adds gemini support

act_runner does not carry setup-ruby's PATH changes into later steps,
so without this the step runs the toolcache default Ruby (3.3.11) and
bundler cannot find the gems installed for 3.1.7.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.gitea/workflows/testflight-release.yml

@@ -1,187 +0,0 @@
-name: TestFlight Release
-
-on:
-  push:
-    tags:
-      - "release/v*.*.*"
-
-permissions:
-  contents: write
-
-jobs:
-  testflight:
-    runs-on: xcode
-
-    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: Import code signing certificates
-        uses: Apple-Actions/import-codesign-certs@v3
-        with:
-          p12-file-base64: ${{ secrets.APPSTORE_CERTIFICATES_FILE_BASE64 }}
-          p12-password: ${{ secrets.APPSTORE_CERTIFICATES_PASSWORD }}
-
-      - name: Create fastlane environment
-        working-directory: ios
-        env:
-          FASTLANE_USER: ${{ secrets.FASTLANE_USER }}
-          FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD: ${{ secrets.FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD }}
-        run: |
-          set -euo pipefail
-
-          : "${FASTLANE_USER:?FASTLANE_USER secret is required}"
-          : "${FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD:?FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD secret is required}"
-
-          {
-            printf 'FASTLANE_USER=%s\n' "${FASTLANE_USER}"
-            printf 'FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD=%s\n' "${FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD}"
-            printf 'FASTLANE_SKIP_UPDATE_CHECK=1\n'
-            printf 'FASTLANE_HIDE_CHANGELOG=1\n'
-          } > .env
-
-      - name: Build and upload to TestFlight
-        working-directory: ios
-        env:
-          FASTLANE_DONT_STORE_PASSWORD: "1"
-        run: |
-          set -euo pipefail
-
-          SYBIL_VERSION_TAG="${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}"

.gitea/workflows/testflight.yml

@@ -0,0 +1,44 @@
+name: TestFlight
+
+on:
+  workflow_dispatch:
+  push:
+    tags:
+      - "release/ios/v*"
+
+jobs:
+  testflight:
+    runs-on: macos-arm64
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: "3.1.7"
+          bundler-cache: true
+          working-directory: ios
+
+      - name: Install XcodeGen
+        run: command -v xcodegen >/dev/null 2>&1 || brew install xcodegen
+
+      - name: Upload to TestFlight
+        working-directory: ios
+        env:
+          APP_STORE_CONNECT_KEY_ID: ${{ secrets.APP_STORE_CONNECT_KEY_ID }}
+          APP_STORE_CONNECT_ISSUER_ID: ${{ secrets.APP_STORE_CONNECT_ISSUER_ID }}
+          APP_STORE_CONNECT_KEY_CONTENT: ${{ secrets.APP_STORE_CONNECT_KEY_CONTENT }}
+          MATCH_PASSWORD: ${{ secrets.MATCH_PASSWORD }}
+          MATCH_GIT_URL: ${{ secrets.MATCH_GIT_URL }}
+          MATCH_GIT_BASIC_AUTHORIZATION: ${{ secrets.MATCH_GIT_BASIC_AUTHORIZATION }}
+          SYBIL_BUILD_NUMBER: ${{ github.run_number }}
+          FASTLANE_SKIP_UPDATE_CHECK: "1"
+          FASTLANE_XCODEBUILD_SETTINGS_TIMEOUT: "120"
+        # act_runner does not propagate setup-ruby's PATH changes into later
+        # steps, so put the selected Ruby back on PATH or `bundle` resolves to
+        # the toolcache default and misses the gems installed above.
+        run: |
+          export PATH="/Users/runner/hostedtoolcache/Ruby/3.1.7/arm64/bin:${PATH}"
+          bundle exec fastlane ios beta

.gitignore

@@ -1,2 +1,3 @@
 .env
-
+ios/fastlane/README.md
+ios/fastlane/report.xml

docker-compose.example.yml

@@ -12,6 +12,7 @@ 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:-}

docs/api/rest.md

@@ -34,11 +34,13 @@ 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.
 
@@ -56,7 +58,7 @@ Chat upload limits:
 ```
 
 Behavior notes:
-- Lists Sybil-managed chat tools that can be enabled for `openai`, `anthropic`, and `xai` chat completions.
