The Parallel Power Upgrade

This release brings a faster, more transparent desktop experience—more concurrency in chat, smoother reliability in memory flows, and easier access to diagnostics. 🚀

Highlights

Faster chat, more parallelism ⚡

Agent inference now runs concurrently instead of one-at-a-time—both across threads (no more single global active-thread lock) and within a thread via parallel "forked" turns. Cancellation is also hardened to be more cooperative and resilient under load. (#3633) — Thank you @senamakel!

Memory source reliability improvements 🧠

Memory sources now re-fetch when a session becomes authenticated, improving consistency and reducing flakiness in memory-source UI flows after reloads. This also adds test coverage to lock in the behavior. (#3621) — Thank you @sanil-23!

Smoother CI + test stability 🧪

CI and tests got a cleanup pass to eliminate multiple flaky/failing categories: removing stale UI assertions, fixing async race conditions in autosave/memory, and adjusting Playwright timeouts to reduce infrastructure flakes. Also includes a small UX regression fix where a join success toast could fail to fire due to an unmounting effect. (#3618, #3623) — Thank you @senamakel-droid and @sanil-23!

Always-on Developer & Diagnostics access 🛠️

Developer & Diagnostics settings are now always visible—no more "Developer Mode" gate. This surfaces the Settings section, related settings search entries, and the Intelligence "council" tab by default, with tests updated accordingly. (#3639) — Thank you @senamakel!

Contributor Credits

Thanks to everyone who contributed to this release: @github-actions[bot], @sanil-23, @senamakel, and @senamakel-droid.

Full Compare

v0.57.39...v0.57.40

Contributors

• @senamakel
• @sanil-23
• @senamakel-droid

The Intelligence Upgrade 🎉

v0.57.18 to v0.57.39 brings 125 PRs across 146 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨

Highlights 🚀

🎙️ Voice & hands-free control

Voice and hands-free control get more useful across the desktop, with always-on listening, global push-to-talk, faster command routing, and stronger automation paths for interacting with apps. (#3349, #3420, #3531, #3545, #3551, #3558, #3619) — Thank you @CodeGhost21, @sanil-23, @M3gA-Mind, and @oxoxDev!

🧠 Memory & intelligence

Memory and intelligence flows are faster, clearer, and more resilient, from source sync controls and richer ingest to batched embeddings and delegated memory retrieval. (#3413, #3417, #3418, #3421, #3422, #3424, #3428, #3438, #3439, #3441, #3444, #3446, #3447, #3454, #3459, #3479, #3480, #3499, #3521, #3578, #3580, #3583, #3586, #3587, #3590, #3598, #3611, #3613) — Thank you @sanil-23, @senamakel, @senamakel-droid, @oxoxDev, @graycyrus, and @michaelk1957!

✅ Tasks, chat & agent workflows

Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#3388, #3399, #3411, #3412, #3419, #3426, #3443, #3456, #3457, #3458, #3477, #3481, #3483, #3497, #3500, #3519, #3528, #3530, #3532, #3533, #3544, #3546, #3553, #3555, #3556, #3562, #3563, #3564, #3581, #3584, #3591, #3594, #3596, #3597, #3600, #3601, #3607, #3610) — Thank you @senamakel, @graycyrus, @sanil-23, @senamakel-droid, @oxoxDev, @alexzhu0, and @YellowSnnowmann!

🔐 Reliability, security & platform polish

Reliability and platform behavior are tightened across security policy, credential handling, session health, CEF startup, Windows filesystem edge cases, and release-only build paths. (#3409, #3423, #3427, #3450, #3496, #3498, #3526, #3529, #3534, #3557, #3559, #3579, #3589) — Thank you @oxoxDev, @senamakel, @M3gA-Mind, and @sanil-23!

🧩 Integrations, UI & developer foundations

Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#3402, #3442, #3445, #3448, #3451, #3452, #3453, #3455, #3460, #3461, #3462, #3473, #3476, #3485, #3492, #3501, #3502, #3515, #3516, #3517, #3518, #3520, #3527, #3536, #3543, #3552, #3569, #3571, #3572, #3573, #3574, #3575, #3582, #3588, #3592, #3593, #3599, #3612, #3614) — Thank you @oxoxDev, @senamakel-droid, @senamakel, @YellowSnnowmann, @Sathvik-1007, @graycyrus, @sanil-23, and @alexzhu0!

New Contributors 🌟

• Welcome michaelk1957! Thank you for #3598 fix(memory): stop oversized/dense chunks from breaking bge-m3 embedding.

Hope you join the Discord for exclusive roles and contributor rewards!

Contributor Credits 🙌

• Alexzhu (#3536, #3543, #3544) — thank you!
• CodeGhost21 (#3349) — thank you!
• Cyrus Gray (#3399, #3518, #3533, #3569, #3573, ...

Contributors

• @senamakel
• @graycyrus
• @M3gA-Mind
• @oxoxDev
• @CodeGhost21
• @YellowSnnowmann
• @alexzhu0
• @Sathvik-1007
• @michaelk1957
• @sanil-23
• @senamakel-droid

