ios: restore working ci p12 import

ios: use temporary keychain path in ci
ios: install ci profiles for xcode signing
2026-06-25 21:48:19 -07:00 · 2026-06-25 21:46:48 -07:00 · 2026-06-25 21:44:42 -07:00 · 2026-06-25 21:36:37 -07:00 · 2026-06-25 21:35:11 -07:00 · 2026-06-25 21:31:51 -07:00
58 changed files with 1439 additions and 2850 deletions
@@ -0,0 +1,265 @@
+name: TestFlight Release
+
+on:
+  push:
+    tags:
+      - "release/v*.*.*"
+
+permissions:
+  contents: write
+
+jobs:
+  testflight:
+    runs-on: xcode
+    env:
+      SIGNING_KEYCHAIN: sybil_signing_temp
+
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Validate release tag
+        run: |
+          set -euo pipefail
+
+          tag_name="${GITHUB_REF#refs/tags/}"
+          if [[ ! "$tag_name" =~ ^release/v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            echo "Release tag must match release/vN.N.N; got ${tag_name}" >&2
+            exit 1
+          fi
+
+          release_version="${tag_name#release/v}"
+          {
+            echo "TAG_NAME=${tag_name}"
+            echo "RELEASE_VERSION=${release_version}"
+          } >> "${GITHUB_ENV}"
+
+      - name: Set up Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: "3.3"
+
+      - name: Install Ruby gems
+        working-directory: ios
+        run: bundle install
+
+      - name: Install release tools
+        run: |
+          set -euo pipefail
+
+          missing_tools=()
+          for tool in xcodegen jq; do
+            if ! command -v "${tool}" >/dev/null 2>&1; then
+              missing_tools+=("${tool}")
+            fi
+          done
+
+          if [[ "${#missing_tools[@]}" -eq 0 ]]; then
+            exit 0
+          fi
+
+          if ! command -v brew >/dev/null 2>&1; then
+            echo "Missing required tools: ${missing_tools[*]}; Homebrew is not available to install them" >&2
+            exit 1
+          fi
+
+          brew install "${missing_tools[@]}"
+
+      - name: Install signing secrets
+        env:
+          APPSTORE_CERTIFICATES_FILE_BASE64: ${{ secrets.APPSTORE_CERTIFICATES_FILE_BASE64 }}
+          APPSTORE_CERTIFICATES_PASSWORD: ${{ secrets.APPSTORE_CERTIFICATES_PASSWORD }}
+          APPSTORE_PROVISIONING_PROFILE_BASE64: ${{ secrets.APPSTORE_PROVISIONING_PROFILE_BASE64 }}
+        run: |
+          set -euo pipefail
+
+          : "${APPSTORE_CERTIFICATES_FILE_BASE64:?APPSTORE_CERTIFICATES_FILE_BASE64 secret is required}"
+          : "${APPSTORE_CERTIFICATES_PASSWORD:?APPSTORE_CERTIFICATES_PASSWORD secret is required}"
+          : "${APPSTORE_PROVISIONING_PROFILE_BASE64:?APPSTORE_PROVISIONING_PROFILE_BASE64 secret is required}"
+
+          keychain_password="$(uuidgen)"
+          previous_default_keychain="$(security default-keychain -d user | sed 's/[ "]//g' || true)"
+          developer_dir="$(xcode-select -p)"
+          signing_dir="$(mktemp -d "${RUNNER_TEMP:-${TMPDIR:-/tmp}}/sybil-signing.XXXXXX")"
+          keychain_path="${HOME}/Library/Keychains/${SIGNING_KEYCHAIN}.keychain-db"
+          certificate_path="${signing_dir}/appstore-signing.p12"
+          wwdr_certificate_path="${signing_dir}/AppleWWDRCAG3.cer"
+          profile_path="${signing_dir}/Sybil_AppStore_CI.mobileprovision"
+          profile_plist="${signing_dir}/profile.plist"
+          old_profile_dir="${HOME}/Library/MobileDevice/Provisioning Profiles"
+          xcode_profile_dir="${HOME}/Library/Developer/Xcode/UserData/Provisioning Profiles"
+          mkdir -p "${HOME}/Library/Keychains" "${old_profile_dir}" "${xcode_profile_dir}"
+
+          printf '%s' "${APPSTORE_CERTIFICATES_FILE_BASE64}" | base64 --decode > "${certificate_path}"
+          printf '%s' "${APPSTORE_PROVISIONING_PROFILE_BASE64}" | base64 --decode > "${profile_path}"
+          curl -fsSL https://www.apple.com/certificateauthority/AppleWWDRCAG3.cer -o "${wwdr_certificate_path}"
+          security cms -D -i "${profile_path}" > "${profile_plist}"
+          profile_uuid="$(/usr/libexec/PlistBuddy -c 'Print UUID' "${profile_plist}")"
+          profile_name="$(/usr/libexec/PlistBuddy -c 'Print Name' "${profile_plist}")"
+          old_profile_path="${old_profile_dir}/${profile_uuid}.mobileprovision"
+          xcode_profile_path="${xcode_profile_dir}/${profile_uuid}.mobileprovision"
+          old_named_profile_path="${old_profile_dir}/Sybil_AppStore_CI.mobileprovision"
+          xcode_named_profile_path="${xcode_profile_dir}/Sybil_AppStore_CI.mobileprovision"
+          cp "${profile_path}" "${old_profile_path}"
+          cp "${profile_path}" "${xcode_profile_path}"
+          cp "${profile_path}" "${old_named_profile_path}"
+          cp "${profile_path}" "${xcode_named_profile_path}"
+
+          security create-keychain -p "${keychain_password}" "${keychain_path}"
+          security set-keychain-settings -lut 21600 "${keychain_path}"
+          security unlock-keychain -p "${keychain_password}" "${keychain_path}"
+          security import "${wwdr_certificate_path}" \
+            -k "${keychain_path}" \
+            -T /usr/bin/codesign \
+            -T /usr/bin/security \
+            -T /usr/bin/xcodebuild
+          security import "${certificate_path}" \
+            -k "${keychain_path}" \
+            -P "${APPSTORE_CERTIFICATES_PASSWORD}" \
+            -T /usr/bin/codesign \
+            -T /usr/bin/security \
+            -T /usr/bin/xcodebuild \
+            -T "${developer_dir}/usr/bin/xcodebuild"
+          security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k "${keychain_password}" "${keychain_path}"
+          security list-keychains -d user -s "${keychain_path}" $(security list-keychains -d user | sed 's/[ "]//g')
+          security default-keychain -d user -s "${keychain_path}"
+          security find-identity -v -p codesigning "${keychain_path}"
+          security find-identity -v -p codesigning
+          echo "Installed ${profile_name} (${profile_uuid}) provisioning profile"
+          {
+            echo "SYBIL_SIGNING_KEYCHAIN_PATH=${keychain_path}"
+            echo "SYBIL_SIGNING_KEYCHAIN_PASSWORD=${keychain_password}"
+            echo "SYBIL_PREVIOUS_DEFAULT_KEYCHAIN=${previous_default_keychain}"
+            echo "SYBIL_PROVISIONING_PROFILE_UUID=${profile_uuid}"
+            echo "SYBIL_SIGNING_DIR=${signing_dir}"
+            echo "SYBIL_OLD_PROFILE_PATH=${old_profile_path}"
+            echo "SYBIL_XCODE_PROFILE_PATH=${xcode_profile_path}"
+            echo "SYBIL_OLD_NAMED_PROFILE_PATH=${old_named_profile_path}"
+            echo "SYBIL_XCODE_NAMED_PROFILE_PATH=${xcode_named_profile_path}"
+          } >> "${GITHUB_ENV}"
+
+      - name: Build and upload to TestFlight
+        working-directory: ios
+        env:
+          APP_STORE_CONNECT_API_KEY_ID: ${{ secrets.APP_STORE_CONNECT_API_KEY_ID }}
+          APP_STORE_CONNECT_API_ISSUER_ID: ${{ secrets.APP_STORE_CONNECT_API_ISSUER_ID }}
+          APP_STORE_CONNECT_API_KEY_CONTENT: ${{ secrets.APP_STORE_CONNECT_API_KEY_CONTENT }}
+          APP_STORE_CONNECT_API_KEY_CONTENT_BASE64: "true"
+          FASTLANE_DONT_STORE_PASSWORD: "1"
+          FASTLANE_HIDE_CHANGELOG: "1"
+          FASTLANE_SKIP_UPDATE_CHECK: "1"
+          SYBIL_PROVISIONING_PROFILE_SPECIFIER: Sybil AppStore CI
+        run: |
+          set -euo pipefail
+
+          security unlock-keychain -p "${SYBIL_SIGNING_KEYCHAIN_PASSWORD}" "${SYBIL_SIGNING_KEYCHAIN_PATH}"
+          security list-keychains -d user -s "${SYBIL_SIGNING_KEYCHAIN_PATH}" $(security list-keychains -d user | sed 's/[ "]//g')
+          security default-keychain -d user -s "${SYBIL_SIGNING_KEYCHAIN_PATH}"
+          security find-identity -v -p codesigning "${SYBIL_SIGNING_KEYCHAIN_PATH}"
+          security find-identity -v -p codesigning
+
+          SYBIL_VERSION_TAG="${TAG_NAME}" bundle exec fastlane ios beta
+
+      - name: Locate IPA
+        run: |
+          set -euo pipefail
+
+          ipa_path="$(find ios/build/fastlane -maxdepth 1 -type f -name '*.ipa' -print | sort | tail -n 1)"
+          if [[ -z "${ipa_path}" ]]; then
+            echo "No IPA found under ios/build/fastlane" >&2
+            exit 1
+          fi
+
+          {
+            echo "IPA_PATH=${ipa_path}"
+            echo "IPA_NAME=$(basename "${ipa_path}")"
+          } >> "${GITHUB_ENV}"
+
+      - name: Publish Gitea release asset
+        env:
+          GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
+          RELEASE_API_URL: ${{ github.api_url }}
+          RELEASE_REPOSITORY: ${{ github.repository }}
+          RELEASE_SHA: ${{ github.sha }}
+        run: |
+          set -euo pipefail
+
+          : "${GITEA_TOKEN:?GITEA_TOKEN is required}"
+
+          api_url="${RELEASE_API_URL:-https://code.buzzert.dev/api/v1}"
+          repository="${RELEASE_REPOSITORY:-buzzert/Sybil-2}"
+          sha="${RELEASE_SHA:-${GITHUB_SHA:-}}"
+          release_name="Sybil v${RELEASE_VERSION}"
+          release_body="Automated TestFlight release for ${TAG_NAME}."
