnx", "decoder.int8.onnx", "joiner.int8.onnx", "tokens.txt"],
-    description:
-      "NVIDIA Parakeet TDT v3 (offline NeMo transducer, 25 European languages, auto-detected).",
+    label: "Parakeet v3",
+    description: "Parakeet for 25 European languages, detecting which one you speak.",
+    languages: PARAKEET_V3_LANGUAGES,
+    downloadSizeBytes: 487_170_055,
+    ...releaseArchive("asr-models", "sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8"),
+    engine: PARAKEET_INT8_ENGINE,
+  },
+  "whisper-tiny-en": {
+    kind: "stt-offline",
+    label: "Whisper Tiny (English)",
+    description: "Small English Whisper model. Quick to download, less accurate than Parakeet.",
+    languages: ["en"],
+    downloadSizeBytes: 118_071_777,
+    ...releaseArchive("asr-models", "sherpa-onnx-whisper-tiny.en"),
+    engine: whisperEngine("tiny.en"),
+  },
+  "whisper-base": {
+    kind: "stt-offline",
+    label: "Whisper Base",
+    description: "Compact Whisper model for 99 languages, detecting which one you speak.",
+    languages: WHISPER_LANGUAGES,
+    downloadSizeBytes: 207_557_382,
+    ...releaseArchive("asr-models", "sherpa-onnx-whisper-base"),
+    engine: whisperEngine("base"),
+  },
+  "whisper-turbo": {
+    kind: "stt-offline",
+    label: "Whisper Turbo",
+    description: "Whisper's most accurate model for 99 languages and Cantonese. Slower on a CPU.",
+    languages: [...WHISPER_LANGUAGES, "yue"],
+    downloadSizeBytes: 563_790_207,
+    ...releaseArchive("asr-models", "sherpa-onnx-whisper-turbo"),
+    engine: whisperEngine("turbo"),
+  },
+  "sense-voice-int8": {
+    kind: "stt-offline",
+    label: "SenseVoice",
+    description: "Chinese, Cantonese, English, Japanese and Korean, detecting which one you speak.",
+    languages: ["zh", "yue", "en", "ja", "ko"],
+    downloadSizeBytes: 165_783_878,
+    ...releaseArchive("asr-models", "sherpa-onnx-sense-voice-zh-en-ja-ko-yue-int8-2025-09-09"),
+    engine: { family: "sense_voice", model: "model.int8.onnx", tokens: "tokens.txt" },
+  },
+  "dolphin-base-int8": {
+    kind: "stt-offline",
+    label: "Dolphin",
+    description: "Small model for 40 Asian and Middle Eastern languages and Chinese dialects.",
+    languages: DOLPHIN_LANGUAGES,
+    downloadSizeBytes: 80_671_385,
+    ...releaseArchive("asr-models", "sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02"),
+    engine: { family: "dolphin", model: "model.int8.onnx", tokens: "tokens.txt" },
+  },
+  "giga-am-v3-ru": {
+    kind: "stt-offline",
+    label: "GigaAM v3 (Russian)",
+    description: "Russian transcription with punctuation.",
+    languages: ["ru"],
+    downloadSizeBytes: 170_197_019,
+    ...releaseArchive(
+      "asr-models",
+      "sherpa-onnx-nemo-transducer-punct-giga-am-v3-russian-2025-12-16",
+    ),
+    engine: {
+      family: "transducer",
+      encoder: "encoder.int8.onnx",
+      decoder: "decoder.onnx",
+      joiner: "joiner.onnx",
+      tokens: "tokens.txt",
+    },
+  },
+  "parakeet-tdt-ctc-0.6b-ja-int8": {
+    kind: "stt-offline",
+    label: "Parakeet (Japanese)",
+    description: "Japanese transcription with punctuation.",
+    languages: ["ja"],
+    downloadSizeBytes: 489_389_564,
+    ...releaseArchive("asr-models", "sherpa-onnx-nemo-parakeet-tdt_ctc-0.6b-ja-35000-int8"),
+    engine: { family: "nemo_ctc", model: "model.int8.onnx", tokens: "tokens.txt" },
   },
   "kokoro-en-v0_19": {
     kind: "tts",
-    archiveUrl:
-      "https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-en-v0_19.tar.bz2",
-    extractedDir: "kokoro-en-v0_19",
-    requiredFiles: ["model.onnx", "voices.bin", "tokens.txt", "espeak-ng-data"],
-    description: "Kokoro TTS (higher quality; larger).",
+    label: "Kokoro (English)",
