my-ai-companion

Configure and debug ZeeMe Gmail/Calendar personal context end-to-end with deterministic contracts for OAuth callback routing, token-encryption readiness, Zee Stage read/write flows, hands-free approvals, and voice/text smoke tests.

Diagnose ZeeMe Gemini integration failures using trace IDs, structured logs, and endpoint-specific checks. Use for live token errors, chat stream failures, live tool-response failures, Google-action approval drift, transcript issues, quota blocks, and model response anomalies.

Build deterministic ZeeMe incident handoff packets from live-debug traces, branch context, and current status so another engineer can continue immediately. Use when voice/chat regressions are active, cross-environment drift exists, or ownership is changing between sessions.

Stabilize and debug ZeeMe live voice sessions that feel clipped, interrupted, delayed, or silent. Use when Gemini Live behavior is inconsistent across mobile/web environments and you need a trace-first diagnosis plus deterministic settings for VAD, interruption handling, thinking budget, token limits, and client audio capture.

Coordinate ZeeMe Replit-first hotfix and production rollouts with deterministic branch-sync checks, risk classification, VITE rebuild enforcement, and explicit rollback sequencing. Use when shipping live voice/chat fixes to Replit without breaking stable paths.

Produce ZeeMe marketing videos with Remotion, including master renders, lightweight previews, and social cutdowns. Use when creating launch demos, campaign assets, or cinematic product showcases.

Qualify ZeeMe live voice reliability on iPhone, Samsung/Android, mobile browsers, and PWA builds before release. Use when mobile sessions show false barge-in interrupts, missed normal-volume speech, transcript gaps, or behavior that differs from desktop.

Validate ZeeMe local tooling health before debugging or release work. Use when Playwright/ImageGen wrappers fail, environment drift is suspected, or setup reliability needs a deterministic preflight.

Run ZeeMe release safety gates before merge, deploy, or publish. Use when validating security, type safety, local API behavior, and regression risk across local and Replit workflows.

Deploy and debug ZeeMe Morning Brief on Google Cloud Run with deterministic preflight, secret wiring checks, smoke tests, and Replit env patch output.

Generate deterministic Replit-agent prompts for applying and verifying ZeeMe database schema changes. Use when schema files change and Replit must stay in sync with local development.

Evaluate ZeeMe agentic game generation quality and reliability using prompt matrices, output-difference checks, QA outcome review, and artifact contract validation. Use when generated games look templated, fail to match user intent, regress in playability, or show unstable publish behavior.

Convert ZeeMe companion expansion ideas into phased, shippable engineering roadmaps with explicit contracts, acceptance criteria, rollout controls, and cross-team workstream sequencing. Use when planning or revising agentic capabilities, sandbox/tooling milestones, unified chat UX constraints, and release-by-release execution plans.

Prepare ZeeMe for iOS TestFlight release with deterministic readiness checks, build sequencing, and submission guardrails. Use when planning iOS beta releases, validating Expo/EAS setup, or producing a safe release runbook.

Maintain reliable cross-session memory for the ZeeMe app. Use when starting or ending a coding session, handing work to another Codex instance, resuming in a new environment, or preventing loss of critical debugging context.