+          release_payload="$(jq -nc \
+            --arg tag "${TAG_NAME}" \
+            --arg name "${release_name}" \
+            --arg body "${release_body}" \
+            --arg target "${sha}" \
+            '{tag_name: $tag, name: $name, body: $body, draft: false, prerelease: false} +
+            (if $target == "" then {} else {target_commitish: $target} end)')"
+
+          response_file="$(mktemp)"
+          status="$(curl -sS -o "${response_file}" -w "%{http_code}" \
+            -X POST "${api_url}/repos/${repository}/releases" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            --data "${release_payload}")"
+
+          if [[ "${status}" == "201" ]]; then
+            release_id="$(jq -r '.id' "${response_file}")"
+          elif [[ "${status}" == "409" ]]; then
+            release_id="$(curl -fsS \
+              -H "Authorization: token ${GITEA_TOKEN}" \
+              "${api_url}/repos/${repository}/releases?limit=100" |
+              jq -r --arg tag "${TAG_NAME}" '.[] | select(.tag_name == $tag) | .id' |
+              head -n 1)"
+          else
+            cat "${response_file}" >&2
+            exit 1
+          fi
+
+          if [[ -z "${release_id}" || "${release_id}" == "null" ]]; then
+            echo "Could not resolve Gitea release id for ${TAG_NAME}" >&2
+            exit 1
+          fi
+
+          existing_asset_id="$(curl -fsS \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            "${api_url}/repos/${repository}/releases/${release_id}/assets" |
+            jq -r --arg name "${IPA_NAME}" '.[] | select(.name == $name) | .id' |
+            head -n 1)"
+
+          if [[ -n "${existing_asset_id}" && "${existing_asset_id}" != "null" ]]; then
+            curl -fsS -X DELETE \
+              -H "Authorization: token ${GITEA_TOKEN}" \
+              "${api_url}/repos/${repository}/releases/${release_id}/assets/${existing_asset_id}"
+          fi
+
+          asset_name="$(jq -rn --arg value "${IPA_NAME}" '$value | @uri')"
+          curl -fsS -X POST \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -F "attachment=@${IPA_PATH}" \
+            "${api_url}/repos/${repository}/releases/${release_id}/assets?name=${asset_name}" >/dev/null
+
+          echo "Published ${IPA_NAME} to ${release_name}"
+
+      - name: Clean up temporary keychain
+        if: always()
+        run: |
+          if [[ -n "${SYBIL_PREVIOUS_DEFAULT_KEYCHAIN:-}" ]]; then
+            security default-keychain -d user -s "${SYBIL_PREVIOUS_DEFAULT_KEYCHAIN}" || true
+          fi
+          rm -f \
+            "${SYBIL_OLD_PROFILE_PATH:-}" \
+            "${SYBIL_XCODE_PROFILE_PATH:-}" \
+            "${SYBIL_OLD_NAMED_PROFILE_PATH:-}" \
+            "${SYBIL_XCODE_NAMED_PROFILE_PATH:-}"
+          security delete-keychain "${SYBIL_SIGNING_KEYCHAIN_PATH:-${HOME}/Library/Keychains/${SIGNING_KEYCHAIN}.keychain-db}" || true
+          rm -rf "${SYBIL_SIGNING_DIR:-}"
@@ -1,39 +0,0 @@
-name: TestFlight
-
-on:
-  push:
-    tags:
-      - "release/ios/v*.*.*"
-
-jobs:
-  testflight:
-    name: Build and upload
-    runs-on: macos-arm64
-    timeout-minutes: 90
-
-    steps:
-      - name: Check out the release tag
-        uses: actions/checkout@v4
-
-      - name: Set up Ruby
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: "3.3.11"
-          bundler-cache: true
-          working-directory: ios
-
-      - name: Install XcodeGen
-        run: command -v xcodegen >/dev/null 2>&1 || brew install xcodegen
-
-      - name: Build and upload to TestFlight
-        working-directory: ios
-        env:
-          ASC_KEY_ID: ${{ secrets.ASC_KEY_ID }}
-          ASC_ISSUER_ID: ${{ secrets.ASC_ISSUER_ID }}
-          ASC_KEY: ${{ secrets.ASC_KEY }}
-          MATCH_PASSWORD: ${{ secrets.MATCH_PASSWORD }}
-          MATCH_GIT_BASIC_AUTHORIZATION: ${{ secrets.MATCH_GIT_BASIC_AUTHORIZATION }}
-          CI: "true"
-          FASTLANE_SKIP_UPDATE_CHECK: "1"
-          FASTLANE_HIDE_CHANGELOG: "1"
-        run: bundle exec fastlane ios beta
@@ -1,3 +1,2 @@
 .env
-ios/fastlane/README.md
-ios/fastlane/report.xml
+
@@ -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.
@@ -1,5 +1,23 @@
-ASC_KEY_ID=
-ASC_ISSUER_ID=
-ASC_KEY=
-MATCH_PASSWORD=
-MATCH_GIT_BASIC_AUTHORIZATION=
+FASTLANE_APP_IDENTIFIER=net.buzzert.sybil2
+FASTLANE_TEAM_ID=DQQH5H6GBD
+FASTLANE_SKIP_UPDATE_CHECK=1
+FASTLANE_HIDE_CHANGELOG=1
+SYBIL_APP_STORE_APPLE_ID=6759442828
+SYBIL_PROVIDER_PUBLIC_ID=c043d167-ad88-4036-84ea-76c223f1b1b2
+SYBIL_PROVISIONING_PROFILE_SPECIFIER=Sybil AppStore CI
+SYBIL_PROVISIONING_PROFILE_UUID=
+SYBIL_CODE_SIGN_IDENTITY=Apple Distribution: James Magahern (DQQH5H6GBD)
+SYBIL_XCODE_CODE_SIGN_IDENTITY=Apple Distribution
+SYBIL_SIGNING_CERTIFICATE_ID=
+SYBIL_SIGNING_KEYCHAIN=
+
+# App Store Connect API key settings for TestFlight upload and signing setup.
+APP_STORE_CONNECT_API_KEY_ID=
+APP_STORE_CONNECT_API_ISSUER_ID=
+APP_STORE_CONNECT_API_KEY_PATH=
+APP_STORE_CONNECT_API_KEY_CONTENT=
+APP_STORE_CONNECT_API_KEY_CONTENT_BASE64=false
+
+# Optional deployment overrides.
