v0.63.0

# The Reliability & Control Upgrade

This release is packed with sturdier workflows, smoother chat and Agent World experiences, and a ton of under-the-hood hardening to keep everything fast and dependable. 🎉

## Highlights

### Workflows you can trust 🧩
The Workflows copilot and canvas got a major reliability pass: proposals consistently render (even for larger graphs), every copilot turn now ends in a real terminal outcome (no more silent trail‑offs), Accept now saves automatically, and the runs UI stays accurate and live-updating. Safety and correctness also improved with fixes for live-arming on updates, better circuit-breaking, approval-state visibility, and stronger tier/approval enforcement for Composio tool calls.

([#4881](https://github.com/tinyhumansai/openhuman/pull/4881), [#4886](https://github.com/tinyhumansai/openhuman/pull/4886), [#4887](https://github.com/tinyhumansai/openhuman/pull/4887), [#4888](https://github.com/tinyhumansai/openhuman/pull/4888), [#4889](https://github.com/tinyhumansai/openhuman/pull/4889), [#4890](https://github.com/tinyhumansai/openhuman/pull/4890), [#4891](https://github.com/tinyhumansai/openhuman/pull/4891), [#4893](https://github.com/tinyhumansai/openhuman/pull/4893), [#4904](https://github.com/tinyhumansai/openhuman/pull/4904), [#4911](https://github.com/tinyhumansai/openhuman/pull/4911), [#4932](https://github.com/tinyhumansai/openhuman/pull/4932), [#4933](https://github.com/tinyhumansai/openhuman/pull/4933), [#4941](https://github.com/tinyhumansai/openhuman/pull/4941), [#4942](https://github.com/tinyhumansai/openhuman/pull/4942), [#4943](https://github.com/tinyhumansai/openhuman/pull/4943), [#4945](https://github.com/tinyhumansai/openhuman/pull/4945), [#4955](https://github.com/tinyhumansai/openhuman/pull/4955), [#4956](https://github.com/tinyhumansai/openhuman/pull/4956), [#4999](https://github.com/tinyhumansai/openhuman/pull/4999), [#5000](https://github.com/tinyhumansai/openhuman/pull/5000), [#5007](https://github.com/tinyhumansai/openhuman/pull/5007), [#5011](https://github.com/tinyhumansai/openhuman/pull/5011), [#5012](https://github.com/tinyhumansai/openhuman/pull/5012), [#5013](https://github.com/tinyhumansai/openhuman/pull/5013)) — Thank you @graycyrus and @senamakel!

### Chat that feels snappier & more controllable 💬
Chat got a big UX win with a Stop button plus ESC-to-interrupt and re-edit, and stronger protection against “hydrate” snapshots wiping fresh streaming or tool timelines. Orchestration also became more transparent: async sub-agent failures and “awaiting user” outcomes now surface correctly in chat, and delegations are now async-by-default with durable, resumable sessions and persistent workflow proposals.

([#4898](https://github.com/tinyhumansai/openhuman/pull/4898), [#4903](https://github.com/tinyhumansai/openhuman/pull/4903), [#4908](https://github.com/tinyhumansai/openhuman/pull/4908), [#5074](https://github.com/tinyhumansai/openhuman/pull/5074)) — Thank you @M3gA-Mind, @graycyrus, and @senamakel!

### Memory & transcript upgrades 🧠
Memory ingestion and recall got sharper and safer: OpenHuman can ingest Codex and Claude coding sessions, Composio sync no longer keys upserts off secret-like titles, and recall avoids pulling same-session “echo” documents that drown out real facts. On top of that, transcripts are now much more robust: cold-boot resumes restore full-fidelity context and thinking, and the transcript system is moving to an append-only, derived view with raw session logs as the source of truth.

([#4863](https://github.com/tinyhumansai/openhuman/pull/4863), [#4953](https://github.com/tinyhumansai/openhuman/pull/4953), [#4991](https://github.com/tinyhumansai/openhuman/pull/4991), [#5077](https://github.com/tinyhumansai/openhuman/pull/5077), [#5086](https://github.com/tinyhumansai/openhuman/pull/5086)) — Thank you @senamakel, @M3gA-Mind, and @graycyrus!

