v0.1.65 —MCP integration, Chat Enhancements & Composio.

What's New

Chat Enhancements

• New /clear command to clear session messages
• New /new command to start a fresh conversation
• renderChatHeader function for improved chat interface presentation

Explore Subagent Update

• Enhanced explore agent prompt with stricter read-only enforcement and retry logic
• New subagent-permissions.ts with parent-child permission rule merging (parent DENY overrides child ALLOW — prevents jailbreak)
• Agent runner propagates parentAgent context to enforce permission chains
• Chat UI now shows live green ▼ Explore header with collapsible sub-thought drill-down (Ctrl+X)
• Tool snapshots for explore operations: file reads, grep searches, glob matches, web results
• delegate/task tool descriptions updated to distinguish explore vs general agents
• Permission isolation tests for explore agent (catch-all DENY, specific ALLOW for read-only tools)

Mercury MCP Integration

• Added Mercury MCP Integration Security & Architecture Guide

Como Session Management

• Server-side Composio session proxy via Render — no more local COMPOSIO_API_KEY
• Paid tier interest check on init
• Enhanced Composio app management

Tool Handling & Models

• toolParams returns default object fallback structurally
• nonStreamingRequest now accepts optional tools parameter
• Tool event tracking in ConcentrateService during streaming responses
• Opus 4.8 model entry added

New Pages

• Contact page with book-a-call and email options
• Pricing page detailing subscription tiers
• Updated stats with new download/active user figures
• Updated footer with pricing and social links

v0.1.56 - Download Page, Dev Gateway & Opus 4.8 Stability

What's New

Download Page

• New /download page with terminal install commands (curl, npm, bun, brew)
• Platform download cards for macOS, Windows, Linux
• Extensions and integrations sections
• FAQ accordion
• Navbar now has an animated Download button replacing Login

Dev Gateway Integration

• Merged provider integration with Opus 4.8 support
• Fixed temperature errors in dev gateway
• Consolidated provider routing

Bug Fixes

• Fixed GPT-5.5 errors on production
• Fixed Claude and GPT production issues

v0.1.42 — Brand Guidelines, Firecrawl Research & Voice Transcription

What's New

Brand & Marketing

• New /brand page — logo variants, color palette, typography, usage rules, downloadable assets
• New /contact page — Resend-style contact form with email links
• Partnerships section and polished get-started terminal on homepage
• Changelog and launch page updated for Product Hunt launch

Web Research Tools

• Firecrawl integration — search, scrape, and map web pages from the CLI
• Exa search/fetch as an alternative web search provider
• Structured tool results and Firecrawl slash commands
• Server-side proxy for Firecrawl/Google tools when local API key is missing

Voice & Transcription

• ElevenLabs Scribe support for voice transcription
• Fixed noise-injected transcriptions and improved retry UX

CLI Enhancements

• Code review analysis prompt on non-empty tool results
• Improved tool call hand output formatting

Infrastructure

• Bumped @infisical/sdk to v5 with adapted API
• Open source prep — Docker setup, Quick Start guide, env defaults
• Repo configured for OSS contributors

Bug Fixes

• Fixed ElevenLabs API key detection
• Fixed Firecrawl tools returning 'not configured' by loading .env before env var check
• Forced model to use firecrawl_search; removed legacy web_search from tool set

v0.1.27 — Analytics, Auto-Update & Enhanced Agent Tools

What's New

Analytics & Usage Tracking

• New usage tracking and analytics feature for monitoring CLI usage patterns
• Improved error handling in analytics route for better reliability

Agent Enhancements

• Enhanced agent functionality with improved tool call handling (v0.1.19, v0.1.24)
• Better tool result processing for more reliable agent responses
• Refined output formatting across the CLI (v0.1.18)

Auto-Update

• New auto-update mechanism to keep supercode-cli up to date (v0.1.21)
• Improved update error handling and diagnostics (v0.1.22)

Model Support

• Added GLM 5.2 support to ConcentrateAI provider (v0.1.17)
• Updated model references and configurations (v0.1.26)

Infrastructure

• Refactored Prisma integration for cleaner database access (v0.1.23)
• Dependency updates across the monorepo
• Device code timestamps migration for auth flows
• Removed remotion video sub-repo to clean up workspace
• Added Star History section to README

Behind the Scenes

• Multiple version bumps (v0.1.17 → v0.1.27) with incremental improvements
• General stability and error handling improvements across the codebase

v0.1.16

What's New

CLI / TUI

• 4 modes → 2. Chat, tool, agent, and plan modes collapsed into two: chat (read-only workspace access: read_file, search_files, url_fetch, browse, etc.) and agent (full workspace + all tools, including write).
• New AgentService with 7 built-in agents (build, plan, general, explore, compaction, title, summary) each with permission profiles and prompt files.
• New permission module — Ruleset types, wildcard matching, and mergePermissions for granular tool access control.
• New /context-window slash command — token usage breakdown per message with context percentage.
• GLM 5.2 added to ConcentrateAI provider.
• Narrowed CliConfig.mode type to "chat" | "agent".