+- Lists Sybil-managed chat tools that can be enabled for `openai`, `anthropic`, `xai`, and `gemini` chat completions.
 - Optional tools such as `codex_exec` and `shell_exec` appear only when enabled by server environment configuration.
 
 ## Active Runs
@@ -128,7 +130,7 @@ Behavior notes:
 ```json
 {
   "title": "optional title",
-  "provider": "optional openai|anthropic|xai|hermes-agent",
+  "provider": "optional openai|anthropic|xai|gemini|hermes-agent",
   "model": "optional model id",
   "additionalSystemPrompt": "optional stored system prompt",
   "enabledTools": ["web_search", "fetch_url"],
@@ -234,7 +236,7 @@ Notes:
 ```json
 {
   "chatId": "optional-chat-id",
-  "provider": "openai|anthropic|xai|hermes-agent",
+  "provider": "openai|anthropic|xai|gemini|hermes-agent",
   "model": "string",
   "messages": [
     {
@@ -285,6 +287,7 @@ 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`.
@@ -293,12 +296,14 @@ 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`, 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.
+- 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, 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.
@@ -416,9 +421,9 @@ Behavior notes:
   "updatedAt": "...",
   "starred": false,
   "starredAt": null,
-  "initiatedProvider": "openai|anthropic|xai|hermes-agent|null",
+  "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
   "initiatedModel": "string|null",
-  "lastUsedProvider": "openai|anthropic|xai|hermes-agent|null",
+  "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
   "lastUsedModel": "string|null",
   "additionalSystemPrompt": null,
   "enabledTools": ["web_search", "fetch_url"]
@@ -468,9 +473,9 @@ Behavior notes:
   "updatedAt": "...",
   "starred": false,
   "starredAt": null,
-  "initiatedProvider": "openai|anthropic|xai|hermes-agent|null",
+  "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
   "initiatedModel": "string|null",
-  "lastUsedProvider": "openai|anthropic|xai|hermes-agent|null",
+  "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null",
   "lastUsedModel": "string|null",
   "additionalSystemPrompt": null,
   "enabledTools": ["web_search", "fetch_url"],

docs/api/streaming-chat.md

@@ -21,7 +21,7 @@ Authentication:
 {
   "chatId": "optional-chat-id",
   "persist": true,
-  "provider": "openai|anthropic|xai|hermes-agent",
+  "provider": "openai|anthropic|xai|gemini|hermes-agent",
   "model": "string",
   "messages": [
     {
@@ -64,6 +64,7 @@ Notes:
 - 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:
@@ -173,9 +174,11 @@ 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.
@@ -184,7 +187,7 @@ Terminal tool-call event:
 - `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`):
+Tool-enabled streaming notes (`openai`/`anthropic`/`xai`/`gemini`):
 - 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.

ios/.env.example

@@ -1,14 +1,18 @@
 FASTLANE_APP_IDENTIFIER=net.buzzert.sybil2
 FASTLANE_TEAM_ID=DQQH5H6GBD
-FASTLANE_USER=you@example.com
-FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD=xxxx-xxxx-xxxx-xxxx
 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=6B74B268C4761720FB2051D01D8BB3E47B55D9F5
+SYBIL_EXPORT_SIGNING_CERTIFICATE=Apple Distribution
+SYBIL_SIGNING_CERTIFICATE_ID=
+SYBIL_SIGNING_KEYCHAIN=
 
-# Optional App Store Connect API key settings for non-interactive upload and
-# TestFlight build-number lookup.
