Skip to content
DevAgentRadarDevAgentRadar
Sign in
Proposals/Move Copilot CLI user settings into ~/.copilot/s
proposaldeveloperP5Worth a lookGCGitHub Copilot CLI

Move Copilot CLI user settings into ~/.copilot/settings.json

Copilot CLI v1.0.93 reads user settings only from ~/.copilot/settings.json (keys in ~/.copilot/config.json are ignored), opens command sandboxing to every user via /sandbox and --sandbox, adds enterprise permissions.limitTo domain boundaries, and honors --context long_context at startup.

Why this loop

v1.0.93 silently changes where Copilot CLI loads user settings: only ~/.copilot/settings.json is read, so any user-setting keys left in ~/.copilot/config.json stop applying. Command sandboxing is now available to all users with /sandbox and --sandbox; sandbox local-network allowlists include localhost and loopback, so isolated shell commands can still reach local services. Enterprises can set permissions.limitTo to keep network requests inside managed domains. Start with --context long_context and confirm the real window via /context. MCP server config changes apply between turns without restarting; plugin skill commands remain after reloading enabled plugins. GitHub.com Connector users can expand GitHub CLI permissions in place and retry instead of switching sign-in. Model picker recommendations now prioritize GPT-6.1 Sol, GPT-6 Astra/Luna, and Claude 5.5.

Proposed actions

  1. Upgrade GitHub Copilot CLI to v1.0.93, then move every user-setting key from ~/.copilot/config.json into ~/.copilot/settings.json (create it if missing). v1.0.93 ignores user-setting keys left in config.json.
  2. Start Copilot CLI with copilot --sandbox or, in an active session, run /sandbox so command sandboxing is on; localhost and loopback are now on the sandbox local-network allowlist.
  3. For managed installs, set enterprise permissions.limitTo to your approved domain list so Copilot CLI network requests stay inside those boundaries.
  4. Launch long-context work with copilot --context long_context, then run /context and confirm the shown context allowance matches the long_context window.
  5. Edit MCP server config mid-session and continue—the new servers apply between turns with no restart. After reloading enabled plugins, confirm plugin skill commands are still listed. If a GitHub.com Connector lacks the GitHub CLI scope, expand permissions in place and retry instead of switching sign-in.

Agent prompt

Paste into your agent or query via MCP (get_agent_prompt) — free, no extra AI cost

AGENTS.md / CLAUDE.md / GEMINI.md rule update

DevAgentRadar → Repo Harness Rule Patch

Goal: update our repository's permanent harness instructions based on this release.

Update the file that tool actually reads. Do not dump everything into one file.

  • Claude Code → CLAUDE.md plus .claude/ (skills, hooks, settings, agents, commands). It does not read AGENTS.md natively; start CLAUDE.md with @AGENTS.md.
  • Codex, Copilot, Cursor, Factory Droid, Grok Build, Roo Code, Goose, OpenCode, Amp, Zed, Aider → AGENTS.md.
  • Gemini CLI / Antigravity → GEMINI.md. AGENTS.md only if context.fileName is set.
  • Cursor glob-scoped rules → .cursor/rules/*.mdc (plain .md is ignored), not a second constitution.
  • Codex MCP → .codex/config.toml, not .mcp.json.
  • Copilot extra instructions → .github/copilot-instructions.md; custom agents → .github/agents/.
  • Windsurf → .windsurf/rules (do not assume AGENTS.md).
  • Cline → .clinerules.
  • Procedures → a skill (SKILL.md). Enforcement the model must not skip → a hook. Isolated roles → subagents.
  • Do not fork the same rule into three tool files.