Web App

• Comparison page (/compare) redesigned with detailed feature breakdown and improved layout.

v0.1.14 — OpenRouter Raw API Migration

v0.1.14 — OpenRouter Raw API Migration

🔧 CLI / Server

• OpenRouter integration rewritten: dropped @openrouter/ai-sdk-provider dependency, migrated to raw fetch API with Snd proper token usage tracking
• Server-side OpenRouter chat endpoint now streams tool calls with tool-call typed events
• OpenRouter structured generation endpoint migrated from SDK to raw API

v0.1.12 — Model Config Tuning

v0.1.12 — Model Config Tuning

🔧 CLI / Server

• Per-model maxTokens configuration for server-side chat and object generation endpoints
• Kimi K2.6 model reference updated (removed :free suffix) — now a paid model across model lists, help docs, and context window config
• Default OpenRouter model max tokens tuned per model

v0.1.11 — Chat API Refactor & Launch Polish

v0.1.11 — Chat API Refactor & Launch Polish

🔧 CLI / Server

• Server-side chat endpoint refactored to use @openrouter/ai-sdk-provider with streamText — cleaner streaming, built-in tool loop (maxSteps: 5), and proper usage reporting
• Removed 200+ lines of manual SSE parsing and tool loop logic

🎨 Homepage

• Launch page enhanced with beta features list, coming next roadmap, and install command section
• Post-launch CTA updated to link to Quickstart guide

v0.1.10 — Beta Launch

v0.1.10 — Beta Launch

🚀 New

• Quickstart guide — Step-by-step install/login/first-prompt walkthrough
• Waitlist feature with email notifications and beta countdown
• Comparison page — Supercode vs other SWE agents
• Launch countdown and beta banner components
• /connect command — Connect AI providers from CLI
• Provider configuration — Enhanced AI model management
• Device code auth — Secure CLI login via browser

📖 Documentation

• Complete docs site redesign: typography overhaul, section-grouped sidebar, prev/next nav
• New quickstart guide
• Scroll-aware On this page TOC
• Auth and architecture pages

🎨 Homepage

• Redesigned hero with tabbed install commands
• Updated footer, navbar, OG images, changelog

🔧 CLI client

• Device approval and code entry screens
• PixelLogo component, cleaned-up login form
• Server dependency updates

Last versions updates

v0.1.8 — Waitlist & Launch Prep

• Waitlist feature with email notifications
• Beta countdown and beta banner components
• Launch page added to footer
• Open Graph images updated for social sharing
• Comparison page — Supercode vs other SWE agents with cursor animation
• Waitlist page layout cleanup

v0.1.9 — Provider & CLI Configuration

• AI model management — Enhanced model configuration and CLI setup
• Provider connections — Connect OpenAI, Anthropic, Gemini, and more
• `/connect` command — Interactive provider setup from the terminal
• CLI help documentation updates

v0.1.7

Docs

• README rewritten with new branding ("AI-Powered SWE Agent"), updated app/package table, Terminal Stack architecture section, and new badges (Next.js 16, License).
• CONTRIBUTING rewritten from scratch: Bun-first setup, both database setup steps (dashboard + terminal CLI), expanded project tree, full command reference, code style guidelines, CLI pattern doc, DB migration workflows.
• Config documentation updated with production URL guidance for OAuth setup — thanks @aviisharma238 (https://github.com/aviisharma238)!

CLI / TUI

• Phosphor CRT terminal theme — green phosphor on black, amber accent for cursor/badges, green glow highlights. New pixelWordmark() renders "SUPERCODE" as ASCII pixel art.
• Main screen redesigned with sectionHeader, cardStack, rowCard, keyValue, statusBar utilities — centered pixel wordmark, system HUD panel, command card stack, and a footer status bar.
• Chat startup overhauled: pixel wordmark header, status bar with mode/model info, /model / /help / Tab quick-start row.
• Framed "goodbye" message on exit instead of a single line.
• Animated thinking spinner with live tool call and reasoning updates (existing, refined).
• 1,048 insertions across 7 files — the TUI is now the primary surface identity.