Skip to content
Models
PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod… PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod…

Devin CLI · Continuity · Jul 13–19, 2026

1 release · updated

Devin CLI adds oauthResource override

This week, Devin CLI released one update with several changes. The main change is the addition of an oauthResource field, which helps users working with MCP servers and identity providers like Microsoft Entra. This update also includes various fixes and improvements to command hooks, permission prompts, and session management.

v3000.2.17 · July 19, 2026

This release adds a new oauthResource field for MCP servers, command hooks now receive session and turn ids, and includes changes to command permission prompts and session management. Notable fixes include improved hook discovery, support for deleting and renaming files with GPT-5.6 models, and reduced token costs and latency in long sessions. The most notable fix is the improvement in hook discovery, which now matches how skills and rules are loaded.

Official release notes

Added

  • MCP servers can now override the RFC 8707 OAuth resource parameter via a new oauthResource field in the MCP server config (or --oauth-resource on devin mcp add / devin mcp login) — needed for identity providers like Microsoft Entra that reject requests containing resource.
  • Command hooks now receive the agent’s session id (session_id for Claude-format hooks, trajectory_id for Windsurf-format hooks) and a per-turn id (prompt_id / execution_id) in their stdin payload.

Changed

  • Command permission prompts now scope known program runners to the wrapped program: uv run ruff check offers to always allow uv run ruff rather than the much broader uv run. Also applies to poetry run, pdm run, pipenv run, rye run, hatch run, pnpm exec, pnpm dlx, npm exec, yarn dlx, and bun run.
  • Sessions now start faster, especially when several reconnect at once.
  • The devin migrate command (devin migrate hooks, devin migrate workflows) is now available for migrating from legacy Cascade.
  • When the same skill name is loaded from more than one location, each copy now surfaces with a location prefix (/agents:foo, /claude:foo) instead of appearing as indistinguishable duplicates.

Fixed

  • Hooks are now discovered in ancestor directories up to the repository root, matching how skills and rules are loaded.
  • Improved support for deleting and renaming files with GPT-5.6 models.
  • Image-heavy sessions no longer invalidate the provider prompt cache on every request once the trailing-image cap is reached; older images are evicted in batches, reducing token costs and latency in long sessions.
  • The CLI no longer leaks a terminal/PTY per tool call: one-shot foreground commands free their shell session as soon as the command finishes, and deliberately retained shells (explicit shell_id, tty, or backgrounded commands) are capped at 16 with least-recently-used eviction.
  • Reusing a shell id for a non-interactive command now works instead of failing with “This shell may not be functional”; a busy shell serializes the next command.
  • Hooks are now deduplicated by source file, so a hook no longer runs multiple times when the same directory is re-added, workspace directories overlap, or a hook file is reached through a symlink.
  • Telemetry: rejected, blocked, or permission-denied tool calls are now recorded with their actual failure reason instead of being mislabelled “turn complete”.

Fan coverage from Devin Central — not an official Cognition announcement. Devin is a trademark of Cognition.