v0.57.44

# The Orchestration & Everyday-Flow Upgrade

This release brings a big leap in how OpenHuman *runs*—from smarter multi-agent orchestration and skills, to a cleaner two-panel app shell, to faster and quieter memory + inference pipelines. 🚀

## Highlights

### Intelligence & multi-agent orchestration 🧠
OpenHuman’s “intelligence layer” gets much more real: async sub-agents can now be steered while running and awaited cleanly, teammate agents can actually execute tasks end-to-end (with messaging captured in timelines), and durable workflow orchestration now has a first-class UI with an approval gate for high-cost runs. Worktree isolation is also wired through RPC + UI so complex runs can stay contained and observable.

([#3641](https://github.com/tinyhumansai/openhuman/pull/3641), [#3637](https://github.com/tinyhumansai/openhuman/pull/3637), [#3697](https://github.com/tinyhumansai/openhuman/pull/3697), [#3696](https://github.com/tinyhumansai/openhuman/pull/3696)) — Thank you @senamakel and @oxoxDev!

### Skills, vision, and better agent grounding 🧰
Skills graduate to a catalog-driven `run_skill` flow with an isolated executor and mid-session refresh—making skill runs more reliable and less invasive to chat history. There’s also a new `vision-v1` tier plus a dedicated vision sub-agent for image understanding, and tighter numeric grounding rules to keep numbers copied exactly from observed sources.

([#3722](https://github.com/tinyhumansai/openhuman/pull/3722), [#3699](https://github.com/tinyhumansai/openhuman/pull/3699), [#3678](https://github.com/tinyhumansai/openhuman/pull/3678)) — Thank you @sanil-23 and @Sam!

### Chat & background work UX polish 💬
Detached sub-agents now have a proper “Background tasks” panel and deliver results back into chat in an idle-gated, batched way—so you don’t get interrupted mid-turn. Conversations also get a key rendering fix: task insights now appear once, after the full response. Plus, proactive messages are now limited to fresh threads, and resume-on-reopen errors are classified and threads are “de-poisoned” to recover cleanly.

([#3735](https://github.com/tinyhumansai/openhuman/pull/3735), [#3726](https://github.com/tinyhumansai/openhuman/pull/3726), [#3713](https://github.com/tinyhumansai/openhuman/pull/3713), [#3714](https://github.com/tinyhumansai/openhuman/pull/3714)) — Thank you @sanil-23!

### A new two-panel desktop shell & settings experience 🧭
The desktop app’s layout continues its transformation: TwoPanelLayout becomes the backbone across Settings/Brain/Connections/Chat, settings panels are unified with shared primitives for consistent navigation, and the root shell now adopts a unified sidebar with Chat as the home experience. There’s also a dedicated Desktop Agent setup panel to make permissions, seamless mode, always-on, and wake-word setup feel centralized and clear.

([#3643](https://github.com/tinyhumansai/openhuman/pull/3643), [#3646](https://github.com/tinyhumansai/openhuman/pull/3646), [#3751](https://github.com/tinyhumansai/openhuman/pull/3751), [#3634](https://github.com/tinyhumansai/openhuman/pull/3634)) — Thank you @senamakel and @M3gA-Mind!

### MCP, connectors, and provider setup—faster and more actionable 🔌
MCP servers are now usable end-to-end by the agent (including OAuth flows and an agent bridge), boot is faster thanks to concurrent server spawning, and 401s are surfaced as an actionable “needs sign-in” state. Claude Code becomes an opt-in provider with a macOS auth fix and OpenHuman memory over MCP, and Composio/memory-source reconciliation is significantly more efficient. A small but helpful settings addition also adds a “Get API key” link for Kimi.

([#3648](https://github.com/tinyhumansai/openhuman/pull/3648), [#3429](https://github.com/tinyhumansai/openhuman/pull/3429), [#3719](https://github.com/tinyhumansai/openhuman/pull/3719), [#3647](https://github.com/tinyhumansai/openhuman/pull/3647), [#3432](https://github.com/tinyhumansai/openhuman/pull/3432), [#3685](https://github.com/tinyhumansai/openhuman/pull/3685)) — Thank you @sanil-23, @mysma-9403, and @Huyuochi!

