Relax Xcode signing identity matching

Use passworded CI keychain
Use user keychain domain in CI
2026-06-25 23:57:17 -07:00 · 2026-06-25 23:53:24 -07:00 · 2026-06-25 23:51:33 -07:00 · 2026-06-25 23:48:26 -07:00 · 2026-06-25 23:44:13 -07:00 · 2026-06-25 23:37:24 -07:00
42 changed files with 548 additions and 2370 deletions
@@ -4,15 +4,20 @@ on:
  workflow_dispatch:
  push:
    tags:
-      - "release/ios/v*"
+      - "v*"

 jobs:
  testflight:
-    runs-on: macos-arm64
+    runs-on: xcode
+    defaults:
+      run:
+        shell: bash

    steps:
      - name: Checkout
        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0

      - name: Setup Ruby
        uses: ruby/setup-ruby@v1
@@ -22,23 +27,44 @@ jobs:
          working-directory: ios

      - name: Install XcodeGen
-        run: command -v xcodegen >/dev/null 2>&1 || brew install xcodegen
+        run: |
+          set -euo pipefail
+          if ! command -v xcodegen >/dev/null 2>&1; then
+            brew install xcodegen
+          fi
+
+      - name: Prepare Runner Keychain
+        env:
+          HOME: /var/lib/act_runner
+        run: |
+          set -euo pipefail
+          mkdir -p "${HOME}/Library/Keychains"
+
+          login_keychain="${HOME}/Library/Keychains/login.keychain"
+          if [ ! -f "${login_keychain}-db" ]; then
+            security create-keychain -p "" "${login_keychain}"
+          fi
+
+          security unlock-keychain -p "" "${login_keychain}" 2>/dev/null || \
+            security unlock-keychain -p "sybil-ci-keychain-password" "${login_keychain}" 2>/dev/null || true
+          security default-keychain -d user -s "${login_keychain}"
+          security list-keychains -d user -s "${login_keychain}-db"
+          security delete-keychain "${HOME}/Library/Keychains/sybil_ci_keychain" >/dev/null 2>&1 || true
+          rm -f "${HOME}/Library/Keychains/sybil_ci_keychain" "${HOME}/Library/Keychains/sybil_ci_keychain-db"

      - name: Upload to TestFlight
        working-directory: ios
        env:
+          HOME: /var/lib/act_runner
          APP_STORE_CONNECT_KEY_ID: ${{ secrets.APP_STORE_CONNECT_KEY_ID }}
          APP_STORE_CONNECT_ISSUER_ID: ${{ secrets.APP_STORE_CONNECT_ISSUER_ID }}
          APP_STORE_CONNECT_KEY_CONTENT: ${{ secrets.APP_STORE_CONNECT_KEY_CONTENT }}
          MATCH_PASSWORD: ${{ secrets.MATCH_PASSWORD }}
          MATCH_GIT_URL: ${{ secrets.MATCH_GIT_URL }}
          MATCH_GIT_BASIC_AUTHORIZATION: ${{ secrets.MATCH_GIT_BASIC_AUTHORIZATION }}
-          SYBIL_BUILD_NUMBER: ${{ github.run_number }}
          FASTLANE_SKIP_UPDATE_CHECK: "1"
          FASTLANE_XCODEBUILD_SETTINGS_TIMEOUT: "120"
-        # act_runner does not propagate setup-ruby's PATH changes into later
-        # steps, so put the selected Ruby back on PATH or `bundle` resolves to
-        # the toolcache default and misses the gems installed above.
        run: |
          export PATH="/Users/runner/hostedtoolcache/Ruby/3.1.7/arm64/bin:${PATH}"
+          ruby --version
          bundle exec fastlane ios beta
@@ -12,43 +12,17 @@ server {
  location /api/ {
    proxy_pass http://server:8787/;
    proxy_http_version 1.1;
-    proxy_buffering off;
-    proxy_cache off;
-    proxy_read_timeout 3600s;
-    proxy_send_timeout 3600s;
    proxy_set_header Host $host;
    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
    proxy_set_header X-Forwarded-Proto $scheme;
-    proxy_set_header Connection "";
-  }
-
-  location = /sw.js {
-    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
-    expires -1;
-    try_files $uri =404;
  }

  location = /manifest.webmanifest {
    default_type application/manifest+json;
-    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
-    expires -1;
-    try_files $uri =404;
-  }
-
-  location = /index.html {
-    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
-    expires -1;
-    try_files $uri =404;
-  }
-
-  location /assets/ {
-    add_header Cache-Control "public, max-age=31536000, immutable" always;
    try_files $uri =404;
  }

  location / {
-    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
-    expires -1;
    try_files $uri $uri/ /index.html;
  }
 }
@@ -12,12 +12,10 @@ services:
      OPENAI_API_KEY: ${OPENAI_API_KEY:-}
      ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
      XAI_API_KEY: ${XAI_API_KEY:-}
-      GEMINI_API_KEY: ${GEMINI_API_KEY:-}
      HERMES_AGENT_API_BASE_URL: ${HERMES_AGENT_API_BASE_URL:-http://127.0.0.1:8642/v1}
      HERMES_AGENT_API_KEY: ${HERMES_AGENT_API_KEY:-}
      HERMES_AGENT_MODEL: ${HERMES_AGENT_MODEL:-}
      EXA_API_KEY: ${EXA_API_KEY:-}
-      BRAVE_SEARCH_API_KEY: ${BRAVE_SEARCH_API_KEY:-}
      CHAT_WEB_SEARCH_ENGINE: ${CHAT_WEB_SEARCH_ENGINE:-exa}
      SEARXNG_BASE_URL: ${SEARXNG_BASE_URL:-}
      CHAT_MAX_TOOL_ROUNDS: ${CHAT_MAX_TOOL_ROUNDS:-100}
@@ -34,13 +34,11 @@ Chat upload limits:
    "openai": { "models": ["gpt-4.1-mini"], "loadedAt": "2026-02-14T00:00:00.000Z", "error": null },
    "anthropic": { "models": ["claude-3-5-sonnet-latest"], "loadedAt": null, "error": null },
    "xai": { "models": ["grok-3-mini"], "loadedAt": null, "error": null },
-    "gemini": { "models": ["gemini-3.5-flash"], "loadedAt": null, "error": null },
    "hermes-agent": { "models": ["hermes-agent"], "loadedAt": null, "error": null }
  }
 }
 ```
 - OpenAI model lists are filtered to models that are expected to work with the backend's Responses API implementation.
- Gemini model lists are loaded from Google's native Models API and filtered to Gemini `generateContent` model ids.
 - `hermes-agent` is included only when `HERMES_AGENT_API_KEY` is configured. Set it to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth. `HERMES_AGENT_API_BASE_URL` defaults to `http://127.0.0.1:8642/v1`; set `HERMES_AGENT_MODEL` only when you need an additional fallback/override model id.
 - The backend loads provider model lists at startup and refreshes them about once every 24 hours. If a later provider refresh fails, the response keeps the last loaded model list for that provider and sets `error` to the latest failure message.

@@ -58,7 +56,7 @@ Chat upload limits:
 ```

 Behavior notes:
- Lists Sybil-managed chat tools that can be enabled for `openai`, `anthropic`, `xai`, and `gemini` chat completions.
+- Lists Sybil-managed chat tools that can be enabled for `openai`, `anthropic`, and `xai` chat completions.
 - Optional tools such as `codex_exec` and `shell_exec` appear only when enabled by server environment configuration.

 ## Active Runs
@@ -130,7 +128,7 @@ Behavior notes:
 ```json
 {
  "title": "optional title",
-  "provider": "optional openai|anthropic|xai|gemini|hermes-agent",
+  "provider": "optional openai|anthropic|xai|hermes-agent",
  "model": "optional model id",
  "additionalSystemPrompt": "optional stored system prompt",
  "enabledTools": ["web_search", "fetch_url"],
@@ -186,7 +184,6 @@ Behavior notes:
 - If the chat already has a non-empty title, server returns the existing chat unchanged.
 - If a title is set while suggestion generation is in flight, server returns the current chat instead of overwriting that title.
 - When no title exists at write time, server uses OpenAI `gpt-4.1-mini` to generate a one-line title (up to ~4 words), updates the chat title, and returns the updated chat.
- If the title provider is unavailable or rejects the request, server still persists a deterministic title derived from the first line of `content` instead of leaving the chat untitled.

 ### `DELETE /v1/chats/:chatId`
 - Response: `{ "deleted": true }`
@@ -237,7 +234,7 @@ Notes:
 ```json
 {
  "chatId": "optional-chat-id",
-  "provider": "openai|anthropic|xai|gemini|hermes-agent",
+  "provider": "openai|anthropic|xai|hermes-agent",
  "model": "string",
  "messages": [
    {
@@ -288,7 +285,6 @@ Behavior notes:
 - For `chatId` calls, server stores only *new* non-assistant messages from provided history to avoid duplicates.
 - `additionalSystemPrompt`, when present directly or loaded from stored chat settings, is prepended to the provider request as a `system` message and is not inserted into the persisted chat transcript by this endpoint.
 - `enabledTools` limits Sybil-managed tools for this request. When omitted for a saved chat, the stored chat setting is used; otherwise all available tools are enabled by default. An empty array disables Sybil-managed tools.
- `maxTokens` is optional. For `anthropic`, when omitted the backend requests the selected model's maximum output token limit from Anthropic's Models API and uses that as `max_tokens`; if the model limit cannot be loaded, the fallback is 128000. For other providers, omitted `maxTokens` is not sent as an explicit cap.
 - Server persists final assistant output and call metadata (`LlmCall`) in DB.
 - Server updates chat-level model metadata on each call: `lastUsedProvider`/`lastUsedModel`; first successful/failed call also initializes `initiatedProvider`/`initiatedModel` if unset.
 - Attachments are optional and currently apply to `user` messages. Persisted chat history stores them under `message.metadata.attachments`.
@@ -297,16 +293,13 @@ Behavior notes:
 - For `openai`, backend calls OpenAI's Responses API and enables internal tool use with an internal system instruction.
 - For `anthropic`, backend calls Anthropic's Messages API and enables internal tool use with Anthropic `tool_use`/`tool_result` content blocks.
 - For `xai`, backend calls xAI's OpenAI-compatible Chat Completions API and enables internal tool use with the same internal system instruction.
- For `gemini`, backend calls Google's native Gemini `generateContent` API and enables internal tool use with Gemini function calling.
 - For `hermes-agent`, backend calls the configured Hermes Agent OpenAI-compatible Chat Completions API without adding Sybil-managed tool definitions; Hermes Agent handles its own tools server-side.
 - For `openai`, image attachments are sent as Responses `input_image` items and text attachments are sent as `input_text` items.
- For `gemini`, image attachments are sent as native Gemini `inlineData` parts and text attachments are sent as text parts.
 - For `xai` and `hermes-agent`, image attachments are sent as Chat Completions content parts alongside text.
 - For `openai`, Responses calls that can enter the server-managed tool loop use `store: true` so reasoning and function-call items can be passed between tool rounds.
 - For `anthropic`, image attachments are sent as Messages API `image` blocks using base64 source data; text attachments are added as `text` blocks.
- Available Sybil-managed tool calls for `openai`, `anthropic`, `xai`, and `gemini`: `web_search` and `fetch_url`. When `CHAT_CODEX_TOOL_ENABLED=true`, `codex_exec` is also available. When `CHAT_SHELL_TOOL_ENABLED=true`, `shell_exec` is also available.
- `web_search` returns ranked results with per-result summaries/snippets. Its backend engine is selected by `CHAT_WEB_SEARCH_ENGINE`: `exa` (default), `brave` (requires `BRAVE_SEARCH_API_KEY`), or `searxng` (requires `SEARXNG_BASE_URL`; the instance must allow `format=json`).
- Brave searches are queued and evenly paced according to the shortest window in Brave's `X-RateLimit-Policy` response header. The backend also honors `X-RateLimit-Remaining`/`X-RateLimit-Reset` and retries `429` responses up to three times with reset-aware exponential backoff; quota resets beyond the bounded retry window fail immediately.
+- Available Sybil-managed tool calls for `openai`, `anthropic`, and `xai`: `web_search` and `fetch_url`. When `CHAT_CODEX_TOOL_ENABLED=true`, `codex_exec` is also available. When `CHAT_SHELL_TOOL_ENABLED=true`, `shell_exec` is also available.
+- `web_search` returns ranked results with per-result summaries/snippets. Its backend engine is selected by `CHAT_WEB_SEARCH_ENGINE` (`exa` default, or `searxng` with `SEARXNG_BASE_URL` set). SearXNG mode requires the instance to allow `format=json`.
 - `fetch_url` fetches a URL with browser-like navigation headers and returns plaintext page content (HTML converted to text server-side).
 - `codex_exec` delegates coding, shell, repository inspection, and other complex software tasks to a persistent remote Codex CLI workspace over SSH. The server runs `codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check <non-interactive wrapped prompt>` on the configured devbox inside `CHAT_CODEX_REMOTE_WORKDIR`, with SSH stdin closed.
 - `shell_exec` runs arbitrary non-interactive shell commands on the same configured devbox, starting in `CHAT_CODEX_REMOTE_WORKDIR`. It uses `bash -lc` when bash exists, otherwise `sh -lc`, closes SSH stdin, and does not run inside the Sybil server container.
@@ -324,16 +317,6 @@ Behavior notes:
  - `CHAT_SHELL_EXEC_TIMEOUT_MS=120000` (optional)
 - When a tool call is executed, backend stores a chat `Message` with `role: "tool"` and tool metadata (`metadata.kind = "tool_call"`). Streaming requests emit an initiated SSE `tool_call` event before execution, then persist each completed or failed tool call as its terminal SSE `tool_call` event is emitted, then store the assistant output when the completion finishes.

-## Streaming Chat
-
-### `POST /v1/chat-completions/stream`
-
- The request accepts the chat-completion fields above plus optional `persist` and `clientRequestId` fields.
- `clientRequestId` is only valid for a persisted request with a `chatId`, may be up to 128 characters, and should be a stable unique value generated once per user submission.
- Retrying with the same `chatId` and `clientRequestId` replays the matching active or completed stream rather than starting a duplicate provider call.
- The server persists the ID in `metadata.clientRequestId` on the submitted user message and completed assistant message.
- The complete request, SSE event, persistence, retry, and attach contracts are defined in `docs/api/streaming-chat.md`.
-
 ## Searches

 ### `GET /v1/searches`
@@ -433,9 +416,9 @@ Behavior notes:
  "updatedAt": "...",
  "starred": false,
  "starredAt": null,
-  "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
+  "initiatedProvider": "openai|anthropic|xai|hermes-agent|null",
  "initiatedModel": "string|null",
-  "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
+  "lastUsedProvider": "openai|anthropic|xai|hermes-agent|null",
  "lastUsedModel": "string|null",
  "additionalSystemPrompt": null,
  "enabledTools": ["web_search", "fetch_url"]
@@ -485,9 +468,9 @@ Behavior notes:
  "updatedAt": "...",
  "starred": false,
  "starredAt": null,
-  "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
+  "initiatedProvider": "openai|anthropic|xai|hermes-agent|null",
  "initiatedModel": "string|null",
-  "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
+  "lastUsedProvider": "openai|anthropic|xai|hermes-agent|null",
  "lastUsedModel": "string|null",
  "additionalSystemPrompt": null,
  "enabledTools": ["web_search", "fetch_url"],
@@ -21,8 +21,7 @@ Authentication:
 {
  "chatId": "optional-chat-id",
  "persist": true,
-  "clientRequestId": "optional-client-generated-id",
-  "provider": "openai|anthropic|xai|gemini|hermes-agent",
+  "provider": "openai|anthropic|xai|hermes-agent",
  "model": "string",
  "messages": [
    {
@@ -62,19 +61,15 @@ Notes:
 - If `persist` is `true` and `chatId` is omitted, backend creates a new chat.
 - If `chatId` is provided, backend validates it exists.
 - If `persist` is `false`, `chatId` must be omitted. Backend does not create a chat and does not persist input messages, tool-call messages, assistant output, or `LlmCall` metadata.
- `clientRequestId` is optional and is only valid for a persisted stream with a `chatId`. Clients should generate one stable, unique value per user submission and reuse it when retrying a disconnected request.
- A retry with the same `chatId` and `clientRequestId` attaches to and replays the matching active stream. If that submission already completed, the endpoint replays `meta` and `done` without invoking the provider again. This makes retrying the initial streaming `POST` idempotent.
- `clientRequestId` values may be up to 128 characters. The server stores the value in `metadata.clientRequestId` on the submitted user message and completed assistant message.
 - For persisted streams, backend stores only new non-assistant input history rows to avoid duplicates.
 - `additionalSystemPrompt`, when present directly or loaded from stored chat settings, is prepended to the provider request as a `system` message and is not inserted into the persisted chat transcript by this endpoint.
 - `enabledTools` limits Sybil-managed tools for this request. When omitted for a saved chat, the stored chat setting is used; otherwise all available tools are enabled by default. An empty array disables Sybil-managed tools.
- `maxTokens` is optional. For `anthropic`, when omitted the backend requests the selected model's maximum output token limit from Anthropic's Models API and uses that as `max_tokens`; if the model limit cannot be loaded, the fallback is 128000. For other providers, omitted `maxTokens` is not sent as an explicit cap.
 - Attachments are optional and are persisted under `message.metadata.attachments` on stored user messages when `persist` is `true`.

 Persisted chat streams with a `chatId` are backend-owned active runs:
 - Once started, the backend keeps the stream running even if the HTTP client disconnects or refreshes.
 - While running, `GET /v1/active-runs` includes the `chatId`.
- Starting a second persisted stream for the same active `chatId` returns `409`, unless its `clientRequestId` matches the active submission, in which case the existing stream is replayed.
+- Starting a second persisted stream for the same active `chatId` returns `409`.
 - Clients can reattach with `POST /v1/chats/:chatId/stream/attach`.

