Skip to content
Guidance/Daily Briefing
digesteveryonedigestevidenceradarclimodel6 min read · Nov 14, 2026

Radar brief — 2026-11-14

Evidence-backed brief across 29 assistants from 40 high-signal releases. Trusted sources ~54%.

Judgment from curated release evidence — not a scrap dump of every vendor page.

What the evidence shows

  • New in the last 36 hours: 31 release(s) from 16 tool(s)
  • Evidence window: new releases first, then top curated signals (versioned releases preferred)
  • Assistants tracked: 29
  • Signals in this brief: 40
  • Trusted source mix (GitHub/changelog vs HTML): 54%
  • Open improvement proposals: 5
  • Sources reporting errors: 1

Themes

  • cli × 27
  • model × 26
  • agent × 24
  • security × 23
  • mcp × 21
  • breaking × 18
  • ide × 14
  • pricing × 11

Notable versioned / high-signal items

  • OpenAI Codex CLI rust-v0.169.0: The opt-in terminal workspace supports multiple side-chat tabs. · Switch between them with the keyboard or mouse, and reopen saved local side chats after restar — source

  • Qwen Code v0.27.3: See the complete change list below. · No known breaking changes. · Added chips above the Web Shell composer for unfinished background workflows, shells, monit — source

  • GitHub Copilot CLI v1.0.110: 2026-11-12 · Experimental: answer git, ssh, and sudo password prompts from agent commands in a masked dialog (enable with /experimental on) · Avoid unnecessary — source

  • GitHub Copilot CLI v1.0.112: 2026-11-13 · A failed /compact now shows the model provider's error message without an internal host-rethrow prefix · A prompt the CLI does not send yet, such a — source

  • OpenAI Codex CLI rust-v0.168.0: Browse model providers under Sessions → Model providers and choose the default for new chats. (#59541, #59722) · Enable features.tui_workspace to view a side — source

  • Claude Code v2.1.323: Added Code Mode, an experimental opt-in in which Claude writes JavaScript to call its tools; see https://code.claude.com/docs/en/code-mode to turn it on, or to — source

  • Claude Code v2.1.325: Fixed a security issue in how zstd-compressed responses are decoded · Added a spinner tip in VS Code and similar integrated terminals about re-running a noteboo — source

  • Google Antigravity 1.5.9: Added the run_workflow tool for everyone: the agent can run a Python workflow script that fans work out to many subagents in parallel or in stages and then co — source

  • Google Antigravity 1.5.8: Added Gemini 4 Hydrogen (Low, Medium, High, and XHigh) and Gemini 4 Carbon (Low, Medium, and High) to /model and --model when you connect with a `GEMINI_API — source

  • GitHub Copilot CLI v1.0.111: 2026-11-13 · Add regular expression support to enterprise-managed Shell, Bash, and PowerShell permission rules · Add --host-allow-session-creation to let remote — source

  • Crush v0.101.0: This release was brought to you by our team and our favorite contributors! Long awaited features ahead, read along! · Skills can now be switched on and off righ — source

  • OpenCode v2.3.0: Background Subagents by Default: Subagents now return immediately, continue in the background, and report back whenever they become idle. · You can keep wor — source

  • Kilo Code jetbrains/v7.2.1-rc.6: Voice dictation input in the prompt, with a configurable shortcut, speech model discovery, and clear recording limits. · Agent Manager sections: group worktrees — source

  • Kimi Code @moonshot-ai/kimi-code@2.6.2: #4875 4c72e1d — source

For developers

  • OpenAI Codex CLI rust-v0.169.0: try the change on one real task before switching defaults.
  • Qwen Code v0.27.3: try the change on one real task before switching defaults.
  • GitHub Copilot CLI v1.0.110: try the change on one real task before switching defaults.
  • GitHub Copilot CLI v1.0.112: try the change on one real task before switching defaults.
  • OpenAI Codex CLI rust-v0.168.0: try the change on one real task before switching defaults.
  • Keep a second assistant ready so vendor downtime is not career downtime.