+    description: "Natural-sounding English voice for voice mode replies.",
+    languages: ["en"],
+    downloadSizeBytes: 319_625_534,
+    ...releaseArchive("tts-models", "kokoro-en-v0_19"),
+    engine: {
+      family: "kokoro",
+      model: "model.onnx",
+      voices: "voices.bin",
+      tokens: "tokens.txt",
+      dataDir: "espeak-ng-data",
+    },
     defaultFor: "tts",
   },
+  "kokoro-int8-en-v0_19": {
+    kind: "tts",
+    label: "Kokoro Lite (English)",
+    description: "The same Kokoro English voices, quantized to a third of the download.",
+    languages: ["en"],
+    downloadSizeBytes: 103_248_205,
+    ...releaseArchive("tts-models", "kokoro-int8-en-v0_19"),
+    engine: {
+      family: "kokoro",
+      model: "model.int8.onnx",
+      voices: "voices.bin",
+      tokens: "tokens.txt",
+      dataDir: "espeak-ng-data",
+    },
+  },
+  "kokoro-int8-multi-lang-v1_1": {
+    kind: "tts",
+    label: "Kokoro (Chinese and English)",
+    description: "Kokoro voices that speak both Mandarin Chinese and English.",
+    languages: ["zh", "en"],
+    downloadSizeBytes: 147_031_220,
+    ...releaseArchive("tts-models", "kokoro-int8-multi-lang-v1_1"),
+    engine: {
+      family: "kokoro",
+      model: "model.int8.onnx",
+      voices: "voices.bin",
+      tokens: "tokens.txt",
+      dataDir: "espeak-ng-data",
+      lexicons: ["lexicon-us-en.txt", "lexicon-zh.txt"],
+      dictDir: "dict",
+      ruleFsts: ["date-zh.fst", "phone-zh.fst", "number-zh.fst"],
+    },
+  },
+  // Kitten v0.8 needs a newer sherpa-onnx than we pin; v0.2 loads on 1.12.28.
+  "kitten-nano-en-v0_2-fp16": {
+    kind: "tts",
+    label: "Kitten Nano (English)",
+    description: "Tiny, very fast English voice.",
+    languages: ["en"],
+    downloadSizeBytes: 26_586_708,
+    ...releaseArchive("tts-models", "kitten-nano-en-v0_2-fp16"),
+    engine: {
+      family: "kitten",
+      model: "model.fp16.onnx",
+      voices: "voices.bin",
+      tokens: "tokens.txt",
+      dataDir: "espeak-ng-data",
+    },
+  },
+  "piper-en-us-libritts-r": {
+    kind: "tts",
+    label: "Piper LibriTTS (US English)",
+    description: "Lightweight American English voice.",
+    languages: ["en-US"],
+    downloadSizeBytes: 23_398_348,
+    ...releaseArchive("tts-models", "vits-piper-en_US-libritts_r-medium-int8"),
+    engine: piperEngine("en_US-libritts_r-medium"),
+  },
+  "piper-en-gb-alba": {
+    kind: "tts",
+    label: "Piper Alba (British English)",
+    description: "Lightweight British English voice.",
+    languages: ["en-GB"],
+    downloadSizeBytes: 21_104_326,
+    ...releaseArchive("tts-models", "vits-piper-en_GB-alba-medium-int8"),
+    engine: piperEngine("en_GB-alba-medium"),
+  },
+  "piper-de-thorsten": {
+    kind: "tts",
+    label: "Piper Thorsten (German)",
+    description: "Lightweight German voice.",
+    languages: ["de"],
+    downloadSizeBytes: 20_949_833,
+    ...releaseArchive("tts-models", "vits-piper-de_DE-thorsten-medium-int8"),
+    engine: piperEngine("de_DE-thorsten-medium"),
+  },
+  "piper-fr-siwis": {
+    kind: "tts",
+    label: "Piper Siwis (French)",
+    description: "Lightweight French voice.",
+    languages: ["fr"],
+    downloadSizeBytes: 20_914_888,
+    ...releaseArchive("tts-models", "vits-piper-fr_FR-siwis-medium-int8"),
+    engine: piperEngine("fr_FR-siwis-medium"),
+  },
+  "piper-es-davefx": {
+    kind: "tts",
+    label: "Piper Davefx (Spanish)",
+    description: "Lightweight Spanish voice.",
+    languages: ["es"],
+    downloadSizeBytes: 21_171_632,
+    ...releaseArchive("tts-models", "vits-piper-es_ES-davefx-medium-int8"),
+    engine: piperEngine("es_ES-davefx-medium"),
+  },
 } as const satisfies Record<string, SherpaOnnxCatalogEntry>;
 