 ## Attach Endpoint
@@ -178,21 +173,18 @@ Terminal tool-call event:
 - `openai`: backend uses OpenAI's Responses API and may execute internal function tool calls (`web_search`, `fetch_url`, optional `codex_exec`, and optional `shell_exec`) before producing final text.
 - `anthropic`: backend uses Anthropic's Messages API and may execute the same internal tools with `tool_use`/`tool_result` content blocks before producing final text.
 - `xai`: backend uses xAI's OpenAI-compatible Chat Completions API and may execute the same internal tool calls before producing final text.
- `gemini`: backend uses Google's native Gemini `streamGenerateContent` API and may execute the same internal tool calls before producing final text.
 - `fetch_url` sends browser-like navigation headers for outbound URL requests to reduce false 403s from sites that reject generic server clients.
 - `hermes-agent`: backend uses the configured Hermes Agent OpenAI-compatible Chat Completions API. Sybil does not add its own tool definitions for this provider; Hermes Agent handles its own tools server-side. Custom Hermes stream events are normalized away unless they produce text deltas in this SSE contract.
 - `openai`: image attachments are sent as Responses `input_image` items; text attachments are sent as `input_text` items.
- `gemini`: image attachments are sent as native Gemini `inlineData` parts; text attachments are inlined as text parts.
 - `xai` and `hermes-agent`: image attachments are sent as Chat Completions content parts; text attachments are inlined as text parts.
 - `openai`: Responses calls that can enter the server-managed tool loop use `store: true` so reasoning and function-call items can be passed between tool rounds.
 - `anthropic`: streamed via event stream; emits `delta` from `content_block_delta` with `text_delta`, and emits normalized `tool_call` SSE events when Anthropic `tool_use` blocks are executed. Image attachments are sent as base64 `image` blocks and text attachments are appended as `text` blocks.
- `web_search` uses `CHAT_WEB_SEARCH_ENGINE`: `exa` (default), `brave` (requires `BRAVE_SEARCH_API_KEY`), or `searxng` (requires `SEARXNG_BASE_URL`; the instance must allow `format=json`). This only affects chat-mode tool calls, not search-mode endpoints.
- Brave searches are queued and evenly paced according to the shortest window in Brave's `X-RateLimit-Policy` response header. The backend also honors `X-RateLimit-Remaining`/`X-RateLimit-Reset` and retries `429` responses up to three times with reset-aware exponential backoff; quota resets beyond the bounded retry window fail immediately.
+- `web_search` uses `CHAT_WEB_SEARCH_ENGINE` (`exa` default, or `searxng` with `SEARXNG_BASE_URL` set). SearXNG mode requires the instance to allow `format=json`. This only affects chat-mode tool calls, not search-mode endpoints.
 - `codex_exec` is available only when `CHAT_CODEX_TOOL_ENABLED=true`. It SSHes to `CHAT_CODEX_REMOTE_HOST`, creates/uses `CHAT_CODEX_REMOTE_WORKDIR`, and runs `codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check <non-interactive wrapped prompt>` there with SSH stdin closed. Prefer `CHAT_CODEX_SSH_KEY_PATH` with a read-only mounted private key; `CHAT_CODEX_SSH_PRIVATE_KEY_B64` is also supported.
 - `shell_exec` is available only when `CHAT_SHELL_TOOL_ENABLED=true`. It uses the same devbox SSH configuration, starts in `CHAT_CODEX_REMOTE_WORKDIR`, and runs non-interactive shell commands there with SSH stdin closed, not inside the Sybil server container.
 - `CHAT_MAX_TOOL_ROUNDS` controls how many model/tool result cycles may occur before the backend returns a tool-call limit message; default is 100.

-Tool-enabled streaming notes (`openai`/`anthropic`/`xai`/`gemini`):
+Tool-enabled streaming notes (`openai`/`anthropic`/`xai`):
 - Stream still emits standard `meta`, `delta`, `done|error` events.
 - Stream may emit `tool_call` events while tool calls are executed.
 - `delta` events carry assistant text and are emitted incrementally for normal text rounds. The backend may buffer model-native text briefly while determining whether a provider round contains tool calls.
@@ -21,12 +21,6 @@ Instructions for work under `/Users/buzzert/src/sybil-2/ios`.
 - To choose a screenshot path, run `just screenshot path=build/name.png`.
 - The underlying screenshot command is `xcrun simctl io booted screenshot <path>` and requires a booted simulator.

-## Release Workflow
- iOS release tags use the annotated tag namespace `release/ios/vX.Y.Z`; increment from the latest existing `release/ios/v*` tag.
- Tag message convention is `ios: X.Y.Z`, for example `git tag -a release/ios/v1.13.5 -m "ios: 1.13.5"`.
- Push the release commit and tag together with `git push origin <branch> release/ios/vX.Y.Z`.
- Fastlane derives the marketing version from the release tag and stamps `ios/Apps/Sybil/project.yml` during CI, so do not manually bump `MARKETING_VERSION` for normal tagged releases unless explicitly requested.
-
 ## App Structure
 - App target entry: `/Users/buzzert/src/sybil-2/ios/Apps/Sybil/Sources/SybilApp.swift`
 - Shared iOS app code lives in Swift package:
@@ -57,5 +51,4 @@ Instructions for work under `/Users/buzzert/src/sybil-2/ios`.
  - OpenAI: `gpt-4.1-mini`
  - Anthropic: `claude-3-5-sonnet-latest`
  - xAI: `grok-3-mini`
-  - Gemini: `gemini-3.5-flash`
  - Hermes Agent: `hermes-agent`
@@ -24,7 +24,7 @@ targets:
        GENERATE_INFOPLIST_FILE: YES
        INFOPLIST_FILE: Apps/Sybil/Info.plist
        ASSETCATALOG_COMPILER_APPICON_NAME: AppIcon
-        MARKETING_VERSION: "1.13.2"
+        MARKETING_VERSION: "1.10"
        CURRENT_PROJECT_VERSION: 11
        INFOPLIST_KEY_CFBundleDisplayName: Sybil
        INFOPLIST_KEY_ITSAppUsesNonExemptEncryption: NO
@@ -58,8 +58,7 @@ struct SybilChatTranscriptView: View {
                        .frame(height: 18 + bottomContentInset)
                        .id(bottomAnchorID)
                }
-                .frame(maxWidth: SybilLayout.webContentMaxWidth, alignment: .leading)
-                .frame(maxWidth: .infinity, alignment: .center)
+                .frame(maxWidth: .infinity, alignment: .leading)
                .padding(.horizontal, 14)
                .padding(.top, 18 + topContentInset)
            }
@@ -67,6 +66,7 @@ struct SybilChatTranscriptView: View {
            .scrollDismissesKeyboard(.interactively)
            .onAppear {
                syncKnownToolCallMessageIDs()
+                scrollToBottom(with: proxy, animated: false)
            }
            .onChange(of: toolCallMessageIDSignature) { _, _ in
                syncKnownToolCallMessageIDs()
@@ -4,7 +4,6 @@ public enum Provider: String, Codable, CaseIterable, Hashable, Sendable {
    case openai
    case anthropic
    case xai
-    case gemini
    case hermesAgent = "hermes-agent"

    public var displayName: String {
@@ -12,7 +11,6 @@ public enum Provider: String, Codable, CaseIterable, Hashable, Sendable {
        case .openai: return "OpenAI"
        case .anthropic: return "Anthropic"
        case .xai: return "xAI"
-        case .gemini: return "Gemini"
        case .hermesAgent: return "Hermes Agent"
        }
    }
@@ -98,8 +98,7 @@ struct SybilSearchResultsView: View {
                        .foregroundStyle(SybilTheme.danger)
                }
            }
-            .frame(maxWidth: SybilLayout.webContentMaxWidth, alignment: .leading)
-            .frame(maxWidth: .infinity, alignment: .center)
+            .frame(maxWidth: .infinity, alignment: .leading)
            .padding(.horizontal, 14)
            .padding(.top, 20 + topContentInset)
            .padding(.bottom, 20 + bottomContentInset)
@@ -11,13 +11,11 @@ final class SybilSettingsStore {
        static let preferredOpenAIModel = "sybil.ios.preferredOpenAIModel"
        static let preferredAnthropicModel = "sybil.ios.preferredAnthropicModel"
        static let preferredXAIModel = "sybil.ios.preferredXAIModel"
-        static let preferredGeminiModel = "sybil.ios.preferredGeminiModel"
        static let preferredHermesAgentModel = "sybil.ios.preferredHermesAgentModel"
        static let quickQuestionPreferredProvider = "sybil.ios.quickQuestionPreferredProvider"
        static let quickQuestionPreferredOpenAIModel = "sybil.ios.quickQuestionPreferredOpenAIModel"
        static let quickQuestionPreferredAnthropicModel = "sybil.ios.quickQuestionPreferredAnthropicModel"
        static let quickQuestionPreferredXAIModel = "sybil.ios.quickQuestionPreferredXAIModel"
-        static let quickQuestionPreferredGeminiModel = "sybil.ios.quickQuestionPreferredGeminiModel"
        static let quickQuestionPreferredHermesAgentModel = "sybil.ios.quickQuestionPreferredHermesAgentModel"
    }

@@ -46,7 +44,6 @@ final class SybilSettingsStore {
            .openai: defaults.string(forKey: Keys.preferredOpenAIModel) ?? "gpt-4.1-mini",
            .anthropic: defaults.string(forKey: Keys.preferredAnthropicModel) ?? "claude-3-5-sonnet-latest",
            .xai: defaults.string(forKey: Keys.preferredXAIModel) ?? "grok-3-mini",
-            .gemini: defaults.string(forKey: Keys.preferredGeminiModel) ?? "gemini-3.5-flash",
            .hermesAgent: defaults.string(forKey: Keys.preferredHermesAgentModel) ?? "hermes-agent"
        ]
        self.preferredModelByProvider = preferredModels
@@ -57,7 +54,6 @@ final class SybilSettingsStore {
            .openai: defaults.string(forKey: Keys.quickQuestionPreferredOpenAIModel) ?? preferredModels[.openai] ?? "gpt-4.1-mini",
            .anthropic: defaults.string(forKey: Keys.quickQuestionPreferredAnthropicModel) ?? preferredModels[.anthropic] ?? "claude-3-5-sonnet-latest",
            .xai: defaults.string(forKey: Keys.quickQuestionPreferredXAIModel) ?? preferredModels[.xai] ?? "grok-3-mini",
-            .gemini: defaults.string(forKey: Keys.quickQuestionPreferredGeminiModel) ?? preferredModels[.gemini] ?? "gemini-3.5-flash",
            .hermesAgent: defaults.string(forKey: Keys.quickQuestionPreferredHermesAgentModel) ?? preferredModels[.hermesAgent] ?? "hermes-agent"
        ]
    }
@@ -76,14 +72,12 @@ final class SybilSettingsStore {
        defaults.set(preferredModelByProvider[.openai], forKey: Keys.preferredOpenAIModel)
        defaults.set(preferredModelByProvider[.anthropic], forKey: Keys.preferredAnthropicModel)
        defaults.set(preferredModelByProvider[.xai], forKey: Keys.preferredXAIModel)
-        defaults.set(preferredModelByProvider[.gemini], forKey: Keys.preferredGeminiModel)
        defaults.set(preferredModelByProvider[.hermesAgent], forKey: Keys.preferredHermesAgentModel)

        defaults.set(quickQuestionPreferredProvider.rawValue, forKey: Keys.quickQuestionPreferredProvider)
        defaults.set(quickQuestionPreferredModelByProvider[.openai], forKey: Keys.quickQuestionPreferredOpenAIModel)
        defaults.set(quickQuestionPreferredModelByProvider[.anthropic], forKey: Keys.quickQuestionPreferredAnthropicModel)
        defaults.set(quickQuestionPreferredModelByProvider[.xai], forKey: Keys.quickQuestionPreferredXAIModel)
-        defaults.set(quickQuestionPreferredModelByProvider[.gemini], forKey: Keys.quickQuestionPreferredGeminiModel)
        defaults.set(quickQuestionPreferredModelByProvider[.hermesAgent], forKey: Keys.quickQuestionPreferredHermesAgentModel)
    }

@@ -64,10 +64,6 @@ extension Font {
    }
 }

-enum SybilLayout {
-    static let webContentMaxWidth: CGFloat = 896
-}
-
 enum SybilTheme {
    static let background = Color(red: 0.02, green: 0.02, blue: 0.05)
    static let surface = Color(red: 0.05, green: 0.04, blue: 0.10)
@@ -160,7 +160,6 @@ final class SybilViewModel {
        .openai: ["gpt-4.1-mini"],
        .anthropic: ["claude-3-5-sonnet-latest"],
        .xai: ["grok-3-mini"],
-        .gemini: ["gemini-3.5-flash", "gemini-flash-latest"],
        .hermesAgent: ["hermes-agent"]
    ]

@@ -1752,16 +1751,13 @@ final class SybilViewModel {
                switch target {
                case let .chat(chatID):
                    SybilLog.debug(SybilLog.app, "Refreshing chat \(chatID)")
-                    let isSelectingDifferentChat = selectedChat?.id != chatID
                    let chat = try await client.getChat(chatID: chatID)
                    guard selectedItem == target, draftKind == nil else {
                        return
                    }
                    selectedChat = chat
                    selectedSearch = nil
-                    if isSelectingDifferentChat {
-                        requestChatBottomPin()
-                    }
+                    requestChatBottomPin()

                    if let provider = chat.lastUsedProvider,
                       let model = chat.lastUsedModel,
@@ -544,14 +544,12 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
@MainActor
@Test func foregroundChatRefreshReloadsSelectedTranscript() async throws {
    let date = Date(timeIntervalSince1970: 1_700_000_100)
-    let staleDetail = makeChatDetail(id: "chat-2", date: date, body: "stale transcript")
    let detail = makeChatDetail(id: "chat-2", date: date, body: "refreshed transcript")
    let client = MockSybilClient(chatDetails: ["chat-2": detail])
    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
    viewModel.isAuthenticated = true
    viewModel.isCheckingSession = false
    viewModel.selectedItem = .chat("chat-2")
-    viewModel.selectedChat = staleDetail

    await viewModel.refreshVisibleContent(refreshCollections: false, refreshSelection: true)

@@ -561,7 +559,7 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
    #expect(snapshot.listSearches == 0)
    #expect(snapshot.getChat == 1)
    #expect(viewModel.selectedChat?.messages.first?.content == "refreshed transcript")
-    #expect(viewModel.chatBottomPinRequestID == 0)
+    #expect(viewModel.chatBottomPinRequestID == 1)
 }

@MainActor
@@ -677,7 +675,6 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran

    #expect(viewModel.displayedMessages.first?.content == "fresh transcript")
    #expect(!viewModel.isLoadingSelection)
-    #expect(viewModel.chatBottomPinRequestID == 1)
 }

@MainActor
@@ -1,3 +1,4 @@
+require "fileutils"
 require "shellwords"

 default_platform(:ios)
@@ -6,59 +7,41 @@ APP_IDENTIFIER = "net.buzzert.sybil2"
 SCHEME = "Sybil"
 TEAM_ID = "DQQH5H6GBD"
 PROFILE_NAME = "Sybil AppStore CI"
+SIGNING_IDENTITY = "Apple Distribution: James Magahern (DQQH5H6GBD)"
 CI_KEYCHAIN_NAME = "sybil_ci_keychain"
 CI_KEYCHAIN_PASSWORD = "sybil-ci-keychain-password"
-CI_KEYCHAIN_DB_PATH = File.expand_path("~/Library/Keychains/#{CI_KEYCHAIN_NAME}-db")
 IOS_ROOT = File.expand_path("..", __dir__)
 PROJECT_FILE = File.join(IOS_ROOT, "Sybil.xcodeproj")
 PROJECT_SPEC = File.join(IOS_ROOT, "project.yml")
-APP_PROJECT_SPEC = File.join(IOS_ROOT, "Apps/Sybil/project.yml")
+CI_KEYCHAIN_PATH = File.join(File.expand_path("~/Library/Keychains"), CI_KEYCHAIN_NAME)
+CI_KEYCHAIN_DB_PATH = "#{CI_KEYCHAIN_PATH}-db"
+LOGIN_KEYCHAIN_PATH = File.expand_path("~/Library/Keychains/login.keychain")
+LOGIN_KEYCHAIN_DB_PATH = "#{LOGIN_KEYCHAIN_PATH}-db"

 def present?(value)
  !value.to_s.strip.empty?
 end

+def release_version
+  tag = ENV["SYBIL_VERSION_TAG"].to_s
+  tag = ENV["GITHUB_REF_NAME"].to_s if !present?(tag)
+  tag = ENV["GITHUB_REF"].to_s.sub(%r{\Arefs/tags/}, "") if !present?(tag)
+  tag = sh("git describe --tags --abbrev=0").strip if !present?(tag)
+  version = tag.sub(%r{\Arelease/}, "").sub(/\Av/, "")
+
+  unless version.match?(/\A\d+\.\d+\.\d+\z/)
+    UI.user_error!("Release tag must look like v1.2.3; got #{tag.inspect}")
+  end
+
+  version
+end
+
 def ci?
  present?(ENV["CI"])
 end

-def release_version
-  tag = ENV["SYBIL_VERSION_TAG"]
-  tag = ENV["GITHUB_REF_NAME"] if !present?(tag)
-  tag = ENV["GITHUB_REF"].to_s.sub(%r{\Arefs/tags/}, "") if !present?(tag)
-  tag = sh("git describe --tags --abbrev=0").strip if !present?(tag)
-  match = tag.to_s.match(%r{\Arelease/ios/v(\d+\.\d+\.\d+)\z})
-
-  unless match
-    UI.user_error!("Release tag must look like release/ios/v1.2.3; got #{tag.inspect}")
-  end
-
-  match[1]
-end
-
-# App Store Connect requires CFBundleVersion to be unique and strictly
-# increasing app-wide (not just per marketing version), so we derive it from
-# the monotonic CI run number rather than querying TestFlight (that query can
-# lag behind builds still processing and hand back a colliding value).
-def build_number
-  value = present?(ENV["SYBIL_BUILD_NUMBER"]) ? ENV["SYBIL_BUILD_NUMBER"] : ENV["GITHUB_RUN_NUMBER"]
-
-  unless value.to_s.match?(/\A\d+\z/)
-    UI.user_error!("Build number must come from SYBIL_BUILD_NUMBER/GITHUB_RUN_NUMBER; got #{value.inspect}")
-  end
-
-  value.to_i
-end
-
-def stamp_marketing_version(version)
-  contents = File.read(APP_PROJECT_SPEC)
-  updated = contents.sub(/^(\s*MARKETING_VERSION:\s*).*/, "\\1\"#{version}\"")
-
-  if updated == contents
-    UI.user_error!("Could not find MARKETING_VERSION in #{APP_PROJECT_SPEC}")
-  end
-
-  File.write(APP_PROJECT_SPEC, updated)
+def ci_keychain_path
+  File.file?(CI_KEYCHAIN_DB_PATH) ? CI_KEYCHAIN_DB_PATH : CI_KEYCHAIN_PATH
 end

 platform :ios do
@@ -71,37 +54,54 @@ platform :ios do
    )
  end

-  # CI signs headlessly, so match needs a fresh unlocked keychain to import
-  # into. codesign resolves identities through the user keychain *search list*
-  # (first match wins; the --keychain flag does not restrict the lookup), and
-  # other projects' keychains on this runner hold the same identity but are
-  # usually locked — so ours must come first. delete_keychain in the beta
-  # lane's ensure removes both the keychain and its search-list entry, which
-  # also keeps our (later locked) copy from shadowing those other projects.
-  private_lane :prepare_ci_keychain do
+  private_lane :setup_ci_signing do
    next unless ci?