For teams

  • OpenAI Codex CLI: review security/pricing/breaking notes before org-wide enablement.
  • Qwen Code: review security/pricing/breaking notes before org-wide enablement.
  • GitHub Copilot CLI: review security/pricing/breaking notes before org-wide enablement.
  • GitHub Copilot CLI: review security/pricing/breaking notes before org-wide enablement.
  • OpenAI Codex CLI: review security/pricing/breaking notes before org-wide enablement.
  • Treat assistants as a portfolio; standardize only after a pilot.

What to ignore

  • Nav/marketing page scrapes without versions
  • Duplicate changelog + release entries for the same version
  • “Stale” assistants until source health recovers (see Compare)

Watch next

  • Open proposals: decide on /proposals
  • Filter to My stack so you only see tools you use
  • Revisit after the next radar refresh for new high-signal releases

How to use DevAgentRadar

  1. Read this brief for judgment
  2. Open linked sources to verify
  3. Act on proposals (approve / defer / ignore)

Related proposals


Evidence appendix

  • New in the last 36 hours: 31 release(s) from 16 tool(s)
  • Evidence window: new releases first, then top curated signals (versioned releases preferred)
  • Assistants tracked: 29
  • Signals in this brief: 40
  • Trusted source mix (GitHub/changelog vs HTML): 54%
  • Open improvement proposals: 5
  • Sources reporting errors: 1

High-signal releases used

  • OpenAI Codex CLI rust-v0.169.0: The opt-in terminal workspace supports multiple side-chat tabs. · Switch between them with the keyboard or mouse, and reopen saved local side chats after restar — source

  • Qwen Code v0.27.3: See the complete change list below. · No known breaking changes. · Added chips above the Web Shell composer for unfinished background workflows, shells, monit — source

  • GitHub Copilot CLI v1.0.110: 2026-11-12 · Experimental: answer git, ssh, and sudo password prompts from agent commands in a masked dialog (enable with /experimental on) · Avoid unnecessary — source

  • GitHub Copilot CLI v1.0.112: 2026-11-13 · A failed /compact now shows the model provider's error message without an internal host-rethrow prefix · A prompt the CLI does not send yet, such a — source

  • OpenAI Codex CLI rust-v0.168.0: Browse model providers under Sessions → Model providers and choose the default for new chats. (#59541, #59722) · Enable features.tui_workspace to view a side — source

  • Claude Code v2.1.323: Added Code Mode, an experimental opt-in in which Claude writes JavaScript to call its tools; see https://code.claude.com/docs/en/code-mode to turn it on, or to — source

  • Claude Code v2.1.325: Fixed a security issue in how zstd-compressed responses are decoded · Added a spinner tip in VS Code and similar integrated terminals about re-running a noteboo — source

  • Google Antigravity 1.5.9: Added the run_workflow tool for everyone: the agent can run a Python workflow script that fans work out to many subagents in parallel or in stages and then co — source

  • Google Antigravity 1.5.8: Added Gemini 4 Hydrogen (Low, Medium, High, and XHigh) and Gemini 4 Carbon (Low, Medium, and High) to /model and --model when you connect with a `GEMINI_API — source

  • GitHub Copilot CLI v1.0.111: 2026-11-13 · Add regular expression support to enterprise-managed Shell, Bash, and PowerShell permission rules · Add --host-allow-session-creation to let remote — source

  • Crush v0.101.0: This release was brought to you by our team and our favorite contributors! Long awaited features ahead, read along! · Skills can now be switched on and off righ — source

  • OpenCode v2.3.0: Background Subagents by Default: Subagents now return immediately, continue in the background, and report back whenever they become idle. · You can keep wor — source

  • Kilo Code jetbrains/v7.2.1-rc.6: Voice dictation input in the prompt, with a configurable shortcut, speech model discovery, and clear recording limits. · Agent Manager sections: group worktrees — source

  • Kimi Code @moonshot-ai/kimi-code@2.6.2: #4875 4c72e1d — source

Open proposals

Was this guidance useful?

Anonymous · one vote per visitor · re-click to clear. Helps improve digests—not a product ranking.