+# 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=

ios/AGENTS.md

@@ -21,6 +21,12 @@ 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:
@@ -51,4 +57,5 @@ 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`

ios/Apps/Sybil/project.yml

@@ -24,7 +24,7 @@ targets:
         GENERATE_INFOPLIST_FILE: YES
         INFOPLIST_FILE: Apps/Sybil/Info.plist
         ASSETCATALOG_COMPILER_APPICON_NAME: AppIcon
-        MARKETING_VERSION: "1.10"
+        MARKETING_VERSION: "1.13.2"
         CURRENT_PROJECT_VERSION: 11
         INFOPLIST_KEY_CFBundleDisplayName: Sybil
         INFOPLIST_KEY_ITSAppUsesNonExemptEncryption: NO
@@ -32,6 +32,12 @@ targets:
         INFOPLIST_KEY_UILaunchScreen_Generation: YES
         INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone: UIInterfaceOrientationPortrait
         INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad: UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight
+      configs:
+        Release:
+          CODE_SIGN_STYLE: Manual
+          CODE_SIGN_IDENTITY: Apple Distribution
+          "CODE_SIGN_IDENTITY[sdk=iphoneos*]": Apple Distribution
+          PROVISIONING_PROFILE_SPECIFIER: Sybil AppStore CI
 
 schemes:
   Sybil:

ios/Gemfile

@@ -1,3 +1,3 @@
 source "https://rubygems.org"
 
-gem "fastlane", "~> 2.227"
+gem "fastlane"

ios/Gemfile.lock

@@ -225,7 +225,7 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  fastlane (~> 2.227)
+  fastlane
 
 BUNDLED WITH
    2.5.23

ios/Packages/Sybil/Sources/Sybil/SybilChatTranscriptView.swift

@@ -58,7 +58,8 @@ struct SybilChatTranscriptView: View {
                         .frame(height: 18 + bottomContentInset)
                         .id(bottomAnchorID)
                 }
-                .frame(maxWidth: .infinity, alignment: .leading)
+                .frame(maxWidth: SybilLayout.webContentMaxWidth, alignment: .leading)
+                .frame(maxWidth: .infinity, alignment: .center)
                 .padding(.horizontal, 14)
                 .padding(.top, 18 + topContentInset)
             }

ios/Packages/Sybil/Sources/Sybil/SybilModels.swift

@@ -4,6 +4,7 @@ public enum Provider: String, Codable, CaseIterable, Hashable, Sendable {
     case openai
     case anthropic
     case xai
+    case gemini
     case hermesAgent = "hermes-agent"
 
     public var displayName: String {
@@ -11,6 +12,7 @@ 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"
         }
     }

ios/Packages/Sybil/Sources/Sybil/SybilSearchResultsView.swift

@@ -98,7 +98,8 @@ struct SybilSearchResultsView: View {
                         .foregroundStyle(SybilTheme.danger)
                 }
             }
-            .frame(maxWidth: .infinity, alignment: .leading)
+            .frame(maxWidth: SybilLayout.webContentMaxWidth, alignment: .leading)
+            .frame(maxWidth: .infinity, alignment: .center)
             .padding(.horizontal, 14)
             .padding(.top, 20 + topContentInset)
             .padding(.bottom, 20 + bottomContentInset)

ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift

@@ -11,11 +11,13 @@ 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"
     }
 
@@ -44,6 +46,7 @@ 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
@@ -54,6 +57,7 @@ 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"
         ]
     }
@@ -72,12 +76,14 @@ 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)
     }
 

ios/Packages/Sybil/Sources/Sybil/SybilTheme.swift

@@ -64,6 +64,10 @@ 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)

ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift

@@ -160,6 +160,7 @@ 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"]
     ]
 

ios/fastlane/Appfile

@@ -1,9 +0,0 @@
-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?

ios/fastlane/CI.md

@@ -1,32 +0,0 @@
-# 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 with
-`Apple-Actions/import-codesign-certs`, builds and uploads the app with fastlane,
-then creates or updates the matching Gitea release with the generated IPA as an
-asset.
-
-Required repository secrets:
-
-```text
-APPSTORE_CERTIFICATES_FILE_BASE64
-APPSTORE_CERTIFICATES_PASSWORD
-FASTLANE_USER
-FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD
-```
-
-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.

ios/fastlane/Fastfile

@@ -1,177 +1,164 @@
-require "dotenv"
-require "open3"
 require "shellwords"
-require "yaml"
-
-Dotenv.load(File.expand_path("../.env", __dir__))
 
 default_platform(:ios)
 
-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")
+APP_IDENTIFIER = "net.buzzert.sybil2"
+SCHEME = "Sybil"
+TEAM_ID = "DQQH5H6GBD"
+PROFILE_NAME = "Sybil AppStore CI"
+CI_KEYCHAIN_NAME = "sybil_ci_keychain"
+CI_KEYCHAIN_PASSWORD = "sybil-ci-keychain-password"
+CI_KEYCHAIN_DB_PATH = File.expand_path("~/Library/Keychains/#{CI_KEYCHAIN_NAME}-db")
 IOS_ROOT = File.expand_path("..", __dir__)
 PROJECT_FILE = File.join(IOS_ROOT, "Sybil.xcodeproj")
 PROJECT_SPEC = File.join(IOS_ROOT, "project.yml")
-APP_SPEC = File.join(IOS_ROOT, "Apps/Sybil/project.yml")
-SCHEME = "Sybil"
-TARGET = "SybilApp"
+APP_PROJECT_SPEC = File.join(IOS_ROOT, "Apps/Sybil/project.yml")
 
 def present?(value)
   !value.to_s.strip.empty?