-    delete_keychain(name: CI_KEYCHAIN_NAME) if File.file?(CI_KEYCHAIN_DB_PATH)
+    FileUtils.mkdir_p(File.dirname(CI_KEYCHAIN_PATH))
+    sh("security delete-keychain #{CI_KEYCHAIN_PATH.shellescape} || true", log: false)
+    FileUtils.rm_f(CI_KEYCHAIN_PATH)
+    FileUtils.rm_f(CI_KEYCHAIN_DB_PATH)
+
    create_keychain(
-      name: CI_KEYCHAIN_NAME,
+      path: CI_KEYCHAIN_PATH,
      password: CI_KEYCHAIN_PASSWORD,
+      default_keychain: false,
      unlock: true,
      timeout: 3600,
+      lock_when_sleeps: true,
      add_to_search_list: false
    )

-    others = sh("security list-keychains -d user", log: false)
-      .scan(/"([^"]+)"/)
-      .flatten
-      .reject { |path| path.include?(CI_KEYCHAIN_NAME) }
-    sh("security list-keychains -d user -s #{([CI_KEYCHAIN_DB_PATH] + others).shelljoin}")
+    sh("security default-keychain -d user -s #{CI_KEYCHAIN_PATH.shellescape}", log: false)
+    sh("security list-keychains -d user -s #{ci_keychain_path.shellescape}", log: false)
+    sh("security list-keychains -d dynamic -s #{ci_keychain_path.shellescape} || true", log: false)
+    sh("security list-keychains -d common -s #{ci_keychain_path.shellescape} || true", log: false)

-    ENV["MATCH_KEYCHAIN_NAME"] = CI_KEYCHAIN_NAME
+    ENV["MATCH_KEYCHAIN_NAME"] = CI_KEYCHAIN_PATH
    ENV["MATCH_KEYCHAIN_PASSWORD"] = CI_KEYCHAIN_PASSWORD
+    ENV["MATCH_READONLY"] = "true"
+  end
+
+  private_lane :cleanup_ci_signing do
+    next unless ci?
+
+    if File.file?(LOGIN_KEYCHAIN_DB_PATH) || File.file?(LOGIN_KEYCHAIN_PATH)
+      sh("security default-keychain -d user -s #{LOGIN_KEYCHAIN_PATH.shellescape} || true", log: false)
+      sh("security list-keychains -d user -s #{LOGIN_KEYCHAIN_DB_PATH.shellescape} || true", log: false)
+    end
+    sh("security delete-keychain #{ci_keychain_path.shellescape} || true", log: false)
+    FileUtils.rm_f(CI_KEYCHAIN_PATH)
+    FileUtils.rm_f(CI_KEYCHAIN_DB_PATH)
+  rescue => error
+    UI.message("Unable to delete temporary CI keychain: #{error.message}")
+  ensure
+    ENV.delete("MATCH_KEYCHAIN_NAME")
+    ENV.delete("MATCH_KEYCHAIN_PASSWORD")
+    ENV.delete("MATCH_READONLY")
  end

  private_lane :sync_signing do |options|
-    match(
+    match_options = {
      type: "appstore",
      readonly: options.fetch(:readonly),
      app_identifier: APP_IDENTIFIER,
@@ -112,7 +112,28 @@ platform :ios do
      git_full_name: "Sybil Release Bot",
      git_user_email: "james.magahern@me.com",
      api_key: options.fetch(:api_key)
-    )
+    }
+    match_options[:keychain_name] = ENV["MATCH_KEYCHAIN_NAME"] if present?(ENV["MATCH_KEYCHAIN_NAME"])
+    match_options[:keychain_password] = ENV["MATCH_KEYCHAIN_PASSWORD"] if ENV.key?("MATCH_KEYCHAIN_PASSWORD")
+
+    match(match_options)
+  end
+
+  private_lane :verify_ci_signing do
+    next unless ci?
+
+    if File.file?(ci_keychain_path)
+      password = ENV.fetch("MATCH_KEYCHAIN_PASSWORD", "")
+      sh("security unlock-keychain -p #{password.shellescape} #{ci_keychain_path.shellescape}", log: false)
+      sh("security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k #{password.shellescape} #{ci_keychain_path.shellescape}", log: false)
+    end
+
+    identities = sh("security find-identity -v -p codesigning #{ci_keychain_path.shellescape}", log: false)
+    UI.message(identities)
+
+    unless identities.include?(SIGNING_IDENTITY)
+      UI.user_error!("The CI keychain search list does not contain #{SIGNING_IDENTITY}")
+    end
  end

  desc "Create or update match signing assets"
@@ -122,29 +143,49 @@ platform :ios do

  desc "Build and upload to TestFlight"
  lane :beta do
-    prepare_ci_keychain
+    setup_ci_signing

    api_key = app_store_api_key

-    version = release_version
-    stamp_marketing_version(version)
-    sh("xcodegen", "--spec", PROJECT_SPEC)
+    sh("xcodegen --spec #{PROJECT_SPEC.shellescape}")

-    increment_version_number(version_number: version, xcodeproj: PROJECT_FILE)
-    increment_build_number(build_number: build_number, xcodeproj: PROJECT_FILE)
+    increment_version_number(
+      version_number: release_version,
+      xcodeproj: PROJECT_FILE
+    )
+
+    latest_build_number = latest_testflight_build_number(
+      app_identifier: APP_IDENTIFIER,
+      api_key: api_key,
+      initial_build_number: 0
+    )
+
+    increment_build_number(
+      build_number: latest_build_number + 1,
+      xcodeproj: PROJECT_FILE
+    )

    sync_signing(api_key: api_key, readonly: true)
+    verify_ci_signing
+
+    xcargs = [
+      "DEVELOPMENT_TEAM=#{TEAM_ID.shellescape}",
+      "CODE_SIGN_STYLE=Manual",
+      "CODE_SIGN_IDENTITY=Apple\\ Distribution",
+      "PROVISIONING_PROFILE_SPECIFIER=#{PROFILE_NAME.shellescape}"
+    ]
+
+    if ci?
+      xcargs << "CODE_SIGN_KEYCHAIN=#{ci_keychain_path.shellescape}"
+      xcargs << "OTHER_CODE_SIGN_FLAGS=#{("--keychain #{ci_keychain_path}").shellescape}"
+    end

    build_app(
      project: PROJECT_FILE,
      scheme: SCHEME,
      export_method: "app-store",
-      xcargs: [
-        "DEVELOPMENT_TEAM=#{TEAM_ID.shellescape}",
-        "CODE_SIGN_STYLE=Manual",
-        "CODE_SIGN_IDENTITY=Apple\\ Distribution",
-        "PROVISIONING_PROFILE_SPECIFIER=#{PROFILE_NAME.shellescape}"
-      ].join(" "),
+      codesigning_identity: "Apple Distribution",
+      xcargs: xcargs.join(" "),
      export_options: {
        signingStyle: "manual",
        teamID: TEAM_ID,
@@ -159,6 +200,6 @@ platform :ios do
      skip_waiting_for_build_processing: true
    )
  ensure
-    delete_keychain(name: CI_KEYCHAIN_NAME) if ci? && File.file?(CI_KEYCHAIN_DB_PATH)
+    cleanup_ci_signing
  end
 end
@@ -1,7 +1,7 @@
 # Sybil Server

 Backend API for:
- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini / Hermes Agent)
+- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Hermes Agent)
 - Personal chat database (chats/messages + LLM call log)

 ## Stack
@@ -43,16 +43,14 @@ If `ADMIN_TOKEN` is not set, the server runs in open mode (dev).
 - `OPENAI_API_KEY`
 - `ANTHROPIC_API_KEY`
 - `XAI_API_KEY`
- `GEMINI_API_KEY`
 - `HERMES_AGENT_API_BASE_URL` (`http://127.0.0.1:8642/v1` by default; include the `/v1` suffix)
 - `HERMES_AGENT_API_KEY` (enables the Hermes Agent provider; set to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth)
 - `HERMES_AGENT_MODEL` (optional fallback/override model id; defaults client-side to `hermes-agent`)
 - `EXA_API_KEY`
- `BRAVE_SEARCH_API_KEY` (required when `CHAT_WEB_SEARCH_ENGINE=brave`)
- `CHAT_WEB_SEARCH_ENGINE` (`exa` by default; `brave` and `searxng` are also supported for chat tool calls only)
+- `CHAT_WEB_SEARCH_ENGINE` (`exa` by default, or `searxng` for chat tool calls only)
 - `SEARXNG_BASE_URL` (required when `CHAT_WEB_SEARCH_ENGINE=searxng`; instance must allow `format=json`)
 - `CHAT_MAX_TOOL_ROUNDS` (`100` by default; maximum model/tool result cycles per chat completion)
- `CHAT_CODEX_TOOL_ENABLED` (`false` by default; enables the `codex_exec` chat tool for managed-tool providers)
+- `CHAT_CODEX_TOOL_ENABLED` (`false` by default; enables the `codex_exec` chat tool for OpenAI/xAI)
 - `CHAT_CODEX_REMOTE_HOST` (required when Codex tool is enabled; SSH host/IP or `user@host`)
 - `CHAT_CODEX_REMOTE_USER` (optional SSH user when host does not include one)
 - `CHAT_CODEX_REMOTE_PORT` (`22` by default)
@@ -60,7 +58,7 @@ If `ADMIN_TOKEN` is not set, the server runs in open mode (dev).
 - `CHAT_CODEX_SSH_KEY_PATH` (recommended: path to a read-only mounted private key)
 - `CHAT_CODEX_SSH_PRIVATE_KEY_B64` (optional fallback private key delivery)
 - `CHAT_CODEX_EXEC_TIMEOUT_MS` (`600000` by default)
- `CHAT_SHELL_TOOL_ENABLED` (`false` by default; enables the `shell_exec` chat tool for managed-tool providers on the same devbox)
+- `CHAT_SHELL_TOOL_ENABLED` (`false` by default; enables the `shell_exec` chat tool for OpenAI/xAI on the same devbox)
 - `CHAT_SHELL_EXEC_TIMEOUT_MS` (`120000` by default)

 ## API
@@ -13,7 +13,6 @@ enum Provider {
  openai
  anthropic
  xai
-  gemini
  hermes_agent @map("hermes-agent")
 }

@@ -24,7 +24,7 @@ const ChatWebSearchEngineSchema = z.preprocess(
    const trimmed = value.trim();
    return trimmed ? trimmed.toLowerCase() : undefined;
  },
-  z.enum(["exa", "searxng", "brave"]).default("exa")
+  z.enum(["exa", "searxng"]).default("exa")
 );

 const BooleanFlagSchema = z.preprocess((value) => {
@@ -66,12 +66,10 @@ const EnvSchema = z.object({
  OPENAI_API_KEY: z.string().optional(),
  ANTHROPIC_API_KEY: z.string().optional(),
  XAI_API_KEY: z.string().optional(),
-  GEMINI_API_KEY: z.string().optional(),
  HERMES_AGENT_API_BASE_URL: HermesAgentApiBaseUrlSchema,
  HERMES_AGENT_API_KEY: OptionalTrimmedStringSchema,
  HERMES_AGENT_MODEL: OptionalTrimmedStringSchema,
  EXA_API_KEY: z.string().optional(),
-  BRAVE_SEARCH_API_KEY: OptionalTrimmedStringSchema,

  // Chat-mode web_search tool configuration. Search mode remains Exa-only for now.
  CHAT_WEB_SEARCH_ENGINE: ChatWebSearchEngineSchema,
@@ -101,14 +99,6 @@ const EnvSchema = z.object({
    });
  }

-  if (value.CHAT_WEB_SEARCH_ENGINE === "brave" && !value.BRAVE_SEARCH_API_KEY) {
-    ctx.addIssue({
-      code: "custom",
-      path: ["BRAVE_SEARCH_API_KEY"],
-      message: "BRAVE_SEARCH_API_KEY is required when CHAT_WEB_SEARCH_ENGINE=brave",
-    });
-  }
-
  if ((value.CHAT_CODEX_TOOL_ENABLED || value.CHAT_SHELL_TOOL_ENABLED) && !value.CHAT_CODEX_REMOTE_HOST) {
    ctx.addIssue({
      code: "custom",
@@ -7,7 +7,6 @@ import { convert as htmlToText } from "html-to-text";
 import { z } from "zod";
 import { buildBrowserLikeNavigationHeaders } from "../browser-fetch-headers.js";
 import { env } from "../env.js";
-import { searchBrave } from "../search/brave.js";
 import { exaClient } from "../search/exa.js";
 import { searchSearxng } from "../search/searxng.js";
 import type { ChatMessage } from "./types.js";
@@ -508,33 +507,11 @@ async function runSearxngWebSearchTool(args: WebSearchArgs): Promise<ToolRunOutc
  };
 }

-async function runBraveWebSearchTool(args: WebSearchArgs): Promise<ToolRunOutcome> {
-  const response = await searchBrave(args.query, {
-    numResults: args.numResults ?? DEFAULT_WEB_RESULTS,
-    includeDomains: args.includeDomains,
-    excludeDomains: args.excludeDomains,
-  });
-
-  return {
-    ok: true,
-    searchEngine: "brave",
-    query: args.query,
-    requestId: response.requestId,
-    results: response.results.map((result, index) => ({
-      rank: index + 1,
-      ...result,
-    })),
-  };
-}
-
 async function runWebSearchTool(input: unknown): Promise<ToolRunOutcome> {
  const args = WebSearchArgsSchema.parse(input);
  if (env.CHAT_WEB_SEARCH_ENGINE === "searxng") {
    return runSearxngWebSearchTool(args);
  }
-  if (env.CHAT_WEB_SEARCH_ENGINE === "brave") {
-    return runBraveWebSearchTool(args);
-  }
  return runExaWebSearchTool(args);
 }