What's Changed

• feat(orchestrator): wire generate_presentation + require grounding (#2780) by @oxoxDev in #3029
• fix(inference): stream + SSE-aggregate Codex OAuth Responses calls (#3201) by @YOMXXX in #3288
• Add task source UI and agent launch flow by @senamakel in #3279
• perf(memory_sync): bounded-concurrency GitHub item reads by @mysma-9403 in #3287
• feat(artifacts): publish ArtifactPending event + artifact_pending socket bridge (#3162 backend) by @YOMXXX in #3277
• feat(file_state): guard cross-agent file edits from stale sibling writes by @senamakel in #3316
• feat(agent): add active-run steering and queue controls by @senamakel in #3317
• fix(chat): rename default thread label to general by @senamakel in #3319
• Suggest OpenRouter free models when credits run out by @senamakel in #3320
• feat(agent): persist oversized tool outputs by @senamakel-droid in #3327
• Bucket chat threads by source by @senamakel in #3330
• feat(chat): Quick/Reasoning toggle + resolved model display by @senamakel in #3325
• feat(tasks): autonomously execute approved/assigned task-board work (poller + update_task + repetition fix) by @sanil-23 in #3326
• feat(tools/system): route node_exec and npm_exec through sandbox backend like shell by @CodeGhost21 in #3309
• feat(artifacts): persist thread_id + ai_list_artifacts thread filter (#3226) by @YOMXXX in #3274
• feat(memory-sync): record periodic Composio syncs in the cost audit (#3111 follow-up) by @justinhsu1477 in #3276
• fix(composio): correct direct-mode v3 execute contract + classify 404/410 as action-not-found (#3219) by @oxoxDev in #3298
• feat(presentation): embed images in generated decks (#3209) by @oxoxDev in #3299
• docs(config): refer to minimax/m3 in team model-pin example by @octo-patch in #3303
• perf(memory_sync): bounded-concurrency Notion/ClickUp/Linear ingest by @mysma-9403 in #3322
• fix(composio): expose daily-budget + sync-interval via env (#2437 F) by @CodeGhost21 in #3314
• feat(settings): make action_dir editable in Agent OS access (#3240) by @oxoxDev in #3305
• feat(computer): main-thread synthetic-input executor + CEF crash fix (1/8 of #3307) by @M3gA-Mind in #3340
• feat: tighten runtime policy + transport guards v3 by @oxoxDev in #3306
• feat(agent): add active-run steering and queue controls by @senamakel in #3270
• fix(cron): halt agent-job retry on backend session-expired (TAURI-RUST-N) by @CodeGhost21 in #3350
• feat(accessibility): AX/UIA perception + automate engine (2/8 of #3307) by @M3gA-Mind in #3341
• fix(onboarding): brand logo on welcome + back-to-welcome from first step by @M3gA-Mind in #3366
• fix(inference,ai-settings): prevent + handle ollama embedding-model-as-chat (Sentry TAURI-RUST-4P6) (#3359) by @oxoxDev in #3360
• fix(intelligence): deduplicate and label connections in integration source picker by @YellowSnnowmann in #3361
• feat(agent): wire automate/ax_interact computer tools (3/8 of #3307) by @M3gA-Mind in #3342
• fix(cron): emit poll-tick health recovery so a single failed job can't permanently brick the scheduler (#3312) by @YOMXXX in #3329
• feat(agent): reduce orchestrator prompt bloat by @senamakel in #3367
• feat(voice): Phase 2 always-on listening engine + RPC (4/8 of #3307) by @M3gA-Mind in #3343
• fix(memory): thread BYO embedding credential — stop Cohere empty-key 401 flood (#3354) by @oxoxDev in #3358
• fix(credentials): retry transient Windows FS errors when persisting auth-profiles.json (#3355) by @oxoxDev in #3364
• feat(memory-sources): default sync sources on with conservative caps, per-source settings & All In by @graycyrus in #3304
• feat(settings): make action_dir editable via Settings → Agent access by @CodeGhost21 in #3313
• Implement SQLite-backed mtime state store by @manucian-official in #3186
• feat(voice): always-on Settings toggle + debug panel + i18n (5/8 of #3307) by @M3gA-Mind in #3344
• feat(notch): always-visible macOS notch status pill (6/8 of #3307) by @M3gA-Mind in #3345
• fix(credentials): reject expired session locally + gate usage polling — RCA for backend 401 flood (#3297) by @oxoxDev in #3384
• feat(agent): add control specialists and async subagent spawning by @senamakel in #3379
• feat(voice): Phase 3 fast command router (7/8 of #3307) by @M3gA-Mind in #3346
• feat(monitor): add first-class background monitor module by @senamakel in #3382
• feat(agent): expose agent library surface by @senamakel in #3383
• feat(memory): Notion doc-aware versioned memory tree + page-content ingest by @sanil-23 in #3378
• feat(accessibility): vision-click fallback for Electron/partial-AX apps (8/8 of #3307) by @M3gA-Mind in #3362
• feat(task-board): autonomous task runs as live task sessions (View work, cancel, degeneration guards) by @sanil-23 in #3380
• docs: add Urdu (ur-pk) README translation with RTL support by @AMIK-coorporations in #3387
• feat(mcp): multi-server lifecycle — enable/disable + error visibility (#3196) by @CodeGhost21 in #3339
• fix(keyring): don't mint a new master key on keychain access-denied (#3311) by @oxoxDev in #3338
• Test subagent cache reuse and chat tier routing by @senamakel in #3389
• Persist thread sidebar visibility by @senamakel in #3390
• feat(memory): clean noisy Notion markdown before ingest by @sanil-23 in #3381
• Persist agent run ledger state by @senamakel in #3391
• refactor(workflows): merge skills into the unified workflows primitive by @sanil-23 in #3324
• fix(composio): enrich connection picker with cached account identity (#3356) by @YellowSnnowmann in #3400
• fix(channels): presentation module private in release breaks the build (v0.57.16 release-blocker) by @M3gA-Mind in #3406
• fix(memory-sync): reliable per-source sync indicators and counters by @graycyrus in #3308
• feat(memory-sources): disable non-syncable toolkits in Add Source picker by @graycyrus in #3395
• feat(appearance): add global font size setting (#3120) by @graycyrus in #3396
• feat(intelligence): strip Memory tab to core view, hide analysis sub-pills by @graycyrus in #3397
• Improve council agent UX and persistence by @senamakel in #3393
• perf(memory): batch re-embed backfill into one provider request by @mysma-9403 in #3392
• test(credentials): cover rename-stage retry + best-effort tmp cleanup (#3364 follow-up) by @oxoxDev in #3398
• fix(composio): show connection ID in picker when no identity cached by @YellowSnnowmann in #3405
• fix(inference): stop Codex CLI import user-state errors flooding Sentry (#3403) by @oxoxDev in #3404
• feat(memory-sync): configurable global sync interval (4h/12h/24h/manual) by @graycyrus in #3408
• chore(welcome): remove orphaned useBackendReachable probe (#2037) by @oxoxDev in #3410
• feat(agent_meetings): wire mascotId through full stack + fix tests by @YellowSnnowmann in https://githu...