 end
 
-def capture(command)
-  stdout, stderr, status = Open3.capture3(command)
-  return stdout.strip if status.success?
-
-  UI.user_error!("Command failed: #{command}\n#{stderr.strip}")
-end
-
-def app_project_settings
-  YAML.safe_load(File.read(APP_SPEC)).fetch("targets").fetch(TARGET).fetch("settings").fetch("base")
-end
-
-def local_marketing_version
-  app_project_settings.fetch("MARKETING_VERSION").to_s
-end
-
-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
+def ci?
+  present?(ENV["CI"])
 end
 
 def release_version
   tag = ENV["SYBIL_VERSION_TAG"]
-  tag = capture("git describe --tags --abbrev=0") unless present?(tag)
-  normalize_version_tag(tag)
-end
+  tag = ENV["GITHUB_REF_NAME"] if !present?(tag)
+  tag = ENV["GITHUB_REF"].to_s.sub(%r{\Arefs/tags/}, "") if !present?(tag)
+  tag = sh("git describe --tags --abbrev=0").strip if !present?(tag)
+  match = tag.to_s.match(%r{\Arelease/ios/v(\d+\.\d+\.\d+)\z})
 
-def xcode_build_setting(key, value)
-  "#{key}=#{value.to_s.shellescape}"
-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"]
-  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"
-    }
+  unless match
+    UI.user_error!("Release tag must look like release/ios/v1.2.3; got #{tag.inspect}")
   end
+
+  match[1]
+end
+
+# App Store Connect requires CFBundleVersion to be unique and strictly
+# increasing app-wide (not just per marketing version), so we derive it from
+# the monotonic CI run number rather than querying TestFlight (that query can
+# lag behind builds still processing and hand back a colliding value).
+def build_number
+  value = present?(ENV["SYBIL_BUILD_NUMBER"]) ? ENV["SYBIL_BUILD_NUMBER"] : ENV["GITHUB_RUN_NUMBER"]
+
+  unless value.to_s.match?(/\A\d+\z/)
+    UI.user_error!("Build number must come from SYBIL_BUILD_NUMBER/GITHUB_RUN_NUMBER; got #{value.inspect}")
+  end
+
+  value.to_i
+end
+
+def stamp_marketing_version(version)
+  contents = File.read(APP_PROJECT_SPEC)
+  updated = contents.sub(/^(\s*MARKETING_VERSION:\s*).*/, "\\1\"#{version}\"")
+
+  if updated == contents
+    UI.user_error!("Could not find MARKETING_VERSION in #{APP_PROJECT_SPEC}")
+  end
+
+  File.write(APP_PROJECT_SPEC, updated)
 end
 
 platform :ios do
-  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}")
+  private_lane :app_store_api_key do
+    app_store_connect_api_key(
+      key_id: ENV.fetch("APP_STORE_CONNECT_KEY_ID"),
+      issuer_id: ENV.fetch("APP_STORE_CONNECT_ISSUER_ID"),
+      key_content: ENV.fetch("APP_STORE_CONNECT_KEY_CONTENT"),
+      is_key_content_base64: true
+    )
   end
 
-  desc "Build Sybil and upload it to TestFlight"
+  # CI signs headlessly, so match needs a fresh unlocked keychain to import
+  # into. codesign resolves identities through the user keychain *search list*
+  # (first match wins; the --keychain flag does not restrict the lookup), and
+  # other projects' keychains on this runner hold the same identity but are
+  # usually locked — so ours must come first. delete_keychain in the beta
+  # lane's ensure removes both the keychain and its search-list entry, which
+  # also keeps our (later locked) copy from shadowing those other projects.
+  private_lane :prepare_ci_keychain do
+    next unless ci?