@@ -1,501 +0,0 @@
-import {
-  buildChatToolSystemPrompt,
-  executeToolCallAndBuildEvent,
-  getEnabledChatTools,
-  getUnstreamedText,
-  looksLikeDanglingToolIntent,
-  MAX_DANGLING_TOOL_INTENT_RETRIES,
-  MAX_TOOL_ROUNDS,
-  prepareToolCallExecution,
-  type NormalizedToolCall,
-  type ToolAwareCompletionParams,
-  type ToolAwareCompletionResult,
-  type ToolAwareStreamingEvent,
-  type ToolAwareUsage,
-  type ToolExecutionEvent,
-} from "../chat-tools.js";
-import {
-  buildImageSummaryText,
-  buildTextAttachmentPrompt,
-  buildTopLevelSystemPrompt,
-  getImageAttachments,
-  getTextAttachments,
-  parseImageDataUrl,
-} from "../message-content.js";
-import type { ChatMessage } from "../types.js";
-
-type GeminiClient = {
-  apiKey: string;
-  baseURL: string;
-};
-
-const INTERNAL_CORRECTION =
-  "Internal correction: the previous assistant message claimed it would run a tool, but no tool call was made. If the task needs an available tool, call it now. Otherwise provide the final answer directly without saying you will run a tool.";
-
-function normalizeModelResourceName(model: string) {
-  const trimmed = model.trim().replace(/^\/+/, "");
-  return trimmed.startsWith("models/") || trimmed.startsWith("tunedModels/") ? trimmed : `models/${trimmed}`;
-}
-
-function geminiUrl(client: GeminiClient, model: string, method: "generateContent" | "streamGenerateContent", extraParams: Record<string, string> = {}) {
-  const url = new URL(`${client.baseURL.replace(/\/+$/, "")}/${normalizeModelResourceName(model)}:${method}`);
-  url.searchParams.set("key", client.apiKey);
-  for (const [key, value] of Object.entries(extraParams)) {
-    url.searchParams.set(key, value);
-  }
-  return url;
-}
-
-function generationConfig(params: Pick<ToolAwareCompletionParams, "temperature" | "maxTokens">) {
-  const config: Record<string, unknown> = {};
-  if (params.temperature !== undefined) config.temperature = params.temperature;
-  if (params.maxTokens !== undefined) config.maxOutputTokens = params.maxTokens;
-  return Object.keys(config).length ? config : undefined;
-}
-
-function toGeminiJsonSchema(schema: unknown): Record<string, unknown> | undefined {
-  if (!schema || typeof schema !== "object" || Array.isArray(schema)) return undefined;
-  const input = schema as Record<string, unknown>;
-  const output: Record<string, unknown> = {};
-
-  if (typeof input.type === "string") output.type = input.type;
-  if (typeof input.description === "string") output.description = input.description;
-  if (typeof input.format === "string") output.format = input.format;
-  if (typeof input.nullable === "boolean") output.nullable = input.nullable;
-  if (Array.isArray(input.enum)) output.enum = input.enum.filter((value) => typeof value === "string");
-  if (Array.isArray(input.required)) output.required = input.required.filter((value) => typeof value === "string");
-
-  const items = toGeminiJsonSchema(input.items);
-  if (items) output.items = items;
-
-  if (input.properties && typeof input.properties === "object" && !Array.isArray(input.properties)) {
-    const properties: Record<string, unknown> = {};
-    for (const [key, value] of Object.entries(input.properties)) {
-      const propertySchema = toGeminiJsonSchema(value);
-      if (propertySchema) properties[key] = propertySchema;
-    }
-    if (Object.keys(properties).length) output.properties = properties;
-  }
-
-  return Object.keys(output).length ? output : undefined;
-}
-
-function toGeminiTools(tools: any[]) {
-  const functionDeclarations = tools
-    .map((tool) => {
-      if (tool?.type !== "function") return null;
-      const declaration: Record<string, unknown> = {
-        name: tool.function.name,
-        description: tool.function.description,
-      };
-      const parameters = toGeminiJsonSchema(tool.function.parameters);
-      if (parameters) declaration.parameters = parameters;
-      return declaration;
-    })
-    .filter(Boolean);
-
-  return functionDeclarations.length ? [{ functionDeclarations }] : undefined;
-}
-
-function toContentParts(message: ChatMessage) {
-  const imageAttachments = getImageAttachments(message);
-  const textAttachments = getTextAttachments(message);
-  const parts: Array<Record<string, unknown>> = [];
-
-  for (const attachment of imageAttachments) {
-    const source = parseImageDataUrl(attachment);
-    parts.push({
-      inlineData: {
-        mimeType: source.mediaType,
-        data: source.data,
-      },
-    });
-  }
-
-  const imageSummary = buildImageSummaryText(imageAttachments);
-  if (imageSummary) {
-    parts.push({ text: imageSummary });
-  }
-
-  for (const attachment of textAttachments) {
-    parts.push({ text: buildTextAttachmentPrompt(attachment) });
-  }
-
-  if (message.content.trim()) {
-    parts.push({ text: message.content });
-  }
-
-  return parts.length ? parts : [{ text: "" }];
-}
-
-function buildConversationContent(message: ChatMessage) {
-  if (message.role === "system") {
-    throw new Error("System messages must be handled separately for Gemini.");
-  }
-
-  if (message.role === "tool") {
-    const name = message.name?.trim() || "tool";
-    return {
-      role: "user",
-      parts: [{ text: `Tool output (${name}):\n${message.content}` }],
-    };
-  }
-
-  return {
-    role: message.role === "assistant" ? "model" : "user",
-    parts: toContentParts(message),
-  };
-}
-
-function buildBaseContents(messages: ChatMessage[]) {
-  return messages.filter((message) => message.role !== "system").map((message) => buildConversationContent(message));
-}
-
-function buildSystemInstruction(params: ToolAwareCompletionParams, toolSystemPrompt?: string) {
-  const text = buildTopLevelSystemPrompt(params.messages, params.userLocation, toolSystemPrompt);
-  return text ? { parts: [{ text }] } : undefined;
-}
-
-function mergeUsage(acc: Required<ToolAwareUsage>, usage: any) {
-  const normalized = normalizeUsage(usage);
-  if (!normalized) return false;
-  acc.inputTokens += normalized.inputTokens;
-  acc.outputTokens += normalized.outputTokens;
-  acc.totalTokens += normalized.totalTokens;
-  return true;
-}
-
-function normalizeUsage(usage: any) {
-  if (!usage) return null;
-  const inputTokens = usage.promptTokenCount ?? 0;
-  const outputTokens = usage.candidatesTokenCount ?? 0;
-  const totalTokens = usage.totalTokenCount ?? inputTokens + outputTokens;
-  return { inputTokens, outputTokens, totalTokens };
-}
-
-function getCandidate(response: any) {
-  return Array.isArray(response?.candidates) ? response.candidates[0] : null;
-}
-
-function getParts(response: any) {
-  const parts = getCandidate(response)?.content?.parts;
-  return Array.isArray(parts) ? parts : [];
-}
-
-function extractText(response: any) {
-  return getParts(response)
-    .map((part: any) => (typeof part?.text === "string" ? part.text : ""))
-    .join("");
-}
-
-function stringifyToolArgs(args: unknown) {
-  try {
-    return JSON.stringify(args ?? {});
-  } catch {
-    return "{}";
-  }
-}
-
-function normalizeToolCallsFromParts(parts: any[], round: number): NormalizedToolCall[] {
-  return parts
-    .filter((part) => part?.functionCall)
-    .map((part, index) => ({
-      id: part.functionCall.id ?? `tool_call_${round}_${index}`,
-      name: part.functionCall.name ?? "unknown_tool",
-      arguments: stringifyToolArgs(part.functionCall.args),
-    }));
-}
-
-function buildFunctionResponsePart(call: NormalizedToolCall, toolResult: unknown) {
-  return {
-    functionResponse: {
-      id: call.id,
-      name: call.name,
-      response: toolResult,
-    },
-  };
-}
-
-function appendCorrection(conversation: any[], text: string) {
-  conversation.push({ role: "model", parts: [{ text }] });
-  conversation.push({ role: "user", parts: [{ text: INTERNAL_CORRECTION }] });
-}
-
-async function parseGeminiResponse(response: Response) {
-  const bodyText = await response.text();
-  let body: any = null;
-  try {
-    body = bodyText ? JSON.parse(bodyText) : null;
-  } catch {
-    body = { raw: bodyText };
-  }
-
-  if (!response.ok) {
-    throw new Error(body?.error?.message ?? `Gemini API request failed with status ${response.status}.`);
-  }
-
-  return body;
-}
-
-async function generateContent(params: ToolAwareCompletionParams, body: Record<string, unknown>) {
-  const response = await fetch(geminiUrl(params.client, params.model, "generateContent"), {
-    method: "POST",
-    headers: { "Content-Type": "application/json" },
-    body: JSON.stringify(body),
-  });
-  return parseGeminiResponse(response);
-}
-
-function getFailureMessage(response: any, text: string, toolCallCount: number) {
-  const promptBlockReason = response?.promptFeedback?.blockReason;
-  if (promptBlockReason) return `Gemini prompt blocked: ${promptBlockReason}.`;
-
-  const candidate = getCandidate(response);
-  const finishReason = candidate?.finishReason;
-  if (!finishReason || finishReason === "STOP" || finishReason === "MAX_TOKENS") return null;
-  if (text || toolCallCount > 0) return null;
-  return candidate?.finishMessage ?? `Gemini response stopped: ${finishReason}.`;
-}
-
-function buildRequest(params: ToolAwareCompletionParams, conversation: any[], enabledTools: any[] = []) {
-  const tools = toGeminiTools(enabledTools);
-  return {
-    contents: conversation,
-    systemInstruction: buildSystemInstruction(params, enabledTools.length ? buildChatToolSystemPrompt(params) : undefined),
-    generationConfig: generationConfig(params),
-    tools,
-    toolConfig: tools ? { functionCallingConfig: { mode: "AUTO" } } : undefined,
-  };
-}
-
-export async function completeWithGeminiApi(params: ToolAwareCompletionParams): Promise<ToolAwareCompletionResult> {
-  const enabledTools = getEnabledChatTools(params);
-  const conversation = buildBaseContents(params.messages);
-  const rawResponses: unknown[] = [];
-  const toolEvents: ToolExecutionEvent[] = [];
-  const usageAcc: Required<ToolAwareUsage> = { inputTokens: 0, outputTokens: 0, totalTokens: 0 };
-  let sawUsage = false;
-  let totalToolCalls = 0;
-  let danglingToolIntentRetries = 0;
-
-  for (let round = 0; round < MAX_TOOL_ROUNDS; round += 1) {
-    const response = await generateContent(params, buildRequest(params, conversation, enabledTools));
-    rawResponses.push(response);
-    sawUsage = mergeUsage(usageAcc, response?.usageMetadata) || sawUsage;
-
-    const parts = getParts(response);
-    const text = extractText(response);
-    const normalizedToolCalls = normalizeToolCallsFromParts(parts, round);
-    const failureMessage = getFailureMessage(response, text, normalizedToolCalls.length);
-    if (failureMessage) throw new Error(failureMessage);
-
-    if (!normalizedToolCalls.length) {
-      if (danglingToolIntentRetries < MAX_DANGLING_TOOL_INTENT_RETRIES && looksLikeDanglingToolIntent(text)) {
-        danglingToolIntentRetries += 1;
-        appendCorrection(conversation, text);
-        continue;
-      }
-      return {
-        text,
-        usage: sawUsage ? usageAcc : undefined,
-        raw: { responses: rawResponses, toolCallsUsed: totalToolCalls, api: "gemini.generateContent" },
-        toolEvents,
-      };
-    }
-
-    totalToolCalls += normalizedToolCalls.length;
-    conversation.push({ role: "model", parts });
-
-    const toolResultParts: any[] = [];
-    for (const call of normalizedToolCalls) {
-      const { execution } = prepareToolCallExecution(call);
-      const { event, toolResult } = await executeToolCallAndBuildEvent(call, execution, params);
-      toolEvents.push(event);
-      toolResultParts.push(buildFunctionResponsePart(call, toolResult));
-    }
-
-    conversation.push({ role: "user", parts: toolResultParts });
-  }
-
-  return {
-    text: "I reached the tool-call limit while gathering information. Please narrow the request and try again.",
-    usage: sawUsage ? usageAcc : undefined,
-    raw: { responses: rawResponses, toolCallsUsed: totalToolCalls, toolCallLimitReached: true, api: "gemini.generateContent" },
-    toolEvents,
-  };
-}
-
-function findSseBoundary(buffer: string) {
-  const crlf = buffer.indexOf("\r\n\r\n");
-  const lf = buffer.indexOf("\n\n");
-  if (crlf === -1) return lf === -1 ? null : { index: lf, length: 2 };
-  if (lf === -1) return { index: crlf, length: 4 };
-  return crlf < lf ? { index: crlf, length: 4 } : { index: lf, length: 2 };
-}
-
-function parseSseEvent(rawEvent: string) {
-  const data = rawEvent
-    .split(/\r?\n/)
-    .filter((line) => line.startsWith("data:"))
-    .map((line) => line.slice("data:".length).trimStart())
-    .join("\n")
-    .trim();
-  if (!data || data === "[DONE]") return null;
-  return JSON.parse(data);
-}
-
-async function* streamGeminiResponses(params: ToolAwareCompletionParams, body: Record<string, unknown>) {
-  const response = await fetch(geminiUrl(params.client, params.model, "streamGenerateContent", { alt: "sse" }), {
-    method: "POST",
-    headers: { "Content-Type": "application/json" },
-    body: JSON.stringify(body),
-  });
-
-  if (!response.ok) {
-    await parseGeminiResponse(response);
-    return;
-  }
-
-  if (!response.body) {
-    throw new Error("Gemini stream response did not include a body.");
-  }
-
-  const reader = response.body.getReader();
-  const decoder = new TextDecoder();
-  let buffer = "";
-
-  while (true) {
-    const { value, done } = await reader.read();
-    if (done) break;
-    buffer += decoder.decode(value, { stream: true });
-    let boundary = findSseBoundary(buffer);
-    while (boundary) {
-      const rawEvent = buffer.slice(0, boundary.index);
-      buffer = buffer.slice(boundary.index + boundary.length);
-      const event = parseSseEvent(rawEvent);
-      if (event) yield event;
-      boundary = findSseBoundary(buffer);
-    }
-  }
-
-  buffer += decoder.decode();
-  const tail = buffer.trim();
-  if (tail) {
-    const event = parseSseEvent(tail);
-    if (event) yield event;
-  }
-}
-
-export async function* streamWithGeminiApi(params: ToolAwareCompletionParams): AsyncGenerator<ToolAwareStreamingEvent> {
-  const enabledTools = getEnabledChatTools(params);
-  const conversation = buildBaseContents(params.messages);
-  const rawResponses: unknown[] = [];
-  const toolEvents: ToolExecutionEvent[] = [];
-  const usageAcc: Required<ToolAwareUsage> = { inputTokens: 0, outputTokens: 0, totalTokens: 0 };
-  let sawUsage = false;
-  let totalToolCalls = 0;
-  let danglingToolIntentRetries = 0;
-
-  if (!enabledTools.length) {
-    let text = "";
-    let latestUsage: any = null;
-    for await (const response of streamGeminiResponses(params, buildRequest(params, conversation))) {
-      rawResponses.push(response);
-      if (response?.usageMetadata) latestUsage = response.usageMetadata;
-      const failureMessage = getFailureMessage(response, extractText(response), 0);
-      if (failureMessage) throw new Error(failureMessage);
-      const delta = extractText(response);
-      if (delta) {
-        text += delta;
-        yield { type: "delta", text: delta };
-      }
-    }
-
-    sawUsage = mergeUsage(usageAcc, latestUsage) || sawUsage;
-
-    yield {
-      type: "done",
-      result: {
-        text,
-        usage: sawUsage ? usageAcc : undefined,
-        raw: { streamed: true, responses: rawResponses, toolCallsUsed: 0, api: "gemini.streamGenerateContent" },
-        toolEvents: [],
-      },
-    };
-    return;
-  }
-
-  for (let round = 0; round < MAX_TOOL_ROUNDS; round += 1) {
-    const roundParts: any[] = [];
-    let roundText = "";
-    let latestRoundResponse: any = null;
-    let latestRoundUsage: any = null;
-
-    for await (const response of streamGeminiResponses(params, buildRequest(params, conversation, enabledTools))) {
-      rawResponses.push(response);
-      latestRoundResponse = response;
-      if (response?.usageMetadata) latestRoundUsage = response.usageMetadata;
-      roundParts.push(...getParts(response));
-      roundText += extractText(response);
-    }
-
-    sawUsage = mergeUsage(usageAcc, latestRoundUsage) || sawUsage;
-
-    const normalizedToolCalls = normalizeToolCallsFromParts(roundParts, round);
-    const failureMessage = getFailureMessage(latestRoundResponse ?? { candidates: [{ content: { parts: roundParts } }] }, roundText, normalizedToolCalls.length);
-    if (failureMessage) throw new Error(failureMessage);
-
-    if (!normalizedToolCalls.length) {
-      if (danglingToolIntentRetries < MAX_DANGLING_TOOL_INTENT_RETRIES && looksLikeDanglingToolIntent(roundText)) {
-        danglingToolIntentRetries += 1;
-        appendCorrection(conversation, roundText);
-        continue;
-      }
-      const unstreamedText = getUnstreamedText(roundText, "");
-      if (unstreamedText) {
-        yield { type: "delta", text: unstreamedText };
-      }
-      yield {
-        type: "done",
-        result: {
-          text: roundText,
-          usage: sawUsage ? usageAcc : undefined,
-          raw: { streamed: true, responses: rawResponses, toolCallsUsed: totalToolCalls, api: "gemini.streamGenerateContent" },
-          toolEvents,
-        },
-      };
-      return;
-    }
-
-    totalToolCalls += normalizedToolCalls.length;
-    conversation.push({ role: "model", parts: roundParts });
-
-    const toolResultParts: any[] = [];
-    for (const call of normalizedToolCalls) {
-      const { event: initiatedEvent, execution } = prepareToolCallExecution(call);
-      yield { type: "tool_call", event: initiatedEvent };
-      const { event, toolResult } = await executeToolCallAndBuildEvent(call, execution, params);
-      toolEvents.push(event);
-      yield { type: "tool_call", event };
-      toolResultParts.push(buildFunctionResponsePart(call, toolResult));
-    }
-
-    conversation.push({ role: "user", parts: toolResultParts });
-  }
-
-  yield {
-    type: "done",
-    result: {
-      text: "I reached the tool-call limit while gathering information. Please narrow the request and try again.",
-      usage: sawUsage ? usageAcc : undefined,
-      raw: {
-        streamed: true,
-        responses: rawResponses,
-        toolCallsUsed: totalToolCalls,
-        toolCallLimitReached: true,
-        api: "gemini.streamGenerateContent",
-      },
-      toolEvents,
-    },
-  };
-}
@@ -28,45 +28,6 @@ import type { ChatMessage } from "../types.js";
 const INTERNAL_CORRECTION =
  "Internal correction: the previous assistant message claimed it would run a tool, but no tool call was made. If the task needs an available tool, call it now. Otherwise provide the final answer directly without saying you will run a tool.";