 export type SherpaOnnxModelId = keyof typeof SHERPA_ONNX_MODEL_CATALOG;
@@ -97,24 +521,44 @@ function createModelIdSchema<T extends string>(modelIds: readonly T[]): z.ZodTyp
     .transform((value) => value as T);
 }
 
+export const LocalSpeechModelIdSchema = createModelIdSchema(ALL_MODEL_IDS);
 export const LocalSttModelIdSchema = createModelIdSchema(LOCAL_STT_MODEL_IDS);
 export const LocalTtsModelIdSchema = createModelIdSchema(LOCAL_TTS_MODEL_IDS);
 
 export type SherpaOnnxModelSpec = SherpaOnnxCatalogEntry & {
   id: SherpaOnnxModelId;
+  // Every file and directory that must exist for the model to count as installed.
+  requiredFiles: string[];
 };
 
 export function listSherpaOnnxModels(): SherpaOnnxModelSpec[] {
-  return ALL_MODEL_IDS.map((id) => Object.assign({ id }, SHERPA_ONNX_MODEL_CATALOG[id]));
+  return ALL_MODEL_IDS.map(getSherpaOnnxModelSpec);
 }
 
 export function getSherpaOnnxModelSpec(id: SherpaOnnxModelId): SherpaOnnxModelSpec {
-  const spec = SHERPA_ONNX_MODEL_CATALOG[id];
+  const spec: SherpaOnnxCatalogEntry | undefined = SHERPA_ONNX_MODEL_CATALOG[id];
   if (!spec) {
     throw new Error(`Unknown local speech model id: ${id}`);
   }
   return {
     id,
     ...spec,
+    requiredFiles: engineFiles(spec.engine),
   };
 }
+
+// Every path an engine names, so the downloader can verify an install.
+export function engineFiles(engine: SttEngine | TtsEngine): string[] {
+  return Object.entries(engine).flatMap(([key, value]) => {
+    if (key === "family") return [];
+    return typeof value === "string" ? [value] : (value as readonly string[]);
+  });
+}
+
+export function getLocalSttEngine(id: LocalSttModelId): SttEngine {
+  return SHERPA_ONNX_MODEL_CATALOG[id].engine;
+}
+
+export function getLocalTtsEngine(id: LocalTtsModelId): TtsEngine {
+  return SHERPA_ONNX_MODEL_CATALOG[id].engine;
+}

packages/server/src/server/speech/providers/local/sherpa/model-downloader.ts

@@ -8,11 +8,16 @@ import type pino from "pino";
 import { getSherpaOnnxModelSpec, type SherpaOnnxModelId } from "./model-catalog.js";
 import { spawnProcess } from "../../../../../utils/spawn.js";
 
+export type SherpaOnnxModelInstallProgress =
+  | { phase: "downloading"; receivedBytes: number; totalBytes: number }
+  | { phase: "extracting" };
+
 export interface EnsureSherpaOnnxModelOptions {
   modelsDir: string;
   modelId: SherpaOnnxModelId;
   logger: pino.Logger;
   signal?: AbortSignal;
+  onProgress?: (progress: SherpaOnnxModelInstallProgress) => void;
 }
 
 export function getSherpaOnnxModelDir(modelsDir: string, modelId: SherpaOnnxModelId): string {
@@ -41,7 +46,9 @@ async function hasRequiredFiles(modelDir: string, requiredFiles: string[]): Prom
 interface DownloadToFileOptions {
   url: string;
   outputPath: string;
+  expectedBytes: number;
   signal?: AbortSignal;
+  onProgress?: (receivedBytes: number, totalBytes: number) => void;
 }
 