+
+    delete_keychain(name: CI_KEYCHAIN_NAME) if File.file?(CI_KEYCHAIN_DB_PATH)
+    create_keychain(
+      name: CI_KEYCHAIN_NAME,
+      password: CI_KEYCHAIN_PASSWORD,
+      unlock: true,
+      timeout: 3600,
+      add_to_search_list: false
+    )
+
+    others = sh("security list-keychains -d user", log: false)
+      .scan(/"([^"]+)"/)
+      .flatten
+      .reject { |path| path.include?(CI_KEYCHAIN_NAME) }
+    sh("security list-keychains -d user -s #{([CI_KEYCHAIN_DB_PATH] + others).shelljoin}")
+
+    ENV["MATCH_KEYCHAIN_NAME"] = CI_KEYCHAIN_NAME
+    ENV["MATCH_KEYCHAIN_PASSWORD"] = CI_KEYCHAIN_PASSWORD
+  end
+
+  private_lane :sync_signing do |options|
+    match(
+      type: "appstore",
+      readonly: options.fetch(:readonly),
+      app_identifier: APP_IDENTIFIER,
+      team_id: TEAM_ID,
+      profile_name: PROFILE_NAME,
+      git_url: ENV.fetch("MATCH_GIT_URL"),
+      git_branch: "master",
+      git_full_name: "Sybil Release Bot",
+      git_user_email: "james.magahern@me.com",
+      api_key: options.fetch(:api_key)
+    )
+  end
+
+  desc "Create or update match signing assets"
+  lane :setup_signing do
+    sync_signing(api_key: app_store_api_key, readonly: false)
+  end
+
+  desc "Build and upload to TestFlight"
   lane :beta do
+    prepare_ci_keychain
+
+    api_key = app_store_api_key
+
     version = release_version
-    build_number = ENV["SYBIL_BUILD_NUMBER"].to_s
-    api_key = nil
+    stamp_marketing_version(version)
+    sh("xcodegen", "--spec", PROJECT_SPEC)
 
-    if app_store_connect_key_options
-      api_key = app_store_connect_api_key(app_store_connect_key_options)
-    end
+    increment_version_number(version_number: version, xcodeproj: PROJECT_FILE)
+    increment_build_number(build_number: build_number, xcodeproj: PROJECT_FILE)
 
-    unless present?(build_number)
-      build_number = (local_build_number + 1).to_s
+    sync_signing(api_key: api_key, readonly: true)
 
-      if api_key
-        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
-    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}")
-
-    xcode_args = [
-      "-allowProvisioningUpdates",
-      xcode_build_setting("MARKETING_VERSION", version),
-      xcode_build_setting("CURRENT_PROJECT_VERSION", build_number)
-    ].join(" ")
-
-    ipa_path = build_app(
+    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_xcargs: "-allowProvisioningUpdates",
+      xcargs: [
+        "DEVELOPMENT_TEAM=#{TEAM_ID.shellescape}",
+        "CODE_SIGN_STYLE=Manual",
+        "CODE_SIGN_IDENTITY=Apple\\ Distribution",
+        "PROVISIONING_PROFILE_SPECIFIER=#{PROFILE_NAME.shellescape}"
+      ].join(" "),
       export_options: {
-        method: "app-store-connect",
-        destination: "export",
-        signingStyle: "automatic",
+        signingStyle: "manual",
         teamID: TEAM_ID,
-        manageAppVersionAndBuildNumber: false,
-        uploadSymbols: true,
-        stripSwiftSymbols: true
+        provisioningProfiles: {
+          APP_IDENTIFIER => PROFILE_NAME
+        }
       }
     )
 
-    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)
-
-    password = ENV["FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD"]
-    UI.user_error!("FASTLANE_USER is required for altool upload") unless present?(ENV["FASTLANE_USER"])
-    UI.user_error!("FASTLANE_APPLE_APPLICATION_SPECIFIC_PASSWORD is required for altool upload") unless present?(password)
-    UI.user_error!("SYBIL_APP_STORE_APPLE_ID is required for altool upload") unless present?(APP_STORE_APPLE_ID)
-    UI.user_error!("SYBIL_PROVIDER_PUBLIC_ID is required for altool upload") unless present?(PROVIDER_PUBLIC_ID)
-
-    ENV["ITMS_TRANSPORTER_PASSWORD"] = password
-    sh([
-      "xcrun altool",
-      "--upload-package #{ipa_path.shellescape}",
-      "--platform ios",
-      "--apple-id #{APP_STORE_APPLE_ID.shellescape}",
-      "--bundle-id #{APP_IDENTIFIER.shellescape}",
-      "--bundle-version #{build_number.shellescape}",
-      "--bundle-short-version-string #{version.shellescape}",
-      "--provider-public-id #{PROVIDER_PUBLIC_ID.shellescape}",
-      "--username #{ENV.fetch("FASTLANE_USER").shellescape}",
-      "--password @env:ITMS_TRANSPORTER_PASSWORD",
-      "--show-progress"
-    ].join(" "))
+    upload_to_testflight(
+      api_key: api_key,
+      skip_waiting_for_build_processing: true
+    )
+  ensure
+    delete_keychain(name: CI_KEYCHAIN_NAME) if ci? && File.file?(CI_KEYCHAIN_DB_PATH)
   end
 end

ios/fastlane/README.md

@@ -1,40 +0,0 @@
-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 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).