+SYBIL_BUILD_NUMBER=
+SYBIL_VERSION_TAG=
@@ -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
@@ -1,3 +1,3 @@
 source "https://rubygems.org"

-gem "fastlane", "2.237.0"
+gem "fastlane", "~> 2.227"
@@ -1,49 +1,46 @@
 GEM
  remote: https://rubygems.org/
  specs:
-    CFPropertyList (3.0.8)
+    CFPropertyList (3.0.9)
    abbrev (0.1.2)
    addressable (2.9.0)
      public_suffix (>= 2.0.2, < 8.0)
    artifactory (3.0.17)
    atomos (0.1.3)
-    aws-eventstream (1.4.0)
-    aws-partitions (1.1274.0)
-    aws-sdk-core (3.254.0)
+    aws-eventstream (1.3.2)
+    aws-partitions (1.1109.0)
+    aws-sdk-core (3.224.1)
      aws-eventstream (~> 1, >= 1.3.0)
      aws-partitions (~> 1, >= 1.992.0)
      aws-sigv4 (~> 1.9)
      base64
-      bigdecimal
      jmespath (~> 1, >= 1.6.1)
      logger
-    aws-sdk-kms (1.130.0)
-      aws-sdk-core (~> 3, >= 3.254.0)
+    aws-sdk-kms (1.101.0)
+      aws-sdk-core (~> 3, >= 3.216.0)
      aws-sigv4 (~> 1.5)
-    aws-sdk-s3 (1.228.1)
-      aws-sdk-core (~> 3, >= 3.254.0)
+    aws-sdk-s3 (1.188.0)
+      aws-sdk-core (~> 3, >= 3.224.1)
      aws-sdk-kms (~> 1)
      aws-sigv4 (~> 1.5)
-    aws-sigv4 (1.12.1)
+    aws-sigv4 (1.11.0)
      aws-eventstream (~> 1, >= 1.0.2)
    babosa (1.0.4)
-    base64 (0.3.0)
-    benchmark (0.5.0)
-    bigdecimal (4.1.2)
+    base64 (0.2.0)
    claide (1.1.0)
    colored (1.2)
    colored2 (3.1.2)
    commander (4.6.0)
      highline (~> 2.0.0)
-    csv (3.3.6)
+    csv (3.3.5)
    declarative (0.0.20)
    digest-crc (0.7.0)
      rake (>= 12.0.0, < 14.0.0)
-    domain_name (0.6.20240107)
+    domain_name (0.5.20190701)
+      unf (>= 0.0.5, < 1.0.0)
    dotenv (2.8.1)
    emoji_regex (3.2.3)
-    excon (1.6.0)
-      logger
+    excon (0.109.0)
    faraday (1.10.6)
      faraday-em_http (~> 1.0)
      faraday-em_synchrony (~> 1.0)
@@ -73,45 +70,42 @@ GEM
    faraday_middleware (1.2.1)
      faraday (~> 1.0)
    fastimage (2.4.1)
-    fastlane (2.237.0)
-      CFPropertyList (>= 2.3, < 5.0.0)
-      abbrev (~> 0.1)
-      addressable (>= 2.9.0, < 3.0.0)
+    fastlane (2.230.0)
+      CFPropertyList (>= 2.3, < 4.0.0)
+      abbrev (~> 0.1.2)
+      addressable (>= 2.8, < 3.0.0)
      artifactory (~> 3.0)
-      aws-sdk-s3 (~> 1.197)
+      aws-sdk-s3 (~> 1.0)
      babosa (>= 1.0.3, < 2.0.0)
-      base64 (~> 0.2)
-      benchmark (>= 0.1.0)
-      bundler (>= 2.4.0, < 5.0.0)
+      base64 (~> 0.2.0)
+      bundler (>= 1.12.0, < 3.0.0)
      colored (~> 1.2)
      commander (~> 4.6)
      csv (~> 3.3)
      dotenv (>= 2.1.1, < 3.0.0)
      emoji_regex (>= 0.1, < 4.0)
-      excon (>= 0.71.0, < 2.0.0)
+      excon (>= 0.71.0, < 1.0.0)
      faraday (~> 1.0)
      faraday-cookie_jar (~> 0.0.6)
      faraday_middleware (~> 1.0)
      fastimage (>= 2.1.0, < 3.0.0)
-      fastlane-sirp (>= 1.1.0)
+      fastlane-sirp (>= 1.0.0)
      gh_inspector (>= 1.1.2, < 2.0.0)
      google-apis-androidpublisher_v3 (~> 0.3)
      google-apis-playcustomapp_v1 (~> 0.1)
-      google-cloud-env (>= 1.6.0, < 2.3.0)
+      google-cloud-env (>= 1.6.0, < 2.0.0)
      google-cloud-storage (~> 1.31)
      highline (~> 2.0)
      http-cookie (~> 1.0.5)
      json (< 3.0.0)
-      jwt (>= 2.10.3, < 4)
+      jwt (>= 2.1.0, < 3)
      logger (>= 1.6, < 2.0)
      mini_magick (>= 4.9.4, < 5.0.0)
-      multi_json (~> 1.12)
      multipart-post (>= 2.0.0, < 3.0.0)
-      mutex_m (~> 0.3)
+      mutex_m (~> 0.3.0)
      naturally (~> 2.2)
-      nkf (~> 0.2)
+      nkf (~> 0.2.0)
      optparse (>= 0.1.1, < 1.0.0)
-      ostruct (>= 0.1.0)
      plist (>= 3.1.0, < 4.0.0)
      rubyzip (>= 2.0.0, < 3.0.0)
      security (= 0.1.5)
@@ -126,46 +120,41 @@ GEM
      xcpretty-travis-formatter (>= 0.0.3, < 2.0.0)
    fastlane-sirp (1.1.0)
    gh_inspector (1.1.3)
-    google-apis-androidpublisher_v3 (0.106.0)
-      google-apis-core (>= 0.15.0, < 2.a)
-    google-apis-core (0.18.0)
+    google-apis-androidpublisher_v3 (0.54.0)
+      google-apis-core (>= 0.11.0, < 2.a)
+    google-apis-core (0.11.3)
      addressable (~> 2.5, >= 2.5.1)
-      googleauth (~> 1.9)
-      httpclient (>= 2.8.3, < 3.a)
+      googleauth (>= 0.16.2, < 2.a)
+      httpclient (>= 2.8.1, < 3.a)
      mini_mime (~> 1.0)
-      mutex_m
      representable (~> 3.0)
      retriable (>= 2.0, < 4.a)
-    google-apis-iamcredentials_v1 (0.28.0)
-      google-apis-core (>= 0.15.0, < 2.a)
-    google-apis-playcustomapp_v1 (0.18.0)
-      google-apis-core (>= 0.15.0, < 2.a)
-    google-apis-storage_v1 (0.65.0)
-      google-apis-core (>= 0.15.0, < 2.a)
-    google-cloud-core (1.9.0)
+      rexml
+    google-apis-iamcredentials_v1 (0.17.0)
+      google-apis-core (>= 0.11.0, < 2.a)
+    google-apis-playcustomapp_v1 (0.13.0)
+      google-apis-core (>= 0.11.0, < 2.a)
+    google-apis-storage_v1 (0.29.0)
+      google-apis-core (>= 0.11.0, < 2.a)
+    google-cloud-core (1.6.1)
      google-cloud-env (>= 1.0, < 3.a)
      google-cloud-errors (~> 1.0)
-    google-cloud-env (2.2.2)
-      base64 (~> 0.2)
-      faraday (>= 1.0, < 3.a)
-    google-cloud-errors (1.7.0)
-    google-cloud-storage (1.62.0)
+    google-cloud-env (1.6.0)
+      faraday (>= 0.17.3, < 3.0)
+    google-cloud-errors (1.3.1)
+    google-cloud-storage (1.45.0)
      addressable (~> 2.8)
      digest-crc (~> 0.4)
-      google-apis-core (>= 0.18, < 2)
-      google-apis-iamcredentials_v1 (~> 0.18)
-      google-apis-storage_v1 (>= 0.42)
+      google-apis-iamcredentials_v1 (~> 0.1)
+      google-apis-storage_v1 (~> 0.29.0)
      google-cloud-core (~> 1.6)
-      googleauth (~> 1.9)
+      googleauth (>= 0.16.2, < 2.a)
      mini_mime (~> 1.0)
-    google-logging-utils (0.2.0)
-    googleauth (1.17.2)
-      faraday (>= 1.0, < 3.a)
-      google-cloud-env (~> 2.2)
-      google-logging-utils (~> 0.1)
-      jwt (>= 1.4, < 4.0)
+    googleauth (1.8.1)
+      faraday (>= 0.17.3, < 3.a)
+      jwt (>= 1.4, < 3.0)
+      multi_json (~> 1.11)
      os (>= 0.9, < 2.0)
-      pstore (~> 0.1)
      signet (>= 0.16, < 2.a)
    highline (2.0.3)
    http-cookie (1.0.8)
@@ -173,24 +162,22 @@ GEM
    httpclient (2.9.0)
      mutex_m
    jmespath (1.6.2)
-    json (2.21.1)
-    jwt (3.2.0)
+    json (2.7.6)
+    jwt (2.10.3)
      base64
    logger (1.7.0)
    mini_magick (4.13.2)
    mini_mime (1.1.5)
-    multi_json (1.21.1)
+    multi_json (1.15.0)
    multipart-post (2.4.1)
    mutex_m (0.3.0)
    nanaimo (0.4.0)
    naturally (2.3.0)
-    nkf (0.3.0)
+    nkf (0.2.0)
    optparse (0.8.1)
    os (1.1.4)
-    ostruct (0.6.3)
    plist (3.7.2)
-    pstore (0.2.1)
-    public_suffix (7.0.5)
+    public_suffix (5.1.1)
    rake (13.4.2)
    representable (3.2.0)
      declarative (< 0.1.0)
@@ -202,10 +189,11 @@ GEM
    ruby2_keywords (0.0.5)
    rubyzip (2.4.1)
    security (0.1.5)
-    signet (0.22.0)
+    signet (0.18.0)
      addressable (~> 2.8)
      faraday (>= 0.17.5, < 3.a)
-      jwt (>= 1.5, < 4.0)
+      jwt (>= 1.5, < 3.0)
+      multi_json (~> 1.10)
    simctl (1.6.10)
      CFPropertyList
      naturally
@@ -218,16 +206,15 @@ GEM
    tty-spinner (0.9.3)
      tty-cursor (~> 0.7)
    uber (0.1.0)
+    unf (0.2.0)
    unicode-display_width (2.6.0)
    word_wrap (1.0.0)
-    xcodeproj (1.28.1)
+    xcodeproj (1.27.0)
      CFPropertyList (>= 2.3.3, < 4.0)
      atomos (~> 0.1.3)
-      base64
      claide (>= 1.0.2, < 2.0)
      colored2 (~> 3.1)
      nanaimo (~> 0.4.0)
-      nkf
      rexml (>= 3.3.6, < 4.0)
    xcpretty (0.4.1)
      rouge (~> 3.28.0)
@@ -238,7 +225,7 @@ PLATFORMS
  ruby

 DEPENDENCIES
-  fastlane (= 2.237.0)
+  fastlane (~> 2.227)

 BUNDLED WITH
   2.5.23
@@ -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
@@ -1,2 +1,9 @@
-app_identifier("net.buzzert.sybil2")
-team_id("DQQH5H6GBD")
+require "dotenv"
+
+Dotenv.load(File.expand_path("../.env", __dir__))
+
+app_identifier(ENV.fetch("FASTLANE_APP_IDENTIFIER", "net.buzzert.sybil2"))
+team_id(ENV.fetch("FASTLANE_TEAM_ID", "DQQH5H6GBD"))
+
+apple_id(ENV["FASTLANE_USER"]) if ENV["FASTLANE_USER"].to_s.strip.length.positive?