 async function downloadToFile(options: DownloadToFileOptions): Promise<void> {
@@ -60,6 +67,13 @@ async function downloadToFile(options: DownloadToFileOptions): Promise<void> {
   // The fetch ReadableStream type is slightly different from what Readable.fromWeb expects
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   const nodeStream = Readable.fromWeb(res.body as any);
+  const contentLength = Number(res.headers.get("content-length"));
+  const totalBytes = contentLength > 0 ? contentLength : options.expectedBytes;
+  let receivedBytes = 0;
+  nodeStream.on("data", (chunk: Buffer) => {
+    receivedBytes += chunk.length;
+    options.onProgress?.(receivedBytes, totalBytes);
+  });
 
   try {
     await pipeline(nodeStream, createWriteStream(tmpPath), { signal: options.signal });
@@ -157,9 +171,13 @@ export async function ensureSherpaOnnxModel(
       await downloadToFile({
         url: spec.archiveUrl,
         outputPath: archivePath,
+        expectedBytes: spec.downloadSizeBytes,
         signal: options.signal,
+        onProgress: (receivedBytes, totalBytes) =>
+          options.onProgress?.({ phase: "downloading", receivedBytes, totalBytes }),
       });
     }
+    options.onProgress?.({ phase: "extracting" });
 
     logger.info(
       {
@@ -213,6 +231,16 @@ export async function ensureSherpaOnnxModel(
   }
 }
 
+export async function deleteSherpaOnnxModel(
+  modelsDir: string,
+  modelId: SherpaOnnxModelId,
+): Promise<void> {
+  const { modelDir, archivePath, extractionDir } = getSherpaOnnxModelPaths(modelsDir, modelId);
+  await rm(modelDir, { recursive: true, force: true });
+  await rm(archivePath, { force: true });
+  await rm(extractionDir, { recursive: true, force: true });
+}
+
 export async function ensureSherpaOnnxModels(options: {
   modelsDir: string;
   modelIds: SherpaOnnxModelId[];

packages/server/src/server/speech/providers/local/sherpa/sherpa-offline-recognizer.ts

@@ -1,6 +1,8 @@
 import { existsSync } from "node:fs";
+import path from "node:path";
 import type pino from "pino";
 
+import { engineFiles, type SttEngine } from "./model-catalog.js";
 import { loadSherpaOnnxNode } from "./sherpa-onnx-node-loader.js";
 
 function assertFileExists(filePath: string, label: string): void {
@@ -9,16 +11,43 @@ function assertFileExists(filePath: string, label: string): void {
   }
 }
 
-export interface SherpaOfflineRecognizerModel {
-  kind: "nemo_transducer";
-  encoder: string;
-  decoder: string;
-  joiner: string;
-  tokens: string;
+// Each engine family takes its own block under sherpa's modelConfig.
+function buildModelConfig(modelDir: string, engine: SttEngine): Record<string, unknown> {
+  const file = (name: string) => path.join(modelDir, name);
+  switch (engine.family) {
+    case "transducer":
+      return {
+        transducer: {
+          encoder: file(engine.encoder),
+          decoder: file(engine.decoder),
+          joiner: file(engine.joiner),
+        },
+        modelType: "nemo_transducer",
+      };
+    case "whisper":
+      // An empty language makes Whisper detect the spoken language.
+      return {
+        whisper: {
+          encoder: file(engine.encoder),
+          decoder: file(engine.decoder),
+          language: "",
+          task: "transcribe",
+        },
+      };
+    case "sense_voice":
+      return {
+        senseVoice: { model: file(engine.model), language: "", useInverseTextNormalization: 1 },
+      };
+    case "dolphin":
+      return { dolphin: { model: file(engine.model) } };
+    case "nemo_ctc":
+      return { nemoCtc: { model: file(engine.model) } };
+  }
 }
 
 export interface SherpaOfflineRecognizerConfig {
-  model: SherpaOfflineRecognizerModel;
+  modelDir: string;
+  engine: SttEngine;
   numThreads?: number;
   provider?: "cpu";
   debug?: 0 | 1;
@@ -54,10 +83,9 @@ export class SherpaOfflineRecognizerEngine {
       component: "offline-recognizer",
     });
 
-    assertFileExists(config.model.encoder, "offline encoder");
-    assertFileExists(config.model.decoder, "offline decoder");
-    assertFileExists(config.model.joiner, "offline joiner");
-    assertFileExists(config.model.tokens, "tokens");
+    for (const name of engineFiles(config.engine)) {
+      assertFileExists(path.join(config.modelDir, name), `${config.engine.family} model file`);
+    }
 
     const sherpa = loadSherpaOnnxNode();
 