server/README.md

@@ -1,7 +1,7 @@
 # Sybil Server
 
 Backend API for:
-- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Hermes Agent)
+- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini / Hermes Agent)
 - Personal chat database (chats/messages + LLM call log)
 
 ## Stack
@@ -43,6 +43,7 @@ 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`)
@@ -50,7 +51,7 @@ If `ADMIN_TOKEN` is not set, the server runs in open mode (dev).
 - `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 OpenAI/xAI)
+- `CHAT_CODEX_TOOL_ENABLED` (`false` by default; enables the `codex_exec` chat tool for managed-tool providers)
 - `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)
@@ -58,7 +59,7 @@ 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 OpenAI/xAI on the same devbox)
+- `CHAT_SHELL_TOOL_ENABLED` (`false` by default; enables the `shell_exec` chat tool for managed-tool providers on the same devbox)
 - `CHAT_SHELL_EXEC_TIMEOUT_MS` (`120000` by default)
 
 ## API

server/prisma/schema.prisma

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

server/src/env.ts

@@ -66,6 +66,7 @@ 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,

server/src/llm/protocols/gemini-api.ts

@@ -0,0 +1,501 @@
+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,
+    },
+  };
+}

server/src/llm/protocols/messages-api.ts

@@ -28,6 +28,45 @@ 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) => {
@@ -160,11 +199,12 @@ 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: params.maxTokens ?? 1024,
+      max_tokens: maxTokens,
       temperature: params.temperature,
       messages: buildBaseMessages(params),
     } as any);
@@ -192,7 +232,7 @@ 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: params.maxTokens ?? 1024,
+      max_tokens: maxTokens,
       temperature: params.temperature,
       messages: conversation,
       tools: toTools(enabledTools),
@@ -248,6 +288,7 @@ 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 };
@@ -259,7 +300,7 @@ export async function* streamWithMessagesApi(params: ToolAwareCompletionParams):
     const stream = await params.client.messages.create({
       model: params.model,
       system: buildTopLevelSystemPrompt(params.messages, params.userLocation),
-      max_tokens: params.maxTokens ?? 1024,
+      max_tokens: maxTokens,
       temperature: params.temperature,
       messages: buildBaseMessages(params),
       stream: true,
@@ -315,7 +356,7 @@ 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: params.maxTokens ?? 1024,
+      max_tokens: maxTokens,
       temperature: params.temperature,
       messages: conversation,
       tools: toTools(enabledTools),

server/src/llm/provider-adapters.ts

@@ -5,10 +5,11 @@ 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, hermesAgentClient, isHermesAgentConfigured, openaiClient, xaiClient } from "./providers.js";
+import { anthropicClient, geminiClient, hermesAgentClient, isHermesAgentConfigured, openaiClient, xaiClient } from "./providers.js";
 import type { ChatMessage, Provider } from "./types.js";
 
 type ProviderAdapterParams = {
@@ -27,7 +28,7 @@ export type ProviderChatAdapter = {
   stream(params: ProviderAdapterParams): AsyncGenerator<ToolAwareStreamingEvent>;
 };
 
-type ChatProtocolId = "chat-completions" | "messages" | "responses";
+type ChatProtocolId = "chat-completions" | "gemini" | "messages" | "responses";
 
 type ChatProtocol = {
   id: ChatProtocolId;
@@ -39,6 +40,7 @@ type ModelCatalogSpec = {
   enabled?: () => boolean;
   fetchModels(client: any): Promise<string[]>;
   fallbackModels?: () => string[];
+  sortModels?: (models: string[]) => string[];
 };
 
 type ProviderBackendSpec = {
@@ -61,6 +63,12 @@ const messagesProtocol: ChatProtocol = {
   stream: streamWithMessagesApi,
 };
 
+const geminiProtocol: ChatProtocol = {
+  id: "gemini",
+  complete: completeWithGeminiApi,
+  stream: streamWithGeminiApi,