Context

Assistant: GitHub Copilot CLI Proposal: Move Copilot CLI user settings into ~/.copilot/settings.json Summary: Copilot CLI v1.0.93 reads user settings only from ~/.copilot/settings.json (keys in ~/.copilot/config.json are ignored), opens command sandboxing to every user via /sandbox and --sandbox, adds enterprise permissions.limitTo domain boundaries, and honors --context long_context at startup. Primary source: https://github.com/github/copilot-cli/releases/tag/v1.0.93

Why it matters

v1.0.93 silently changes where Copilot CLI loads user settings: only ~/.copilot/settings.json is read, so any user-setting keys left in ~/.copilot/config.json stop applying. Command sandboxing is now available to all users with /sandbox and --sandbox; sandbox local-network allowlists include localhost and loopback, so isolated shell commands can still reach local services. Enterprises can set permissions.limitTo to keep network requests inside managed domains. Start with --context long_context and confirm the real window via /context. MCP server config changes apply between turns without restarting; plugin skill commands remain after reloading enabled plugins. GitHub.com Connector users can expand GitHub CLI permissions in place and retry instead of switching sign-in. Model picker recommendations now prioritize GPT-6.1 Sol, GPT-6 Astra/Luna, and Claude 5.5.

Suggested actions

  1. Upgrade GitHub Copilot CLI to v1.0.93, then move every user-setting key from ~/.copilot/config.json into ~/.copilot/settings.json (create it if missing). v1.0.93 ignores user-setting keys left in config.json.
  2. Start Copilot CLI with copilot --sandbox or, in an active session, run /sandbox so command sandboxing is on; localhost and loopback are now on the sandbox local-network allowlist.
  3. For managed installs, set enterprise permissions.limitTo to your approved domain list so Copilot CLI network requests stay inside those boundaries.
  4. Launch long-context work with copilot --context long_context, then run /context and confirm the shown context allowance matches the long_context window.
  5. Edit MCP server config mid-session and continue—the new servers apply between turns with no restart. After reloading enabled plugins, confirm plugin skill commands are still listed. If a GitHub.com Connector lacks the GitHub CLI scope, expand permissions in place and retry instead of switching sign-in.

Config surfaces this release may change

  • settings files (high confidence) — check your repo before applying

After you finish

Do not report this as applied to DevAgentRadar. You cannot write the visitor's loop.

Tell the human: open https://devagentradar.com/proposals/github-copilot-cli-v1-0-93-move-copilot-cli-user-settings-into-copilot-s and mark Applied, Skipped, or Failed. Proposal id: 9d29e7f2-85fe-470a-8137-8d3ec265c02f

Instructions:

  1. Read the existing context files and settings for the tools in this repo.
  2. Draft an explicit Git diff. Update ONLY agent harness rules or tool configuration.
  3. Call out deprecated flags, obsolete habits, or changed permission boundaries.
  4. Do not touch application logic.

Start with the proposed diff and say which layer and which tool's file it belongs in.

mcpmodelsecuritycliRelease source ↗

Your loop

This browser · no sign-in · not shared as “you”

After you run the prompt

Only you can mark this. Agents cannot write your loop.

Your decision stays on this device. A public tally appears after a few votes.

Originating release signal

GCGitHub Copilot CLIv1.0.93Oct 7, 2026

v1.0.93 1.0.93

2026-10-07 · Add enterprise permissions.limitTo to enforce managed domain boundaries for network requests · Run safe /user commands immediately during active turns, reject unsafe remote commands during active turns without opening dialogs, and queue commands advertised by relay hosts · Plugin skill commands stay available after reloading enabled plugins · Sandbox local-network allowlists now include localhost and loopback hosts. · GitHub.com Connector users can expand GitHub CLI permissions in place and retry connections without switching sign-in methods. · +8 more changes
Verified excerpt — the source's own words

2026-10-07

  • Add enterprise permissions.limitTo to enforce managed domain boundaries for network requests
  • Run safe /user commands immediately during active turns, reject unsafe remote commands during active turns without opening dialogs, and queue commands advertised by relay hosts
  • Plugin skill commands stay available after reloading enabled plugins
  • Sandbox local-network allowlists now include localhost and loopback hosts.
  • GitHub.com Connector users can expand GitHub CLI permissions in place and retry connections without switching sign-in methods.
  • Honor --context long_context at startup and show accurate context allowance in /context
  • Connecting a Connector without the required GitHub scope now prompts to update your authorization instead of failing with an authentication error
  • Warmed language servers stay running across LSP requests when sandboxing is disabled
  • Clicking a truncated compact shell command expands it
  • Command sandboxing is available to all users via /sandbox and --sandbox.
  • MCP server configuration changes apply between turns without restarting the session.

Excerpt ends here — this release continues at the source ↗.

Primary source ↗