> ## Documentation Index
> Fetch the complete documentation index at: https://sitegpt.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# August 2026

> Updates and improvements for August 2026

## August 2026

### New features

<AccordionGroup>
  <Accordion title="Human take-over and closed conversations" icon="user-headset">
    Two new controls on every conversation in Chat History. **Take over the
    chat** silences the AI while you hold the conversation: the visitor's
    messages still land in the transcript, the visitor cannot switch back
    to AI, and only **Release to AI** hands it back. **Mark as Resolved**
    closes a conversation: the widget stops accepting new visitor
    messages, API sends return `409 CONVERSATION_CLOSED`, and only your
    team can reopen it. Both rules hold across the widget, all channel
    integrations, and the v0 and v2 APIs.
  </Accordion>

  <Accordion title="Sign in with AgentID — accounts for AI agents" icon="robot">
    AI agents can now create and use full SiteGPT accounts with their own
    verified identity. SiteGPT is an [AgentID](https://www.agentid.com)
    relying party: an agent with an AgentMail inbox starts at
    `https://sitegpt.ai/auth/agentid`, approves the request by signing a
    challenge with its registered key, and lands in the dashboard as a
    normal account under its verified `@agentmail.to` address — the same
    account a person would get, with the same API tokens, chatbots, and
    billing. The login page offers the flow, and agents discover it
    programmatically through the `agent_auth.identity_assertion` block in
    the [OAuth discovery
    metadata](https://sitegpt.ai/.well-known/oauth-authorization-server)
    and [auth.md](https://sitegpt.ai/auth.md). See
    [use SiteGPT with AI agents](/docs/cli/use-with-ai-agents#sign-in-with-agentid).
  </Accordion>

  <Accordion title="Agent-mode views: ?mode=agent" icon="file-code">
    Marketing pages answer the emerging `?mode=agent` convention: request
    any sitegpt.ai marketing page with `?mode=agent` as the only query
    parameter and it redirects to the page's markdown twin — the same
    machine view the `.md` suffix serves. Pages whose content depends on
    other query parameters keep serving HTML so agents never receive a
    default-variant markdown page labeled as something else.
  </Accordion>

  <Accordion title="MCP server: 17 tools and inline app views" icon="window-restore">
    The [SiteGPT MCP server](/docs/cli/mcp-server) grew from three tools to
    seventeen. Alongside `search`, `execute_read`, and `execute_write` —
    which still reach the whole API — purpose-built tools now cover chatting
    with a chatbot, onboarding status, widget appearance (read and update),
    conversation inboxes and transcripts, analytics, leads, waiting
    escalations, and knowledge sources (list, connect, authorize, and file
    upload). On AI apps that support MCP Apps, these tools render as eight
    live views directly in the conversation — the actual chat widget, an
    analytics card, a leads browser, and more — and the same views ship in
    the OpenAI Apps format for hosts that use that dialect. Anonymous
    clients can complete the handshake and list every tool before
    authorizing; every tool call still requires the OAuth grant. See
    [what the tools cover](/docs/cli/mcp-server#what-claude-can-do).
  </Accordion>

  <Accordion title="Markdown twins on every page — and a docs MCP server" icon="markdown">
    Every public sitegpt.ai page now serves a markdown twin for AI agents:
    append `.md` to the URL (`https://sitegpt.ai/pricing.md`; the homepage
    is `/index.md`), or request the page with `Accept: text/markdown` —
    docs pages included. [llms.txt](https://sitegpt.ai/llms.txt) states the
    convention and links the machine-readable entry points, and a dedicated
    docs MCP server at `https://sitegpt.ai/docs/mcp` gives agents search
    over this documentation with no authentication. See
    [machine-readable surfaces for agents](/docs/cli/use-with-ai-agents#machine-readable-surfaces-for-agents).
  </Accordion>

  <Accordion title="Engagement analytics through the API — widget opens included" icon="chart-line">
    The dashboard's daily engagement series is now readable by your own
    tools: `GET /api/v2/chatbots/{chatbotId}/analytics` returns widget
    opens, messages, conversations started, unique visitors, escalations,
    leads, and unanswered turns per UTC day, with totals and a
    prior-period comparison (default: the trailing 30 days). The same
    surface ships everywhere at once: `chatbots.analytics` in the
    [TypeScript](/docs/developers/sdk-typescript) and
    [Python](/docs/developers/sdk-python) SDKs, `Chatbots.Analytics` in
    [Go](/docs/developers/sdk-go), `sitegpt analytics` in the CLI, the
    `getChatbotAnalytics` action in the
    [Convex component](https://www.npmjs.com/package/@sitegpt/convex),
    and engagement totals on the MCP analytics card. The account needs
    analytics enabled (the API answers 403 `ANALYTICS_LOCKED` otherwise),
    and insight-derived counters appear only when insights is on. See
    [reading analytics through the API](/docs/navigating-your-chatbot/analytics#read-the-numbers-through-the-api).
  </Accordion>