+};
+
 const responsesProtocol: ChatProtocol = {
   id: "responses",
   complete: completeWithResponsesApi,
@@ -77,6 +85,10 @@ 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;
@@ -86,6 +98,37 @@ 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 ${response.status}.`);
+  }
+  return body;
+}
+
 function withClient(params: ProviderAdapterParams, client: any, enabledTools?: string[]): ToolAwareCompletionParams {
   return {
     client,
@@ -160,6 +203,29 @@ const backendSpecs: Record<Provider, ProviderBackendSpec> = {
       },
     },
   },
+  gemini: {
+    createClient: geminiClient,
+    plainProtocol: geminiProtocol,
+    toolProtocol: geminiProtocol,
+    managedTools: true,
+    modelCatalog: {
+      async fetchModels(client) {
+        const url = new URL(`${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,
@@ -209,7 +275,8 @@ export function listModelCatalogProviders(): Provider[] {
 export async function fetchProviderCatalogModels(provider: Provider) {
   const spec = backendSpecs[provider].modelCatalog;
   if (!spec) return [];
-  return uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient()));
+  const models = uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient()));
+  return spec.sortModels ? spec.sortModels(models) : models;
 }
 
 export function getProviderCatalogFallbackModels(provider: Provider) {

server/src/llm/provider-ids.ts

@@ -6,6 +6,7 @@ const apiToPrismaProvider = {
   openai: "openai",
   anthropic: "anthropic",
   xai: "xai",
+  gemini: "gemini",
   "hermes-agent": "hermes_agent",
 } as const satisfies Record<Provider, PrismaProvider>;
 
@@ -13,6 +14,7 @@ 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>;

server/src/llm/providers.ts

@@ -1,5 +1,5 @@
-import OpenAI from "openai";
 import Anthropic from "@anthropic-ai/sdk";
+import OpenAI from "openai";
 import { env } from "../env.js";
 
 export function openaiClient() {
@@ -13,6 +13,14 @@ 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);
 }

server/src/llm/types.ts

@@ -1,4 +1,4 @@
-export const PROVIDERS = ["openai", "anthropic", "xai", "hermes-agent"] as const;
+export const PROVIDERS = ["openai", "anthropic", "xai", "gemini", "hermes-agent"] as const;
 
 export type Provider = (typeof PROVIDERS)[number];
 

server/src/routes.ts

@@ -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", "hermes-agent"]);
+const ProviderSchema = z.enum(["openai", "anthropic", "xai", "gemini", "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));
 

server/tests/chat-tools-streaming.test.ts

@@ -140,6 +140,94 @@ 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 }> = [];

server/tests/provider-adapters.test.ts

@@ -27,6 +27,12 @@ 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",

server/tests/provider-ids.test.ts

@@ -5,8 +5,10 @@ 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.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "xai" }), {
+  assert.equal(toPrismaProvider("gemini"), "gemini");
+  assert.equal(fromPrismaProvider("gemini"), "gemini");
+  assert.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "gemini" }), {
     initiatedProvider: "hermes-agent",
-    lastUsedProvider: "xai",
+    lastUsedProvider: "gemini",
   });
 });

tui/src/config.ts

@@ -1,6 +1,6 @@
 import type { Provider } from "./types.js";
 
-const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "hermes-agent"];
+const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini", "hermes-agent"];
 
 function normalizeBaseUrl(value: string) {
   const trimmed = value.trim();

tui/src/index.ts

@@ -42,12 +42,13 @@ type ToolLogMetadata = {
   resultPreview?: string | null;
 };
 
-const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai"];
+const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"];
 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"],
 };
 