-const DEFAULT_ANTHROPIC_MAX_TOKENS = 128_000;
-const MODEL_MAX_TOKENS_CACHE_MS = 24 * 60 * 60 * 1000;
-
-const modelMaxTokensCache = new Map<string, { maxTokens: number; expiresAt: number }>();
-
-function readMaxTokens(value: unknown) {
-  return Number.isSafeInteger(value) && (value as number) > 0 ? (value as number) : undefined;
-}
-
-function getModelInfoMaxTokens(modelInfo: any) {
-  return readMaxTokens(modelInfo?.max_tokens) ?? readMaxTokens(modelInfo?.maxTokens);
-}
-
-async function getMessagesMaxTokens(params: ToolAwareCompletionParams) {
-  if (params.maxTokens) return params.maxTokens;
-
-  const cached = modelMaxTokensCache.get(params.model);
-  if (cached && cached.expiresAt > Date.now()) return cached.maxTokens;
-
-  try {
-    const retrieve = params.client?.models?.retrieve;
-    if (typeof retrieve === "function") {
-      const modelInfo = await retrieve.call(params.client.models, params.model);
-      const maxTokens = getModelInfoMaxTokens(modelInfo);
-      if (maxTokens) {
-        modelMaxTokensCache.set(params.model, {
-          maxTokens,
-          expiresAt: Date.now() + MODEL_MAX_TOKENS_CACHE_MS,
-        });
-        return maxTokens;
-      }
-    }
-  } catch {
-    // Fall back to the documented max for Claude Opus 4.8 and related high-output models.
-  }
-
-  return DEFAULT_ANTHROPIC_MAX_TOKENS;
-}
-
 function toTools(tools: any[]) {
  return tools
    .map((tool) => {
@@ -199,12 +160,11 @@ function mergeUsage(acc: Required<ToolAwareUsage>, usage: any) {

 export async function completeWithMessagesApi(params: ToolAwareCompletionParams): Promise<ToolAwareCompletionResult> {
  const enabledTools = getEnabledChatTools(params);
-  const maxTokens = await getMessagesMaxTokens(params);
  if (!enabledTools.length) {
    const response = await params.client.messages.create({
      model: params.model,
      system: buildTopLevelSystemPrompt(params.messages, params.userLocation),
-      max_tokens: maxTokens,
+      max_tokens: params.maxTokens ?? 1024,
      temperature: params.temperature,
      messages: buildBaseMessages(params),
    } as any);
@@ -232,7 +192,7 @@ export async function completeWithMessagesApi(params: ToolAwareCompletionParams)
    const response = await params.client.messages.create({
      model: params.model,
      system: buildTopLevelSystemPrompt(params.messages, params.userLocation, buildChatToolSystemPrompt(params)),
-      max_tokens: maxTokens,
+      max_tokens: params.maxTokens ?? 1024,
      temperature: params.temperature,
      messages: conversation,
      tools: toTools(enabledTools),
@@ -288,7 +248,6 @@ export async function completeWithMessagesApi(params: ToolAwareCompletionParams)

 export async function* streamWithMessagesApi(params: ToolAwareCompletionParams): AsyncGenerator<ToolAwareStreamingEvent> {
  const enabledTools = getEnabledChatTools(params);
-  const maxTokens = await getMessagesMaxTokens(params);
  if (!enabledTools.length) {
    const rawResponses: unknown[] = [];
    const usageAcc: Required<ToolAwareUsage> = { inputTokens: 0, outputTokens: 0, totalTokens: 0 };
@@ -300,7 +259,7 @@ export async function* streamWithMessagesApi(params: ToolAwareCompletionParams):
    const stream = await params.client.messages.create({
      model: params.model,
      system: buildTopLevelSystemPrompt(params.messages, params.userLocation),
-      max_tokens: maxTokens,
+      max_tokens: params.maxTokens ?? 1024,
      temperature: params.temperature,
      messages: buildBaseMessages(params),
      stream: true,
@@ -356,7 +315,7 @@ export async function* streamWithMessagesApi(params: ToolAwareCompletionParams):
    const stream = await params.client.messages.create({
      model: params.model,
      system: buildTopLevelSystemPrompt(params.messages, params.userLocation, buildChatToolSystemPrompt(params)),
-      max_tokens: maxTokens,
+      max_tokens: params.maxTokens ?? 1024,
      temperature: params.temperature,
      messages: conversation,
      tools: toTools(enabledTools),
@@ -5,11 +5,10 @@ import {
  type ToolAwareStreamingEvent,
 } from "./chat-tools.js";
 import { completeWithChatCompletionsApi, streamWithChatCompletionsApi } from "./protocols/chat-completions-api.js";
-import { completeWithGeminiApi, streamWithGeminiApi } from "./protocols/gemini-api.js";
 import { completeWithMessagesApi, streamWithMessagesApi } from "./protocols/messages-api.js";
 import { completeWithResponsesApi, streamWithResponsesApi } from "./protocols/responses-api.js";
 import { env } from "../env.js";
-import { anthropicClient, geminiClient, hermesAgentClient, isHermesAgentConfigured, openaiClient, xaiClient } from "./providers.js";
+import { anthropicClient, hermesAgentClient, isHermesAgentConfigured, openaiClient, xaiClient } from "./providers.js";
 import type { ChatMessage, Provider } from "./types.js";

 type ProviderAdapterParams = {
@@ -28,7 +27,7 @@ export type ProviderChatAdapter = {
  stream(params: ProviderAdapterParams): AsyncGenerator<ToolAwareStreamingEvent>;
 };

-type ChatProtocolId = "chat-completions" | "gemini" | "messages" | "responses";
+type ChatProtocolId = "chat-completions" | "messages" | "responses";

 type ChatProtocol = {
  id: ChatProtocolId;
@@ -40,7 +39,6 @@ type ModelCatalogSpec = {
  enabled?: () => boolean;
  fetchModels(client: any): Promise<string[]>;
  fallbackModels?: () => string[];
-  sortModels?: (models: string[]) => string[];
 };

 type ProviderBackendSpec = {
@@ -63,12 +61,6 @@ const messagesProtocol: ChatProtocol = {
  stream: streamWithMessagesApi,
 };

-const geminiProtocol: ChatProtocol = {
-  id: "gemini",
-  complete: completeWithGeminiApi,
-  stream: streamWithGeminiApi,
-};
-
 const responsesProtocol: ChatProtocol = {
  id: "responses",
  complete: completeWithResponsesApi,
@@ -85,10 +77,6 @@ function modelIdsFromListResponse(page: any) {
    : [];
 }

-function stripModelResourcePrefix(model: string) {
-  return model.startsWith("models/") ? model.slice("models/".length) : model;
-}
-
 function isLikelyResponsesApiModel(model: string) {
  const id = model.toLowerCase();
  if (id.includes("embedding") || id.includes("moderation")) return false;
@@ -98,37 +86,6 @@ function isLikelyResponsesApiModel(model: string) {
  return /^(gpt-|o\d|chatgpt-)/.test(id);
 }

-function isLikelyGeminiChatModel(model: string) {
-  const id = model.toLowerCase();
-  if (!id.startsWith("gemini-")) return false;
-  if (id.includes("embedding") || id.includes("embed")) return false;
-  if (id.includes("image") || id.includes("imagen") || id.includes("veo")) return false;
-  if (id.includes("audio") || id.includes("tts") || id.includes("live")) return false;
-  if (id.includes("computer-use") || id.includes("robotics")) return false;
-  return true;
-}
-
-function preferGeminiModels(models: string[]) {
-  const preferred = [
-    "gemini-3.5-flash",
-    "gemini-flash-latest",
-    "gemini-3.1-flash-lite",
-    "gemini-3-flash-preview",
-    "gemini-pro-latest",
-  ];
-  const modelSet = new Set(models);
-  return [...preferred.filter((model) => modelSet.delete(model)), ...[...modelSet].sort((a, b) => a.localeCompare(b))];
-}
-
-async function fetchJson(url: URL): Promise<any> {
-  const response = await fetch(url);
-  const body: any = await response.json().catch(() => null);
-  if (!response.ok) {
-    throw new Error(body?.error?.message ?? `Gemini model fetch failed with status ${response.status}.`);
-  }
-  return body;
-}
-
 function withClient(params: ProviderAdapterParams, client: any, enabledTools?: string[]): ToolAwareCompletionParams {
  return {
    client,
@@ -203,29 +160,6 @@ const backendSpecs: Record<Provider, ProviderBackendSpec> = {
      },
    },
  },
-  gemini: {
-    createClient: geminiClient,
-    plainProtocol: geminiProtocol,
-    toolProtocol: geminiProtocol,
-    managedTools: true,
-    modelCatalog: {
-      async fetchModels(client) {
-        const url = new URL(`${client.baseURL.replace(/\/+$/, "")}/models`);
-        url.searchParams.set("key", client.apiKey);
-        url.searchParams.set("pageSize", "1000");
-        const page = await fetchJson(url);
-        return Array.isArray(page?.models)
-          ? page.models
-              .filter((model: any) => Array.isArray(model?.supportedGenerationMethods) && model.supportedGenerationMethods.includes("generateContent"))
-              .map((model: any) => model?.name)
-              .filter((id: unknown): id is string => typeof id === "string")
-              .map(stripModelResourcePrefix)
-              .filter(isLikelyGeminiChatModel)
-          : [];
-      },
-      sortModels: preferGeminiModels,
-    },
-  },
  "hermes-agent": {
    createClient: hermesAgentClient,
    plainProtocol: chatCompletionsProtocol,
@@ -275,8 +209,7 @@ export function listModelCatalogProviders(): Provider[] {
 export async function fetchProviderCatalogModels(provider: Provider) {
  const spec = backendSpecs[provider].modelCatalog;
  if (!spec) return [];
-  const models = uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient()));
-  return spec.sortModels ? spec.sortModels(models) : models;
+  return uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient()));
 }

 export function getProviderCatalogFallbackModels(provider: Provider) {
@@ -6,7 +6,6 @@ const apiToPrismaProvider = {
  openai: "openai",
  anthropic: "anthropic",
  xai: "xai",
-  gemini: "gemini",
  "hermes-agent": "hermes_agent",
 } as const satisfies Record<Provider, PrismaProvider>;

@@ -14,7 +13,6 @@ const prismaToApiProvider = {
  openai: "openai",
  anthropic: "anthropic",
  xai: "xai",
-  gemini: "gemini",
  hermes_agent: "hermes-agent",
  "hermes-agent": "hermes-agent",
 } as const satisfies Record<PrismaProvider | "hermes-agent", Provider>;
@@ -1,5 +1,5 @@
-import Anthropic from "@anthropic-ai/sdk";
 import OpenAI from "openai";
+import Anthropic from "@anthropic-ai/sdk";
 import { env } from "../env.js";

 export function openaiClient() {
@@ -13,14 +13,6 @@ export function xaiClient() {
  return new OpenAI({ apiKey: env.XAI_API_KEY, baseURL: "https://api.x.ai/v1" });
 }

-export function geminiClient() {
-  if (!env.GEMINI_API_KEY) throw new Error("GEMINI_API_KEY not set");
-  return {
-    apiKey: env.GEMINI_API_KEY,
-    baseURL: "https://generativelanguage.googleapis.com/v1beta",
-  };
-}
-
 export function isHermesAgentConfigured() {
  return Boolean(env.HERMES_AGENT_API_KEY);
 }
@@ -119,12 +119,7 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
    if (shouldPersist && chatId && call) {
      await prisma.$transaction(async (tx) => {
        await tx.message.create({
-          data: {
-            chatId,
-            role: "assistant" as any,
-            content: text,
-            metadata: req.clientRequestId ? ({ clientRequestId: req.clientRequestId } as any) : undefined,
-          },
+          data: { chatId, role: "assistant" as any, content: text },
        });
        await tx.llmCall.update({
          where: { id: call.id },
@@ -1,4 +1,4 @@
-export const PROVIDERS = ["openai", "anthropic", "xai", "gemini", "hermes-agent"] as const;
+export const PROVIDERS = ["openai", "anthropic", "xai", "hermes-agent"] as const;

 export type Provider = (typeof PROVIDERS)[number];

@@ -33,7 +33,6 @@ export type ChatMessage = {
 export type MultiplexRequest = {
  chatId?: string;
  persist?: boolean;
-  clientRequestId?: string;
  provider: Provider;
  model: string;
  messages: ChatMessage[];
@@ -16,7 +16,7 @@ import { exaClient } from "./search/exa.js";
 import { isFreshSearchCacheHit, normalizeSearchQuery } from "./search-cache.js";
 import type { ChatAttachment } from "./llm/types.js";

-const ProviderSchema = z.enum(["openai", "anthropic", "xai", "gemini", "hermes-agent"]);
+const ProviderSchema = z.enum(["openai", "anthropic", "xai", "hermes-agent"]);
 const MAX_ADDITIONAL_SYSTEM_PROMPT_CHARS = 12_000;
 const EnabledToolsSchema = z.array(z.string().trim().min(1).max(80)).max(20).transform((value) => normalizeEnabledChatTools(value));

@@ -88,7 +88,7 @@ function withRequestUserLocation<T extends { userLocation?: string }>(body: T, r
  return body.userLocation ? body : { ...body, userLocation: inferRequestUserLocation(req) };
 }

-async function storeNonAssistantMessages(chatId: string, messages: IncomingChatMessage[], clientRequestId?: string) {
+async function storeNonAssistantMessages(chatId: string, messages: IncomingChatMessage[]) {
  const incoming = messages.filter((m) => m.role !== "assistant");
  if (!incoming.length) return;

@@ -109,21 +109,14 @@ async function storeNonAssistantMessages(chatId: string, messages: IncomingChatM
  const toInsert = sharedPrefix === existingNonAssistant.length ? incoming.slice(existingNonAssistant.length) : incoming;
  if (!toInsert.length) return;

-  const finalUserMessageIndex = toInsert.map((message) => message.role).lastIndexOf("user");
  await prisma.message.createMany({
-    data: toInsert.map((m, index) => {
-      const metadata = {
-        ...(m.attachments?.length ? { attachments: m.attachments } : {}),
-        ...(clientRequestId && index === finalUserMessageIndex ? { clientRequestId } : {}),
-      };
-      return {
-        chatId,
-        role: m.role as any,
-        content: m.content,
-        name: m.name,
-        metadata: Object.keys(metadata).length ? (metadata as any) : undefined,
-      };
-    }),
+    data: toInsert.map((m) => ({
+      chatId,
+      role: m.role as any,
+      content: m.content,
+      name: m.name,
+      metadata: m.attachments?.length ? ({ attachments: m.attachments } as any) : undefined,
+    })),
  });
 }

@@ -176,7 +169,6 @@ const CompletionStreamBody = z
  .object({
    chatId: z.string().optional(),
    persist: z.boolean().optional(),
-    clientRequestId: z.string().trim().min(1).max(128).optional(),
    provider: ProviderSchema,
    model: z.string().min(1),
    messages: z.array(CompletionMessageSchema),
@@ -194,13 +186,6 @@ const CompletionStreamBody = z
        path: ["chatId"],
      });
    }
-    if (value.clientRequestId && (value.persist === false || !value.chatId)) {
-      ctx.addIssue({
-        code: z.ZodIssueCode.custom,
-        message: "clientRequestId requires a persisted stream with chatId",
-        path: ["clientRequestId"],
-      });
-    }
  });

 function mergeAttachmentsIntoMetadata(metadata: unknown, attachments?: ChatAttachment[]) {
@@ -414,7 +399,6 @@ function buildSseHeaders(originHeader: string | undefined) {
 type SearchRunRequest = z.infer<typeof SearchRunBody>;

 const activeChatStreams = new Map<string, ActiveSseStream>();
-const activeChatStreamRequestIds = new Map<string, string>();
 const activeSearchStreams = new Map<string, ActiveSseStream>();
 const STARRED_PROJECT_ID = "starred";

@@ -570,7 +554,6 @@ function writeSseEvent(reply: FastifyReply, event: SseStreamEvent) {
 }

 async function streamActiveRun(req: FastifyRequest, reply: FastifyReply, stream: ActiveSseStream) {
-  if (reply.raw.destroyed || reply.raw.writableEnded) return reply;
  reply.raw.writeHead(200, buildSseHeaders(typeof req.headers.origin === "string" ? req.headers.origin : undefined));
  reply.raw.flushHeaders?.();

@@ -605,24 +588,10 @@ function mapChatStreamEvent(ev: StreamEvent): SseStreamEvent {
  return { event: ev.type, data: ev };
 }

-function registerActiveChatStream(chatId: string, clientRequestId?: string) {
+function startActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>) {
  const stream = new ActiveSseStream();
  activeChatStreams.set(chatId, stream);
-  if (clientRequestId) {
-    activeChatStreamRequestIds.set(chatId, clientRequestId);
-  } else {
-    activeChatStreamRequestIds.delete(chatId);
-  }
-  return stream;
-}

-function clearActiveChatStream(chatId: string, stream: ActiveSseStream) {
-  if (activeChatStreams.get(chatId) !== stream) return;
-  activeChatStreams.delete(chatId);
-  activeChatStreamRequestIds.delete(chatId);
-}
-
-function executeActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>, stream: ActiveSseStream) {
  void (async () => {
    let sawTerminalEvent = false;
    try {
@@ -642,54 +611,13 @@ function executeActiveChatStream(chatId: string, body: z.infer<typeof Completion
    } catch (err) {
      stream.complete({ event: "error", data: { message: getErrorMessage(err) } });
    } finally {
-      clearActiveChatStream(chatId, stream);
+      activeChatStreams.delete(chatId);
    }
  })();
-}

-function startActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>) {
-  const stream = registerActiveChatStream(chatId, body.clientRequestId);
-  executeActiveChatStream(chatId, body, stream);
  return stream;
 }