Contributors

• @YOMXXX
• @senamakel
• @mysma-9403
• @graycyrus
• @M3gA-Mind
• @oxoxDev
• @CodeGhost21
• @YellowSnnowmann
• @justinhsu1477
• @manucian-official
• @AMIK-coorporations
• @sanil-23
• @octo-patch
• @senamakel-droid

What's Changed

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

New Contributors

• @finedesignz made their first contribution in #2472

Full Changelog: v0.57.11...v0.57.13

Contributors

• @finedesignz
• @senamakel
• @mysma-9403
• @M3gA-Mind
• @oxoxDev
• @CodeGhost21
• @YellowSnnowmann
• @alexzhu0
• @manucian-official
• @zahica1234
• @sanil-23

What's Changed

• Add vault file-system watcher implementation by @manucian-official in #3183
• fix(subconscious): degrade WAL journal mode to fix Intelligence tab hang on shm-incompatible filesystems by @M3gA-Mind in #3233

Full Changelog: v0.57.10...v0.57.11

Contributors

• @M3gA-Mind
• @manucian-official

What's Changed

• fix(agent): refresh orchestrator integration context on mid-session OAuth (#3044) by @oxoxDev in #3153
• feat(memory): record real LLM cost in sync audit (#3110) by @oxoxDev in #3150
• feat(agent/multimodal): support [FILE:...] markers with text extraction (#2777) by @oxoxDev in #2954
• feat(security): separate agent action sandbox from internal workspace state by @senamakel in #3074
• fix(inference): surface actionable error when Managed route fails with no credits by @senamakel-droid in #3121
• fix(memory/safety): exclude bare-phone patterns from strict PII rejection (#2848) by @oxoxDev in #3028
• test: green Rust Core Coverage (stale assertions + env-race serialization) by @sanil-23 in #3156
• fix(composio): complete connection-disconnect cleanup (config entry + memory tree) by @sanil-23 in #3140
• feat(analytics): wire product event tracking by @senamakel in #3123
• refactor(agent): unwire eager 7-day memory-tree digest from turn loop (#3170) by @sanil-23 in #3171
• docs: clarify script install verification status by @alexzhu0 in #3066
• fix(scripts): make checklist help exit cleanly by @alexzhu0 in #3067
• fix(scripts): normalize agent-batch help exits by @alexzhu0 in #3068
• fix(scripts): add help to coverage gates by @alexzhu0 in #3070
• fix(scripts): validate i18n bundle dist flag by @alexzhu0 in #3071
• fix(scripts): reject invalid mock API ports by @alexzhu0 in #3072
• test(scripts): run OpenClaw formatter tests without vitest by @alexzhu0 in #3063
• fix(ai-settings): reset orphaned local-runtime routing when the runtime is disabled by @sanil-23 in #3167
• revert: remove all Sentry error suppression (12 PRs) by @graycyrus in #2959
• perf(memory_tree): batch drill_down BFS walker per depth by @mysma-9403 in #3032
• fix(subagent): box-pin engine recursion to fix tokio worker stack overflow by @CodeGhost21 in #3151
• refactor(composio): extract derive_toolkit_slug helper by @YOMXXX in #3035
• fix(runtime): apply 16 MiB worker stack to desktop core + agent CLI runtimes (#3159) by @YOMXXX in #3175
• fix(sentry): bind scope user at session boundaries + core boot (#3135) by @YOMXXX in #3176
• fix(inference): normalize 0.0.0.0 to 127.0.0.1 in Ollama URL + add endpoint edit button by @senamakel-droid in #3161
• feat: sync budget controls + agent activity level picker (#3117) by @senamakel-droid in #3174
• feat(memory-sync): track Composio API action count + cost in sync audit (#3111) by @justinhsu1477 in #3138
• fix(cron): make cron_run non-blocking, enqueue async execution (#3127) by @YellowSnnowmann in #3142
• chore(ci): simplify release workflows — remove pretests, add commit picker and bump-only mode by @senamakel in #3177
• feat(mascot): sync Rive mascot with new poses, viseme codes & mood detection by @senamakel in #3173
• chore(ci): remove staging_tag promotion path from release-production by @senamakel in #3179
• fix(codex): compare strict preflight paths by realpath by @alexzhu0 in #3060
• feat(meet): pre-fill owner display name from Persona settings (refs #2945) by @hemanth1999k in #3034
• refactor(subconscious): replace task system with agent-per-tick model by @senamakel in #3079
• fix: Homebrew install error and Discord channel listing (#3085) by @YellowSnnowmann in #3144
• fix(email): add date_local field with host timezone to email reshaper (#3128) by @YellowSnnowmann in #3143
• docs: remove stale PR markers from coverage matrix by @alexzhu0 in #3064
• fix(scripts): validate mock webview bridge port by @alexzhu0 in #3073
• fix(e2e): improve core startup diagnostics and fail-fast error reporting by @manucian-official in #3131
• feat(about_app): catalog entry for GitHub repo memory source (#3047 follow-up) by @justinhsu1477 in #3114
• feat(mascot): add emotional reaction layer for conversation state (#1144) by @staimoorulhassan in #3019
• fix(routines): deduplicate morning_briefing jobs on seed boot (#3126) by @YellowSnnowmann in #3141
• observability(sentry): attach user id to Rust-core events (#3135) by @oxoxDev in #3136
• fix(memory-sync): migrate ClickUp sync to memory_tree pipeline (#2885) by @YOMXXX in #3080
• feat(onboarding): guided memory & vault setup with health checklist (#2910) by @oxoxDev in #3160
• Add deployment workflow for OpenHuman by @manucian-official in #3178
• fix(test): feed multi_batch_volume_builds_full_tree past the 50k seal threshold (#3115) by @oxoxDev in #3181
• fix(oauth): reject persisted profiles without access tokens by @izumi0uu in #3180
• fix(e2e): fix 32 failing E2E tests across chat, onboarding, skills, connectors and settings by @M3gA-Mind in #3137
• feat(chat): redesign composer to two-row layout with toolbar by @graycyrus in #3165
• test(e2e): update composer selectors for new placeholder + voice button by @graycyrus in #3206
• fix(chat): give agent-error "Report on Discord" its own error-report modal by @graycyrus in #3208
• feat(tools): add generate_presentation tool (native rust engine, ppt-rs) (#2778) by @oxoxDev in #3016
• fix(chat): hide image attachment button until backend supports it (#3205) by @sanil-23 in #3212
• fix(test): only source ~/.cargo/env when it exists by @erxiong0 in #3184
• feat(chat): ArtifactCard + Tauri download + backend artifact events (#2779) by @oxoxDev in #3017
• fix(scheduler-gate): build fresh System per CPU sample to avoid sysinfo OOB panic by @oxoxDev in #3191
• fix: disable storage for Codex responses requests by @honor2030 in #3192
• fix(composio): empty connections in direct mode without api key (TAURI-RUST-R4) by @oxoxDev in #3198
• docs(env): document OPENHUMAN_BRAVE_API_KEY + OPENHUMAN_PARALLEL_API_KEY in .env.example (#3098 sub-issue 4) by @CodeGhost21 in #3218
• fix(channels): honor chat_provider workload routing in channel runtime (#3098 sub-issue 1) by @CodeGhost21 in #3217
• fix(channels): classify empty-response, 4xx and vision chat errors with actionable copy (#3119) by @oxoxDev in #3199
• fix(tauri): gate cef_preflight to macOS/Linux to fix Windows build by @M3gA-Mind in #3225
• fix(scripts): add short help to PR main sync by @alexzhu0 in #3221
• perf(learning): overlap reflection pattern/pref writes with join_all by @mysma-9403 in #3216
• fix(ci): key vendored tauri-cli cache by runner.arch to fix Linux x64 release build by @M3gA-Mind in #3228