  <Accordion title="Official API SDKs: TypeScript, Python, and Go" icon="cubes">
    Three official clients for the [API v2](/docs/api-reference/v2/getting-started)
    shipped this month: [`@sitegpt/sdk`](/docs/developers/sdk-typescript) on npm
    (typed end to end from the live OpenAPI document),
    [`sitegpt`](/docs/developers/sdk-python) on PyPI (standard library only,
    Python 3.9+), and
    [`github.com/sitegpt/sitegpt-go`](/docs/developers/sdk-go) (zero
    dependencies). All three share the same shape: convenience namespaces
    over chatbots, knowledge, conversations, leads, messages, and
    onboarding; structured errors carrying the API's `code`, `message`, and
    `hint`; confirm-guarded deletes; a generic request escape hatch for
    every other endpoint; and the public no-token onboarding bootstrap.
    Releases publish from CI through npm, PyPI, and Go module trusted
    publishing.
  </Accordion>

  <Accordion title="SiteGPT answers other agents over A2A" icon="handshake">
    SiteGPT now speaks the [A2A protocol](/docs/developers/a2a): an agent card at
    `https://sitegpt.ai/.well-known/agent-card.json` declares the SiteGPT
    Support Agent, and a JSON-RPC `message/send` endpoint at
    `https://sitegpt.ai/a2a` answers questions about SiteGPT — features,
    pricing, setup, APIs — from the same knowledge base as the sitegpt.ai
    support chatbot. No authentication required, and the reply's
    `contextId` continues the conversation. See the
    [A2A agent guide](/docs/developers/a2a).
  </Accordion>

  <Accordion title="MCP registry listings and a local launcher" icon="server">
    Both SiteGPT MCP servers are now in the
    [official MCP registry](https://registry.modelcontextprotocol.io/?search=io.github.sitegpt):
    `io.github.sitegpt/sitegpt` (the account server at
    `https://sitegpt.ai/mcp`) and `io.github.sitegpt/sitegpt-docs` (the
    docs server at `https://sitegpt.ai/docs/mcp`). For clients that prefer
    a local stdio server, `npx -y @sitegpt/mcp` launches the same
    implementation through the CLI. See
    [where to find the server](/docs/cli/mcp-server#where-to-find-the-server).
  </Accordion>

  <Accordion title="An API built for agents — honest errors, public health check, open MCP handshake" icon="robot">
    Unknown API paths now answer structured JSON errors with a hint instead of an HTML page, `GET /api/v2/health` confirms reachability with no token, and MCP clients can complete the `initialize` handshake and list tools before authorizing (every tool call still requires the OAuth grant). The OpenAPI document now types every response, documents every parameter, and reports the real success statuses. See [Getting started](/docs/api-reference/v2/getting-started).
  </Accordion>

  <Accordion title="Per-page conversation starters — the right prompt on the right page" icon="location-dot">
    Each conversation starter now has an optional **Show on pages**
    field: list paths like `/pricing` or `/docs/*` (the same grammar as
    Excluded Pages) and the starter appears only when the visitor is on
    a matching page — "What's included in the Pro plan?" on pricing,
    "How do I install the widget?" across the docs. Starters with the
    field empty keep showing everywhere, and channels without a page
    (Slack, WhatsApp, Messenger, Crisp) always show every starter. Also
    in the CLI (`--page`, `--clear-pages`) and API v2 (a `paths` array
    on each starter). See
    [showing a starter only on certain pages](/docs/features/conversation-starters#show-a-starter-only-on-certain-pages).
  </Accordion>

  <Accordion title="Excluded Pages — keep the chat off specific pages" icon="eye-slash">
    Embedding the widget site-wide but don't want it on checkout or
    pricing? A new **Excluded Pages** setting under **Settings →
    General** hides the floating chat button on the paths you name —
    `/pricing` for that page, `/checkout/*` for a whole section. It
    follows along in single-page apps, never loses the conversation,
    and leaves inline embeds and custom (`hideBubble`) launchers
    untouched. See
    [hiding the widget on specific pages](/docs/setup/integrating-with-your-website#hide-the-widget-on-specific-pages).
  </Accordion>