+itc_team_id(ENV["FASTLANE_ITC_TEAM_ID"]) if ENV["FASTLANE_ITC_TEAM_ID"].to_s.strip.length.positive?
@@ -0,0 +1,72 @@
+# TestFlight Release CI
+
+Gitea Actions publishes iOS releases from tags that match:
+
+```sh
+release/vN.N.N
+```
+
+For example:
+
+```sh
+git tag release/v1.10.0
+git push origin release/v1.10.0
+```
+
+The release job runs on the `xcode` runner label, imports the signing p12 into
+a temporary per-user keychain, makes that keychain the user default for the
+duration of the job, installs the App Store provisioning profile in both the
+legacy MobileDevice directory and the Xcode UserData directory used by newer
+Xcode releases, builds and uploads the app with fastlane, then creates or
+updates the matching Gitea release with the generated IPA as an asset. The job
+restores the previous user default keychain and deletes the temporary signing
+keychain and installed profiles in an `always()` cleanup step.
+
+Required repository secrets:
+
+```text
+APP_STORE_CONNECT_API_KEY_ID
+APP_STORE_CONNECT_API_ISSUER_ID
+APP_STORE_CONNECT_API_KEY_CONTENT
+APPSTORE_CERTIFICATES_FILE_BASE64
+APPSTORE_CERTIFICATES_PASSWORD
+APPSTORE_PROVISIONING_PROFILE_BASE64
+```
+
+Generate or refresh the signing assets locally with:
+
+```sh
+cd ios
+fastlane ios create_ci_signing
+```
+
+The generated `build/signing/ci-secrets.env` file is ignored by Git. Copy its
+certificate and provisioning profile values into the repository secrets listed
+above. The workflow uses the `Sybil AppStore CI` provisioning profile name by
+default.
+
+Fastlane keeps two signing names separate. `SYBIL_CODE_SIGN_IDENTITY` is the
+exact certificate common name used when exporting a local p12 for secrets, while
+`SYBIL_XCODE_CODE_SIGN_IDENTITY` defaults to the generic `Apple Distribution`
+selector that Xcode uses during archive/export.
+
+The Release signing settings are also present in `Apps/Sybil/project.yml` so
+XcodeGen emits a manually signed App Store archive configuration. CI passes the
+installed provisioning profile UUID to Fastlane as
+`SYBIL_PROVISIONING_PROFILE_UUID`; Fastlane writes that UUID into the generated
+project before archiving.
+
+If the Apple team has reached the Distribution certificate limit, set
+`SYBIL_SIGNING_CERTIFICATE_ID` to the portal id for a certificate whose private
+key exists in the local login keychain before running `create_ci_signing`. The
+lane will export the local identity and create the provisioning profile against
+that existing certificate instead of creating another Distribution certificate.
+
+If `create_ci_signing` fails with an expired or missing agreement error, the
+Apple Developer Program account holder must accept the current agreements in
+App Store Connect before new certificates or provisioning profiles can be
+created through the API.
+
+The workflow uses Gitea's built-in `GITEA_TOKEN` for release creation and asset
+upload, with `contents: write` permissions. In Gitea this covers release asset
+publication.
@@ -1,47 +1,476 @@
+require "dotenv"
+require "base64"
+require "fileutils"
+require "json"
+require "net/http"
+require "open3"
+require "openssl"
+require "securerandom"
+require "shellwords"
+require "uri"
+require "yaml"
+
+Dotenv.load(File.expand_path("../.env", __dir__))
+
 default_platform(:ios)

-platform :ios do
-  desc "Build a release tag and upload it to TestFlight"
-  lane :beta do
-    setup_ci
+APP_IDENTIFIER = ENV.fetch("FASTLANE_APP_IDENTIFIER", "net.buzzert.sybil2")
+TEAM_ID = ENV.fetch("FASTLANE_TEAM_ID", "DQQH5H6GBD")
+APP_STORE_APPLE_ID = ENV.fetch("SYBIL_APP_STORE_APPLE_ID", "6759442828")
+PROVIDER_PUBLIC_ID = ENV.fetch("SYBIL_PROVIDER_PUBLIC_ID", "c043d167-ad88-4036-84ea-76c223f1b1b2")
+PROFILE_SPECIFIER = ENV["SYBIL_PROVISIONING_PROFILE_SPECIFIER"].to_s.strip.empty? ? "Sybil AppStore CI" : ENV["SYBIL_PROVISIONING_PROFILE_SPECIFIER"]
+SIGNING_CERTIFICATE_NAME = ENV["SYBIL_CODE_SIGN_IDENTITY"].to_s.strip.empty? ? "Apple Distribution: James Magahern (DQQH5H6GBD)" : ENV["SYBIL_CODE_SIGN_IDENTITY"]
+XCODE_CODE_SIGN_IDENTITY = ENV["SYBIL_XCODE_CODE_SIGN_IDENTITY"].to_s.strip.empty? ? "Apple Distribution" : ENV["SYBIL_XCODE_CODE_SIGN_IDENTITY"]
+IOS_ROOT = File.expand_path("..", __dir__)
+PROJECT_FILE = File.join(IOS_ROOT, "Sybil.xcodeproj")
+PROJECT_SPEC = File.join(IOS_ROOT, "project.yml")
+APP_SPEC = File.join(IOS_ROOT, "Apps/Sybil/project.yml")
+SIGNING_OUTPUT_DIR = File.join(IOS_ROOT, "build/signing")
+SCHEME = "Sybil"
+TARGET = "SybilApp"

-    match(type: "appstore")
+def present?(value)
+  !value.to_s.strip.empty?
+end

-    tag = ENV.fetch("GITHUB_REF_NAME")
-    version = tag[%r{\Arelease/ios/v(\d+\.\d+\.\d+)\z}, 1]
-    UI.user_error!("Expected a tag in the form release/ios/vX.Y.Z; got #{tag.inspect}") unless version
+def capture(command)
+  stdout, stderr, status = Open3.capture3(command)
+  return stdout.strip if status.success?

-    build_number = ENV.fetch("GITHUB_RUN_NUMBER")
-    UI.user_error!("GITHUB_RUN_NUMBER must be a positive integer") unless build_number.match?(/\A[1-9]\d*\z/)
+  UI.user_error!("Command failed: #{command}\n#{stderr.strip}")
+end

-    ios_dir = File.expand_path("..", __dir__)
-    project_spec = File.join(ios_dir, "Apps/Sybil/project.yml")
-    contents = File.read(project_spec)
-    unless contents.match?(/^\s*MARKETING_VERSION:/) && contents.match?(/^\s*CURRENT_PROJECT_VERSION:/)
-      UI.user_error!("Could not find version settings in #{project_spec}")
+def run_silent(*command, error_message:)
+  _stdout, stderr, status = Open3.capture3(*command)
+  return if status.success?
+
+  UI.user_error!("#{error_message}\n#{stderr.strip}")
+end
+
+def user_keychains
+  capture("security list-keychains -d user").lines.map { |line| line.strip.delete('"') }.reject(&:empty?)
