Releases
Product release notes, changelog, and feed links for Wizzo.
v0.51.0
Jun 9, 2026- Selected `v0.51.0` as the First-Win Follow-Through Beta, focused on turning one source-backed recommendation into one visible completed win across chat, Today/Journey, voice, personalization, and onboarding.
- Improved accepted first-win recommendations so source-backed chat suggestions keep Trial-aware routing, useful labels, time estimates, and show/accept/create telemetry instead of landing as generic quests.
- Kept accepted first-win recommendation quests visible in Today/Journey as the primary next-win path when no overdue or due-today work needs attention.
- Aligned Journey voice follow-up quests with the first-win contract so spoken check-ins create classified AI recommendations with useful labels, theme decisions, and funnel telemetry.
- Extended Today/Journey first-win follow-through telemetry so started, snoozed, completed, and chat-handoff actions emit privacy-safe funnel evidence without raw quest title or notes.
v0.50.1
Jun 8, 2026v0.50.0
Jun 2, 2026- Added the first v0.50 Today/Journey command-center slice: Journey now promotes one transparent Today plan with due, time, label, priority, source, and recent-behavior signals plus accept, snooze, complete, and chat handoff telemetry.
- Added structured connector context to the v0.50 Today/Journey command center so connector-created quests carry safe connector labels and the Today plan can explain Gmail, Calendar, GitHub, or Drive provenance without exposing raw connector event IDs.
- Added contextual chat tool guidance so the tool menu can recommend web search, deep research, document analysis, code execution, or image generation from the current draft, Journey or voice handoff state, and attached files while preserving explicit confirmation gates.
- Added the first Microsoft 365 connector implementation slice with source-specific Outlook Calendar and OneDrive registry entries, least-privilege Graph scope policy, Pro-preview gating, and attribution/retention guardrails for connector-derived suggestions.
- Added Microsoft 365 OAuth connection lifecycle support for Outlook Calendar and OneDrive, including signed consent state, token/profile persistence, settings-panel connect/disconnect controls, and local token deletion after the final Microsoft 365 source is disconnected.
v0.49.0
May 26, 2026- Added quest time tracking and privacy-safe labels as personalization primitives, including Trials create/edit fields, telemetry payloads, sequencing inputs, and personalization dataset exports.
- Deepened personalized recommendations with current quest time/label inputs, opt-in safe memory signals, accept/reject feedback loops, and visible source attribution.
- Added CDN and edge-cache policy for static assets, public release metadata, app metadata, and public OG images, plus release promotion verification and live bug-bash evidence gates for major release windows.
- Added a unified observability dashboard at `/admin/observability` that consolidates release health, runtime telemetry, admin analytics, AI/ML evidence, system context, alerts, and cache signals with source-level failure handling and release-health drilldowns.
- Added chat tool-menu and tool-run conversion telemetry so impressions, selections, invocations, cancellations, completed tool results, and downstream chat/quest follow-through are captured as privacy-safe product events.
v0.48.0
May 25, 2026- Added opt-in MCP connector quest automation rules: connector events can now create review-first quest drafts or explicitly enabled auto-created quests with product-event and quest-audit provenance.
- Added voice-first Journey check-ins with daily and weekly review modes that capture speech, preserve editable transcripts, and hand off progress prompts to the main chat with telemetry.
v0.47.0
May 24, 2026- Added connector-aware smart quest suggestions so opted-in Calendar, Gmail, and Google Drive MCP activity can create attributed next-action prompts with acceptance/follow-through telemetry.
- Repositioned `/journey` as the daily "Today" cockpit: sidebar hierarchy now puts Today before Trials, and the page now uses a decision-first command surface, weekly pulse cards, and a capped next-move queue instead of duplicating full management dashboards.
v0.46.0
May 24, 2026- Reorganized backlog documentation so `docs/backlog/ACTIVE_BACKLOG.md` is the current execution queue, `docs/backlog/RELEASE_GATES.md` is the validation contract, completed release-prep and AI rebaseline artifacts live under `docs/backlog/archive/`, and sprint-history backlog redirect stubs are removed.
