The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
Rust agent-orchestrationai-agentsai-assistantdesktopllmlocal-firstmcppersonal-aiprivacyrustsecond-braintauri
docs: update chat and architecture documentation
Steven Enamakeld98325a64442
diff --git a/docs/gitbooks/en/developing/architecture/agent-harness.md b/docs/gitbooks/en/developing/architecture/agent-harness.mdindex 09256dcf1b..29688ed892 100644--- a/docs/gitbooks/en/developing/architecture/agent-harness.md+++ b/docs/gitbooks/en/developing/architecture/agent-harness.md@@ -121,6 +121,12 @@ This page walks through what happens in one turn, then zooms in on each of the mEvery turn goes through the same lifecycle, whether the user just typed a message, a Telegram webhook fired or a 9am cron ticked:+Messaging-channel ingress is prepared by the configured TinyChannels module+through typed bus operations. OpenHuman applies account authorization and+session policy, then binds the conversation to its durable TinyAgents session.+Provider transports and normalization stay in TinyChannels; the model turn,+tool policy, approvals, and transcript storage stay in the OpenHuman host.+```text┌─ inbound ─────────────────────────────────────────────────────────┐│ user message · channel inbound · webhook · cron · composio event │diff --git a/docs/gitbooks/en/developing/architecture/frontend.md b/docs/gitbooks/en/developing/architecture/frontend.mdindex 5c54ba462c..45839f599a 100644--- a/docs/gitbooks/en/developing/architecture/frontend.md+++ b/docs/gitbooks/en/developing/architecture/frontend.md@@ -64,6 +64,14 @@ OpenHuman's desktop UI is a React 19 app (`app/src/`) that:- Leaves AI prompts to the core: bundled `crates/openhuman-core/src/agent/prompts` ship as Tauri resources (see `crates/openhuman-app/tauri.conf.json` resources) and are read core-side, not by the frontend- Uses a minimal MCP-style helper layer under `lib/mcp/` (transport, validation)+Chat messages use the core's typed content contract. Attachment uploads are+accepted by the core, which stores them and returns opaque references for the+message; the frontend does not persist local paths or inline media bytes as+conversation content. The core resolves those references within the trusted+turn context before calling a model. Web chat, TUI, and relayed web progress+share the TinyChannels compiled web-output projection; provider delivery keeps+its separate channel terminal event.+### Entry points| File | Purpose |diff --git a/docs/gitbooks/en/features/chat.md b/docs/gitbooks/en/features/chat.mdindex f96968081f..65efcc7be5 100644--- a/docs/gitbooks/en/features/chat.md+++ b/docs/gitbooks/en/features/chat.md@@ -74,6 +74,14 @@ A thread can carry a goal and a to-do list that the agent sets. They show as a pA long conversation is compacted, not truncated. Compaction seals what came before and starts a new generation that points back to the sealed one. Nothing is deleted on disk, though the model reads only the latest generation. There is no UI for browsing older generations yet.+Chat attachments travel as typed content parts. The core keeps uploaded bytes+behind scoped opaque references in the durable user row; local file paths and+base64 data are not used as the persisted message reference. When a turn runs,+the trusted host resolves those references and passes the supported image,+audio, video, or file content to the model route. Voice notes retain typed+audio and transcript metadata in the conversation, so they can be replayed+after reload; dictation sends text only.+## Keyboard| Shortcut | Action |