@@ -67,13 +95,8 @@ export class SherpaOfflineRecognizerEngine {
         featureDim: config.featureDim ?? 80,
       },
       modelConfig: {
-        transducer: {
-          encoder: config.model.encoder,
-          decoder: config.model.decoder,
-          joiner: config.model.joiner,
-        },
-        tokens: config.model.tokens,
-        modelType: "nemo_transducer",
+        ...buildModelConfig(config.modelDir, config.engine),
+        tokens: path.join(config.modelDir, config.engine.tokens),
         numThreads: config.numThreads ?? 1,
         provider: config.provider ?? "cpu",
         debug: config.debug ?? 0,

packages/server/src/server/speech/providers/local/sherpa/sherpa-tts.test.ts

@@ -3,6 +3,7 @@ import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 import pino from "pino";
+import { engineFiles, getLocalTtsEngine, type LocalTtsModelId } from "./model-catalog.js";
 import { SherpaOnnxTTS } from "./sherpa-tts.js";
 
 const directories: string[] = [];
@@ -11,17 +12,28 @@ afterEach(() => {
     rmSync(directory, { recursive: true, force: true });
 });
 
-function createTts(numThreads?: number, beforeGenerate?: () => Promise<void>) {
+function createTts(
+  numThreads?: number,
+  beforeGenerate?: () => Promise<void>,
+  modelId: LocalTtsModelId = "kokoro-en-v0_19",
+) {
   const modelDir = mkdtempSync(join(tmpdir(), "paseo-tts-"));
   directories.push(modelDir);
-  for (const name of ["model.onnx", "voices.bin", "tokens.txt"])
-    writeFileSync(join(modelDir, name), "");
-  mkdirSync(join(modelDir, "espeak-ng-data"));
+  // Data directories have no extension; everything else is a model file.
+  for (const name of engineFiles(getLocalTtsEngine(modelId))) {
+    if (name.includes(".")) writeFileSync(join(modelDir, name), "");
+    else mkdirSync(join(modelDir, name));
+  }
   let nativeConfig: unknown;
   const requests: unknown[] = [];
   const released: boolean[] = [];
   const tts = new SherpaOnnxTTS(
-    { preset: "kokoro-en-v0_19", modelDir, numThreads },
+    {
+      modelId,
+      modelDir,
+      engine: getLocalTtsEngine(modelId),
+      numThreads,
+    },
     pino({ level: "silent" }),
     () => ({
       OfflineTts: class {
@@ -138,4 +150,31 @@ describe("SherpaOnnxTTS", () => {
       expect(nativeConfig).not.toHaveProperty("provider");
     },
   );
+
+  it("loads Piper voices through the vits engine", () => {
+    const { nativeConfig } = createTts(undefined, undefined, "piper-de-thorsten");
+    expect(nativeConfig).toMatchObject({
+      model: {
+        vits: {
+          model: expect.stringMatching(/de_DE-thorsten-medium\.onnx$/),
+          tokens: expect.stringMatching(/tokens\.txt$/),
+          dataDir: expect.stringMatching(/espeak-ng-data$/),
+        },
+      },
+    });
+    expect(nativeConfig).not.toHaveProperty("model.kokoro");
+  });
+
+  it("gives multi-language Kokoro its lexicons, dictionary and number rules", () => {
+    const { nativeConfig } = createTts(undefined, undefined, "kokoro-int8-multi-lang-v1_1");
+    expect(nativeConfig).toMatchObject({
+      model: {
+        kokoro: {
+          lexicon: expect.stringMatching(/lexicon-us-en\.txt,.*lexicon-zh\.txt$/),
+          dictDir: expect.stringMatching(/dict$/),
+        },
+      },
+      ruleFsts: expect.stringMatching(/date-zh\.fst,.*phone-zh\.fst,.*number-zh\.fst$/),
+    });
+  });
 });

packages/server/src/server/speech/providers/local/sherpa/sherpa-tts.ts

@@ -1,16 +1,17 @@
 import type pino from "pino";
 import { Readable } from "node:stream";
 import { existsSync } from "node:fs";
+import path from "node:path";
 