- Added an RC smoke-test gate with `pnpm test:rc-smoke` and `pnpm validate:rc-smoke-gate` so pre-tag checks cover public status/metrics, authenticated chat, Public API token issuance, and core settings surfaces.
- Added rollback drill evidence and `pnpm validate:rollback` so release rollback procedures are validated before release freeze.
- Added release bug bash and freeze evidence plus `pnpm validate:release-freeze` so release-critical issue gates are checked before production validation.
- Added a release notes approval gate with a required issue template, release-owner/product/technical/marketing sign-offs, and `pnpm validate:release-approval` before tagging.
v0.45.0
May 11, 2026- Closed Milestone 10 sprint documentation by replacing Sprint 45 and Sprint 46 planning artifacts with canonical completion records, including a deferred closeout for mobile scope and a final connector closeout record for provider rollout and webhook audit delivery.
- Added an April 2026 AI competitiveness audit, rebaseline plan, and active AI backlog to recenter Wizzo around the main chat, grounded tools, integrations, and deliberate de-scoping of stale pilot-era AI surfaces.
- Graduated connector positioning for the 2026 AI reset: Google Drive, Gmail, and Calendar are now treated as core work connectors, while GitHub remains supported as an advanced technical connector.
- Improved AI memory recall so chat context now prioritizes execution-oriented memories such as plans, follow-ups, blockers, quest context, deadlines, and recent progress over generic preference replay.
- Completed the agentic planning decision: the legacy planning flow is now framed as an internal Labs fallback, with neutral deep-research telemetry and a deprecated compatibility route.
v0.44.2
Feb 11, 2026- Stabilized first-message chat UX by preventing conversation bootstrap reloads from clobbering optimistic assistant streaming updates.
v0.44.1
Feb 11, 2026- Hardened production API exposure controls with verified post-deploy endpoint gating and payload redaction for sensitive diagnostics and migration routes.
- Added security-focused production validation assertions so endpoint access-control regressions fail release validation before rollout sign-off.
v0.44.0
Feb 10, 2026- Published Sprint 44 closeout artifacts for Milestone 10 reprioritization continuity: `SPRINT_44_COMPLETION.md`, `sprint_44_master_prompt.md`, `SPRINT_44_TESTING_GUIDE.md`, and `SPRINT_44_TEST_REPORT.md`.
- Aligned Milestone 10 references across planning docs, roadmap, backlog, and milestone README so Sprint 46 remains the active connector closeout path while mobile implementation stays deferred.
- Delivered connector webhook/analytics MVP foundations in Sprint 44 recovery: new `POST /api/mcp/connectors/webhooks` ingestion route with signature verification + dedupe, connector usage persistence (`integration_activations` / `integration_activity_log`), billing metering signal events, and `/admin/connectors` operations dashboard.
- Hardened connector webhook operations with timestamp replay protection, receipt-backed retry/dead-letter handling, MCP connector health integration in partner-health dashboards, and a new ops job (`jobs/mcp-connector-health.ts`) for failure/dead-letter alerting.
- Added provider-aware webhook hardening: GitHub/Google adapter normalization, owner-scoped receipt dedupe with payload-conflict detection, and rollout controls via `MCP_CONNECTOR_PROVIDER_VALIDATION_MODE` (`observe`/`enforce`) with a dedicated rollout runbook.
v0.43.0
Feb 9, 2026- Sprint 43 (Milestone 9) closed with full phase coverage (0-8), including explainable autonomy decisions, follow-up suppression intelligence, and explicit user controls/kill-switch behavior.
- Deep research flow is now action-oriented in chat with `/research` and `/research-quest`, structured output (`Summary`, `Sources`, `Recommendations`, `Suggested quests`), and explicit research-to-quest confirmation.
- Sprint 43 closeout artifacts are now canonical and linked across milestone docs (`SPRINT_43_COMPLETION.md`, testing guide/report, backlog, roadmap, milestone README).
v0.42.0
Feb 8, 2026- **Agentic tools phase 2 shipped:** code execution and image generation added to the explicit-invocation toolset with bounded outputs and visible result states.
- **Unified tool lifecycle:** queued/running/completed/failed/canceled states now emit consistently across search, document analysis, code execution, and image generation.