### Agent World (Tiny Place) feels alive 🌍
Tiny Place is now more interactive and complete: DMs and feeds update in real time, ledgers and feeds paginate beyond the first 50 items, and directory entries finally open a rich profile view. Profiles also leveled up with editing for your own profile (name/bio/avatar) and a public viewer route for arbitrary handles.

([#4951](https://github.com/tinyhumansai/openhuman/pull/4951), [#4952](https://github.com/tinyhumansai/openhuman/pull/4952), [#4988](https://github.com/tinyhumansai/openhuman/pull/4988), [#4989](https://github.com/tinyhumansai/openhuman/pull/4989), [#4990](https://github.com/tinyhumansai/openhuman/pull/4990), [#4994](https://github.com/tinyhumansai/openhuman/pull/4994), [#4996](https://github.com/tinyhumansai/openhuman/pull/4996), [#4997](https://github.com/tinyhumansai/openhuman/pull/4997)) — Thank you @M3gA-Mind!

### Performance, polish, and “it just works” fixes ⚡
From accessibility and UI polish to startup and runtime performance, this release reduces friction across the app: improved dark theme contrast, paused mesh-gradient rendering when the app isn’t visible, and boot polling is consolidated and quieter. First-run setup overlays now appear only when actually provisioning, channel setup guidance is corrected in-app, pricing/checkout redirects behave properly, and the settings “Clear App Data” reset now correctly targets the signed-in user.

([#4897](https://github.com/tinyhumansai/openhuman/pull/4897), [#4902](https://github.com/tinyhumansai/openhuman/pull/4902), [#4905](https://github.com/tinyhumansai/openhuman/pull/4905), [#4910](https://github.com/tinyhumansai/openhuman/pull/4910), [#4939](https://github.com/tinyhumansai/openhuman/pull/4939), [#4954](https://github.com/tinyhumansai/openhuman/pull/4954), [#5035](https://github.com/tinyhumansai/openhuman/pull/5035), [#5036](https://github.com/tinyhumansai/openhuman/pull/5036), [#5066](https://github.com/tinyhumansai/openhuman/pull/5066), [#5075](https://github.com/tinyhumansai/openhuman/pull/5075), [#5085](https://github.com/tinyhumansai/openhuman/pull/5085)) — Thank you @M3gA-Mind, @YellowSnnowmann, and @senamakel!

### Build flexibility, CI hardening, and new surfaces 🛠️
The core is now far more modular and easier to ship in slim builds via compile-time feature gates (media, web3, flows, skills, MCP, meet) and a new feature-gated terminal chat UI (`openhuman tui`). Desktop shipping and CI also got stricter and safer: voice and tokenjuice-treesitter are correctly forwarded into the desktop build, CI now gates feature-forwarding drift, macOS clippy blockers are resolved, the “gates-off” smoke lane is repaired and runs tests, and learning startup subscribers are decoupled from channels and covered with more stable tests. There’s also a core refactor moving the web chat conduit out of `channels/`.

([#4840](https://github.com/tinyhumansai/openhuman/pull/4840), [#4855](https://github.com/tinyhumansai/openhuman/pull/4855), [#4912](https://github.com/tinyhumansai/openhuman/pull/4912), [#4913](https://github.com/tinyhumansai/openhuman/pull/4913), [#4914](https://github.com/tinyhumansai/openhuman/pull/4914), [#4915](https://github.com/tinyhumansai/openhuman/pull/4915), [#4916](https://github.com/tinyhumansai/openhuman/pull/4916), [#4917](https://github.com/tinyhumansai/openhuman/pull/4917), [#4934](https://github.com/tinyhumansai/openhuman/pull/4934), [#5004](https://github.com/tinyhumansai/openhuman/pull/5004), [#5020](https://github.com/tinyhumansai/openhuman/pull/5020), [#5023](https://github.com/tinyhumansai/openhuman/pull/5023), [#5025](https://github.com/tinyhumansai/openhuman/pull/5025), [#5070](https://github.com/tinyhumansai/openhuman/pull/5070), [#5082](https://github.com/tinyhumansai/openhuman/pull/5082), [#5084](https://github.com/tinyhumansai/openhuman/pull/5084)) — Thank you @oxoxDev, @CodeGhost21, @senamakel, and @M3gA-Mind!

