Claude Code 2.1.323 adds Code Mode and plugin version ranges
Updated Claude Code
Summary
Claude Code 2.1.323 (Nov 12, 2026) adds experimental Code Mode, engines ranges for plugins and a 1M default context for unknown models, plus dozens of permission and sandbox fixes.
- Tool
- Claude Code
- Category
- Coding agents
- Date
- MCP
- Yes
- Pricing
- Not stated in the sources we cited.
Claude Code v2.1.323 reached npm on November 12, 2026 at 20:29 UTC (23:29 Istanbul time) and is the current latest tag. It is the first build we cover since 2.1.316, and the notes are long: about 290 entries, roughly 150 of them fixes. The headline is Code Mode, an experimental opt-in where Claude writes JavaScript to call its tools. Most of the rest tightens permissions and the Bash sandbox, and a few defaults change in ways that can surprise teams on gateways or other vendors' models.
Release facts
| Fact | Detail |
|---|---|
| Product | Claude Code, Anthropic's terminal coding agent |
| Version | 2.1.323 |
| Release date | November 12, 2026 (npm and GitHub release) |
| Previous version we covered | 2.1.316, October 31, 2026 |
| Install | npm install -g @anthropic-ai/claude-code@2.1.323 |
Check before upgrading
- Unknown model IDs now assume a 1M context window. It was 200K. If you run Claude Code on another vendor's model with a smaller window, sessions can fail every turn once full until
/clear. SetCLAUDE_CODE_DISABLE_1M_CONTEXT=1before that happens, or use/autocompactto compact earlier. MCP_SDK_GENERATION=v1no longer gives you the v1 client. The v1 MCP client is removed; that setting now runs the v2 client in a compatibility mode with an earlier handshake and relaxed OAuth checks.ALL_PROXYalone is ignored for organization settings and policy requests. SetHTTPS_PROXYif your network needs a proxy for them.- Sandbox writes through symlinks stop working. On macOS, Linux and WSL, write access granted through a symlink that leads elsewhere is ignored; grant the real path.
git worktree add,moveandremovealso fail read-only inside the sandbox. - Project MCP approvals match exact names. An
.mcp.jsonapproval written in another spelling will ask again. - Cross-session messaging limit raised. Sessions on the same machine can send each other about 100,000 messages without a prompt, up from about 20. Teams that relied on the old cap as a brake should know it is effectively gone.
What's new
- Code Mode (experimental). Claude writes JavaScript that calls its tools instead of calling them one at a time. It is off by default; the Code Mode docs explain how to turn it on, or off for an organization.
- Plugin version ranges.
plugin.jsonacceptsengines["claude-code"]. Plugins outside the range are not installed, updated or loaded, and installs pick the newest version that fits.claude plugin validatealso type-checks a plugin's TypeScript hooks, with--strictfailing on findings. - Usage-credit menu. When a model needs usage credits that are off or used up, you get options to stop, switch to credits or upgrade.
- Hook heartbeat. Long-running hooks in
claude -pand SDK sessions send a progress heartbeat every 30 seconds, so hosts such as Claude Desktop do not end the turn as hung. - Smaller additions.
.docxuploads for the Artifact tool, a startup warning for Bash allow rules with*inside a variable value such asBash(PORT=* npm run dev), andCLAUDE_CODE_DISABLE_AGENT_PROGRESS_SUMMARIESto turn off subagent progress summaries.
Permission and sandbox fixes worth knowing
--permission-mode autonow starts in Manual mode when auto mode is unavailable, instead of a mode that could allow more.- Bash allow rules with an attached wildcard such as
Bash(ls*), or combinedsudoflags, could skip the prompt in some cases; deny and ask rules could miss commands run throughsudoorenv. Both are fixed. - Write and Edit could write to a path covered by a
Readdeny rule, andsandbox.excludedCommandscould let unlisted commands run outside the sandbox. Both are fixed. claude -pand the Agent SDK ran Bash unsandboxed when sandbox settings failed validation; they now stop at startup and name the bad setting.