### Memory & retrieval that feels more “right” 🧠
Memory status reporting is smarter (only unrecoverable failures show as “error,” and the degraded latch clears on any completed extraction). There’s a new RPC to fully delete a memory source by exact `source_id`, and a new `cover_window` retrieval mode that powers a more relevant “last 24h” morning brief. Under the hood, extraction scoring avoids unnecessary cloning for lower overhead.

([#3630](https://github.com/tinyhumansai/openhuman/pull/3630), [#3631](https://github.com/tinyhumansai/openhuman/pull/3631), [#3664](https://github.com/tinyhumansai/openhuman/pull/3664), [#3700](https://github.com/tinyhumansai/openhuman/pull/3700), [#3436](https://github.com/tinyhumansai/openhuman/pull/3436)) — Thank you @sanil-23, @michaelk1957, and @mysma-9403!

### Inference, embeddings, and observability hardening 🛡️
This range focuses heavily on making the app quieter, safer, and more resilient: OAuth requests now use a Codex-compatible client version; Responses API role/kind mismatches are fixed; extraction now caps `max_tokens` and correctly treats provider 402s as non-retryable to stop storms. Embeddings get multiple guardrails (refuse empty inputs, block chat-only custom endpoints with no embeddings API, and prevent LM Studio “no models loaded” floods). BYO provider 401/403 auth failures are demoted from Sentry, SQLite “disk full” noise is filtered, and model test failures are properly classified.

([#3414](https://github.com/tinyhumansai/openhuman/pull/3414), [#3626](https://github.com/tinyhumansai/openhuman/pull/3626), [#3617](https://github.com/tinyhumansai/openhuman/pull/3617), [#3670](https://github.com/tinyhumansai/openhuman/pull/3670), [#3629](https://github.com/tinyhumansai/openhuman/pull/3629), [#3688](https://github.com/tinyhumansai/openhuman/pull/3688), [#3689](https://github.com/tinyhumansai/openhuman/pull/3689), [#3672](https://github.com/tinyhumansai/openhuman/pull/3672), [#3676](https://github.com/tinyhumansai/openhuman/pull/3676)) — Thank you @junwon, @oxoxDev, @CodeGhost21, @obchain, and @Zhang!

### Meetings & voice in the real world 🗣️
Meetings level up in multiple directions: the Meet bot can now participate in-call (streaming, approvals, active vs listen-only), Recent Calls is populated correctly for the backend meet flow, and after-call summaries + context labels make threads immediately scannable. Calendar-triggered prompts and a Meeting Assistant settings UI help you join at the right time. Telegram bots also now accept inbound voice messages and transcribe them before dispatching to the agent.

([#3677](https://github.com/tinyhumansai/openhuman/pull/3677), [#3710](https://github.com/tinyhumansai/openhuman/pull/3710), [#3709](https://github.com/tinyhumansai/openhuman/pull/3709), [#3721](https://github.com/tinyhumansai/openhuman/pull/3721), [#3679](https://github.com/tinyhumansai/openhuman/pull/3679)) — Thank you @YellowSnnowmann and @Ron Liu!

### Security, stability, and test coverage ✅
A major hardening audit pass tightens core RPC auth, deep-link CSRF protections, inference resilience, and secrets handling—with regression tests included. Agent harness behavior now has robust Rust + browser E2E coverage (plus docs updates), the desktop Appium suite is repaired after the IA refactors, and observability regressions are explicitly tested for known transient shapes. There’s also a deps bump in the Postgres stack to clear recent RUSTSEC advisories.

([#3652](https://github.com/tinyhumansai/openhuman/pull/3652), [#3665](https://github.com/tinyhumansai/openhuman/pull/3665), [#3666](https://github.com/tinyhumansai/openhuman/pull/3666), [#3667](https://github.com/tinyhumansai/openhuman/pull/3667), [#3669](https://github.com/tinyhumansai/openhuman/pull/3669), [#3668](https://github.com/tinyhumansai/openhuman/pull/3668), [#3649](https://github.com/tinyhumansai/openhuman/pull/3649), [#3658](https://github.com/tinyhumansai/openhuman/pull/3658), [#3659](https://github.com/tinyhumansai/openhuman/pull/3659), [#3660](https://github.com/tinyhumansai/openhuman/pull/3660), [#3661](https://github.com/tinyhumansai/openhuman/pull/3661), [#3662](https://github.com/tinyhumansai/openhuman/pull/3662), [#3690](https://github.com/tinyhumansai/openhuman/pull/3690)) — Thank you @senamakel, @YellowSnnowmann, @Zhang, and @obchain!