### Integrations, inference, and tooling improvements 🔌
Integrations and local AI got more reliable: OpenAI-compatible local runtimes now probe `/v1/models` correctly, custom embedding endpoint verification errors are clearer and actionable, and streaming retries now honor `Retry-After`. Composio tool execution is smarter and safer with per-action tools gated on their full contracts (reducing argument guessing), and unsyncable toolkits no longer auto-register as memory sources. There’s also a new `generate_document` tool that emits real `.docx`, plus a public accessor for last-turn usage totals for downstream hosting/billing.

([#4899](https://github.com/tinyhumansai/openhuman/pull/4899), [#4909](https://github.com/tinyhumansai/openhuman/pull/4909), [#4940](https://github.com/tinyhumansai/openhuman/pull/4940), [#4993](https://github.com/tinyhumansai/openhuman/pull/4993), [#4995](https://github.com/tinyhumansai/openhuman/pull/4995), [#5064](https://github.com/tinyhumansai/openhuman/pull/5064), [#5067](https://github.com/tinyhumansai/openhuman/pull/5067)) — Thank you @M3gA-Mind and @senamakel!

### Account, sharing, and navigation delights 🔗
You can now generate one-tap “look what my agent did” share cards for X and LinkedIn, the X/Twitter “Continue with Google” popup stays in-app, Rewards is finally discoverable via a cloud-gated sidebar entry, and the Codex auth button is properly localized. Plus: proactive “Agentic task insights” fixtures and lifecycle resets were tightened to keep the UI consistent.

([#4892](https://github.com/tinyhumansai/openhuman/pull/4892), [#4944](https://github.com/tinyhumansai/openhuman/pull/4944), [#4949](https://github.com/tinyhumansai/openhuman/pull/4949), [#4992](https://github.com/tinyhumansai/openhuman/pull/4992), [#5010](https://github.com/tinyhumansai/openhuman/pull/5010), [#5015](https://github.com/tinyhumansai/openhuman/pull/5015), [#5065](https://github.com/tinyhumansai/openhuman/pull/5065)) — Thank you @YellowSnnowmann, @graycyrus, and @M3gA-Mind!

### Safety & prompt discipline changes 🧯
Desktop automation safety controls saw churn: an Emergency Stop was introduced and later fully removed based on product direction. Meanwhile, agent behavior improved for local LLM providers with provider-aware context/delegation guardrails, stronger structured-output enforcement, more resilient tool-call parsing for small models, and AGENTS.md instructions are now loaded into the system prompt—with follow-up security hardening to prevent symlink/path escape and to redact debug logs when AGENTS.md is present.

([#4600](https://github.com/tinyhumansai/openhuman/pull/4600), [#4900](https://github.com/tinyhumansai/openhuman/pull/4900), [#4935](https://github.com/tinyhumansai/openhuman/pull/4935), [#4938](https://github.com/tinyhumansai/openhuman/pull/4938), [#5073](https://github.com/tinyhumansai/openhuman/pull/5073), [#5087](https://github.com/tinyhumansai/openhuman/pull/5087), [#5096](https://github.com/tinyhumansai/openhuman/pull/5096)) — Thank you @CodeGhost21, @M3gA-Mind, @sanil-23, @yh928, and @senamakel!
### Additional highlights 🔗

A few more focused contributions round out this release with targeted fixes and improvements that are worth calling out. ([#4872](https://github.com/tinyhumansai/openhuman/pull/4872), [#4877](https://github.com/tinyhumansai/openhuman/pull/4877), [#4906](https://github.com/tinyhumansai/openhuman/pull/4906), [#5008](https://github.com/tinyhumansai/openhuman/pull/5008)) — Thank you @senamakel, @graycyrus, and @M3gA-Mind!

## New Contributors

- Thank you @yh928 for improving tool-call robustness by recovering pipe-garbled `<tool_call>` tags from small models. ([#4938](https://github.com/tinyhumansai/openhuman/pull/4938))

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

## Contributor Credits

Thank you @CodeGhost21, @Cyrus Gray, @Mega Mind, @oxoxDev, @sanil-23, @Steven Enamakel, @YellowSnnowmann, and @yh928!

## Full Compare

https://github.com/tinyhumansai/openhuman/compare/v0.61.8...v0.63.0