 import type { SpeechStreamResult, TextToSpeechProvider } from "../../../speech-provider.js";
 import { chunkBuffer, float32ToPcm16le } from "../../../audio.js";
 import { loadSherpaOnnxNode } from "./sherpa-onnx-node-loader.js";
-
-export type SherpaTtsPreset = "kokoro-en-v0_19";
+import { engineFiles, type LocalTtsModelId, type TtsEngine } from "./model-catalog.js";
 
 export interface SherpaTtsConfig {
-  preset: SherpaTtsPreset;
+  modelId: LocalTtsModelId;
   modelDir: string;
+  engine: TtsEngine;
   speakerId?: number;
   speed?: number;
   lengthScale?: number;
@@ -23,6 +24,53 @@ function assertFileExists(filePath: string, label: string): void {
   }
 }
 
+// Each engine family takes its own block under sherpa's TTS model config.
+function buildTtsModelConfig(
+  modelDir: string,
+  engine: TtsEngine,
+  lengthScale: number,
+): Record<string, unknown> {
+  const file = (name: string) => path.join(modelDir, name);
+  switch (engine.family) {
+    case "kokoro":
+      return {
+        kokoro: {
+          model: file(engine.model),
+          voices: file(engine.voices),
+          tokens: file(engine.tokens),
+          dataDir: file(engine.dataDir),
+          lexicon: (engine.lexicons ?? []).map(file).join(","),
+          dictDir: engine.dictDir ? file(engine.dictDir) : "",
+          lengthScale,
+        },
+      };
+    case "kitten":
+      return {
+        kitten: {
+          model: file(engine.model),
+          voices: file(engine.voices),
+          tokens: file(engine.tokens),
+          dataDir: file(engine.dataDir),
+          lengthScale,
+        },
+      };
+    case "vits":
+      return {
+        vits: {
+          model: file(engine.model),
+          tokens: file(engine.tokens),
+          dataDir: file(engine.dataDir),
+          lengthScale,
+        },
+      };
+  }
+}
+
+function ruleFsts(modelDir: string, engine: TtsEngine): string {
+  if (engine.family !== "kokoro" || !engine.ruleFsts) return "";
+  return engine.ruleFsts.map((name) => path.join(modelDir, name)).join(",");
+}
+
 interface SherpaOfflineTtsNative {
   sampleRate?: number;
   generateAsync: (args: {
@@ -59,39 +107,28 @@ export class SherpaOnnxTTS implements TextToSpeechProvider {
       throw new Error("sherpa-onnx-node OfflineTts is unavailable");
     }
 
-    const modelPath = `${config.modelDir}/model.onnx`;
-    const voicesPath = `${config.modelDir}/voices.bin`;
-    const tokensPath = `${config.modelDir}/tokens.txt`;
-    const dataDir = `${config.modelDir}/espeak-ng-data`;
-
-    assertFileExists(modelPath, "TTS model");
-    assertFileExists(voicesPath, "TTS voices");
-    assertFileExists(tokensPath, "TTS tokens");
-    assertFileExists(dataDir, "TTS espeak-ng dataDir");
+    for (const name of engineFiles(config.engine)) {
+      assertFileExists(path.join(config.modelDir, name), `${config.engine.family} TTS file`);
+    }
 
     const modelConfig = {
       // The native parser reads these under model, despite the upstream JS typedef.
       numThreads: config.numThreads ?? 2,
       provider: "cpu",
-      kokoro: {
-        model: modelPath,
-        voices: voicesPath,
-        tokens: tokensPath,
-        dataDir,
-        lengthScale: config.lengthScale ?? 1.0,
-      },
+      ...buildTtsModelConfig(config.modelDir, config.engine, config.lengthScale ?? 1.0),
     };
 
     const offlineTtsConfig = {
       model: modelConfig,
       maxNumSentences: 1,
+      ruleFsts: ruleFsts(config.modelDir, config.engine),
     };
 
     this.tts = new (
       sherpa as unknown as { OfflineTts: new (config: unknown) => SherpaOfflineTtsNative }
     ).OfflineTts(offlineTtsConfig);
     this.logger.info(
-      { preset: config.preset, modelDir: config.modelDir },
+      { modelId: config.modelId, modelDir: config.modelDir },
       "Sherpa offline TTS initialized",
     );
   }

packages/server/src/server/speech/providers/local/sherpa/speech-download.e2e.test.ts