New Contributors

• @alexzhu0 made their first contribution in #3066
• @izumi0uu made their first contribution in #3180
• @erxiong0 made their first contribution in #3184

Full Changelog: v0.57.5...v0.57.10

Contributors

• @YOMXXX
• @honor2030
• @senamakel
• @staimoorulhassan
• @hemanth1999k
• @mysma-9403
• @erxiong0
• @izumi0uu
• @graycyrus
• @M3gA-Mind
• @oxoxDev
• @CodeGhost21
• @YellowSnnowmann
• @alexzhu0
• @justinhsu1477
• @manucian-official
• @sanil-23
• @senamakel-droid

What's Changed (since v0.56.0)

✨ Features

Agent & Orchestration

• feat(agent): multi-agent personalities with scoped memory and delegation by @senamakel in #2895
• feat(agent): add orchestration control plane by @senamakel in #2996
• feat(agent): live streaming subagent view with reopenable sub-threads by @senamakel in #3007
• feat(agent): apply iteration turn cap only to short-running agents by @senamakel in #3056
• feat(agent-registry): add configurable agent registry by @senamakel in #2993
• feat(subagent): persist sub-agent runs and let orchestrator relay user messages by @senamakel in #3055
• feat(model-council): multi-model deliberation — parallel members + chair synthesis by @aashir-athar in #2890
• feat(workflows): agent workflows — phase-keyed task lifecycle playbooks by @senamakel in #3008
• feat: proactive agent task pipeline — dispatcher, approval, executors, write-back by @sanil-23 in #2974
• feat: Agent Tasks board + Settings > Agents registry panel by @senamakel in #2998
• Enrich agent task board workflow by @senamakel in #2891
• feat(task-sources): proactive task ingestion from GitHub/Notion/Linear/ClickUp by @senamakel in #2894

Memory & Intelligence

• feat(memory): redesign sync flow with ingest_summary, graph improvements, audit log by @senamakel in #3113
• feat(memory): smart multi-strategy retrieval walk by @senamakel in #3077
• feat(memory): repo-grouped GitHub raw archive + entities & priority by @senamakel in #3047
• feat: Memory subtabs + WebGL memory graph; drop Knowledge Vaults by @senamakel in #3040
• feat(memory_sources): add Memory Sources domain — user-configurable data connectors by @senamakel in #2893
• feat(memory-conversations): trigram inverted index for cross-thread search by @mysma-9403 in #2756
• feat(migration): add Hermes Agent memory importer (#1440) by @YOMXXX in #2799
• feat(intelligence): add Knowledge Graph Centrality by @aashir-athar in #2931
• feat(intelligence): add Knowledge Freshness by @aashir-athar in #2932
• feat(intelligence): add Entity Associations by @aashir-athar in #2942
• feat(intelligence): add Connection Path finder by @aashir-athar in #2946
• feat(intelligence): add Memory Timeline by @aashir-athar in #2950
• feat(intelligence): add Graph Cohesion by @aashir-athar in #2978
• feat(intelligence): add Namespace Overview by @aashir-athar in #2964
• feat(intelligence): add architecture diagram viewer by @sunilkumarvalmiki in #2687

MCP

• feat(mcp): ship MCP registry — unhide UI, transport-aware install, reconfigure, registry creds (#3039) by @senamakel-droid in #3058
• feat(mcp): interactive Tool Execution Playground (schema viewer + JSON args editor + run + history) by @aashir-athar in #2644
• feat(mcp): Sharable Inventory — portable secret-free manifest with export, parse, validate, and explicit per-entry import by @aashir-athar in #2655
• feat(mcp): connection health toolbar with bulk Retry All / Disconnect All actions by @aashir-athar in #2641
• feat(mcp): search + keyboard navigation for installed MCP servers by @aashir-athar in #2639
• feat(mcp): expose bundled prompts as static MCP resources by @M3gA-Mind in #2745
• feat(mcp): implement resources/templates/list as static empty catalog by @obchain in #2828
• feat(mcp): i18n + a11y McpStatusBadge status labels by @aashir-athar in #2635
• feat(mcp-registry): InstalledServer HTTP-remote transport by @justinhsu1477 in #2603

