Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

Reference / Feature flags

tengu_auto_mode_config

A Claude Code feature flag, read out of the shipped bundle. It has been in the build since v2.1.138, including the newest one read.

What it is

Auto-mode permission checks can score risk 0-100 instead of yes/no, but only for configured models.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.

Presence across releases

ReleasesReadingDeclared typeDefault
2.1.245 – 2.1.250 5 releases never mined
2.1.138 – 2.1.243 95 releases in the build object,unknown

A row reading never mined is a release with no archived bundle behind it. Nothing was read out of it, so nothing here says whether the name was in it. A declared type or a default is only ever what that release's own bundle stated.

Gate readings

ReleaseResolvedThis accountAnonymousCompiled default
v2.1.248 Not enough to say no value returned no value returned not a boolean we can read
v2.1.242 Not enough to say no value returned no value returned not a boolean we can read
v2.1.236 Not enough to say no value returned no value returned not a boolean we can read
v2.1.232 read on another version Not enough to say no value returned no value returned not a boolean we can read
v2.1.221 read on another version Not enough to say no value returned no value returned not a boolean we can read
v2.1.219 read on another version Not enough to say no value returned no value returned not a boolean we can read
v2.1.205 read on another version Not enough to say no value returned no value returned not a boolean we can read
v2.1.166 read on another version Not enough to say no value returned no value returned not a boolean we can read
v2.1.71 read on another version Not enough to say no value returned no value returned no gate table built for this version

Two arms, because they disagree: this account is the one account this site reads and anonymous is a baseline with no identity attached. A reading says nothing about your account, and off cannot rule out a rollout both readings sit outside of. What these readings can and cannot show.

Changelog entries naming it

  1. v2.1.248Auto mode can be switched off server-side when /fast is on

    Auto mode can be disabled server-side while /fast is on, but nothing sets that today.

    gate cited by this entry

  2. v2.1.248CLAUDE_CODE_ENABLE_AUTO_MODE is no longer required, or read at all

    Auto mode no longer needs CLAUDE_CODE_ENABLE_AUTO_MODE; setting it now does nothing at all.

    gate cited by this entry

  3. v2.1.242Subagent results can carry a provenance frame that skips the hand-off review

    Subagent results can be tagged to show which parts Claude Code wrote versus the model.

    gate cited by this entry

  4. v2.1.236Auto mode falls back to real defaults when remote config is unavailable

    Auto mode uses sensible built-in defaults when remote config is missing, instead of everything off.

    gate cited by this entry

  5. v2.1.232Non-interactive /auto-mode-setup no longer needs the onboarding flag

    Non-interactive /auto-mode-setup now just needs a resolved model and no remote flag.

    gate cited by this entry

  6. v2.1.221Auto-mode outcome-code visibility moved behind a wrapper with a dead conditional

    The switch controlling outcome codes in auto mode now runs through a wrapper with an empty branch.

    gate cited by this entry

  7. v2.1.219Auto-mode permission classifier can emit a numeric severity instead of a yes/no block

    Auto-mode permission checks can score risk 0-100 instead of yes/no, but only for configured models.

    gate cited by this entry

  8. v2.1.205Auto-mode repo visibility lookup

    gate cited by this entry

  9. v2.1.166Auto-mode model config supports per-model overrides

    gate cited by this entry

  10. v2.1.71Auto Mode (--permission-mode auto)

    gate cited by this entry

Documentation pages

None of Anthropic's documentation pages this site has a copy of carries this name.

Names beside it

Every feature flag in the inventory starting tengu_auto_mode, up to twelve of them.

tengu_auto_mode_beta_latchThe automatic retry that would drop a rejected classifier beta can never trigger in this build. never mined tengu_auto_mode_classifier_queueNo description from anybody. 2.1.218 tengu_auto_mode_decisionSubagent results can be tagged to show which parts Claude Code wrote versus the model. never mined tengu_auto_mode_denial_dialog_auto_deniedAuto mode can show a prompt that denies itself after two minutes when you are away; off by default. never mined tengu_auto_mode_denial_limit_exceededMore auto-mode permission events record whether the tool was from an MCP server. never mined tengu_auto_mode_entry_warning_shownNew automatic prompts appear: a first-time auto mode warning, a spending threshold dialog and a worktree tip. never mined tengu_auto_mode_env_onboarding_laterThe auto-mode environment setup offer only shows the fuller flow after you've declined several times. never mined tengu_auto_mode_fallback_to_askIn auto mode, a question can be classified and handled instead of halting the run. never mined tengu_auto_mode_hook_allow_funneledHook-approved tool calls could still be checked by the auto-mode classifier, but the flag is off. never mined tengu_auto_mode_malformed_tool_inputAuto-mode approval events now note whether the tool came from an MCP server. never mined tengu_auto_mode_outer_retryAuto mode retries instead of failing when the model that routes your turn is briefly unavailable. never mined tengu_auto_mode_repo_visibility_lookup_failedNo description from anybody. never mined

Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the feature flag does. All feature flags.