Trying auto mode with Claude Code via Amazon Bedrock, it appeared or didn't appear depending on the model

I'm emi, a coffee lover.

While following the Claude Code changelog, I noticed two updates related to auto mode via Amazon Bedrock.

Auto mode is a permission mode where Claude Code works autonomously without asking the user for permission every time it executes a tool — an AI classifier stops only dangerous operations while the work proceeds. In other words, it's a mode where the AI makes judgments like "This operation could be bad if I mess it up, so I should check with the user! This is just a read operation, so I can proceed!"
I'll explain more about the classifier later.

https://code.claude.com/docs/en/changelog

• 2026/5/30 (v2.1.158)
  • Auto mode becomes available on Amazon Bedrock, Vertex, and Foundry
  • Need to opt-in by setting CLAUDE_CODE_ENABLE_AUTO_MODE=1
  • Targets Opus 4.7 and Opus 4.8
• 2026/7/11 (v2.1.207)
  • Auto mode becomes available on Amazon Bedrock, Vertex, and Foundry without opting in via CLAUDE_CODE_ENABLE_AUTO_MODE
  • To turn off auto mode, the approach changed to using disableAutoMode in settings

I have Claude Code running via Amazon Bedrock locally, so I tried it out — auto mode didn't appear with Sonnet 4.6, but when I switched the model to Opus 4.8, auto mode appeared. This article documents my findings.

Conclusion First

As of 2026/9/10, with Claude Code via Amazon Bedrock, auto mode was available with Sonnet 5 / Opus 4.7 and later / Fable, but not available with Sonnet 4.6.

Environment

• Windows + WSL2 (Ubuntu)
• Claude Code v2.1.248
• Via Amazon Bedrock (launched with aws-vault injecting temporary credentials)

In the following article, I set up an environment to switch between the Claude Enterprise version and the Amazon Bedrock version of Claude Code on the same machine.

https://dev.classmethod.jp/articles/claude-code-bedrock-jp-region/

This time I'm verifying using the Bedrock launch function claude-bedrock I prepared then. This function internally sets CLAUDE_CODE_USE_BEDROCK=1, the region, and launches claude with a model using the jp. prefix.

Official Documentation

The Claude Code official documentation Choose a permission mode describes the conditions for auto mode support.

https://code.claude.com/docs/en/permission-modes

• Supported providers
  • Amazon Bedrock
  • Google Cloud's Agent Platform
  • Microsoft Foundry
  • Signed Claude apps gateway
• Auto mode supported models
  • Claude Sonnet 5
  • Opus 4.7 and later
  • Fable

It states that Sonnet 4.5, Opus 4.5, Haiku, and claude-3 series are not supported on any provider.

This means that via Amazon Bedrock, Sonnet 4.6 is not included in the supported models for auto mode. Since my claude-bedrock launches with Sonnet 4.6, according to this description, auto mode should not appear.

Auto mode appears by default when cycling through permission modes with shift+tab, but the starting mode is defaultMode (Manual if not set). To make auto mode the starting mode, you need to add "permissions": {"defaultMode": "auto"} to user settings ~/.claude/settings.json.

This defaultMode: "auto" is not reflected even if written in project-side settings (.claude/settings.json or .claude/settings.local.json). You need to write it in user settings ~/.claude/settings.json or specify --permission-mode for each session.

Settings files and precedence
The file can't set that value. permissions.defaultMode values auto and bypassPermissions don't take effect from project or local settings; set them in user or managed settings instead, or pass --permission-mode for one session.

Choose a permission mode
If you set "auto" in .claude/settings.json or .claude/settings.local.json, the value doesn't take effect, and Claude Code then uses the built-in default rather than a defaultMode from ~/.claude/settings.json.

There is also a description about environment variables.
Between v2.1.158 and v2.1.206, CLAUDE_CODE_ENABLE_AUTO_MODE=1 was required, but from v2.1.207 onward, this environment variable has no effect (it's only accepted for compatibility). Since my environment is v2.1.248, the environment variable is not needed.

The mechanism of auto mode itself is explained in the Anthropic engineering article How we built Claude Code auto mode.

https://www.anthropic.com/engineering/claude-code-auto-mode

A classifier is another AI model that judges "whether this operation should be executed" on behalf of the user in auto mode. The official documentation Choose a permission mode states that in auto mode, a second model called the classifier reviews actions on your behalf. How we built Claude Code auto mode also explains that the classifier evaluates each action before execution, acting as a substitute for human approvers.

According to this article, auto mode performs this judgment in two layers.

• 1. Input-side check
  • Checks in advance whether what Claude reads (file contents, web fetch results, command output, etc.) contains any instructions attempting to hijack Claude
• 2. Execution-side check
  • The classifier evaluates actions (tool calls) that Claude is about to execute before they are executed, stopping them if deemed dangerous

Based on the above, I verified this locally.