@@ -55,6 +56,7 @@ 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) {
@@ -79,6 +81,7 @@ 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 "";
 }
@@ -266,6 +269,7 @@ async function main() {
     openai: null,
     anthropic: null,
     xai: null,
+    gemini: null,
     "hermes-agent": null,
   };
   let model: string = config.defaultModel ?? pickProviderModel(getModelOptions(modelCatalog, provider), null);

tui/src/types.ts

@@ -1,4 +1,4 @@
-export type Provider = "openai" | "anthropic" | "xai" | "hermes-agent";
+export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent";
 
 export type ProviderModelInfo = {
   models: string[];

web/src/App.tsx

@@ -123,6 +123,7 @@ 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"],
 };
 
@@ -130,9 +131,10 @@ 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 },
 };
 
-const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai"];
+const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"];
 const ALL_PROVIDERS: Provider[] = [...BASE_PROVIDERS, "hermes-agent"];
 
 const MODEL_PREFERENCES_STORAGE_KEY = "sybil:modelPreferencesByProvider";
@@ -149,6 +151,7 @@ const EMPTY_MODEL_PREFERENCES: ProviderModelPreferences = {
   openai: null,
   anthropic: null,
   xai: null,
+  gemini: null,
   "hermes-agent": null,
 };
 const EMPTY_ACTIVE_RUNS: ActiveRunsState = {
@@ -345,6 +348,7 @@ function loadStoredModelPreferences() {
       openai: typeof parsed.openai === "string" && parsed.openai.trim() ? parsed.openai.trim() : null,
       anthropic: typeof parsed.anthropic === "string" && parsed.anthropic.trim() ? parsed.anthropic.trim() : null,
       xai: typeof parsed.xai === "string" && parsed.xai.trim() ? parsed.xai.trim() : null,
+      gemini: typeof parsed.gemini === "string" && parsed.gemini.trim() ? parsed.gemini.trim() : null,
       "hermes-agent":
         typeof parsed["hermes-agent"] === "string" && parsed["hermes-agent"].trim() ? parsed["hermes-agent"].trim() : null,
     };
@@ -354,7 +358,9 @@ function loadStoredModelPreferences() {
 }
 
 function normalizeStoredProvider(value: unknown): Provider {
-  return value === "anthropic" || value === "xai" || value === "openai" || value === "hermes-agent" ? value : "openai";
+  return value === "anthropic" || value === "xai" || value === "gemini" || value === "openai" || value === "hermes-agent"
+    ? value
+    : "openai";
 }
 
 function normalizeStoredModelPreferences(value: unknown): ProviderModelPreferences {
@@ -364,6 +370,7 @@ function normalizeStoredModelPreferences(value: unknown): ProviderModelPreferenc
       openai: typeof parsed.openai === "string" && parsed.openai.trim() ? parsed.openai.trim() : null,
       anthropic: typeof parsed.anthropic === "string" && parsed.anthropic.trim() ? parsed.anthropic.trim() : null,
       xai: typeof parsed.xai === "string" && parsed.xai.trim() ? parsed.xai.trim() : null,
+      gemini: typeof parsed.gemini === "string" && parsed.gemini.trim() ? parsed.gemini.trim() : null,
       "hermes-agent":
         typeof parsed["hermes-agent"] === "string" && parsed["hermes-agent"].trim() ? parsed["hermes-agent"].trim() : null,
     };
@@ -395,6 +402,7 @@ 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 "";
 }

web/src/index.css

@@ -286,6 +286,14 @@ 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;
@@ -384,7 +392,8 @@ textarea {
 
 .md-content ul,
 .md-content ol {
-  margin-top: 0.65rem;
+  margin-top: 0.85rem;
+  margin-bottom: 0.85rem;
   margin-left: 0;
   padding-left: 0;
   list-style: none;
@@ -396,6 +405,26 @@ 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;
 }

web/src/lib/api.ts

@@ -149,7 +149,7 @@ export type CompletionRequestMessage = {
   attachments?: ChatAttachment[];
 };
 
-export type Provider = "openai" | "anthropic" | "xai" | "hermes-agent";
+export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent";
 
 export type ProviderModelInfo = {
   models: string[];