Tools

• feat(tools): expose ~160 agent tools across 23 core domains (overextending tools default-OFF) by @senamakel in #3050
• feat(tool-registry): add trusted capability providers by @YOMXXX in #2551
• feat(tool_policy): diagnostics RPC and Developer Options panel by @MrMrVlad in #2715
• Add generated tool provenance and admission checks by @vaddisrinivas in #2549
• feat(image): add image tool contracts by @senamakel in #2997
• feat(search): add registry-backed search module by @senamakel in #2999
• feat(search): add Querit provider by @MurphyZzzzz in #2753

Inference & Providers

• Expand inference provider catalog (#3057) by @senamakel in #3062
• feat(inference): add claude_agent_sdk provider (Claude CLI subprocess) by @M3gA-Mind in #2746
• Add Codex OAuth provider support by @junjunjunbong in #2748
• feat(dashboard): per-model health comparison table by @Sathvik-1007 in #2823

UI & Chat

• feat(chat): auto-resize composer textarea to fit content by @graycyrus in #3139
• feat(chat): add image attachment support to composer by @rsd-darshan in #2676
• feat(chat): render agent-bubble LaTeX with KaTeX and safe math detection by @YellowSnnowmann in #2697
• feat(ui): hide dev-only features in production, clean up homepage by @senamakel in #3157
• feat(ui): user-friendly tool and agent labels in the chat tool timeline by @senamakel in #3054
• feat(ui): add Routines page — user-friendly scheduled tasks view in #2858
• feat(events): live domain event stream log panel by @Sathvik-1007 in #2653

Settings

• feat(settings): Agents settings hub + dedicated agent editor by @senamakel in #3005
• feat(settings): Crypto + Notifications hubs, wallet send/receive & multi-network balances by @senamakel in #3027
• feat(settings): surface approval history audit trail by @obchain in #2949
• feat(settings): make autocomplete tuning fields editable by @obchain in #2973
• feat(settings): add Dev Workflow config panel by @graycyrus in #2703
• feat(config): add UI control for agent action timeout (#3100) by @senamakel-droid in #3112
• feat(cost): add settings cost dashboard with global tracker, dashboard RPCs, and charts by @YellowSnnowmann in #2762

Wallet & Web3

• feat(web3): add swap/bridge/dapp module; slim wallet to primitives by @senamakel in #3006
• feat(wallet): surface multi-chain balances in Settings by @obchain in #2686
• feat(wallet): bind prepared transaction quotes to originating chat session in #2688

Cron & Skills

• feat(cron): complete smart scheduling flow from chat + polish cron management UI by @YellowSnnowmann in #2943
• feat(skills): scheduled dashboard + run/new pages + [github] preflight gate + composio-only GitHub I/O by @M3gA-Mind in #2882
• feat(skills,tools): schema↔serde roundtrip tests, triggers field, bus subscriber, registry integrity by @zahica1234 in #2718

Voice & Mascot

• feat(voice): polish mascot TTS/STT session states and lifecycle by @staimoorulhassan in #2916
• feat(mascot): add emotional reaction layer for conversation state by @staimoorulhassan in #2900

Other Features

• feat(approval): per-launch UUID session_id + scrub legacy bearer leaks by @oxoxDev in #2952
• feat(core): pass in-process RPC bearer via internal handle, not process env by @oxoxDev in #2709
• feat(artifacts): define artifact storage types,...

Contributors

• @lrt4836
• @YOMXXX
• @sunilkumarvalmiki
• @senamakel
• @Zavianx
• @vaddisrinivas
• @EvanCarson
• @staimoorulhassan
• @mysma-9403
• @MurphyZzzzz
• @ccpty
• @aashir-athar
• @HariNayan
• @Felyx-Fu
• @graycyrus
• @M3gA-Mind
• @ARYAN007H
• @junjunjunbong
• @oxoxDev
• @CodeGhost21
• @YellowSnnowmann
• @obchain
• @shriii257
• @rsd-darshan
• @justinhsu1477
• @Sathvik-1007
• @zahica1234
• @sanil-23
• @MrMrVlad
• @senamakel-droid