+end
+
+def app_project_settings
+  YAML.safe_load(File.read(APP_SPEC)).fetch("targets").fetch(TARGET).fetch("settings").fetch("base")
+end
+
+def apply_release_signing_settings
+  require "xcodeproj"
+
+  project = Xcodeproj::Project.open(PROJECT_FILE)
+  target = project.targets.find { |candidate| candidate.name == TARGET }
+  UI.user_error!("Could not find target #{TARGET} in #{PROJECT_FILE}") unless target
+
+  target.build_configurations.each do |configuration|
+    next unless configuration.name == "Release"
+
+    settings = configuration.build_settings
+    settings["CODE_SIGN_STYLE"] = "Manual"
+    settings["DEVELOPMENT_TEAM"] = TEAM_ID
+    settings["PROVISIONING_PROFILE_SPECIFIER"] = PROFILE_SPECIFIER
+    settings["CODE_SIGN_IDENTITY"] = XCODE_CODE_SIGN_IDENTITY
+    settings["CODE_SIGN_IDENTITY[sdk=iphoneos*]"] = XCODE_CODE_SIGN_IDENTITY
+    if present?(ENV["SYBIL_PROVISIONING_PROFILE_UUID"])
+      settings["PROVISIONING_PROFILE"] = ENV["SYBIL_PROVISIONING_PROFILE_UUID"]
+      settings["PROVISIONING_PROFILE[sdk=iphoneos*]"] = ENV["SYBIL_PROVISIONING_PROFILE_UUID"]
    end
-    contents.sub!(/^(\s*MARKETING_VERSION:\s*).*/, "\\1\"#{version}\"")
-    contents.sub!(/^(\s*CURRENT_PROJECT_VERSION:\s*).*/, "\\1#{build_number}")
-    File.write(project_spec, contents)
+  end
+  project.save
+end

-    sh("xcodegen", "--spec", File.join(ios_dir, "project.yml"))
+def local_marketing_version
+  app_project_settings.fetch("MARKETING_VERSION").to_s
+end

-    api_key = app_store_connect_api_key(
-      key_id: ENV.fetch("ASC_KEY_ID"),
-      issuer_id: ENV.fetch("ASC_ISSUER_ID"),
-      key_content: ENV.fetch("ASC_KEY"),
-      is_key_content_base64: true
+def local_build_number
+  app_project_settings.fetch("CURRENT_PROJECT_VERSION").to_i
+end
+
+def normalize_version_tag(tag)
+  version = tag.to_s.strip.sub(%r{\Arelease/}, "").sub(/\Av/, "")
+  unless version.match?(/\A\d+\.\d+\.\d+\z/)
+    UI.user_error!("Release tag #{tag.inspect} must look like release/v1.10.0")
+  end
+  version
+end
+
+def release_version
+  tag = ENV["SYBIL_VERSION_TAG"]
+  tag = capture("git describe --tags --abbrev=0") unless present?(tag)
+  normalize_version_tag(tag)
+end
+
+def xcode_build_setting(key, value)
+  "#{key.to_s.shellescape}=#{value.to_s.shellescape}"
+end
+
+def env_line(key, value)
+  "#{key}=#{value.to_s.shellescape}"
+end
+
+def base64url(value)
+  Base64.urlsafe_encode64(value).delete("=")
+end
+
+def integer_to_fixed_bytes(integer, length)
+  hex = integer.to_s(16)
+  hex = "0#{hex}" if hex.length.odd?
+  [hex].pack("H*").rjust(length, "\0")[-length, length]
+end
+
+def app_store_connect_private_key
+  key_path = ENV["APP_STORE_CONNECT_API_KEY_PATH"]
+  key_content = ENV["APP_STORE_CONNECT_API_KEY_CONTENT"]
+
+  pem = if present?(key_path)
+          File.read(key_path)
+        elsif present?(key_content)
+          ENV["APP_STORE_CONNECT_API_KEY_CONTENT_BASE64"].to_s == "true" ? Base64.decode64(key_content) : key_content
+        end
+  UI.user_error!("App Store Connect API key content is required") unless present?(pem)
+
+  OpenSSL::PKey::EC.new(pem)
+end
+
+def app_store_connect_jwt
+  key_id = ENV["APP_STORE_CONNECT_API_KEY_ID"]
+  issuer_id = ENV["APP_STORE_CONNECT_API_ISSUER_ID"]
+  issuer_id = ENV["APP_STORE_CONNECT_API_KEY_ISSUER_ID"] unless present?(issuer_id)
+  UI.user_error!("App Store Connect API key id and issuer id are required") unless present?(key_id) && present?(issuer_id)
+
+  header = { alg: "ES256", kid: key_id, typ: "JWT" }
+  payload = { iss: issuer_id, iat: Time.now.to_i, exp: Time.now.to_i + 600, aud: "appstoreconnect-v1" }
+  unsigned = [base64url(header.to_json), base64url(payload.to_json)].join(".")
+  asn1_signature = app_store_connect_private_key.dsa_sign_asn1(OpenSSL::Digest::SHA256.digest(unsigned))
+  signature_sequence = OpenSSL::ASN1.decode(asn1_signature)
+  raw_signature = signature_sequence.value.map { |part| integer_to_fixed_bytes(part.value, 32) }.join
+  [unsigned, base64url(raw_signature)].join(".")
+end
+
+def app_store_connect_request(method, path, payload = nil)
+  uri = URI("https://api.appstoreconnect.apple.com#{path}")
+  request_class = Net::HTTP.const_get(method.to_s.capitalize)
+  request = request_class.new(uri)
+  request["Authorization"] = "Bearer #{app_store_connect_jwt}"
+  if payload
+    request["Content-Type"] = "application/json"
+    request.body = payload.to_json
+  end
+
+  response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(request) }
+  return {} if response.is_a?(Net::HTTPSuccess) && response.body.to_s.empty?
+  return JSON.parse(response.body) if response.is_a?(Net::HTTPSuccess)
+
+  UI.user_error!("App Store Connect API request failed: #{method.to_s.upcase} #{path}\n#{response.body}")
+end
+
+def bundle_id_resource_id
+  response = app_store_connect_request(
+    :get,
+    "/v1/bundleIds?filter[identifier]=#{URI.encode_www_form_component(APP_IDENTIFIER)}&limit=1"
+  )
+  id = response.fetch("data", []).first&.fetch("id", nil)
+  UI.user_error!("Could not find App Store Connect bundle id resource for #{APP_IDENTIFIER}") unless present?(id)
+  id
+end
+
+def recreate_app_store_profile(certificate_id)
+  existing = app_store_connect_request(
+    :get,
+    "/v1/profiles?filter[name]=#{URI.encode_www_form_component(PROFILE_SPECIFIER)}&limit=200"
+  )
+  existing.fetch("data", []).each do |profile|
+    app_store_connect_request(:delete, "/v1/profiles/#{profile.fetch("id")}")
+  end
+
+  payload = {
+    data: {
+      type: "profiles",
+      attributes: {
+        name: PROFILE_SPECIFIER,
+        profileType: "IOS_APP_STORE"
+      },
+      relationships: {
+        bundleId: {
+          data: { type: "bundleIds", id: bundle_id_resource_id }
+        },
+        certificates: {
+          data: [{ type: "certificates", id: certificate_id }]
+        }
+      }
+    }
+  }
+  response = app_store_connect_request(:post, "/v1/profiles", payload)
+  profile_content = response.dig("data", "attributes", "profileContent")
+  UI.user_error!("App Store Connect profile response did not include profileContent") unless present?(profile_content)
+
+  profile_path = File.join(SIGNING_OUTPUT_DIR, "Sybil_AppStore_CI.mobileprovision")
+  File.binwrite(profile_path, Base64.decode64(profile_content))
+  install_dir = File.expand_path("~/Library/MobileDevice/Provisioning Profiles")
+  FileUtils.mkdir_p(install_dir)
+  FileUtils.cp(profile_path, File.join(install_dir, "Sybil_AppStore_CI.mobileprovision"))
+  profile_path
+end
+
+def signing_identity_p12(p12_path, p12_password)
+  work_dir = File.join(SIGNING_OUTPUT_DIR, "single-identity")
+  FileUtils.rm_rf(work_dir)
+  FileUtils.mkdir_p(work_dir)
+
+  all_pem = File.join(work_dir, "all.pem")
+  stdout, stderr, status = Open3.capture3(
+    "openssl", "pkcs12",
+    "-in", p12_path,
+    "-nodes",
+    "-passin", "pass:#{p12_password}",
+    "-out", all_pem
+  )
+  UI.user_error!("Could not inspect exported p12\n#{stderr}\n#{stdout}") unless status.success?