@@ -7,6 +7,7 @@ import pino from "pino";
 import { ensureSherpaOnnxModels, getSherpaOnnxModelDir } from "./model-downloader.js";
 import { createDaemonTestContext } from "../../../../test-utils/index.js";
 import { parsePcm16MonoWav, wordSimilarity } from "../../../../test-utils/dictation-e2e.js";
+import { getLocalSttEngine, getLocalTtsEngine } from "./model-catalog.js";
 import { SherpaOnnxTTS } from "./sherpa-tts.js";
 import { SherpaOfflineRecognizerEngine } from "./sherpa-offline-recognizer.js";
 import { SherpaOnnxParakeetSTT } from "./sherpa-parakeet-stt.js";
@@ -192,7 +193,12 @@ downloadTest(
       const ttsText = "This is a voice note.";
       const ttsModelDir = getSherpaOnnxModelDir(modelsDir, "kokoro-en-v0_19");
       const tts = new SherpaOnnxTTS(
-        { preset: "kokoro-en-v0_19", modelDir: ttsModelDir, speakerId: 0 },
+        {
+          modelId: "kokoro-en-v0_19",
+          modelDir: ttsModelDir,
+          engine: getLocalTtsEngine("kokoro-en-v0_19"),
+          speakerId: 0,
+        },
         logger,
       );
       const { stream, format: ttsFormat } = await tts.synthesizeSpeech(ttsText);
@@ -206,13 +212,8 @@ downloadTest(
       const sttModelDir = getSherpaOnnxModelDir(modelsDir, "parakeet-tdt-0.6b-v2-int8");
       const engine = new SherpaOfflineRecognizerEngine(
         {
-          model: {
-            kind: "nemo_transducer",
-            encoder: `${sttModelDir}/encoder.int8.onnx`,
-            decoder: `${sttModelDir}/decoder.int8.onnx`,
-            joiner: `${sttModelDir}/joiner.int8.onnx`,
-            tokens: `${sttModelDir}/tokens.txt`,
-          },
+          modelDir: sttModelDir,
+          engine: getLocalSttEngine("parakeet-tdt-0.6b-v2-int8"),
           numThreads: 2,
           debug: 0,
         },

packages/server/src/server/speech/providers/local/worker-process.ts

@@ -3,6 +3,7 @@ import pino from "pino";
 import type { StreamingTranscriptionSession } from "../../speech-provider.js";
 import type { TurnDetectionSession } from "../../turn-detection-provider.js";
 import { getLocalSpeechModelDir, type LocalSttModelId, type LocalTtsModelId } from "./models.js";
+import { getLocalSttEngine, getLocalTtsEngine } from "./sherpa/model-catalog.js";
 import { SherpaOfflineRecognizerEngine } from "./sherpa/sherpa-offline-recognizer.js";
 import { SherpaOnnxParakeetSTT } from "./sherpa/sherpa-parakeet-stt.js";
 import { SherpaParakeetRealtimeTranscriptionSession } from "./sherpa/sherpa-parakeet-realtime-session.js";
@@ -85,13 +86,8 @@ function getSttEngine(
   const modelDir = getLocalSpeechModelDir(config.modelsDir, modelId);
   const created = new SherpaOfflineRecognizerEngine(
     {
-      model: {
-        kind: "nemo_transducer",
-        encoder: `${modelDir}/encoder.int8.onnx`,
-        decoder: `${modelDir}/decoder.int8.onnx`,
-        joiner: `${modelDir}/joiner.int8.onnx`,
-        tokens: `${modelDir}/tokens.txt`,
-      },
+      modelDir,
+      engine: getLocalSttEngine(modelId),
       numThreads: 2,
       debug: 0,
     },
@@ -125,8 +121,9 @@ function getTtsProvider(config: LocalSpeechWorkerConfig): SherpaOnnxTTS {
   const modelDir = getLocalSpeechModelDir(config.modelsDir, ttsModelId(config));
   const created = new SherpaOnnxTTS(
     {
-      preset: ttsModelId(config),
+      modelId: ttsModelId(config),
       modelDir,
+      engine: getLocalTtsEngine(ttsModelId(config)),
       speakerId: config.voiceTtsSpeakerId,
       speed: config.voiceTtsSpeed,
     },