### Core plumbing & compatibility improvements ⚙️
Under-the-hood changes improve compatibility and reduce surprises: CDP scanners are migrated to an in-process transport (dropping the TCP DevTools port), Notion markdown fetch is now bounded-concurrent, managed-tool budget probing is cached behind a short TTL, subagents can auto-compact summarize when context fills, scheduler routing is scoped to avoid misroutes for calendar/meet-link reads, legacy health RPC names now alias to `health_snapshot`, and unknown-method probe traffic no longer pages Sentry. Login troubleshooting also improves by surfacing a previously silent `/auth/me` store failure.

([#3636](https://github.com/tinyhumansai/openhuman/pull/3636), [#3433](https://github.com/tinyhumansai/openhuman/pull/3433), [#3431](https://github.com/tinyhumansai/openhuman/pull/3431), [#3694](https://github.com/tinyhumansai/openhuman/pull/3694), [#3731](https://github.com/tinyhumansai/openhuman/pull/3731), [#3743](https://github.com/tinyhumansai/openhuman/pull/3743), [#3744](https://github.com/tinyhumansai/openhuman/pull/3744), [#3734](https://github.com/tinyhumansai/openhuman/pull/3734)) — Thank you @oxoxDev and @sanil-23!

### Cloud/marketplace integration (opt-in) ☁️
An opt-in AgentBox adapter adds marketplace-style `/run` + job polling endpoints and can auto-register a GMI OpenAI-compatible provider at startup—kept fully off by default to avoid impacting desktop builds.

([#3651](https://github.com/tinyhumansai/openhuman/pull/3651)) — Thank you @CodeGhost21!
### Additional highlights 🔗

A few more focused contributions round out this release with targeted fixes and improvements that are worth calling out. ([#3622](https://github.com/tinyhumansai/openhuman/pull/3622), [#3632](https://github.com/tinyhumansai/openhuman/pull/3632), [#3698](https://github.com/tinyhumansai/openhuman/pull/3698)) — Thank you @YellowSnnowmann, @senamakel, and @oxoxDev!

## New Contributors

Thanks for your first contributions—welcome to the OpenHuman crew!

- Thank you @Huyuochi for adding a Kimi provider “Get API key” affiliate link to streamline setup. ([#3685](https://github.com/tinyhumansai/openhuman/pull/3685))
- Thank you @Ron Liu for enabling Telegram inbound voice messages with transcription support. ([#3679](https://github.com/tinyhumansai/openhuman/pull/3679))
- Thank you @Sam for tightening numeric grounding rules in agent prompts (with regression coverage). ([#3678](https://github.com/tinyhumansai/openhuman/pull/3678))
- Thank you @Zhang for expanding observability regression coverage across multiple real-world transient/error shapes. ([#3658](https://github.com/tinyhumansai/openhuman/pull/3658), [#3659](https://github.com/tinyhumansai/openhuman/pull/3659), [#3660](https://github.com/tinyhumansai/openhuman/pull/3660), [#3661](https://github.com/tinyhumansai/openhuman/pull/3661), [#3662](https://github.com/tinyhumansai/openhuman/pull/3662), [#3676](https://github.com/tinyhumansai/openhuman/pull/3676))

Hope you’ll join the Discord too—there are exclusive roles and contributor rewards waiting.

## Contributor Credits

Thank you to everyone who shipped this release: @CodeGhost21, @Huyuochi, @junwon, @Mega Mind, @michaelk1957, @mysma-9403, @obchain, @oxoxDev, @Ron Liu, @Sam, @sanil-23, @Steven Enamakel, @Steven Enamakel's Droid, @YellowSnnowmann, @Zhang, and @github-actions[bot].

## Full Compare

https://github.com/tinyhumansai/openhuman/compare/v0.57.40...v0.57.44