+
+  records = File.read(all_pem).split(/(?=Bag Attributes\n)/)
+  cert_record = records.find do |record|
+    record.include?("friendlyName: #{SIGNING_CERTIFICATE_NAME}") && record.include?("-----BEGIN CERTIFICATE-----")
+  end
+  UI.user_error!("Could not find #{SIGNING_CERTIFICATE_NAME} certificate in exported p12") unless cert_record
+
+  local_key_id = cert_record[/localKeyID: (.+)/, 1].to_s.strip
+  UI.user_error!("Could not resolve localKeyID for #{SIGNING_CERTIFICATE_NAME}") unless present?(local_key_id)
+
+  key_record = records.find do |record|
+    record.include?("localKeyID: #{local_key_id}") && record.include?("-----BEGIN PRIVATE KEY-----")
+  end
+  UI.user_error!("Could not find private key for #{SIGNING_CERTIFICATE_NAME}") unless key_record
+
+  cert_path = File.join(work_dir, "identity.cer.pem")
+  key_path = File.join(work_dir, "identity.key.pem")
+  File.write(cert_path, cert_record[/-----BEGIN CERTIFICATE-----.*?-----END CERTIFICATE-----/m])
+  File.write(key_path, key_record[/-----BEGIN PRIVATE KEY-----.*?-----END PRIVATE KEY-----/m])
+
+  root_cer = File.join(work_dir, "AppleIncRootCertificate.cer")
+  wwdr_cer = File.join(work_dir, "AppleWWDRCAG3.cer")
+  root_pem = File.join(work_dir, "AppleIncRootCertificate.pem")
+  wwdr_pem = File.join(work_dir, "AppleWWDRCAG3.pem")
+  chain_pem = File.join(work_dir, "chain.pem")
+  run_silent("curl", "-fsSL", "https://www.apple.com/appleca/AppleIncRootCertificate.cer", "-o", root_cer, error_message: "Could not download Apple root certificate")
+  run_silent("curl", "-fsSL", "https://www.apple.com/certificateauthority/AppleWWDRCAG3.cer", "-o", wwdr_cer, error_message: "Could not download Apple WWDR G3 certificate")
+  run_silent("openssl", "x509", "-inform", "DER", "-in", root_cer, "-out", root_pem, error_message: "Could not convert Apple root certificate")
+  run_silent("openssl", "x509", "-inform", "DER", "-in", wwdr_cer, "-out", wwdr_pem, error_message: "Could not convert Apple WWDR G3 certificate")
+  File.write(chain_pem, File.read(wwdr_pem) + File.read(root_pem))
+
+  single_p12_path = File.join(work_dir, "appstore-signing.p12")
+  run_silent(
+    "openssl", "pkcs12", "-export",
+    "-inkey", key_path,
+    "-in", cert_path,
+    "-certfile", chain_pem,
+    "-name", SIGNING_CERTIFICATE_NAME,
+    "-out", single_p12_path,
+    "-passout", "pass:#{p12_password}",
+    error_message: "Could not create single-identity p12"
+  )
+  FileUtils.cp(single_p12_path, p12_path)
+ensure
+  FileUtils.rm_rf(work_dir) if present?(work_dir)
+end
+
+def app_store_connect_key_options
+  key_id = ENV["APP_STORE_CONNECT_API_KEY_ID"]
+  issuer_id = ENV["APP_STORE_CONNECT_API_ISSUER_ID"]
+  issuer_id = ENV["APP_STORE_CONNECT_API_KEY_ISSUER_ID"] unless present?(issuer_id)
+  return nil unless present?(key_id) && present?(issuer_id)
+
+  key_path = ENV["APP_STORE_CONNECT_API_KEY_PATH"]
+  key_content = ENV["APP_STORE_CONNECT_API_KEY_CONTENT"]
+  if present?(key_path)
+    {
+      key_id: key_id,
+      issuer_id: issuer_id,
+      key_filepath: key_path
+    }
+  elsif present?(key_content)
+    {
+      key_id: key_id,
+      issuer_id: issuer_id,
+      key_content: key_content,
+      is_key_content_base64: ENV["APP_STORE_CONNECT_API_KEY_CONTENT_BASE64"].to_s == "true"
+    }
+  end
+end
+
+platform :ios do
+  private_lane :load_app_store_connect_api_key do
+    options = app_store_connect_key_options
+    UI.user_error!("App Store Connect API key is required") unless options
+
+    app_store_connect_api_key(options)
+  end
+
+  desc "Show the version Fastlane will stamp into the next TestFlight archive"
+  lane :version do
+    UI.message("Git tag version: #{release_version}")
+    UI.message("Checked-in app version: #{local_marketing_version}")
+    UI.message("Checked-in build number: #{local_build_number}")
+  end
+
+  desc "Create CI signing certificate/profile and write ignored secret material under build/signing"
+  lane :create_ci_signing do
+    api_key = load_app_store_connect_api_key
+
+    FileUtils.rm_rf(SIGNING_OUTPUT_DIR)
+    FileUtils.mkdir_p(SIGNING_OUTPUT_DIR)
+
+    cert_id = ENV["SYBIL_SIGNING_CERTIFICATE_ID"].to_s
+    keychain_path = nil
+    keychain_password = nil
+    p12_path = File.join(SIGNING_OUTPUT_DIR, "appstore-signing.p12")
+    p12_password = ENV["SYBIL_CI_P12_PASSWORD"].to_s
+    if p12_password.empty?
+      p12_password = SecureRandom.base64(24)
+      UI.important("Generated a p12 password for CI secrets.")
+    end
+
+    begin
+      if present?(cert_id)
+        UI.message("Using existing signing certificate id #{cert_id}")
+        export_keychain = ENV["SYBIL_SIGNING_KEYCHAIN"].to_s
+        export_keychain = File.expand_path("~/Library/Keychains/login.keychain-db") unless present?(export_keychain)
+        run_silent(
+          "security", "export", "-k", export_keychain, "-t", "identities", "-f", "pkcs12", "-P", p12_password, "-o", p12_path,
+          error_message: "Could not export the local CI signing identity"
+        )
+      else
+        keychain_path = File.join(SIGNING_OUTPUT_DIR, "sybil_ci_signing.keychain-db")
+        keychain_password = SecureRandom.base64(24)
+        run_silent(
+          "security", "create-keychain", "-p", keychain_password, keychain_path,
+          error_message: "Could not create temporary signing keychain"
+        )
+        run_silent(
+          "security", "set-keychain-settings", "-lut", "21600", keychain_path,
+          error_message: "Could not configure temporary signing keychain"
+        )
+        run_silent(
+          "security", "unlock-keychain", "-p", keychain_password, keychain_path,
+          error_message: "Could not unlock temporary signing keychain"
+        )
+        run_silent(
+          "security", "list-keychains", "-d", "user", "-s", keychain_path, *user_keychains,
+          error_message: "Could not add temporary signing keychain to the user search list"
+        )
+
+        cert(
+          api_key: api_key,
+          development: false,
+          force: true,
+          generate_apple_certs: true,
+          keychain_password: keychain_password,
+          keychain_path: keychain_path,
+          output_path: SIGNING_OUTPUT_DIR,
+          platform: "ios"
+        )
+
+        cert_id = lane_context[SharedValues::CERT_CERTIFICATE_ID]
+        UI.user_error!("Could not resolve generated certificate id") unless present?(cert_id)
+        run_silent(
+          "security", "export", "-k", keychain_path, "-t", "identities", "-f", "pkcs12", "-P", p12_password, "-o", p12_path,
+          error_message: "Could not export the generated CI signing identity"
+        )
+      end
+
+      UI.user_error!("Could not find exported p12 at #{p12_path}") unless File.exist?(p12_path)
+      signing_identity_p12(p12_path, p12_password)
+
+      profile_path = recreate_app_store_profile(cert_id)
+      UI.user_error!("Could not resolve generated provisioning profile path") unless present?(profile_path) && File.exist?(profile_path)
+
+      secrets_path = File.join(SIGNING_OUTPUT_DIR, "ci-secrets.env")
+      File.write(
+        secrets_path,
+        [
+          env_line("APPSTORE_CERTIFICATES_FILE_BASE64", Base64.strict_encode64(File.binread(p12_path))),
+          env_line("APPSTORE_CERTIFICATES_PASSWORD", p12_password),
+          env_line("APPSTORE_PROVISIONING_PROFILE_BASE64", Base64.strict_encode64(File.binread(profile_path))),
+          env_line("SYBIL_PROVISIONING_PROFILE_SPECIFIER", PROFILE_SPECIFIER)
+        ].join("\n") + "\n"
+      )
+    ensure
+      system("security", "delete-keychain", keychain_path, out: File::NULL, err: File::NULL) if present?(keychain_path) && File.exist?(keychain_path)
+    end
+
+    UI.success("Created CI signing files in #{SIGNING_OUTPUT_DIR}")
+    UI.important("Add the values from #{secrets_path} as repository secrets.")