- **MCP foundation delivered:** connector registry, per-connector health/readiness checks, and per-user connector controls are now available in Settings.
- **Tool governance:** per-user agentic tool preferences, cost-tier visibility, and high-cost confirmation gating are enforced server-side across chat tool commands.
- **Reliability hardening:** agentic sessions persist in Postgres with cleanup/resume behavior, and production/performance validations are reproducible with seeded telemetry.
v0.41.0
Jan 3, 2026- **Agentic tools phase 1:** web search, file uploads, and document analysis with explicit tool controls and structured outputs.
- **Unified tools UI:** single composer surface for search + uploads, with clear toggles and tool state feedback.
- **Security hardening:** SSRF guardrails for outbound fetches and CSP headers for scripts/images/connect.
v0.40.0
Jan 4, 2026- **Offline quest editing:** title, notes, and status changes persist locally and sync on reconnect with deterministic conflict handling.
- **Offline caching:** service worker coverage for core routes, static assets, and trial hero imagery with resilient cache strategies.
- **Trial notification preferences:** per-trial mute + quiet hours override panel in Trial detail, with scheduler/delivery enforcement.
- **Quiet hours guardrail:** notification policy now defers queued notifications during quiet hours and re-checks on delivery.
v0.39.0
Jan 3, 2026- **Cohort insights dashboard:** Journey AI Insights now surfaces cohort maps, cadence timing, and actionable behavior guidance based on clustering analysis.
- **Community trial template discovery:** new `/trials/templates` browse experience with search, filters, and clean import separation.
- **Hero gallery upgrades:** search, favorites, curated sets, and a personal hero library for uploaded/AI images.
- **Notification visual polish:** trial hero thumbnails and clearer context on notification tiles.
- **Telemetry hardening:** trial lifecycle + creation events and weekly engagement pinging for reliable baselines.
v0.38.0
Jan 2, 2026- **Weighted quest scoring v2:** complexity, duration, difficulty, and theme importance multipliers with per-quest breakdowns and overrides.
- **Quest leaderboards:** opt-in global, trial, and theme leaderboards with weekly/monthly filters and score breakdowns.
- **Quest celebrations:** non-blocking completion overlays for quests, subtasks, and achievements with reduced-motion support, intensity preferences, and share-ready copy.
- **Scoring transparency:** Help Center details quest multipliers, bounds, rounding rules, and leaderboard bonuses.
- **Quest sharing:** public/unlisted quest template shares with preview and customizable imports.
v0.37.0
Dec 31, 2025- **Trial-scoped conversations:** create Trial-linked chats from nav and Trial pages with grouped navigation and filters.
- **Trial context injection:** mentor prompts include bounded Trial context (name, theme, progress, recent quests).
- **Auto-quest creation:** trial chat suggestions convert into quests with review, Trial theme enforcement, and conversation references.
- **Trial chat UI enhancements:** breadcrumbs and Trial accent styling clarify context.
- **Trial onboarding flow:** guided walkthrough on `/trials` with progress, highlights, and skip/resume persistence.
v0.36.0
Dec 31, 2025- **Trial hero AI generation (flagged):** new AI hero studio flow with prompt presets, quota guardrails, and S3-backed storage (uses supported image sizes).
- **Trial branding defaults:** theme-based palettes and icon accents now style headers, quest cards, and progress bars on trial detail pages.
- **Visual trial header:** hero image banner with layered overlays keeps trial details readable across breakpoints.
- **Trial sharing & templates:** public share pages, import flow, and share settings panel with view/import counters.
- **Trial-aware notifications:** quest reminders and notification center now show trial context in messaging and badges.
v0.35.0
Dec 23, 2025- **Trial analytics + comparison:** Trial progress dashboard, `/api/trials/[trialId]/progress`, and `/trials/compare` for side-by-side metrics.
- **Trial lifecycle controls:** Archive/complete/restore states persisted per user with archived trials hidden by default in nav.
- **Quest productivity upgrades:** Explicit dependencies, subtasks, duplication endpoint, and a templates library with built-in starters.
v0.32.0
Nov 4, 2025- **Companion presence orchestration**: `PresenceProvider` and the animated `WizzoAvatar` now drive idle, listening, thinking, success, and warning states across chat, quest mutations, and navigation with reduced-motion fallbacks.
