v0.50.3

## What's Changed
* refactor: replace dynamic imports with static imports in app/src by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/111
* feat(web-search): add Parallel search provider to WebSearchTool by @YellowSnnowmann in https://github.com/tinyhumansai/openhuman/pull/114
* Feat/memory agent by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/115
* refactor(config): centralize env vars and add .env.example docs by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/116
* Add core memory RPC surface (#69) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/112
* feat: add Discord notification for new releases in GitHub Actions wor… by @YellowSnnowmann in https://github.com/tinyhumansai/openhuman/pull/118
* feat(local-ai): guided model tier selection by device capability by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/120
* update: modify .gitignore to include `create_issue` and remove redund… by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/121
* Add GLiNER relex ingestion pipeline (#60) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/113
* feat(installer): add one-command installer flow and release smoke checks by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/123
* feat(autocomplete): persist accepted completions in memory and reuse them for suggestions (#108) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/119
* fix(agent): execute fallback tool calls in the loop by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/125
* feat: re-setup skills runtime and add model-callable skills bridge by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/126
* fix(tauri): restore working tray controls in desktop shell by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/127
* feat(memory): connect graph query and doc ingest APIs by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/124
* test: add cross-stack coverage for core and tauri flows by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/130
* feat(observability): add Sentry error reporting to Rust core by @senamakel in https://github.com/tinyhumansai/openhuman/pull/131
* fix: propagate entity_type into retrieval context for graph visualization by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/135
* fix(e2e): harden deep-link login flow reliability by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/137
* fix(skills): enforce per-skill runtime tool isolation by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/140
* fix: service gate buttons unclickable on startup by @senamakel in https://github.com/tinyhumansai/openhuman/pull/139
* refactor: migrate memory service to controller registry by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/138
* feat(onboarding): calmer onboarding + local AI download snackbar by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/134
* ci: speed up GitHub Actions builds (~14m → ~3-5m warm) by @senamakel in https://github.com/tinyhumansai/openhuman/pull/136
* fix(local-ai): Ollama bootstrap failure UX and auto-recovery by @senamakel in https://github.com/tinyhumansai/openhuman/pull/142
* fix(skills): persist OAuth credentials and fix skill auto-start lifecycle by @senamakel in https://github.com/tinyhumansai/openhuman/pull/146
* Update issue templates by @senamakel in https://github.com/tinyhumansai/openhuman/pull/148
* feat(agent): add self-learning subsystem with post-turn reflection by @senamakel in https://github.com/tinyhumansai/openhuman/pull/149
* feat(auth): Telegram bot registration flow — /auth/telegram endpoint by @senamakel in https://github.com/tinyhumansai/openhuman/pull/150
* feat(webhooks): webhook tunnel routing for skills + remove legacy tunnel module by @senamakel in https://github.com/tinyhumansai/openhuman/pull/147
* feat(agent): architecture improvements — context guard, cost tracking, permissions, events by @senamakel in https://github.com/tinyhumansai/openhuman/pull/151
* refactor(models): standardize to reasoning-v1, agentic-v1, coding-v1 by @senamakel in https://github.com/tinyhumansai/openhuman/pull/152
* fix(skills): debug infrastructure + disconnect credential cleanup by @senamakel in https://github.com/tinyhumansai/openhuman/pull/154
* feat(agent): multi-agent harness with 8 archetypes, DAG planning, and episodic memory by @senamakel in https://github.com/tinyhumansai/openhuman/pull/155

## New Contributors
* @YellowSnnowmann made their first contribution in https://github.com/tinyhumansai/openhuman/pull/114
* @sanil-23 made their first contribution in https://github.com/tinyhumansai/openhuman/pull/112

**Full Changelog**: https://github.com/tinyhumansai/openhuman/compare/v0.49.32...v0.50.3