+  end
+
+  desc "Build Sybil and upload it to TestFlight"
+  lane :beta do
+    version = release_version
+    build_number = ENV["SYBIL_BUILD_NUMBER"].to_s
+    api_key = load_app_store_connect_api_key
+
+    unless present?(build_number)
+      build_number = (local_build_number + 1).to_s
+
+      begin
+        latest = latest_testflight_build_number(
+          app_identifier: APP_IDENTIFIER,
+          version: version,
+          api_key: api_key,
+          initial_build_number: local_build_number
+        ).to_i
+        build_number = [latest + 1, local_build_number + 1].max.to_s
+      rescue StandardError => e
+        UI.important("Could not look up TestFlight build number: #{e.message}")
+        UI.important("Using checked-in build number + 1: #{build_number}")
+      end
+    end
+
+    UI.user_error!("Build number must be a positive integer") unless build_number.match?(/\A[1-9]\d*\z/)
+
+    sh("xcodegen --spec #{PROJECT_SPEC.shellescape}")
+    apply_release_signing_settings
+
+    xcode_args = [
+      xcode_build_setting("MARKETING_VERSION", version),
+      xcode_build_setting("CURRENT_PROJECT_VERSION", build_number)
+    ]
+    if present?(ENV["SYBIL_SIGNING_KEYCHAIN_PATH"])
+      xcode_args << xcode_build_setting("OTHER_CODE_SIGN_FLAGS", "--keychain #{ENV.fetch("SYBIL_SIGNING_KEYCHAIN_PATH")}")
+    end
+    xcode_args = xcode_args.join(" ")
+
+    ipa_path = build_app(
+      project: PROJECT_FILE,
+      scheme: SCHEME,
+      clean: true,
+      sdk: "iphoneos",
+      export_method: "app-store",
+      output_directory: File.join(IOS_ROOT, "build/fastlane"),
+      output_name: "Sybil-#{version}-#{build_number}.ipa",
+      xcargs: xcode_args,
+      export_options: {
+        method: "app-store",
+        destination: "export",
+        signingStyle: "manual",
+        provisioningProfiles: {
+          APP_IDENTIFIER => PROFILE_SPECIFIER
+        },
+        signingCertificate: XCODE_CODE_SIGN_IDENTITY,
+        teamID: TEAM_ID,
+        manageAppVersionAndBuildNumber: false,
+        uploadSymbols: true,
+        stripSwiftSymbols: true
+      }
    )

-    build_app(
-      project: File.join(ios_dir, "Sybil.xcodeproj"),
-      scheme: "Sybil"
-    )
+    ipa_path ||= lane_context[SharedValues::IPA_OUTPUT_PATH]
+    UI.user_error!("IPA export failed; no IPA path was returned") unless present?(ipa_path) && File.exist?(ipa_path)

    upload_to_testflight(
      api_key: api_key,
-      skip_waiting_for_build_processing: true,
-      uses_non_exempt_encryption: false
+      app_identifier: APP_IDENTIFIER,
+      ipa: ipa_path,
+      skip_waiting_for_build_processing: true
    )
  end
 end
@@ -1,7 +0,0 @@
-git_url("https://code.buzzert.dev/buzzert/fastlane-match.git")
-storage_mode("git")
-type("appstore")
-
-app_identifier(["net.buzzert.sybil2"])
-team_id("DQQH5H6GBD")
-profile_name("Sybil AppStore CI")
@@ -0,0 +1,48 @@
+fastlane documentation
+----
+
+# Installation
+
+Make sure you have the latest version of the Xcode command line tools installed:
+
+```sh
+xcode-select --install
+```
+
+For _fastlane_ installation instructions, see [Installing _fastlane_](https://docs.fastlane.tools/#installing-fastlane)
+
+# Available Actions
+
+## iOS
+
+### ios version
+
+```sh
+[bundle exec] fastlane ios version
+```
+
+Show the version Fastlane will stamp into the next TestFlight archive
+
+### ios create_ci_signing
+
+```sh
+[bundle exec] fastlane ios create_ci_signing
+```
+
+Create CI signing certificate/profile and write ignored secret material under build/signing
+
+### ios beta
+
+```sh
+[bundle exec] fastlane ios beta
+```
+
+Build Sybil and upload it to TestFlight
+
+----
+
+This README.md is auto-generated and will be re-generated every time [_fastlane_](https://fastlane.tools) is run.
+
+More information about _fastlane_ can be found on [fastlane.tools](https://fastlane.tools).
+
+The documentation of _fastlane_ can be found on [docs.fastlane.tools](https://docs.fastlane.tools).
@@ -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[];
@@ -7,7 +7,6 @@
    "dev": "vite",
    "build": "tsc -b && vite build",
    "preview": "vite preview",
-    "test": "node --test --experimental-strip-types tests/*.test.mjs",
    "typecheck": "tsc --noEmit"
  },
  "dependencies": {
@@ -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));
 });
@@ -1,140 +0,0 @@
-import { useLayoutEffect, useRef, useState } from "preact/hooks";
-import { Paperclip, Search, SendHorizontal } from "lucide-preact";
-import { Button } from "@/components/ui/button";
-import { Textarea } from "@/components/ui/textarea";
-import { cn } from "@/lib/utils";
-
-type MutableValueRef = {
-  current: string;
-};
-
-type Props = {
-  draftRef: MutableValueRef;
-  draftRevision: number;
-  error: string | null;
-  isSearchMode: boolean;
-  isSending: boolean;
-  pendingAttachmentCount: number;
-  attachmentButtonDisabled: boolean;
-  onOpenAttachmentPicker: () => void;
-  onPaste: (event: ClipboardEvent) => void;
-  onSend: (draft: string) => void | Promise<void>;
-};
-
-const MIRROR_SENTINEL = "\u200b";
-const HAS_NON_WHITESPACE = /\S/;
-
-export function ChatComposer({
-  draftRef,
-  draftRevision,
-  error,
-  isSearchMode,
-  isSending,
-  pendingAttachmentCount,
-  attachmentButtonDisabled,
-  onOpenAttachmentPicker,
-  onPaste,
-  onSend,
-}: Props) {
-  // The draft stays in the DOM/ref so typing never schedules a render of the workspace transcript.
-  const textareaContainerRef = useRef<HTMLDivElement>(null);
-  const mirrorRef = useRef<HTMLDivElement>(null);
-  const [hasDraft, setHasDraft] = useState(() => HAS_NON_WHITESPACE.test(draftRef.current));
-  const hasDraftRef = useRef(hasDraft);
-
-  const getTextarea = () => textareaContainerRef.current?.querySelector("textarea") ?? null;
-
-  const updateMirror = (value: string) => {
-    // The overlapping mirror lets normal layout size the textarea without synchronous scrollHeight reads.
-    if (mirrorRef.current) mirrorRef.current.textContent = `${value}${MIRROR_SENTINEL}`;
-  };
-
-  const updateHasDraft = (value: string) => {
-    const nextHasDraft = HAS_NON_WHITESPACE.test(value);
-    if (nextHasDraft !== hasDraftRef.current) {
-      hasDraftRef.current = nextHasDraft;
-      setHasDraft(nextHasDraft);
-    }
-  };
-
-  useLayoutEffect(() => {
-    const value = draftRef.current;
-    const textarea = getTextarea();
-    if (textarea && textarea.value !== value) {
-      textarea.value = value;
-    }
-    updateMirror(value);
-    updateHasDraft(value);
-  }, [draftRevision]);
-
-  const submit = () => {
-    const textarea = getTextarea();
-    const draft = textarea?.value ?? draftRef.current;
-    const canSend = HAS_NON_WHITESPACE.test(draft) || (!isSearchMode && pendingAttachmentCount > 0);
-    if (isSending || !canSend) return;
-
-    draftRef.current = "";
-    if (textarea) textarea.value = "";
-    updateMirror("");
-    updateHasDraft("");
-    void onSend(draft);
-  };
-
-  return (
-    <>
-      <div ref={textareaContainerRef} className="grid max-h-40 min-h-0 overflow-hidden">
-        <div
-          ref={mirrorRef}
-          className="pointer-events-none invisible col-start-1 row-start-1 max-h-40 min-h-0 overflow-x-hidden overflow-y-auto whitespace-pre-wrap break-words px-3 py-3 text-base"
-          aria-hidden="true"
-        />
-        <Textarea
-          id="composer-input"
-          rows={1}
-          onInput={(event) => {
-            const value = event.currentTarget.value;
-            draftRef.current = value;
-            updateMirror(value);
-            updateHasDraft(value);
-          }}
-          onPaste={(event) => {
-            onPaste(event);
-          }}
-          onKeyDown={(event) => {
-            if (event.key === "Enter" && !event.shiftKey && !event.isComposing) {
-              event.preventDefault();
-              submit();
-            }
-          }}
-          placeholder={isSearchMode ? "Search the web" : "Enter prompt..."}
-          className="col-start-1 row-start-1 h-full max-h-40 min-h-0 resize-none overflow-y-auto border-0 bg-transparent px-3 py-3 text-base text-violet-50 shadow-none placeholder:text-violet-200/45 focus-visible:ring-0"
-          disabled={isSending}
-        />
-      </div>
-      <div className={cn("flex items-center gap-3 px-2 pb-1", error ? "justify-between" : "justify-end")}>
-        {error ? <p className="min-w-0 truncate text-xs text-rose-300">{error}</p> : null}
-        {!isSearchMode ? (
-          <Button
-            className="h-10 w-10 rounded-lg"
-            onClick={onOpenAttachmentPicker}
-            size="icon"