- **Ambient mentor audio + controls**: A new audio stack (controller, provider, navigation controls, and voice playback ducking) delivers ambient loops and stingers that respect reduced-audio preferences and autoplay limits.
- **Token-driven UI re-theme**: Replaced legacy CSS tokens with the neutral-first `styles/tokens.ts`, refreshed dashboards, notifications, and chat surfaces, and documented the system in the presence design addendum for Classic Wizzo/Dark parity.
v0.31.0
Nov 3, 2025- **RL-driven inference caching**: Redis adapters now support an epsilon-greedy cache TTL policy with telemetry surfaced on the admin ML dashboard, improving hit rate and latency for personalization and pattern endpoints.
- **Emotion-aware agentic mentoring**: Voice tone snapshots flow into the agentic orchestrator, injecting supportive steps and tone-aware summaries when frustration or low energy is detected, with Labs sandbox UI exposing the snapshot.
- **Pokee Deep Research resilience**: Credit exhaustion now returns a friendly fallback plan, optional retry guidance, and never triggers toast errors; attach hooks and API routes surface retry timing to Ops.
v0.30.0
Nov 2, 2025- **Multi-channel notifications shipped**: Push/email/webhook preferences, quiet hours, delivery worker, and Notification Settings UI now coordinate real-time community alerts across achievements, streak milestones, agentic confirmations, and challenge feed events.
- **Public API v1 live for partners**: OAuth client credentials flow with scoped tokens powers Calendar events, Slack achievement actions, and Notion quest sync endpoints plus signed webhook dispatch and onboarding guides.
- **Integration activation analytics**: New admin dashboard, activation/activity tables, and partner usage logging illuminate adoption trends and top accounts for pilot integrations.
- **Explainability everywhere**: Labs Image→Quest dialog, agentic confirmation rationale cards, and updated memory context endpoints surface AI reasoning with source transparency.
- **Forecasting & telemetry upgrades**: Multimodal daily metrics table with backfill script, forecast/alert cards, Pokee latency insights, voice guardrail panel, and memory backlog monitor bolster Ops readiness.
v0.28.0
Oct 12, 2025- Enabled multi-image uploads for the Labs Image→Quest pilot with combined OCR processing, per-image telemetry, and weekly cost tracking surfaced on admin dashboards.
- Refreshed referral milestones with polished UI, clear reward messaging, and direct invite link sharing to support growth loops ahead of RC.
- Tuned voice persona defaults and moderation safeguards, aligning fallback heuristics with the new tone QA checklist and ensuring empathetic adaptations only trigger from real signals.
v0.27.1
Oct 11, 2025- Automated the 24-hour staging soak through the jobs runner with cron scheduling, artifact reports, and Slack alerts so Ops get daily Labs coverage without manual kickoff.
- Surfaced weekly Labs S3/OCR spend, telemetry freshness, and partner export usage on the admin analytics dashboards to keep Growth and Labs watchers informed.
- Added a Product Analytics entry point to the admin console so teams can reach the new analytics dashboards quickly.
v0.27.0
Oct 9, 2025v0.26.0
Oct 7, 2025v0.25.0
Oct 6, 2025v0.24.0
May 23, 2024v0.23.0
Oct 3, 2025- Replaces the Trials due-date picker with a responsive shadcn popover calendar so mobile users get a full-width, accessible control without triggering the keyboard.
- Refreshes quest cards and overlays to use design tokens for borders, foregrounds, and safe-area spacing, keeping contrast compliant across light and dark themes.
v0.22.1
Oct 1, 2025- Keeps the Labs Image→Quest pilot safely gated for staged cohorts while preserving telemetry.
- Strengthens onboarding funnel analytics and caching so activation tracking stays accurate.
- Lights up performance budget guardrails and updated release checklist ahead of the Growth & Monetization preview.
v0.21.3
Sep 29, 2025v0.21.2
Jan 27, 2025v0.21.1
Sep 27, 2025v0.21.0
Sep 27, 2025- Community feed refinements
- Insights dashboards
- Performance and stability improvements