What's Changed

• fix(shell): use app-level hide on macOS close button (#2049) by @M3gA-Mind in #2118
• feat(memory): activate chat memory pipeline — Archivist wiring, LLM recaps, cross-thread STM recall, segment-granular tree, unified compaction by @sanil-23 in #2175
• feat(memory): #1574 Stage 2 — per-(row,model) embedding storage live (cutover + migration + re-embed backfill + switch UX) by @sanil-23 in #2153
• fix(ai-settings): filter reserved slugs in loadAISettings and saveAISettings by @M3gA-Mind in #2184
• fix(core-state): clarify retry failure logs by @okbexx in #2167
• fix(core-state): fix retry counter log and add backoff after bootstrap exhaustion by @M3gA-Mind in #2194
• fix(integrations): strip inference path from backend URL (#2075) by @obchain in #2101
• feat(billing): drop rate-limit UI, surface cycle usage insights by @senamakel in #2027
• fix(core): skip memory init on config failure instead of fabricating a default workspace (OPENHUMAN-CORE-48) by @sanil-23 in #2120
• feat(learning): explicit user-preference tool + always-on pinned-facet prompt injection by @sanil-23 in #2150
• feat(integrations): Polymarket trading + market data (#1398, venue 1/3) by @oxoxDev in #2145
• feat(inference): gate local Ollama models by memory-layer context-window minimum by @sanil-23 in #2122
• fix(observability): demote loopback sidecar-down noise to expected (#R5 #R6) by @oxoxDev in #2063
• fix(onboarding): clarify continue to chat fallback by @ajay-automates in #2173
• fix(inference): propagate temperature_unsupported_models to local routing providers by @YellowSnnowmann in #2221
• harden: validate webview event payloads by @LawyerLyu in #2036
• fix(security): docker hardening, homoglyph detection, async persist, public-bind warning by @Liohtml in #2011
• feat(core): desktop companion domain — session, pipeline, pointing (#1909) by @yuvrxj-afk in #2025
• fix(i18n): translate zh-CN contextGathering errorDesc (#1917) by @YOMXXX in #2042
• fix(memory): connection pooling + circuit breaker for memory_tree SQLite (#2206) by @M3gA-Mind in #2212
• fix: ignore core state commits after unmount by @LawyerLyu in #2021
• fix(observability): classify provider config-rejection 4xx as expected user-state (#2079) by @sanil-23 in #2239
• fix(voice): bound dictation WS audio buffer (partial fix for #1924) by @sanil-23 in #2238
• fix(memory): accept ISO-8601 / missing modified_at + default provider by @sanil-23 in #2237
• Enhance path validation to prevent symlink escape vulnerabilities by @why060522-Ayu in #2051
• fix(docker): chown workspace volume before dropping privileges so core can start (#2065) by @sanil-23 in #2235
• fix(appimage): unbreak Linux launch on modern GPUs / glibc by @mechmyday in #2052
• fix(linux): restore tauri-cef pin so AppImage stops bundling libm.so.6 (#2154) by @sanil-23 in #2236
• fix(meet): guard orchestrator handoff against transcript prompt injection by @obchain in #2056
• fix(telegram): stop duplicate operator-approval prompts for allowed users (#1948) by @sanil-23 in #2240
• fix(credentials): diagnose + recover from H8 auth-profile-lock create failures by @YellowSnnowmann in #2180
• fix(agent): bound cached resume transcript by max_history_messages by @YellowSnnowmann in #2224
• fix(reliable): fail fast on SESSION_EXPIRED in provider retry loop by @YellowSnnowmann in #2200
• fix(config): guard env overrides during config load by @YellowSnnowmann in #2201
• fix(tauri): resolve Linux CEF init panic — root/container + SingletonLock + display-server guards (OPENHUMAN-TAURI-K1) by @YellowSnnowmann in #2103
• Fix/embeddings OpenAI expected error reporting by @YellowSnnowmann in #2190
• docs: fix README spelling inconsistency by @navneet-singh2907 in #2233
• fix(i18n): translate contextGathering errorDesc across 8 remaining locales (#1917) by @evanclan in #2057
• feat(agent): cap runtime subagent spawn depth at MAX_SPAWN_DEPTH=3 by @srikaanthh in #2234
• test(cron): add stable job row selectors by @honor2030 in #2062
• fix(router): fall back to default_model when tier alias has no configured route (#2079) by @YOMXXX in #2080
• docs: fix markdown-lint warnings in README.md, README.ja-JP.md, README.ko.md by @HariNayan in #2168
• fix(channels): surface channel error status in selector by @honor2030 in #2169
• fix(providers): disable Responses API fallback for custom_openai by @M3gA-Mind in #2214
• fix(temperature): add Kimi K2 + Moonshot to default temperature-unsupported list (#2076) by @YOMXXX in #2082
• feat(channels): surface Lark/Feishu and DingTalk in the Settings UI (#2048) by @YOMXXX in #2083
• fix(db): restore Phase 3 user_profile indexes with correct migration ordering by @M3gA-Mind in #2211
• test(observability): pin SESSION_EXPIRED wire-shape regression tests (#SG) by @oxoxDev in #2188
• feat(migration): OpenClaw import surface + unblock unified-core Apply by @obchain in #2087
• docs: fix spelling inconsistency — summarised to summarized in README.md by @HariNayan in #2172
• fix(billing): suppress budget banner when all chat workloads route to a user-supplied provider (#2040, #2041) by @YOMXXX in #2053
• fix(tauri): forward hot-instance OAuth deep links by @NgoQuocViet2001 in #2229
• Fix Windows development setup: correct line endings and Rust PATH by @rmgy in #2066
• fix(e2e): resolve 30+ failing E2E specs — i18n, assertion, and import fixes by @senamakel in #2092
• fix(memory): guard against char-boundary panics in ingest persist path by @M3gA-Mind in #2102
• fix(linux): install silent X error handler to fix BadWindow exit on Wayland by @Muscolino96 in #2096
• fix: block Unicode homoglyph prompt-injection bypass by @LawyerLyu in #2067
• fix(core,app): authenticate /events/webhooks SSE with per-launch core RPC bearer (#1922) by @oxoxDev in #2114
• docs: add German translation (README.de.md) and update language switcher by @flitzrrr in #2160
• i18n: replace hardcoded Settings UI strings with t() calls (fixes #2225) by @Kymi808 in #2258
• fix(voice): allow local provider selection before install by @aqilaziz in #2257
• feat(app): desktop companion UI — Tauri bridge, overlay, settings (#1909) by @yuvrxj-afk in #2246
• feat(i18n): add Korean locale by @navneet-singh2907 in #2241
• fix(auth): point welcome legal links to docs by @aqilaziz in #2253
• fix(memory): serialize memory_tree schema init across worker pool by @oxoxDev in #2059
• fix: cap full-audio accumulator to prevent OOM in streaming dictation by @LawyerLyu in #2068
• fix(credentials): recover from leaked auth-profile lock on Windows (Sentry OPENHUMAN-TAURI-H1) by @YellowSnnowmann in #2085
• fix(search): let web_search_tool use direct search API by @aqilaziz in #2263
• Prevent duplicate chat sends while pending by @moningbird in #2071
• fix(observability): classify Kimi access_terminated 403 as expected provider use...

Contributors

• @distorx
• @DeadlySilent
• @leighstillard
• @kunci115
• @okbexx
• @YOMXXX
• @xiekailian
• @neillee95
• @honor2030
• @sunilkumarvalmiki
• @MootSeeker
• @senamakel
• @umarhadi
• @rmgy
• @Jessomadic
• @flitzrrr
• @Zavianx
• @Alexxigang
• @jimmershere
• @navneet-singh2907
• @vaddisrinivas
• @mechmyday
• @offbyone1
• @Minoo7
• @EvanCarson
• @aqilaziz
• @esadomer
• @yuvrxj-afk
• @hemanth1999k
• @mysma-9403
• @JAYcodr
• @1363033915
• @Muscolino96
• @HariNayan
• @pranavjana
• @evanclan
• @hobostay
• @dhimasardinata
• @NgoQuocViet2001
• @hakaitech
• @Felyx-Fu
• @SATYAM-PRATIBHAN
• @Kymi808
• @graycyrus
• @mengqiuzhen
• @M3gA-Mind
• @srikanthakkaru
• @ARYAN007H
• @xinzhuwang-wxz
• @Liohtml
• @sjh9714
• @oxoxDev
• @CodeGhost21
• @ajay-automates
• @Subharup-31
• @YellowSnnowmann
• @obchain
• @Bortlesboat
• @blu1606
• @shriii257
• @moningbird
• @justinhsu1477
• @manucian-official
• @YUHAO-corn
• @iamrhn
• @JZKK720
• @emixor
• @shadowdoggie
• @sanil-23
• @xilema2
• @MrMrVlad
• @LawyerLyu
• @why060522-Ayu
• @antfleet-ops