-function getMetadataClientRequestId(metadata: unknown) {
-  if (!metadata || typeof metadata !== "object" || Array.isArray(metadata)) return null;
-  const clientRequestId = (metadata as Record<string, unknown>).clientRequestId;
-  return typeof clientRequestId === "string" ? clientRequestId : null;
-}
-
-async function findCompletedChatSubmission(chatId: string, clientRequestId: string) {
-  const assistantMessages = await prisma.message.findMany({
-    where: { chatId, role: "assistant" as any },
-    orderBy: { createdAt: "desc" },
-    select: { content: true, metadata: true },
-  });
-  return assistantMessages.find((message) => getMetadataClientRequestId(message.metadata) === clientRequestId) ?? null;
-}
-
-function completeChatSubmissionStream(
-  stream: ActiveSseStream,
-  chatId: string,
-  body: z.infer<typeof CompletionStreamBody>,
-  assistantText: string
-) {
-  stream.emit("meta", {
-    type: "meta",
-    chatId,
-    callId: null,
-    provider: body.provider,
-    model: body.model,
-  });
-  stream.complete({
-    event: "done",
-    data: {
-      type: "done",
-      text: assistantText,
-    },
-  });
-}
-
 async function executeSearchRunStream(searchId: string, body: SearchRunRequest, stream: ActiveSseStream) {
  const startedAt = performance.now();
  const query = body.query?.trim();
@@ -1007,18 +935,7 @@ export async function registerRoutes(app: FastifyInstance) {
    if (existing.title?.trim()) return { chat: serializeChatLike(existing) };

    const fallback = body.content.split(/\r?\n/)[0]?.trim().slice(0, 48) || "New chat";
-    let suggestedRaw = "";
-    try {
-      suggestedRaw = await generateChatTitle(body.content);
-    } catch (err) {
-      req.log.warn(
-        {
-          chatId: body.chatId,
-          err: getErrorMessage(err),
-        },
-        "chat title generation failed; using fallback"
-      );
-    }
+    const suggestedRaw = await generateChatTitle(body.content);
    const title = normalizeSuggestedTitle(suggestedRaw, fallback);

    await prisma.chat.updateMany({
@@ -1436,39 +1353,15 @@ export async function registerRoutes(app: FastifyInstance) {
      if (!exists) return app.httpErrors.notFound("chat not found");
    }

+    // Store only new non-assistant messages to avoid duplicate history entries.
    if (body.persist !== false && body.chatId) {
-      const activeStream = activeChatStreams.get(body.chatId);
-      if (activeStream) {
-        if (body.clientRequestId && activeChatStreamRequestIds.get(body.chatId) === body.clientRequestId) {
-          return streamActiveRun(req, reply, activeStream);
-        }
+      await storeNonAssistantMessages(body.chatId, body.messages);
+    }
+
+    if (body.persist !== false && body.chatId) {
+      if (activeChatStreams.has(body.chatId)) {
        return app.httpErrors.conflict("chat completion already running");
      }
-
-      if (body.clientRequestId) {
-        const reservedStream = registerActiveChatStream(body.chatId, body.clientRequestId);
-        try {
-          const completedSubmission = await findCompletedChatSubmission(body.chatId, body.clientRequestId);
-          if (completedSubmission) {
-            completeChatSubmissionStream(reservedStream, body.chatId, body, completedSubmission.content);
-            clearActiveChatStream(body.chatId, reservedStream);
-            return streamActiveRun(req, reply, reservedStream);
-          }
-
-          // Store only new non-assistant messages to avoid duplicate history entries.
-          await storeNonAssistantMessages(body.chatId, body.messages, body.clientRequestId);
-          const configuredBody = await applyStoredChatSettings(body);
-          executeActiveChatStream(body.chatId, configuredBody, reservedStream);
-          return streamActiveRun(req, reply, reservedStream);
-        } catch (err) {
-          reservedStream.complete({ event: "error", data: { message: getErrorMessage(err) } });
-          clearActiveChatStream(body.chatId, reservedStream);
-          throw err;
-        }
-      }
-
-      // Legacy requests without an idempotency key retain the original behavior.
-      await storeNonAssistantMessages(body.chatId, body.messages);
      const stream = startActiveChatStream(body.chatId, await applyStoredChatSettings(body));
      return streamActiveRun(req, reply, stream);
    }
@@ -1,305 +0,0 @@
-import { buildBrowserLikeRequestHeaders } from "../browser-fetch-headers.js";
-import { env } from "../env.js";
-
-const BRAVE_WEB_SEARCH_URL = "https://api.search.brave.com/res/v1/web/search";
-const BRAVE_SEARCH_TIMEOUT_MS = 12_000;
-const DEFAULT_BRAVE_REQUEST_INTERVAL_MS = 1_000;
-const RATE_LIMIT_INTERVAL_SAFETY_RATIO = 0.05;
-const MIN_RATE_LIMIT_INTERVAL_SAFETY_MS = 2;
-const RATE_LIMIT_RESET_SAFETY_MS = 50;
-const MAX_RATE_LIMIT_RETRIES = 3;
-const MAX_RATE_LIMIT_RETRY_DELAY_MS = 8_000;
-
-type RateLimitPolicy = {
-  limit: number;
-  windowSeconds: number;
-};
-
-let requestIntervalMs = addIntervalSafety(DEFAULT_BRAVE_REQUEST_INTERVAL_MS);
-let lastRequestAtMs = 0;
-let nextRequestAtMs = 0;
-let quotaUnavailableUntilMs = 0;
-let requestQueue = Promise.resolve();
-
-export type BraveSearchOptions = {
-  numResults: number;
-  includeDomains?: string[];
-  excludeDomains?: string[];
-};
-
-export type BraveSearchResult = {
-  title: string | null;
-  url: string | null;
-  publishedDate: string | null;
-  author: string | null;
-  summary: string | null;
-  text: string | null;
-  highlights: string[];
-};
-
-export type BraveSearchResponse = {
-  query: string;
-  requestId: string | null;
-  results: BraveSearchResult[];
-};
-
-function clipText(input: string, maxCharacters: number) {
-  return input.length <= maxCharacters ? input : `${input.slice(0, maxCharacters)}...`;
-}
-
-function compactWhitespace(input: string) {
-  return input.replace(/\r/g, "").replace(/[ \t]+\n/g, "\n").replace(/\n{3,}/g, "\n\n").replace(/\s+/g, " ").trim();
-}
-
-function requireBraveSearchApiKey() {
-  if (!env.BRAVE_SEARCH_API_KEY) {
-    throw new Error("BRAVE_SEARCH_API_KEY not set");
-  }
-  return env.BRAVE_SEARCH_API_KEY;
-}
-
-function sleep(milliseconds: number) {
-  return new Promise<void>((resolve) => setTimeout(resolve, milliseconds));
-}
-
-function addIntervalSafety(intervalMs: number) {
-  return intervalMs + Math.max(MIN_RATE_LIMIT_INTERVAL_SAFETY_MS, Math.ceil(intervalMs * RATE_LIMIT_INTERVAL_SAFETY_RATIO));
-}
-
-function parseCommaSeparatedNumbers(value: string | null) {
-  if (!value) return [];
-  return value.split(",").map((part) => Number(part.trim())).map((number) => (Number.isFinite(number) ? number : null));
-}
-
-function parseRateLimitPolicy(value: string | null): RateLimitPolicy[] {
-  if (!value) return [];
-  return value.split(",").flatMap((part) => {
-    const match = part.trim().match(/^(\d+)\s*;\s*w=(\d+)$/i);
-    if (!match) return [];
-    const limit = Number(match[1]);
-    const windowSeconds = Number(match[2]);
-    return limit > 0 && windowSeconds > 0 ? [{ limit, windowSeconds }] : [];
-  });
-}
-
-function getBurstPolicyIndex(policies: RateLimitPolicy[]) {
-  if (!policies.length) return null;
-  let burstIndex = 0;
-  for (let index = 1; index < policies.length; index += 1) {
-    if (policies[index]!.windowSeconds < policies[burstIndex]!.windowSeconds) burstIndex = index;
-  }
-  return burstIndex;
-}
-
-function updateRateLimitState(headers: Headers) {
-  const policies = parseRateLimitPolicy(headers.get("x-ratelimit-policy"));
-  const burstIndex = getBurstPolicyIndex(policies);
-  if (burstIndex === null) return;
-
-  const burstPolicy = policies[burstIndex]!;
-  const learnedIntervalMs = addIntervalSafety(Math.ceil((burstPolicy.windowSeconds * 1_000) / burstPolicy.limit));
-  if (learnedIntervalMs < requestIntervalMs && lastRequestAtMs > 0) {
-    nextRequestAtMs = Math.min(nextRequestAtMs, lastRequestAtMs + learnedIntervalMs);
-  }
-  requestIntervalMs = learnedIntervalMs;
-
-  const remaining = parseCommaSeparatedNumbers(headers.get("x-ratelimit-remaining"));
-  const resetSeconds = parseCommaSeparatedNumbers(headers.get("x-ratelimit-reset"));
-  for (let index = 0; index < policies.length; index += 1) {
-    if ((remaining[index] ?? null) === null || remaining[index]! >= 1 || (resetSeconds[index] ?? 0) <= 0) continue;
-    const unavailableUntilMs = Date.now() + resetSeconds[index]! * 1_000 + RATE_LIMIT_RESET_SAFETY_MS;
-    if (index === burstIndex) {
-      nextRequestAtMs = Math.max(nextRequestAtMs, unavailableUntilMs);
-    } else {
-      quotaUnavailableUntilMs = Math.max(quotaUnavailableUntilMs, unavailableUntilMs);
-    }
-  }
-}
-
-function assertLongTermQuotaAvailable() {
-  if (quotaUnavailableUntilMs <= Date.now()) {
-    quotaUnavailableUntilMs = 0;
-    return;
-  }
-  const resetSeconds = Math.ceil((quotaUnavailableUntilMs - Date.now()) / 1_000);
-  throw new Error(`Brave Search API long-term quota is exhausted; reset is expected in ${resetSeconds} seconds.`);
-}
-
-async function waitForRateLimitSlot() {
-  const reservation = requestQueue.then(async () => {
-    while (true) {
-      assertLongTermQuotaAvailable();
-      const waitMs = nextRequestAtMs - Date.now();
-      if (waitMs <= 0) break;
-      await sleep(waitMs);
-    }
-    lastRequestAtMs = Date.now();
-    nextRequestAtMs = lastRequestAtMs + requestIntervalMs;
-  });
-  requestQueue = reservation.catch(() => undefined);
-  await reservation;
-}
-
-function get429RetryDelayMs(headers: Headers, retryNumber: number) {
-  const remaining = parseCommaSeparatedNumbers(headers.get("x-ratelimit-remaining"));
-  const resetSeconds = parseCommaSeparatedNumbers(headers.get("x-ratelimit-reset"));
-  const exhaustedResetSeconds = resetSeconds.filter((reset, index): reset is number => reset !== null && (remaining[index] ?? 0) < 1);
-  const headerDelayMs = exhaustedResetSeconds.length ? Math.max(...exhaustedResetSeconds) * 1_000 : 0;
-  const exponentialDelayMs = 2 ** retryNumber * 1_000;
-  const delayMs = Math.max(headerDelayMs + RATE_LIMIT_RESET_SAFETY_MS, exponentialDelayMs);
-  return delayMs <= MAX_RATE_LIMIT_RETRY_DELAY_MS ? delayMs : null;
-}
-
-async function fetchBrave(url: URL) {
-  const apiKey = requireBraveSearchApiKey();
-  for (let attempt = 0; attempt <= MAX_RATE_LIMIT_RETRIES; attempt += 1) {
-    await waitForRateLimitSlot();
-
-    const controller = new AbortController();
-    const timeout = setTimeout(() => controller.abort(), BRAVE_SEARCH_TIMEOUT_MS);
-    let response: Response;
-    try {
-      response = await fetch(url, {
-        signal: controller.signal,
-        headers: {
-          ...buildBrowserLikeRequestHeaders("application/json"),
-          "X-Subscription-Token": apiKey,
-        },
-      });
-    } finally {
-      clearTimeout(timeout);
-    }
-
-    updateRateLimitState(response.headers);
-    if (response.status !== 429 || attempt === MAX_RATE_LIMIT_RETRIES) return response;
-
-    const retryDelayMs = get429RetryDelayMs(response.headers, attempt);
-    await response.arrayBuffer();
-    if (retryDelayMs === null) {
-      throw new Error("Brave Search API rate limit quota is exhausted beyond the retry window.");
-    }
-    await sleep(retryDelayMs);
-  }
-
-  throw new Error("Brave Search API request failed after rate-limit retries.");
-}
-
-function normalizeDomain(input: string) {
-  const trimmed = input.trim().toLowerCase();
-  if (!trimmed) return null;
-
-  try {
-    const parsed = new URL(trimmed.includes("://") ? trimmed : `https://${trimmed}`);
-    return parsed.hostname.replace(/^www\./, "");
-  } catch {
-    return trimmed.split(/[/?#]/, 1)[0]?.replace(/^www\./, "") || null;
-  }
-}
-
-function normalizeDomains(input: string[] | undefined) {
-  return Array.from(new Set((input ?? []).map(normalizeDomain).filter((domain): domain is string => Boolean(domain))));
-}
-
-function hostnameMatchesDomain(urlRaw: string | null, domain: string) {
-  if (!urlRaw) return false;
-  try {
-    const hostname = new URL(urlRaw).hostname.toLowerCase().replace(/^www\./, "");
-    return hostname === domain || hostname.endsWith(`.${domain}`);
-  } catch {
-    return false;
-  }
-}
-
-function filterResultsByDomains(results: BraveSearchResult[], options: BraveSearchOptions) {
-  const includeDomains = normalizeDomains(options.includeDomains);
-  const excludeDomains = normalizeDomains(options.excludeDomains);
-  return results.filter((result) => {
-    if (includeDomains.length && !includeDomains.some((domain) => hostnameMatchesDomain(result.url, domain))) return false;
-    if (excludeDomains.some((domain) => hostnameMatchesDomain(result.url, domain))) return false;
-    return true;
-  });
-}
-
-function buildBraveQuery(query: string, options: BraveSearchOptions) {
-  const includeDomains = normalizeDomains(options.includeDomains);
-  const excludeDomains = normalizeDomains(options.excludeDomains);
-  const includeClause =
-    includeDomains.length === 0
-      ? ""
-      : includeDomains.length === 1
-        ? `site:${includeDomains[0]}`
-        : `(${includeDomains.map((domain) => `site:${domain}`).join(" OR ")})`;
-  const excludeClause = excludeDomains.map((domain) => `-site:${domain}`).join(" ");
-  return [query, includeClause, excludeClause].filter(Boolean).join(" ");
-}
-
-function buildSearchUrl(query: string, options: BraveSearchOptions) {
-  const url = new URL(BRAVE_WEB_SEARCH_URL);
-  url.searchParams.set("q", buildBraveQuery(query, options));
-  url.searchParams.set("count", String(options.numResults));
-  url.searchParams.set("safesearch", "moderate");
-  url.searchParams.set("result_filter", "web");
-  url.searchParams.set("text_decorations", "false");
-  url.searchParams.set("extra_snippets", "true");
-  return url;
-}
-
-function stringOrNull(value: unknown) {
-  if (typeof value !== "string") return null;
-  const normalized = compactWhitespace(value);
-  return normalized || null;
-}
-
-function stringArray(value: unknown) {
-  if (!Array.isArray(value)) return [];
-  return value.filter((item): item is string => typeof item === "string").map(compactWhitespace).filter(Boolean);
-}
-
-function mapWebResult(result: any): BraveSearchResult {
-  const description = stringOrNull(result?.description);
-  const extraSnippets = stringArray(result?.extra_snippets);
-  const snippets = [description, ...extraSnippets].filter((snippet): snippet is string => Boolean(snippet));
-  const combinedText = snippets.join("\n\n");
-
-  return {
-    title: stringOrNull(result?.title),
-    url: stringOrNull(result?.url),
-    publishedDate: stringOrNull(result?.page_age),
-    author: stringOrNull(result?.profile?.name) ?? stringOrNull(result?.article?.author),
-    summary: description ? clipText(description, 1_400) : null,
-    text: combinedText ? clipText(combinedText, 700) : null,
-    highlights: snippets.slice(0, 3).map((snippet) => clipText(snippet, 280)),
-  };
-}
-
-export async function searchBrave(query: string, options: BraveSearchOptions): Promise<BraveSearchResponse> {
-  const url = buildSearchUrl(query, options);
-  const response = await fetchBrave(url);
-
-  if (!response.ok) {
-    await response.arrayBuffer();
-    throw new Error(`Brave Search API request failed with status ${response.status}.`);
-  }
-
-  const contentType = response.headers.get("content-type")?.toLowerCase() ?? "";
-  if (!contentType.includes("application/json")) {
-    await response.arrayBuffer();
-    throw new Error(`Brave Search API returned ${contentType || "unknown content type"}.`);
-  }
-
-  const data: any = await response.json();
-  const results = Array.isArray(data?.web?.results) ? data.web.results.map(mapWebResult) : [];
-  return {
-    query,
-    requestId: response.headers.get("x-request-id"),
-    results: filterResultsByDomains(results, options).slice(0, options.numResults),
-  };
-}
-
-export function resetBraveRateLimitStateForTests() {
-  requestIntervalMs = addIntervalSafety(DEFAULT_BRAVE_REQUEST_INTERVAL_MS);
-  lastRequestAtMs = 0;
-  nextRequestAtMs = 0;
-  quotaUnavailableUntilMs = 0;
-  requestQueue = Promise.resolve();
-}
@@ -1,284 +0,0 @@
-import assert from "node:assert/strict";
-import test from "node:test";
-import { env } from "../src/env.js";
-import { resetBraveRateLimitStateForTests, searchBrave } from "../src/search/brave.js";
-
-test("searchBrave authenticates, builds filters, and normalizes web results", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  const fetchCalls: Array<{ input: RequestInfo | URL; init?: RequestInit }> = [];
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
-    fetchCalls.push({ input, init });
-    return new Response(
-      JSON.stringify({
-        web: {
-          results: [
-            {
-              title: " Brave result ",
-              url: "https://docs.example.com/article",
-              description: "Main\n snippet",
-              extra_snippets: ["Extra snippet one", "Extra snippet two"],
-              page_age: "2026-07-18T12:00:00Z",
-              profile: { name: "Example Docs" },
-            },
-            {
-              title: "Excluded result",
-              url: "https://blocked.example.com/article",
-              description: "Should be filtered",
-            },
-          ],
-        },
-      }),
-      {
-        status: 200,
-        headers: {
-          "content-type": "application/json; charset=utf-8",
-          "x-request-id": "brave-request-1",
-        },
-      }
-    );
-  }) as typeof fetch;
-
-  try {
-    const response = await searchBrave("latest docs", {
-      numResults: 5,
-      includeDomains: ["https://example.com/path"],
-      excludeDomains: ["blocked.example.com"],
-    });
-
-    assert.equal(fetchCalls.length, 1);
-    const requestUrl = new URL(String(fetchCalls[0]?.input));
-    assert.equal(requestUrl.origin + requestUrl.pathname, "https://api.search.brave.com/res/v1/web/search");
-    assert.equal(requestUrl.searchParams.get("q"), "latest docs site:example.com -site:blocked.example.com");
-    assert.equal(requestUrl.searchParams.get("count"), "5");
-    assert.equal(requestUrl.searchParams.get("safesearch"), "moderate");
-    assert.equal(requestUrl.searchParams.get("result_filter"), "web");
-    assert.equal(requestUrl.searchParams.get("text_decorations"), "false");
-    assert.equal(requestUrl.searchParams.get("extra_snippets"), "true");
-    assert.equal((fetchCalls[0]?.init?.headers as Record<string, string>)["X-Subscription-Token"], "test-brave-key");
-
-    assert.deepEqual(response, {
-      query: "latest docs",
-      requestId: "brave-request-1",
-      results: [
-        {
-          title: "Brave result",
-          url: "https://docs.example.com/article",
-          publishedDate: "2026-07-18T12:00:00Z",
-          author: "Example Docs",
-          summary: "Main snippet",
-          text: "Main snippet\n\nExtra snippet one\n\nExtra snippet two",
-          highlights: ["Main snippet", "Extra snippet one", "Extra snippet two"],
-        },
-      ],
-    });
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-  }
-});
-
-test("searchBrave rejects requests without an API key", async () => {
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = undefined;
-  try {
-    await assert.rejects(() => searchBrave("test", { numResults: 1 }), /BRAVE_SEARCH_API_KEY not set/);
-  } finally {
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-  }
-});
-
-test("searchBrave reports non-JSON responses", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () =>
-    new Response("upstream error", {
-      status: 200,
-      headers: { "content-type": "text/plain" },
-    })) as typeof fetch;
-
-  try {
-    await assert.rejects(
-      () => searchBrave("test", { numResults: 1 }),
-      /Brave Search API returned text\/plain/
-    );
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-  }
-});
-
-test("searchBrave evenly paces concurrent bursts using Brave's shortest policy window", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  const requestStartedAt: number[] = [];
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () => {
-    requestStartedAt.push(Date.now());
-    return new Response(JSON.stringify({ web: { results: [] } }), {
-      status: 200,
-      headers: {
-        "content-type": "application/json",
-        "x-ratelimit-policy": "1;w=1, 2000;w=2678400",
-        "x-ratelimit-remaining": "1, 1999",
-        "x-ratelimit-reset": "1, 2678400",
-      },
-    });
-  }) as typeof fetch;
-
-  try {
-    await Promise.all([
-      searchBrave("burst one", { numResults: 1 }),
-      searchBrave("burst two", { numResults: 1 }),
-      searchBrave("burst three", { numResults: 1 }),
-    ]);
-
-    assert.equal(requestStartedAt.length, 3);
-    assert.ok(requestStartedAt[1]! - requestStartedAt[0]! >= 1_000);
-    assert.ok(requestStartedAt[2]! - requestStartedAt[1]! >= 1_000);
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-    resetBraveRateLimitStateForTests();
-  }
-});
-
-test("searchBrave adapts its pacing to a 50 request-per-second Search plan", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  const requestStartedAt: number[] = [];
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () => {
-    requestStartedAt.push(Date.now());
-    return new Response(JSON.stringify({ web: { results: [] } }), {
-      status: 200,
-      headers: {
-        "content-type": "application/json",
-        "x-ratelimit-policy": "50;w=1, 0;w=2678400",
-        "x-ratelimit-remaining": "49, 0",
-        "x-ratelimit-reset": "1, 2678400",
-      },
-    });
-  }) as typeof fetch;
-
-  try {
-    await searchBrave("learn upgraded policy", { numResults: 1 });
-    await Promise.all(Array.from({ length: 8 }, (_, index) => searchBrave(`fast burst ${index}`, { numResults: 1 })));
-
-    assert.equal(requestStartedAt.length, 9);
-    const burstStartedAt = requestStartedAt.slice(1);
-    for (let index = 1; index < burstStartedAt.length; index += 1) {
-      assert.ok(burstStartedAt[index]! - burstStartedAt[index - 1]! >= 18);
-    }
-    assert.ok(burstStartedAt.at(-1)! - burstStartedAt[0]! < 500);
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-    resetBraveRateLimitStateForTests();
-  }
-});
-
-test("searchBrave retries 429 responses after the burst window resets", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  let fetchCount = 0;
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () => {
-    fetchCount += 1;
-    const rateLimitHeaders = {
-      "content-type": "application/json",
-      "x-ratelimit-policy": "1;w=1, 2000;w=2678400",
-      "x-ratelimit-remaining": fetchCount === 1 ? "0, 1999" : "1, 1998",
-      "x-ratelimit-reset": "1, 2678400",
-    };
-    if (fetchCount === 1) {
-      return new Response(JSON.stringify({ error: { detail: "Rate limit exceeded" } }), {
-        status: 429,
-        headers: rateLimitHeaders,
-      });
-    }
-    return new Response(JSON.stringify({ web: { results: [] } }), { status: 200, headers: rateLimitHeaders });
-  }) as typeof fetch;
-
-  try {
-    const startedAt = Date.now();
-    await searchBrave("retry burst", { numResults: 1 });
-    assert.equal(fetchCount, 2);
-    assert.ok(Date.now() - startedAt >= 1_000);
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-    resetBraveRateLimitStateForTests();
-  }
-});
-
-test("searchBrave does not wait for exhausted long-term quotas", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () =>
-    new Response(JSON.stringify({ error: { detail: "Quota exceeded" } }), {
-      status: 429,
-      headers: {
-        "content-type": "application/json",
-        "x-ratelimit-policy": "1;w=1, 2000;w=2678400",
-        "x-ratelimit-remaining": "0, 0",
-        "x-ratelimit-reset": "1, 100000",
-      },
-    })) as typeof fetch;
-
-  try {
-    const startedAt = Date.now();
-    await assert.rejects(
-      () => searchBrave("quota exhausted", { numResults: 1 }),
-      /rate limit quota is exhausted beyond the retry window/
-    );
-    assert.ok(Date.now() - startedAt < 1_000);
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-    resetBraveRateLimitStateForTests();
-  }
-});
-
-test("searchBrave blocks locally after a successful request exhausts the long-term quota", async () => {
-  const originalFetch = globalThis.fetch;
-  const originalApiKey = env.BRAVE_SEARCH_API_KEY;
-  let fetchCount = 0;
-  resetBraveRateLimitStateForTests();
-  env.BRAVE_SEARCH_API_KEY = "test-brave-key";
-  globalThis.fetch = (async () => {
-    fetchCount += 1;
-    return new Response(JSON.stringify({ web: { results: [] } }), {
-      status: 200,
-      headers: {
-        "content-type": "application/json",
-        "x-ratelimit-policy": "1;w=1, 2000;w=2678400",
-        "x-ratelimit-remaining": "0, 0",
-        "x-ratelimit-reset": "1, 100000",
-      },
-    });
-  }) as typeof fetch;
-
-  try {
-    await searchBrave("last allowed query", { numResults: 1 });
-    await assert.rejects(
-      () => searchBrave("over quota query", { numResults: 1 }),
-      /long-term quota is exhausted/
-    );
-    assert.equal(fetchCount, 1);
-  } finally {
-    globalThis.fetch = originalFetch;
-    env.BRAVE_SEARCH_API_KEY = originalApiKey;
-    resetBraveRateLimitStateForTests();
-  }
-});
@@ -140,94 +140,6 @@ test("plain Chat Completions stream does not send Sybil-managed tools", async ()
  assert.equal(events.at(-1)?.type === "done" ? events.at(-1)?.result.text : null, "Hi");
 });

