v0.57.13

## What's Changed
* refactor: improve matrix parsing validation and performance by @manucian-official in https://github.com/tinyhumansai/openhuman/pull/3129
* fix(inference/ollama): use prompt-guided tool calling so skills work on Ollama (#3098 sub-issue 3) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3229
* feat(memory-tree): per-integration health strip (#2763) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3230
* fix(channels/telegram): wire ApprovalGate end-to-end for Telegram turns (#3098 sub-issue 2) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3232
* docs(claude.md): document action sandbox vs internal workspace split by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3241
* test(memory-sync): E2E + Vitest coverage for #3113 sync pipeline (#3116) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3194
* feat(voice): auto-send dictation transcript + allowlist app-launch commands (#3148 Phase 1) by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/3168
* fix(scripts): add short help to GitHub test map by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3223
* fix(scripts): add short help to stale CI cleanup by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3222
* docs: remove stale coverage matrix PR-local markers by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3220
* perf(learning): bounded-concurrency persist in transcript ingestion by @mysma-9403 in https://github.com/tinyhumansai/openhuman/pull/3234
* fix(orchestrator): force code-repo delegation when reading stalls (#3102) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3214
* perf(memory_store): batch chunk embeddings in upsert_document by @mysma-9403 in https://github.com/tinyhumansai/openhuman/pull/3213
* fix(inference): actionable error for completion-only model 404 + unmistakable run_code failure (#3193) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3211
* feat(memory): pipeline hardening — typed failures, BYO embeddings, doctor, honest status by @zahica1234 in https://github.com/tinyhumansai/openhuman/pull/3076
* fix(agent_prompts): anchor coding-agent prompts in action_dir, not workspace_dir by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3242
* test(tools/system): lock in action_dir as the CWD for shell-family tools by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3243
* fix(shell): Windows pre-CEF cache-lock wait to stop relaunch panic (TAURI-RUST-F) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3210
* feat(mcp): sanitize remote tool descriptions + length caps by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3215
* feat(chat): Files in this chat — persistent per-chat artifact panel (#3024) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3026
* feat(backend_meet): integrate with backend gmeet bot via Socket.IO by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3182
* feat(settings): AgentAccessPanel reads live action_dir/workspace_dir via RPC by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3245
* feat(claude-code): Claude Code CLI provider — Phases 1–5 by @finedesignz in https://github.com/tinyhumansai/openhuman/pull/2472
* feat(security): explicit agent turn origin + fail-closed approval gate + memory provenance by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3227
* test(playwright): add functional UI flow coverage by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3257
* feat(sandbox): add real sandbox execution backends for agent tools by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3261
* fix(review): use exec and interactive mode for agent CLI invocations by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3262
* feat(inference): local provider profiles and MLX/generic-local support by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3260
* feat(todos): atomic claim primitive for task-board dispatch by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3258
* feat(session_db): add durable agent session database by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3259
* feat(todos): durable task-run liveness and stale reclaim by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3267
* feat(settings): add UI for sandbox execution backend configuration by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3265
* feat(analytics): track chat browser touchpoints by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3269
* fix(memory): group selector ingests by source scope by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3264
* fix(memory): redact source tag debug identifiers by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3272
* feat(todos): add task scheduler race and invariant tests by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3271
* fix(agent): snap budget-trim past orphaned tool results by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3266
* fix(agent): drop removed memory_tree modes from orchestrator prompt by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3275
* feat(chat): implement image attachment pipeline, gated off (#3205) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3268
* fix(onboarding,billing): surface completeAndExit errors and suppress near-limit banner for custom providers by @YellowSnnowmann in https://github.com/tinyhumansai/openhuman/pull/3278
* fix(composio): defer on_connection_created sync until onboarding completes by @YellowSnnowmann in https://github.com/tinyhumansai/openhuman/pull/3283
* fix(memory-graph): render large graphs in the SVG fallback without freezing by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3291

## New Contributors
* @finedesignz made their first contribution in https://github.com/tinyhumansai/openhuman/pull/2472

**Full Changelog**: https://github.com/tinyhumansai/openhuman/compare/v0.57.11...v0.57.13