What's Changed

• fix(observability): skip Sentry for vision-disabled RAM-tier errors (OPENHUMAN-TAURI-3B) by @CodeGhost21 in #1623
• fix(observability): drop transient backend_api + integrations failures from Sentry by @oxoxDev in #1632
• test(local-ai): serialize Ollama env mutations by @Zavianx in #1656
• fix(socket): route sustained-outage escalation through observability classifier (OPENHUMAN-TAURI-BH) by @CodeGhost21 in #1672
• fix(triage): defer instead of error on prompt-guard rejection (OPENHUMAN-TAURI-X) by @CodeGhost21 in #1678
• docs: add open PR reconciliation handoff by @jwalin-shah in #1680
• fix(memory): use floor_char_boundary in body_preview slice by @Sathvik-1007 in #1681
• feat(memory): add #1538 benchmark fixtures for retrieval scenarios by @unn-Known1 in #1561
• fix(credentials): recover from stale auth-profiles.lock by @obchain in #1636
• fix(si_server): idempotent start_session, suppress benign 'session already active' (#5J, #5H) by @oxoxDev in #1635
• fix(updater): quiet passive check failures by @aqilaziz in #1685
• fix(agent): refresh delegation surface on mid-session Composio connect/revoke by @sanil-23 in #1687
• fix(startup): warn on WSL X11 desktop runs by @aqilaziz in #1686
• docs: add CONTRIBUTING-BEGINNERS.md for new contributors by @hemanth1999k in #1682
• Document portfolio readiness lint cleanup by @jwalin-shah in #1646
• chore: automate contributor reward invites by @Zavianx in #1589
• feat(orchestrator): collapse per-integration delegation into one tool (#1335) by @obchain in #1488
• fix(integrations): fall back to default backend when api_url points at local AI (#51, #80, #7Z) by @oxoxDev in #1630
• fix(agent): skip Sentry on max-iteration cap, emit info (#99, #98) by @oxoxDev in #1634
• fix(observability): classify backend 4xx as BackendUserError (OPENHUMAN-TAURI-BC) by @CodeGhost21 in #1676
• fix(normalization): guard function.arguments against malformed JSON and default to {} by @YellowSnnowmann in #1645
• Fix UTF-8 body_preview slicing in memory ingest by @honor2030 in #1620
• fix(windows): retry-with-backoff for transient FS errors on auth-profiles.lock + .openhuman wipe (#9E, #9C, #4Y, #61, #5Q, #9F, #4M) by @oxoxDev in #1641
• Update build-desktop.yml by @senamakel in #1706
• test(e2e): unify driver onto Appium Chromium attached to CEF CDP by @senamakel in #1696
• fix(providers): drop budget-exhausted 400s from Sentry (#3M, #12, #13) by @oxoxDev in #1633
• chore(review): inline review/fix prompts and add ws-reset workflow helper by @senamakel in #1695
• fix(settings): add type=button to analytics toggle for Windows WebView2 (#1698) by @PranavAgarkar07 in #1722
• test: expand unit + e2e coverage from test-map across core domains by @senamakel in #1724
• Fix composio integrations URL base normalization by @oxoxDev in #1715
• test(harness): smart mock LLM provider + fake Composio backend + 21 new tests by @senamakel in #1729
• fix(orchestrator): prefer live integrations over memory_tree for inbox/doc queries by @senamakel in #1731
• feat(agent): add dedicated crypto_agent for wallet & market ops (#1397) by @senamakel in #1736
• chore(migrations): phase out PROFILE.md from disk on schema_version=1 by @sanil-23 in #1734
• fix(memory_tree, e2e tests ): deterministic query_topic ordering + robust CEF cleanup by @sanil-23 in #1751
• test: expand unit + e2e coverage from test-map (batch 2) by @senamakel in #1752
• feat(voice): fully-local STT + TTS via Whisper/Piper provider factory by @sanil-23 in #1755
• fix(memory): add fallback model chain for unavailable GMI models by @Sathvik-1007 in #1704
• fix(composio): retry once on post-OAuth auth-error gap (#1688) by @obchain in #1708
• feat(orchestrator): use reasoning-quick-v1 for low-latency chat by @senamakel in #1761
• Fix Jira Composio subdomain authorization by @aqilaziz in #1733
• fix(voice): forward audio setup errors through setup_tx (OPENHUMAN-TAURI-AE) by @CodeGhost21 in #1770
• fix(e2e/linux): silence dead-session noise + local docker harness refresh by @senamakel in #1777
• fix(update): keep dismissed repeated errors hidden by @aqilaziz in #1773
• fix(onboarding): keep skip completion moving after task sync failure by @aqilaziz in #1771
• fix: pre-CEF single-instance mutex guard on Windows + provider retry for 502s by @YellowSnnowmann in #1723
• fix(channels): demote channel-message 404s to typed error (OPENHUMAN-TAURI-2Y) by @oxoxDev in #1732
• feat(agent-workflows): Cursor Cloud Agents parallel workflow (#1480) by @CodeGhost21 in #1759
• feat(mcp): add stdio memory server by @Zavianx in #1760
• fix(observability): classify SessionExpired at agent layer (OPENHUMAN-TAURI-26) by @CodeGhost21 in #1763
• refactor(api): migrate callers to effective_backend_api_url by @Sathvik-1007 in #1764
• Allow private HTTP core URLs by @vaddisrinivas in #1765
• fix(tauri): skip deep-link register_all when xdg-mime is missing (OPENHUMAN-TAURI-AS) by @CodeGhost21 in #1766
• chore: gitignore tmp/ by @senamakel in #1780
• fix(composio): retry post-oauth action readiness error by @Zavianx in #1707
• fix(providers): user-actionable hint when model_fallbacks unconfigured (#1596) by @obchain in #1712
• Filter transient updater Sentry noise by @oxoxDev in #1716
• test: expand unit + e2e coverage from test-map (batch 3) by @senamakel in #1778
• fix(security): surface Windows ACL repair hint when .secret_key is unreadable by @Lunar-feedmob in #1748
• docs(CONTRIBUTING): add missing macOS prereqs (Ninja, x86_64 target, ... by @aregmii in #1783
• feat(memory): optional agentmemory backend (closes #1664) by @rohitg00 in #1743
• feat(tools): integrate Seltz as a direct-API search tool by @amallia in #1717
• Update README.md by @senamakel in #1792
• fix(e2e): dismiss BootCheckGate picker before every spec (mega-flow root cause) by @senamakel in #1779
• refactor(routing): rename hint:reasoning-quick → hint:chat by @senamakel in #1801
• fix: add error handling to parseServiceCliOutput by @hobostay in #1737
• fix(observability): drop 401 session-expired Sentry noise (#25, #1Q, #27, #1G) by @oxoxDev in #1719
• fix(jira): collect Atlassian subdomain and handle ConnectedAccount_MissingRequiredFields by @YellowSnnowmann in #1726
• fix(tauri): disable GPU on Linux for Mesa 26+ EGL compatibility (closes #1697) by @PranavAgarkar07 in #1809
• fix(observability): demote composio validation noise to expected user-state (#3R #3S #33 #34 #97) by @oxoxDev in #1795
• fix(voice): atomic install-start guard for Whisper/Piper install RPCs by @sanil-23 in #1787
• fix(app): tame core state and rewards timeout noise by @RajvardhanPatil07 in #1822
• test: guard RPC alias catalog freshness by @honor2030 in https://githu...