  <Accordion title="Timestamps in your chatbot's language" icon="language">
    The relative timestamps under each widget message ("just now",
    "2 minutes ago") were the one string **Language & Region** could not
    translate — they always rendered in English. A new **Timestamp
    language** dropdown at the top of Language & Region fixes that: pick
    from 47 languages and the widget writes them natively, with correct
    plurals — Danish shows "lige nu", Japanese shows「1 分前」. The
    localization settings API accepts the same setting as `locale`
    ([endpoint reference](/docs/api-reference/chatbot-settings/update-chatbot-settings--localization)).
    See
    [Language & Region](/docs/customize/language-and-region#set-the-timestamp-language).
  </Accordion>

  <Accordion title="Long answers start at the top" icon="arrow-down-to-line">
    When the chatbot streams an answer longer than the chat window, the
    view now stays at the **start** of the reply — the visitor's question
    holds at the top and the answer grows below it, so reading begins at
    the beginning instead of the end. Short answers behave exactly as
    before, any scroll the visitor makes takes priority, and a small
    arrow button appears whenever the latest messages are below the
    visible area.
    No configuration needed — this is the new default for every chatbot.
  </Accordion>

  <Accordion title="Allowed Domains — restrict where your chatbot can be embedded" icon="shield-check">
    A new **Allowed Domains** setting under **Settings → General** locks your
    chat widget to the websites you name. Add domains as chips; each entry
    covers all of its subdomains, and enforcement happens in the visitor's
    browser itself, so a copied embed snippet on an unauthorized site
    renders nothing. Your dashboard preview always keeps working, and
    leaving the field empty keeps today's behavior — the widget loads
    anywhere. See [restricting where your chatbot can be
    embedded](/docs/setup/integrating-with-your-website#restrict-where-your-chatbot-can-be-embedded).
  </Accordion>

  <Accordion title="Automatic plan entitlements" icon="unlock">
    Integrations and API access now switch on automatically with your plan:
    Growth and up unlocks the messaging integrations (Slack, Crisp,
    Messenger, Google Chat, Freshdesk, Zoho) and API keys, and the Zendesk
    AI Agent is included from Scale up. Downgrades revoke automatically —
    no support ticket in either direction.
  </Accordion>

  <Accordion title="Analytics in every plan tier" icon="chart-mixed">
    Advanced analytics is now part of the plan tiers, and the insights
    experience was upgraded: unified topics, explicit analysis modes, a
    re-analyze action, an Analytics badge in the navigation, and the
    engagement funnel completing the insights view.
  </Accordion>

  <Accordion title="Brand kit" icon="palette">
    A new /brand page with official SiteGPT logos and the brand color, plus
    a right-click menu on the site logo for quick asset downloads.
  </Accordion>
</AccordionGroup>

### Improvements

* **Clear trial terms on the pricing page**: every self-serve plan now states its trial exactly — a 7-day free trial, credit card required, cancel anytime before it ends — and the yearly-billing toggle says "Save up to 40%", matching the real per-plan discounts.
* **No cookie banner needed in the EU**: visitors from the EEA and UK now get a fully storage-free analytics setup on sitegpt.ai — no analytics identifiers or tracking cookies are written to their device, so there is nothing to consent to. The chat widget you embed was already tracker-free and is unchanged.
* **Leaner AI-assistant responses**: replies served to AI assistants over MCP no longer carry internal identifiers or teammate email addresses. API responses are unchanged — tools and scripts still need those fields.
* **Widget accessibility**: fixes across the chat widget from a WCAG 2.1 AA audit — contrast, focus handling, and screen-reader semantics.
* **Dashboard update banner**: long-open dashboard tabs offer a one-click refresh when a new version ships, instead of running stale.
* **Auto-sync jobs go live**: the sync-jobs list updates in real time with accurate loading states.
* **Ingestion resilience**: transient quota-check hiccups no longer fail documents during training.

### Bug fixes

* **Resolved conversations leave the Attention view**: marking a conversation resolved now removes it from Chat History's **Attention** view whatever its flags — so triage shows exactly what still needs a human. Later in August, resolving became a hard close: see the **Human take-over and closed conversations** entry above. See [chat history](/docs/navigating-your-chatbot/chat-history#the-conversation-list).
* **Connecting messaging integrations works again**: a provisioning bug broke new Messenger, Google Chat, Zoho, and Freshdesk connections for about three weeks in July and August; connecting them works again. Existing connections were unaffected.
* **iPhone app reply delivery (update 1.0.1)**: replies sent from the iOS app were failing with a connection error after a backend migration. Delivery was restored server-side for the app version already on phones, and the 1.0.1 update completes the fix — it also renders lead-capture and human-handoff system messages in conversations and shows an error with retry when lists fail to load.