-            variant="secondary"
-            disabled={attachmentButtonDisabled}
-            aria-label="Attach files"
-          >
-            <Paperclip className="h-4 w-4" />
-          </Button>
-        ) : null}
-        <Button
-          className="h-10 w-10 rounded-lg"
-          onClick={submit}
-          size="icon"
-          disabled={isSending || (!hasDraft && (isSearchMode || pendingAttachmentCount === 0))}
-          aria-label={isSearchMode ? "Search" : "Send message"}
-        >
-          {isSearchMode ? <Search className="h-4 w-4" /> : <SendHorizontal className="h-4 w-4" />}
-        </Button>
-      </div>
-    </>
-  );
-}
@@ -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 }} />;
 }
@@ -131,45 +131,6 @@ textarea {
  }
 }

-@media (horizontal-viewport-segments: 2) {
-  .app-safe-frame {
-    padding:
-      max(0.5rem, var(--safe-area-top))
-      max(0.5rem, var(--safe-area-right))
-      max(0.5rem, var(--safe-area-bottom))
-      max(0.5rem, var(--safe-area-left));
-  }
-
-  .workspace-shell {
-    display: grid;
-    grid-template-columns:
-      calc(env(viewport-segment-width 0 0) - max(0.5rem, var(--safe-area-left)))
-      calc(env(viewport-segment-width 1 0) - max(0.5rem, var(--safe-area-right)));
-    column-gap: calc(env(viewport-segment-left 1 0) - env(viewport-segment-right 0 0));
-  }
-
-  .workspace-sidebar {
-    position: static;
-    width: 100%;
-    max-width: none;
-    transform: none;
-    border-width: 1px;
-    border-radius: 1rem;
-  }
-
-  .workspace-content {
-    min-width: 0;
-    border-width: 1px;
-    border-radius: 1rem;
-    touch-action: auto;
-  }
-
-  .workspace-sidebar-backdrop,
-  .workspace-sidebar-trigger {
-    display: none;
-  }
-}
-
 .glass-panel {
  background:
    linear-gradient(180deg, hsl(243 42% 12% / 0.88), hsl(236 48% 5% / 0.92)),
@@ -325,14 +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;
@@ -431,8 +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;
@@ -444,26 +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 }) {
@@ -1,24 +0,0 @@
-import type { Provider } from "./api";
-
-type PersistedChatModel = {
-  lastUsedProvider: Provider | null;
-  lastUsedModel: string | null;
-};
-
-export type ChatModelSelection = {
-  provider: Provider;
-  model: string;
-};
-
-export function getChatModelSelection(chat: PersistedChatModel | null): ChatModelSelection | null {
-  if (!chat?.lastUsedProvider || !chat.lastUsedModel?.trim()) return null;
-  return {
-    provider: chat.lastUsedProvider,
-    model: chat.lastUsedModel.trim(),
-  };
-}
-
-export function getChatModelSelectionSyncKey(chatId: string | null, selection: ChatModelSelection | null) {
-  if (!chatId || !selection) return null;
-  return JSON.stringify([chatId, selection.provider, selection.model]);
-}
@@ -1,31 +0,0 @@
-export type SidebarSelection = { kind: "chat" | "search"; id: string };
-
-type WorkspaceSelectionItem = { type: SidebarSelection["kind"]; id: string };
-
-type ResolveSidebarSelectionOptions = {
-  initialSelection?: SidebarSelection;
-  selectFallback?: boolean;
-};
-
-export function resolveSidebarSelectionAfterRefresh(
-  current: SidebarSelection | null,
-  workspaceItems: WorkspaceSelectionItem[],
-  { initialSelection, selectFallback = false }: ResolveSidebarSelectionOptions = {}
-): SidebarSelection | null {
-  const hasItem = (candidate: SidebarSelection | null | undefined) => {
-    if (!candidate) return false;
-    return workspaceItems.some((item) => item.type === candidate.kind && item.id === candidate.id);
-  };
-
-  if (hasItem(current)) {
-    return current;
-  }
-  if (hasItem(initialSelection)) {
-    return initialSelection ?? null;
-  }
-  if (!selectFallback) {
-    return null;
-  }
-  const first = workspaceItems[0];
-  return first ? { kind: first.type, id: first.id } : null;
-}
@@ -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);
+    });
  });
 }
@@ -1,49 +0,0 @@
-import assert from "node:assert/strict";
-import test from "node:test";
-import {
-  getChatModelSelection,
-  getChatModelSelectionSyncKey,
-} from "../src/lib/chat-model-selection.ts";
-
-test("chat model selections are normalized from persisted metadata", () => {
-  assert.deepEqual(
-    getChatModelSelection({
-      lastUsedProvider: "anthropic",
-      lastUsedModel: "  claude-sonnet-4-5  ",
-    }),
-    {
-      provider: "anthropic",
-      model: "claude-sonnet-4-5",
-    }
-  );
-});
-
-test("unrelated chat updates do not change the model synchronization key", () => {
-  const beforeSettingsSave = getChatModelSelection({
-    lastUsedProvider: "openai",
-    lastUsedModel: "gpt-4.1-mini",
-  });
-  const afterSettingsSave = getChatModelSelection({
-    lastUsedProvider: "openai",
-    lastUsedModel: "gpt-4.1-mini",
-  });
-
-  assert.equal(
-    getChatModelSelectionSyncKey("chat-1", beforeSettingsSave),
-    getChatModelSelectionSyncKey("chat-1", afterSettingsSave)
-  );
-});
-
-test("switching chats or persisted models changes the synchronization key", () => {
-  const original = { provider: "openai", model: "gpt-4.1-mini" };
-  const updated = { provider: "gemini", model: "gemini-3.5-flash" };
-
-  assert.notEqual(
-    getChatModelSelectionSyncKey("chat-1", original),
-    getChatModelSelectionSyncKey("chat-2", original)
-  );
-  assert.notEqual(
-    getChatModelSelectionSyncKey("chat-1", original),
-    getChatModelSelectionSyncKey("chat-1", updated)
-  );
-});
@@ -1,45 +0,0 @@
-import assert from "node:assert/strict";
-import test from "node:test";
-import { resolveSidebarSelectionAfterRefresh } from "../src/lib/sidebar-selection.ts";
-
-const workspaceItems = [
-  { type: "chat", id: "completed-chat" },
-  { type: "chat", id: "selected-chat" },
-  { type: "search", id: "selected-search" },
-];
-
-test("a collection refresh preserves the current thread selection", () => {
-  assert.deepEqual(
-    resolveSidebarSelectionAfterRefresh({ kind: "chat", id: "selected-chat" }, workspaceItems),
-    { kind: "chat", id: "selected-chat" }
-  );
-});
-
-test("an initial route selection cannot override a current thread selection", () => {
-  assert.deepEqual(
-    resolveSidebarSelectionAfterRefresh(
-      { kind: "search", id: "selected-search" },
-      workspaceItems,
-      { initialSelection: { kind: "chat", id: "completed-chat" }, selectFallback: true }
-    ),
-    { kind: "search", id: "selected-search" }
-  );
-});
-
-test("a collection refresh preserves an intentionally empty selection", () => {
-  assert.equal(resolveSidebarSelectionAfterRefresh(null, workspaceItems), null);
-});
-
-test("initial load can select the URL thread or fall back to the first item", () => {
-  assert.deepEqual(
-    resolveSidebarSelectionAfterRefresh(null, workspaceItems, {
-      initialSelection: { kind: "search", id: "selected-search" },
-      selectFallback: true,
-    }),
-    { kind: "search", id: "selected-search" }
-  );
-  assert.deepEqual(resolveSidebarSelectionAfterRefresh(null, workspaceItems, { selectFallback: true }), {
-    kind: "chat",
-    id: "completed-chat",
-  });
-});
@@ -1 +1 @@
-{"root":["./src/App.tsx","./src/main.tsx","./src/pwa.ts","./src/root-router.tsx","./src/vite-env.d.ts","./src/components/sybil-character.tsx","./src/components/auth/auth-screen.tsx","./src/components/chat/chat-attachment-list.tsx","./src/components/chat/chat-composer.tsx","./src/components/chat/chat-messages-panel.tsx","./src/components/markdown/markdown-content.tsx","./src/components/search/search-results-panel.tsx","./src/components/ui/button.tsx","./src/components/ui/input.tsx","./src/components/ui/scroll-area.tsx","./src/components/ui/separator.tsx","./src/components/ui/textarea.tsx","./src/hooks/use-session-auth.ts","./src/lib/api.ts","./src/lib/chat-model-selection.ts","./src/lib/sidebar-selection.ts","./src/lib/utils.ts","./src/pages/search-route-page.tsx"],"version":"5.9.3"}
+{"root":["./src/App.tsx","./src/main.tsx","./src/pwa.ts","./src/root-router.tsx","./src/vite-env.d.ts","./src/components/sybil-character.tsx","./src/components/auth/auth-screen.tsx","./src/components/chat/chat-attachment-list.tsx","./src/components/chat/chat-messages-panel.tsx","./src/components/markdown/markdown-content.tsx","./src/components/search/search-results-panel.tsx","./src/components/ui/button.tsx","./src/components/ui/input.tsx","./src/components/ui/scroll-area.tsx","./src/components/ui/separator.tsx","./src/components/ui/textarea.tsx","./src/hooks/use-session-auth.ts","./src/lib/api.ts","./src/lib/utils.ts","./src/pages/search-route-page.tsx"],"version":"5.9.3"}
Author	SHA1	Message	Date
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