Contributors

• @dwd888999
• @amallia
• @okbexx
• @paulpanwang
• @xuruiray
• @YOMXXX
• @MackDing
• @honor2030
• @eltociear
• @senamakel
• @Zavianx
• @vaddisrinivas
• @aqilaziz
• @rohitg00
• @hemanth1999k
• @shguddn8591
• @Monking-21
• @PranavAgarkar07
• @JasonOA888
• @hobostay
• @NgoQuocViet2001
• @Yong-yuan-X
• @therahul-yo
• @chiehwangs
• @graycyrus
• @M3gA-Mind
• @aregmii
• @xinzhuwang-wxz
• @Liohtml
• @oxoxDev
• @CodeGhost21
• @NikhilDhaliya
• @YellowSnnowmann
• @obchain
• @aryash45
• @ZaynRae
• @amiitt001
• @justinhsu1477
• @LuoYe17
• @Sathvik-1007
• @unn-Known1
• @Lunar-feedmob
• @jwalin-shah
• @HereIsKrishna
• @RajvardhanPatil07
• @sanil-23
• @rohanvibe
• @iuyup
• @rafaelfiguereod-stack
• @LawyerLyu

What's Changed

• fix(observability): skip Sentry for transport-level + transient-upstream errors (TAURI-32 / 5Z / 2G) by @CodeGhost21 in #1601
• feat: add yellow mascot bum dance animation by @NeilDesign1 in #1603
• fix(observability): skip Sentry for transport-level update.check_releases failures (OPENHUMAN-TAURI-2F) by @CodeGhost21 in #1605
• docs: clarify contributor setup by @honor2030 in #1618
• fix(chat): stop duplicating assistant replies on multi-segment turns by @sanil-23 in #1648
• fix(api): safely join api_url + path so misconfigured base can't corrupt routes by @senamakel in #1650
• refactor(mock-api): domain split + OAuth + Composio + e2e workflow + macOS mega-spec scaffold by @senamakel in #1532
• docs: add Windows-specific setup instructions for beginners (closes #... by @iuyup in #1629
• feat(local_ai): unify memory embeddings — cloud Voyage default + live local toggle + dev infra by @sanil-23 in #1640
• fix(auth): offer "clear app data" recovery when login decryption fails by @senamakel in #1652
• feat(scripts): add 8-check pre-merge gate to merge.sh by @graycyrus in #1665
• chore: add issue triage workflow for removing dupes by @graycyrus in #1668
• fix(whatsapp_data): preserve anyhow cause chain in RPC error envelopes (OPENHUMAN-TAURI-6B) by @CodeGhost21 in #1639
• test: wait for local model usage flags to load by @honor2030 in #1643
• fix(si_server): skip Sentry for benign "session already active" start_session race (OPENHUMAN-TAURI-5H) by @CodeGhost21 in #1625
• fix(core_process): demote expected port-clash + Windows bind ACL to warn (#2B, #AT, #BV, #BT) by @oxoxDev in #1628
• fix(observability): skip Sentry for local-AI " binary not found" errors (OPENHUMAN-TAURI-9N) by @CodeGhost21 in #1669
• Document OpenHuman portfolio readiness cleanup by @jwalin-shah in #1661
• perf(composio/gmail): cut redundant fetches on incremental sync (#1404) by @obchain in #1474
• feat(local_ai): bind owned ollama serve lifecycle to openhuman (#1622) by @sanil-23 in #1638
• fix(team): preserve anyhow cause chain in backend RPC error envelopes (OPENHUMAN-TAURI-AD) by @CodeGhost21 in #1647
• fix(agent): synthesise delegate_ tools after live integrations fetch by @senamakel in #1670
• feat(settings): add mascot color customization (closes #1651) by @senamakel in #1667
• fix(settings): round-trip LLM provider model_routes and consolidate UI by @senamakel in #1660

New Contributors

• @honor2030 made their first contribution in #1618
• @iuyup made their first contribution in #1629

Full Changelog: v0.53.40...v0.53.43

Contributors

• @honor2030
• @senamakel
• @graycyrus
• @oxoxDev
• @CodeGhost21
• @obchain
• @jwalin-shah
• @sanil-23
• @NeilDesign1
• @iuyup