-test("Messages API defaults max_tokens to the Anthropic model maximum", async () => {
-  let requestBody: any = null;
-  let retrievedModel: string | null = null;
-  const client = {
-    models: {
-      retrieve: async (model: string) => {
-        retrievedModel = model;
-        return { id: model, max_tokens: 128000 };
-      },
-    },
-    messages: {
-      create: async (body: any) => {
-        requestBody = body;
-        return {
-          content: [{ type: "text", text: "Done" }],
-          usage: { input_tokens: 1, output_tokens: 1 },
-        };
-      },
-    },
-  };
-
-  const result = await completeWithMessagesApi({
-    client: client as any,
-    model: "claude-max-default-test",
-    messages: [{ role: "user", content: "Say done" }],
-  });
-
-  assert.equal(retrievedModel, "claude-max-default-test");
-  assert.equal(requestBody?.max_tokens, 128000);
-  assert.equal(result.text, "Done");
-});
-
-test("Messages API preserves explicit maxTokens", async () => {
-  let requestBody: any = null;
-  let didRetrieveModel = false;
-  const client = {
-    models: {
-      retrieve: async () => {
-        didRetrieveModel = true;
-        return { max_tokens: 128000 };
-      },
-    },
-    messages: {
-      create: async (body: any) => {
-        requestBody = body;
-        return streamFrom([
-          {
-            type: "message_start",
-            message: {
-              usage: { input_tokens: 1, output_tokens: 0 },
-            },
-          },
-          {
-            type: "content_block_start",
-            index: 0,
-            content_block: { type: "text", text: "" },
-          },
-          {
-            type: "content_block_delta",
-            index: 0,
-            delta: { type: "text_delta", text: "Done" },
-          },
-          { type: "content_block_stop", index: 0 },
-          {
-            type: "message_delta",
-            delta: { stop_reason: "end_turn", stop_sequence: null },
-            usage: { output_tokens: 1 },
-          },
-          { type: "message_stop" },
-        ]);
-      },
-    },
-  };
-
-  const events = await collectEvents(
-    streamWithMessagesApi({
-      client: client as any,
-      model: "claude-explicit-max-test",
-      messages: [{ role: "user", content: "Say done" }],
-      maxTokens: 4096,
-    })
-  );
-
-  assert.equal(didRetrieveModel, false);
-  assert.equal(requestBody?.max_tokens, 4096);
-  assert.equal(events.at(-1)?.type === "done" ? events.at(-1)?.result.text : null, "Done");
-});
-
 test("fetch_url sends browser-like navigation headers", async () => {
  const originalFetch = globalThis.fetch;
  const fetchCalls: Array<{ input: RequestInfo | URL; init?: RequestInit }> = [];
@@ -27,12 +27,6 @@ test("provider backend registry selects chat protocol and managed-tool mode", ()
    managedTools: true,
    enabledTools: ["web_search"],
  });
-  assert.deepEqual(describeProviderChatBackend("gemini", ["web_search"]), {
-    provider: "gemini",
-    protocol: "gemini",
-    managedTools: true,
-    enabledTools: ["web_search"],
-  });
  assert.deepEqual(describeProviderChatBackend("hermes-agent", ["web_search"]), {
    provider: "hermes-agent",
    protocol: "chat-completions",
@@ -5,10 +5,8 @@ import { fromPrismaProvider, serializeProviderFields, toPrismaProvider } from ".
 test("Hermes Agent provider id maps between API and Prisma enum forms", () => {
  assert.equal(toPrismaProvider("hermes-agent"), "hermes_agent");
  assert.equal(fromPrismaProvider("hermes_agent"), "hermes-agent");
-  assert.equal(toPrismaProvider("gemini"), "gemini");
-  assert.equal(fromPrismaProvider("gemini"), "gemini");
-  assert.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "gemini" }), {
+  assert.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "xai" }), {
    initiatedProvider: "hermes-agent",
-    lastUsedProvider: "gemini",
+    lastUsedProvider: "xai",
  });
 });
@@ -1,6 +1,6 @@
 import type { Provider } from "./types.js";

-const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini", "hermes-agent"];
+const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "hermes-agent"];

 function normalizeBaseUrl(value: string) {
  const trimmed = value.trim();
@@ -42,13 +42,12 @@ type ToolLogMetadata = {
  resultPreview?: string | null;
 };

-const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"];
+const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai"];
 const PROVIDERS: Provider[] = [...BASE_PROVIDERS, "hermes-agent"];
 const PROVIDER_FALLBACK_MODELS: Record<Provider, string[]> = {
  openai: ["gpt-4.1-mini"],
  anthropic: ["claude-3-5-sonnet-latest"],
  xai: ["grok-3-mini"],
-  gemini: ["gemini-3.5-flash", "gemini-flash-latest"],
  "hermes-agent": ["hermes-agent"],
 };

@@ -56,7 +55,6 @@ const EMPTY_MODEL_CATALOG: ModelCatalogResponse["providers"] = {
  openai: { models: [], loadedAt: null, error: null },
  anthropic: { models: [], loadedAt: null, error: null },
  xai: { models: [], loadedAt: null, error: null },
-  gemini: { models: [], loadedAt: null, error: null },
 };

 function escapeTags(value: string) {
@@ -81,7 +79,6 @@ function getProviderLabel(provider: Provider | null | undefined) {
  if (provider === "openai") return "OpenAI";
  if (provider === "anthropic") return "Anthropic";
  if (provider === "xai") return "xAI";
-  if (provider === "gemini") return "Gemini";
  if (provider === "hermes-agent") return "Hermes Agent";
  return "";
 }
@@ -269,7 +266,6 @@ async function main() {
    openai: null,
    anthropic: null,
    xai: null,
-    gemini: null,
    "hermes-agent": null,
  };
  let model: string = config.defaultModel ?? pickProviderModel(getModelOptions(modelCatalog, provider), null);
@@ -1,4 +1,4 @@
-export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent";
+export type Provider = "openai" | "anthropic" | "xai" | "hermes-agent";

 export type ProviderModelInfo = {
  models: string[];
@@ -3,24 +3,10 @@ self.addEventListener("install", () => {
 });

 self.addEventListener("activate", (event) => {
-  event.waitUntil(
-    (async () => {
-      await self.clients.claim();
-      const windows = await self.clients.matchAll({ type: "window", includeUncontrolled: true });
-      await Promise.all(
-        windows.map(async (client) => {
-          try {
-            await client.navigate(client.url);
-          } catch {
-            // The client may have closed while the new worker was activating.
-          }
-        })
-      );
-    })()
-  );
+  event.waitUntil(self.clients.claim());
 });

 self.addEventListener("fetch", (event) => {
  if (event.request.mode !== "navigate") return;
-  event.respondWith(fetch(new Request(event.request, { cache: "no-store" })));
+  event.respondWith(fetch(event.request));
 });
@@ -478,7 +478,6 @@ export function ChatMessagesPanel({ messages, isLoading, isSending }: Props) {
                ) : message.content.trim() ? (
                  <MarkdownContent
                    markdown={message.content}
-                    openLinksInNewTab
                    className={cn("[&_a]:text-inherit [&_a]:underline", isUser ? "leading-[1.78] text-fuchsia-50" : "leading-[1.82] text-violet-50")}
                  />
                ) : null}
@@ -10,7 +10,6 @@ type Props = {
  className?: string;
  mode?: MarkdownMode;
  resolveCitationIndex?: (href: string) => number | undefined;
-  openLinksInNewTab?: boolean;
 };

 function replaceMarkdownLinksWithCitationTokens(markdown: string, resolveCitationIndex?: (href: string) => number | undefined) {
@@ -29,30 +28,17 @@ markdownRenderer.table = (token) => {
  return `<div class="md-table-scroll">${renderTable(token)}</div>`;
 };

-function setNewTabLinkAttributes(currentNode: Element) {
-  if (currentNode.tagName !== "A") return;
-  currentNode.setAttribute("target", "_blank");
-  currentNode.setAttribute("rel", "noopener noreferrer");
-}
-
-function renderMarkdown(markdown: string, openLinksInNewTab: boolean) {
+function renderMarkdown(markdown: string) {
  const rawHtml = marked.parse(markdown, { gfm: true, breaks: true, renderer: markdownRenderer }) as string;
-  if (!openLinksInNewTab) return DOMPurify.sanitize(rawHtml, { ADD_ATTR: ["class", "target", "rel"] });
-
-  DOMPurify.addHook("afterSanitizeAttributes", setNewTabLinkAttributes);
-  try {
-    return DOMPurify.sanitize(rawHtml, { ADD_ATTR: ["class", "target", "rel"] });
-  } finally {
-    DOMPurify.removeHook("afterSanitizeAttributes", setNewTabLinkAttributes);
-  }
+  return DOMPurify.sanitize(rawHtml, { ADD_ATTR: ["class", "target", "rel"] });
 }

-export function MarkdownContent({ markdown, className, mode = "default", resolveCitationIndex, openLinksInNewTab = false }: Props) {
+export function MarkdownContent({ markdown, className, mode = "default", resolveCitationIndex }: Props) {
  const html = useMemo(() => {
    const prepared =
      mode === "citationTokens" ? replaceMarkdownLinksWithCitationTokens(markdown, resolveCitationIndex) : markdown;
-    return renderMarkdown(prepared, openLinksInNewTab);
-  }, [markdown, mode, openLinksInNewTab, resolveCitationIndex]);
+    return renderMarkdown(prepared);
+  }, [markdown, mode, resolveCitationIndex]);

  return <div className={cn("md-content", className)} dangerouslySetInnerHTML={{ __html: html }} />;
 }
@@ -286,14 +286,6 @@ textarea {
  word-break: break-word;
 }