Other notable fixes
- Running
/compacttwice, or after/context, no longer summarizes away a message Claude had not answered yet. - MCP tool calls that fail with the sign-in server's error, such as
TOKEN_EXPIRED, now ask you to sign in again. - Several cases where a background session moved to a different sign-in or account are fixed; affected sessions now stop and say so.
- Edit and Bash no longer run out of memory on certain
/procfiles, devices or named pipes.
Questions
What is Claude Code Code Mode? An experimental, opt-in mode in which Claude writes JavaScript to call its tools. It is off unless you turn it on, and organizations can turn it off.
Why does my non-Anthropic model fail after upgrading?
Unknown model IDs now get a 1M-token context assumption. If your model's window is smaller, set CLAUDE_CODE_DISABLE_1M_CONTEXT=1.
Is 2.1.323 the stable npm release?
Yes. On November 13, 2026, npm's latest tag pointed to 2.1.323.
More on the Claude Code hub, the previous Claude Code 2.1.316 launch and the coding agents category. For comparisons, see Claude Code vs Codex and Aider vs Claude Code.
Alternatives
| Tool | License | Pricing note |
|---|---|---|
Claude CodeThis launchClaude Code is an agentic coding tool that runs in your terminal and works on your codebase. | — | Not stated |
Codex CLICodex CLI is OpenAI's Apache-2.0 coding agent that runs locally in your terminal, signed in with a ChatGPT plan or an OpenAI API key. | Apache-2.0 | The CLI is Apache-2.0. Usage comes from a ChatGPT plan or is billed at API rates when you sign in with an API key. |
OpenCodeOpen-source coding agent from the anomalyco/opencode repository, MIT-licensed, with a terminal client and a site at opencode.ai. | MIT | The client is MIT-licensed. Model access is separate; this page does not quote a hosted plan. |
Gemini CLIGoogle's Apache-2.0 terminal coding agent for Gemini models. Version 0.67.0 (November 4, 2026) adds a models command and sandbox IDE diffs. | Apache-2.0 | The CLI is free under Apache-2.0. Model use is set by how you sign in: a free Google account tier, a Gemini API key (free or paid), Vertex AI, or a Google AI Pro, Ultra or Code Assist plan. |
More from Claude Code
Claude Code 2.1.316 adds subagent effort and shared gateway budgets
Claude CodeSubagent defaults, layered gateway policies and cloud forms arrive alongside an Opus fast-mode migration notice.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.314 adds a working-directory write boundary
Claude CodeA new write restriction and group-scoped gateway routing accompany idle compaction and startup fixes.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.312 changes policy loading and cloud routines
Claude CodeThe update adds cloud-routine effort selection and gateway identity configuration, with fixes for large-file edits and late code-review events.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.311 repairs background-agent lifecycles
Claude CodeThe release addresses premature worktree cleanup, duplicate hook activity and background-session recovery, with new self-hosted idle controls.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.310 expands Monitor availability
Claude CodeMonitor and plugin monitors reach Bedrock, Vertex and Foundry, including configurations with telemetry or nonessential traffic disabled.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.304 adds review levels and guided auto-mode setup
Claude CodeClaude Code adds organization and repository review levels, guided auto-mode setup, and mod permission checks that explicitly require a person.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.302 changes subagent defaults and adds idle-compaction control
Claude CodeThe October 16 release adds an idle-compaction toggle, expands fork-subagent defaults and fixes cloud routine retries that could repeat work.
Category: Coding agents
Pricing: Not stated
Claude Code 2.1.295 adds hook blocking and gateway controls
Claude CodeClaude Code v2.1.295, released October 8, 2026, adds fail-closed hooks, OSC 7501 status support and new Claude apps gateway upstream controls.
Category: Coding agents
Pricing: Not stated
Questions
What is Claude Code?
The repository describes it as an agentic coding tool that lives in your terminal, understands your codebase, and handles routine tasks and git workflows through natural language commands.
Is Claude Code open source?
Not stated in the cited sources. The GitHub API does not report a recognized license for the repository.
Does Claude Code support MCP?
The docs overview lists connecting your tools with MCP, and the v2.1.295 release notes include MCP fixes.
Filed on Agent Radar. Claims in this note are limited to the sources above.