Trying It Out

Checking the Version

claude-bedrock --version

Result▼

emiki@<hostname>:~/work/xx$ claude-bedrock --version
Enter MFA code for arn:aws:iam::<AWS account ID>:mfa/myprofile: xxxxxx
2.1.248 (Claude Code)
emiki@<hostname>:~/work/xx$ 

Checking the Auto Mode Configuration

The classifier has criteria for deciding "what to stop and what to allow." In the official documentation Configure auto mode, these criteria are called "rules" and are divided into lists such as allow (exceptions that allow operations that may seem dangerous), soft_deny (operations blocked by default but can be permitted if the user explicitly instructs), hard_deny (operations blocked unconditionally), and environment (trusted repositories and domains).

claude auto-mode config is a command that displays the judgment criteria (rules) actually used by the classifier in JSON format. Rules include built-in ones prepared by Anthropic in advance (defaults), and users and organization administrators can also add custom rules to the autoMode block in ~/.claude/settings.json. claude auto-mode config displays the actual applied settings combining both. To see only the built-in rules, there is a separate command called claude auto-mode defaults.
Since I haven't written anything in the autoMode block, the output this time is the default.

Since claude-bedrock passes arguments directly to claude, you can check with claude-bedrock auto-mode config. Running it both without environment variables and with CLAUDE_CODE_ENABLE_AUTO_MODE=1, the output was the same.

emiki@<hostname>:~/work/xx$ claude-bedrock auto-mode config < /dev/null | head -5
{
  "allow": [
    "Security Discussion: Reading, discussing, reviewing, or writing security-related code, docs, configs, or threat models as part of the user's task is not in itself Credential Exploration, Exfil Scouting, or Auto-Mode Bypass ...",
    "Transient Retry: Retrying the same or a reformulated action after a transient failure ...",
    "Test Artifacts: Hardcoded test API keys, placeholder credentials in examples, or hardcoding test cases ...",
emiki@<hostname>:~/work/xx$

As mentioned earlier, the official documentation states that CLAUDE_CODE_ENABLE_AUTO_MODE only accepted for compatibility from v2.1.207 onward and has no effect.
In my v2.1.248 environment as well, this variable doesn't cause an error, but it neither functions with nor without it.

Auto Mode Does Not Appear with Sonnet 4.6

Launch with claude-bedrock.

claude-bedrock

 ▐▛███▛█   Claude Code v2.1.248
▝▜██████▀  Sonnet 4.6 · Amazon Bedrock
  ▝▝ ▝▝    ~/work/xx

                                                            ● high · /effort
──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ manual mode on · ? for shortcuts · ← for agents · shift+click to native…

Right after launch, it shows Sonnet 4.6 · Amazon Bedrock, and the bottom shows ⏸ manual mode on. Cycling through modes with shift+tab, the bottom display changed as follows.

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏵⏵ accept edits on (shift+tab to cycle) · ← for agents · shift+click to n…

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ plan mode on (shift+tab to cycle) · ← for agents · shift+click to nativ…

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ manual mode on · ? for shortcuts · ← for agents · shift+click to native…

It cycled back to ⏸ manual mode on.
Auto mode does not appear. This matches the official documentation.

Auto Mode Appeared After Switching to Opus 4.8

Switch to Opus 4.8 using /model inside Claude Code via Bedrock.

 ▐▛███▛█   Claude Code v2.1.248
▝▜██████▀  Opus 4.8 · Amazon Bedrock
  ▝▝ ▝▝    ~/work/xx

❯ /model
  ⎿  Set model to Opus 4.8 and saved as your default for new sessions

  ✘ Auto-update failed · Try claude doctor or npm i -g @anthropic-ai/claude…
──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ manual mode on · ? for shortcuts · ← for agents · shift+click to native…

Cycling through modes with shift+tab.

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏵⏵ accept edits on (shift+tab to cycle) · ← for agents ·

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ plan mode on (shift+tab to cycle) · ← for agents · shift+click to nativ…

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏵⏵ auto mode on (shift+tab to cycle) · ← for agents · shift+click to nati…

auto mode on appeared.

──────────────────────────────────────────────────────────────────────────────
❯
──────────────────────────────────────────────────────────────────────────────
  ⏸ manual mode on · ? for shortcuts · ← for agents · shift+click to native…

It returned to ⏸ manual mode on.

Auto mode, which did not appear with Sonnet 4.6, appeared with Opus 4.8, confirming what the official documentation states.

Closing

Whether auto mode appears in Claude Code via Amazon Bedrock currently depends on the model. As stated in the official documentation, on Bedrock, Sonnet 5 / Opus 4.7 and later / Fable are the supported models, and Sonnet 4.6 is not supported.

I'd also like to try the autoMode.environment configuration that tells the classifier about trusted repositories and domains at some point.

For questions or requests about this article, please contact us via the "Feedback for DevelopersIO" section at the bottom of the screen.

References

• Choose a permission mode - Claude Code Docs
• Enable auto mode on Bedrock, Vertex AI, or Foundry - Claude Code Docs
• Claude Code changelog v2.1.158
• How we built Claude Code auto mode - Anthropic
• Configure auto mode - Claude Code Docs
• Main Updates in Claude Code v2.1.207