-.md-content > :first-child {
-  margin-top: 0;
-}
-
-.md-content > :last-child {
-  margin-bottom: 0;
-}
-
 .md-table-scroll {
  max-width: 100%;
  margin: 0.35rem 0 1rem;
@@ -392,8 +384,7 @@ textarea {

 .md-content ul,
 .md-content ol {
-  margin-top: 0.85rem;
-  margin-bottom: 0.85rem;
+  margin-top: 0.65rem;
  margin-left: 0;
  padding-left: 0;
  list-style: none;
@@ -405,26 +396,6 @@ textarea {
  padding-left: 1.35rem;
 }

-.md-content ul > li {
-  position: relative;
-  padding-left: 1.1rem;
-}
-
-.md-content ul > li::before {
-  content: "";
-  position: absolute;
-  left: 0;
-  top: 0.76em;
-  width: 0.36rem;
-  height: 0.36rem;
-  border-radius: 9999px;
-  background: hsl(188 86% 62%);
-  box-shadow:
-    0 0 0 2px hsl(188 86% 62% / 0.12),
-    0 0 10px hsl(188 86% 62% / 0.42);
-  transform: translateY(-50%);
-}
-
 .md-content li + li {
  margin-top: 0.3rem;
 }
@@ -149,7 +149,7 @@ export type CompletionRequestMessage = {
  attachments?: ChatAttachment[];
 };

-export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent";
+export type Provider = "openai" | "anthropic" | "xai" | "hermes-agent";

 export type ProviderModelInfo = {
  models: string[];
@@ -450,7 +450,6 @@ async function readSseStream(response: Response, dispatch: (eventName: string, p
  let buffer = "";
  let eventName = "message";
  let dataLines: string[] = [];
-  let sawTerminalEvent = false;

  const flushEvent = () => {
    if (!dataLines.length) {
@@ -467,9 +466,6 @@ async function readSseStream(response: Response, dispatch: (eventName: string, p
    }

    dispatch(eventName, payload);
-    if (eventName === "done" || eventName === "error") {
-      sawTerminalEvent = true;
-    }

    dataLines = [];
    eventName = "message";
@@ -509,10 +505,6 @@ async function readSseStream(response: Response, dispatch: (eventName: string, p
    }
  }
  flushEvent();
-
-  if (!sawTerminalEvent) {
-    throw new Error("Stream disconnected before completion");
-  }
 }

 export async function runSearchStream(
@@ -536,14 +528,87 @@ export async function runSearchStream(
    signal: options?.signal,
  });

-  await readSseStream(response, (eventName, payload) => {
+  if (!response.ok) {
+    const fallback = `${response.status} ${response.statusText}`;
+    let message = fallback;
+    try {
+      const body = (await response.json()) as { message?: string };
+      if (body.message) message = body.message;
+    } catch {
+      // keep fallback message
+    }
+    throw new Error(message);
+  }
+
+  if (!response.body) {
+    throw new Error("No response stream");
+  }
+
+  const reader = response.body.getReader();
+  const decoder = new TextDecoder();
+  let buffer = "";
+  let eventName = "message";
+  let dataLines: string[] = [];
+
+  const flushEvent = () => {
+    if (!dataLines.length) {
+      eventName = "message";
+      return;
+    }
+
+    const dataText = dataLines.join("\n");
+    let payload: any = null;
+    try {
+      payload = JSON.parse(dataText);
+    } catch {
+      payload = { message: dataText };
+    }
+
    if (eventName === "search_results") handlers.onSearchResults?.(payload);
    else if (eventName === "search_error") handlers.onSearchError?.(payload);
    else if (eventName === "answer") handlers.onAnswer?.(payload);
    else if (eventName === "answer_error") handlers.onAnswerError?.(payload);
    else if (eventName === "done") handlers.onDone?.(payload);
    else if (eventName === "error") handlers.onError?.(payload);
-  });
+
+    dataLines = [];
+    eventName = "message";
+  };
+
+  while (true) {
+    const { value, done } = await reader.read();
+    if (done) break;
+
+    buffer += decoder.decode(value, { stream: true });
+    let newlineIndex = buffer.indexOf("\n");
+
+    while (newlineIndex >= 0) {
+      const rawLine = buffer.slice(0, newlineIndex);
+      buffer = buffer.slice(newlineIndex + 1);
+      const line = rawLine.endsWith("\r") ? rawLine.slice(0, -1) : rawLine;
+
+      if (!line) {
+        flushEvent();
+      } else if (line.startsWith("event:")) {
+        eventName = line.slice("event:".length).trim();
+      } else if (line.startsWith("data:")) {
+        dataLines.push(line.slice("data:".length).trimStart());
+      }
+
+      newlineIndex = buffer.indexOf("\n");
+    }
+  }
+
+  buffer += decoder.decode();
+  if (buffer.length) {
+    const line = buffer.endsWith("\r") ? buffer.slice(0, -1) : buffer;
+    if (line.startsWith("event:")) {
+      eventName = line.slice("event:".length).trim();
+    } else if (line.startsWith("data:")) {
+      dataLines.push(line.slice("data:".length).trimStart());
+    }
+  }
+  flushEvent();
 }

 export async function attachSearchStream(searchId: string, handlers: RunSearchStreamHandlers, options?: { signal?: AbortSignal }) {
@@ -589,7 +654,6 @@ export async function runCompletionStream(
  body: {
    chatId?: string | null;
    persist?: boolean;
-    clientRequestId?: string;
    provider: Provider;
    model: string;
    messages: CompletionRequestMessage[];
@@ -615,13 +679,86 @@ export async function runCompletionStream(
    signal: options?.signal,
  });

-  await readSseStream(response, (eventName, payload) => {
+  if (!response.ok) {
+    const fallback = `${response.status} ${response.statusText}`;
+    let message = fallback;
+    try {
+      const body = (await response.json()) as { message?: string };
+      if (body.message) message = body.message;
+    } catch {
+      // keep fallback message
+    }
+    throw new Error(message);
+  }
+
+  if (!response.body) {
+    throw new Error("No response stream");
+  }
+
+  const reader = response.body.getReader();
+  const decoder = new TextDecoder();
+  let buffer = "";
+  let eventName = "message";
+  let dataLines: string[] = [];
+
+  const flushEvent = () => {
+    if (!dataLines.length) {
+      eventName = "message";
+      return;
+    }
+
+    const dataText = dataLines.join("\n");
+    let payload: any = null;
+    try {
+      payload = JSON.parse(dataText);
+    } catch {
+      payload = { message: dataText };
+    }
+
    if (eventName === "meta") handlers.onMeta?.(payload);
    else if (eventName === "tool_call") handlers.onToolCall?.(payload);
    else if (eventName === "delta") handlers.onDelta?.(payload);
    else if (eventName === "done") handlers.onDone?.(payload);
    else if (eventName === "error") handlers.onError?.(payload);
-  });
+
+    dataLines = [];
+    eventName = "message";
+  };
+
+  while (true) {
+    const { value, done } = await reader.read();
+    if (done) break;
+
+    buffer += decoder.decode(value, { stream: true });
+    let newlineIndex = buffer.indexOf("\n");
+
+    while (newlineIndex >= 0) {
+      const rawLine = buffer.slice(0, newlineIndex);
+      buffer = buffer.slice(newlineIndex + 1);
+      const line = rawLine.endsWith("\r") ? rawLine.slice(0, -1) : rawLine;
+
+      if (!line) {
+        flushEvent();
+      } else if (line.startsWith("event:")) {
+        eventName = line.slice("event:".length).trim();
+      } else if (line.startsWith("data:")) {
+        dataLines.push(line.slice("data:".length).trimStart());
+      }
+
+      newlineIndex = buffer.indexOf("\n");
+    }
+  }
+
+  buffer += decoder.decode();
+  if (buffer.length) {
+    const line = buffer.endsWith("\r") ? buffer.slice(0, -1) : buffer;
+    if (line.startsWith("event:")) {
+      eventName = line.slice("event:".length).trim();
+    } else if (line.startsWith("data:")) {
+      dataLines.push(line.slice("data:".length).trimStart());
+    }
+  }
+  flushEvent();
 }

 export async function attachCompletionStream(chatId: string, handlers: CompletionStreamHandlers, options?: { signal?: AbortSignal }) {
@@ -2,11 +2,8 @@ export function registerServiceWorker() {
  if (!import.meta.env.PROD || !("serviceWorker" in navigator)) return;

  window.addEventListener("load", () => {
-    void navigator.serviceWorker
-      .register("/sw.js", { updateViaCache: "none" })
-      .then((registration) => registration.update())
-      .catch((error: unknown) => {
-        console.warn("Sybil service worker registration failed", error);
-      });
+    void navigator.serviceWorker.register("/sw.js").catch((error: unknown) => {
+      console.warn("Sybil service worker registration failed", error);
+    });
  });
 }
Author	SHA1	Message	Date
buzzert	730d609f81	Relax Xcode signing identity matching TestFlight / testflight (push) Failing after 26s Details	2026-06-25 23:57:17 -07:00
buzzert	137fce8558	Use passworded CI keychain TestFlight / testflight (push) Failing after 25s Details	2026-06-25 23:53:24 -07:00
buzzert	3e6d3c6817	Use user keychain domain in CI TestFlight / testflight (push) Failing after 23s Details	2026-06-25 23:51:33 -07:00
buzzert	100b51de12	Use explicit CI signing keychain TestFlight / testflight (push) Failing after 18s Details	2026-06-25 23:48:26 -07:00
buzzert	23ee30a53a	Simplify TestFlight CI signing TestFlight / testflight (push) Failing after 22s Details	2026-06-25 23:44:13 -07:00
buzzert	0be2442ad0	Pass signing keychain to Xcode resolver TestFlight / testflight (push) Failing after 28s Details	2026-06-25 23:37:24 -07:00
buzzert	c84ef8c242	Refresh CI key partition access before build TestFlight / testflight (push) Failing after 27s Details	2026-06-25 23:35:00 -07:00
buzzert	98f96eda45	Let Xcode select Apple Distribution identity TestFlight / testflight (push) Failing after 25s Details	2026-06-25 23:32:38 -07:00
buzzert	3904457c21	Use runner home for CI keychain preferences TestFlight / testflight (push) Failing after 24s Details	2026-06-25 23:30:46 -07:00
buzzert	0fc2117a11	Set CI keychain as default for Xcode TestFlight / testflight (push) Failing after 18s Details	2026-06-25 23:28:58 -07:00
buzzert	60469f05b5	Tolerate login keychain preference failure TestFlight / testflight (push) Failing after 23s Details	2026-06-25 23:27:13 -07:00
buzzert	d834ed7931	Create CI login keychain when missing TestFlight / testflight (push) Failing after 19s Details	2026-06-25 23:25:42 -07:00
buzzert	f98a002f52	Use explicit runner login keychain TestFlight / testflight (push) Failing after 17s Details	2026-06-25 23:23:13 -07:00
buzzert	b0c0a2d55e	Reset CI keychain search list TestFlight / testflight (push) Failing after 19s Details	2026-06-25 23:21:42 -07:00
buzzert	3262f4ff80	Detect runner login keychain path TestFlight / testflight (push) Failing after 19s Details	2026-06-25 23:20:06 -07:00
buzzert	585be09eb7	Target login keychain path for CI signing TestFlight / testflight (push) Failing after 19s Details	2026-06-25 23:18:01 -07:00
buzzert	387896741c	Use runner login keychain for CI signing TestFlight / testflight (push) Failing after 21s Details	2026-06-25 23:16:22 -07:00
buzzert	f6a10af7a9	Use signing certificate identity hash TestFlight / testflight (push) Failing after 24s Details	2026-06-25 23:13:08 -07:00
buzzert	8aab86e2a6	Avoid changing default keychain in CI TestFlight / testflight (push) Failing after 25s Details	2026-06-25 23:10:35 -07:00
buzzert	eb4b233e33	Resolve CI signing keychain path TestFlight / testflight (push) Failing after 18s Details	2026-06-25 23:08:35 -07:00
buzzert	cbd7a68e57	Make CI signing keychain visible to Xcode TestFlight / testflight (push) Failing after 21s Details	2026-06-25 23:06:00 -07:00
buzzert	04c15e8f12	Use absolute iOS paths in Fastlane TestFlight / testflight (push) Failing after 25s Details	2026-06-25 22:50:30 -07:00
buzzert	ca28ebc0a0	Use disposable match keychain in CI TestFlight / testflight (push) Failing after 16s Details	2026-06-25 22:48:59 -07:00
buzzert	87787642b5	Preserve Ruby path for TestFlight workflow TestFlight / testflight (push) Failing after 22s Details	2026-06-25 22:46:14 -07:00
buzzert	4124a31a34	Use Ruby 3.1 for TestFlight workflow TestFlight / testflight (push) Failing after 21s Details	2026-06-25 22:43:27 -07:00
buzzert	a68f1e50ca	Reset iOS TestFlight deployment TestFlight / testflight (push) Failing after 14s Details	2026-06-25 22:41:00 -07:00
buzzert	272ad0bbf0	ios: pass signing settings to archive TestFlight Release / testflight (push) Failing after 17s Details	2026-06-25 22:19:25 -07:00
buzzert	de7b448bc5	ios: avoid system default keychain writes TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 22:16:24 -07:00
buzzert	3c7fc51fdb	ios: set ci keychain in default domain TestFlight Release / testflight (push) Failing after 10s Details	2026-06-25 22:14:25 -07:00
buzzert	0062f37b9f	ios: sign with disposable login keychain TestFlight Release / testflight (push) Failing after 17s Details	2026-06-25 22:12:17 -07:00
buzzert	0ae551615f	ios: use signing identity fingerprint in ci TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 22:10:06 -07:00
buzzert	88bef50ae7	ios: create named ci keychain in home TestFlight Release / testflight (push) Failing after 15s Details	2026-06-25 22:07:12 -07:00
buzzert	0d069b4233	ios: create ci keychain by name TestFlight Release / testflight (push) Failing after 11s Details	2026-06-25 22:05:47 -07:00
buzzert	60bbe077e8	ios: pass signing keychain to xcode TestFlight Release / testflight (push) Failing after 18s Details	2026-06-25 22:02:19 -07:00
buzzert	0b09d5425b	ios: handle empty ci keychain list TestFlight Release / testflight (push) Failing after 15s Details	2026-06-25 21:58:01 -07:00
buzzert	c9a3015e35	ios: parse ci profile without keychain TestFlight Release / testflight (push) Failing after 9s Details	2026-06-25 21:56:19 -07:00
buzzert	abd8a80daa	ios: isolate ci signing keychains TestFlight Release / testflight (push) Failing after 8s Details	2026-06-25 21:52:17 -07:00
buzzert	0f76ef91a9	ios: restore working ci p12 import TestFlight Release / testflight (push) Failing after 9s Details	2026-06-25 21:48:19 -07:00
buzzert	72e2ffd898	ios: use temporary keychain path in ci TestFlight Release / testflight (push) Failing after 9s Details	2026-06-25 21:46:48 -07:00
buzzert	4c610c89e1	ios: install ci profiles for xcode signing TestFlight Release / testflight (push) Failing after 9s Details	2026-06-25 21:44:42 -07:00
buzzert	477921563f	ios: remove invalid ci codesign path TestFlight Release / testflight (push) Failing after 18s Details	2026-06-25 21:36:37 -07:00
buzzert	0fca0e93ec	ios: grant ci key access to xcode tools TestFlight Release / testflight (push) Failing after 10s Details	2026-06-25 21:35:11 -07:00
buzzert	f977f9943c	ios: patch generated release signing settings TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 21:31:51 -07:00
buzzert	f445730a41	ios: override iphoneos signing identity TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 21:29:35 -07:00
buzzert	76cb808c33	ios: use disposable keychain as ci default TestFlight Release / testflight (push) Failing after 15s Details	2026-06-25 21:27:19 -07:00
buzzert	e167bd983f	ios: use generic xcode signing selector TestFlight Release / testflight (push) Failing after 19s Details	2026-06-25 21:25:13 -07:00
buzzert	e4dd91564f	ios: unlock signing keychain before build TestFlight Release / testflight (push) Failing after 17s Details	2026-06-25 21:20:31 -07:00
buzzert	3bfde476a6	ios: use single identity signing p12 TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 21:18:54 -07:00
buzzert	b8676027db	ios: trust Apple root in CI signing keychain TestFlight Release / testflight (push) Failing after 8s Details	2026-06-25 21:12:53 -07:00
buzzert	d36d2c60a3	ios: install Apple WWDR intermediate in CI TestFlight Release / testflight (push) Failing after 18s Details	2026-06-25 21:11:01 -07:00
buzzert	3d7031bb40	ios: avoid default keychain mutation in ci TestFlight Release / testflight (push) Failing after 17s Details	2026-06-25 21:08:32 -07:00
buzzert	fa9b725c77	ios: expose signing keychain to xcodebuild TestFlight Release / testflight (push) Failing after 9s Details	2026-06-25 21:07:38 -07:00
buzzert	a88987d08d	ios: pin distribution signing identity TestFlight Release / testflight (push) Failing after 15s Details	2026-06-25 21:05:26 -07:00
buzzert	e137ea1077	ios: bootstrap signing with existing certificate TestFlight Release / testflight (push) Failing after 17s Details	2026-06-25 21:03:43 -07:00
buzzert	fad25d7f2b	ios: configure api-key TestFlight signing	2026-06-25 20:51:01 -07:00
buzzert	fb28508764	ios: ci: keychain cleanup	2026-06-25 20:35:39 -07:00
buzzert	4365798f5e	workflow: fix TestFlight Release / testflight (push) Failing after 16s Details	2026-06-25 20:21:39 -07:00