Feature flags, all 2,081.

tengu_violin_winding ◇ When a computer Claude is working on goes away, Claude now checks again after 30 seconds, 2 minutes and 5 minutes, and handles a sleeping one separatelyv2.1.295 → v2.1.308 ◆in the build AND v2.1.295 tengu_violin_wood ◇ If you have too many untracked files, cloud seeding refuses and tells you which budget you blew.v2.1.227 → v2.1.308 ◆in the build AND v2.1.295 tengu_virtual_knuth ◇ Hook-approved tool calls could still be checked by the auto-mode classifier, but the flag is off.v2.1.246 → v2.1.308 ◆in the build AND v2.1.292 tengu_virtual_pancake ◇ New system-prompt note warns Claude that pasted content may carry instructions the user didn't writev2.1.274 → v2.1.308 ◆in the build AND v2.1.274 tengu_virtual_pine ◇ No description from anybody.v2.1.295 → v2.1.303 ○gone never read tengu_vivid_crayon ◇ No description from anybody.v2.1.302 → v2.1.308 ◆in the build never read tengu_vivid_crown ◇ The reminder Claude Code sends the model in auto mode gains a setting about finishing work, off unless switched on remotelyv2.1.307 → v2.1.308 ◆in the build AND v2.1.307 tengu_voice_circuit_breaker_tripped ◇ When voice input pauses itself, it now tells you the specific reason.never mined ·never mined never read tengu_vscode_feedback_survey ◇ Default false. When on, the session's SDK initialize response carries a feedback_survey_config (the tengu_feedback_survey_config value, with its probability overridden by the feedbackSurveyRate setting when set, plus the last time a survey was shown) for VS Code extension sessions and certain other entrypoints. No config is sent when CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY is set or the allow_product_feedback policy is off.v2.1.162 → v2.1.308 ◆in the build AND v2.1.308 tengu_vscode_inline_pastes ◇ VS Code extension adds default-on settings for inline pastes and 'tranquil cloud', plus a new max-effort reminder optionv2.1.280 → v2.1.308 ◆in the build AND v2.1.296 tengu_vscode_math_rendering ◇ Claude Code now passes two new remotely controlled switches to the VS Code extension, one for math rendering and one for a restore breakerv2.1.301 → v2.1.308 ◆in the build AND v2.1.301 tengu_vscode_onboarding ◇ A resume-precheck gate is now passed to the VS Code extension, on by default.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.284 tengu_vscode_python_beside_start ◇ The VS Code extension has two new remotely controlled settings, about stored startup configuration and Python, that are on by defaultv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_vscode_restore_breaker ◇ Claude Code now passes two new remotely controlled switches to the VS Code extension, one for math rendering and one for a restore breakerv2.1.301 → v2.1.308 ◆in the build AND v2.1.301 tengu_vscode_resume_precheck ◇ A resume-precheck gate is now passed to the VS Code extension, on by default.v2.1.248 → v2.1.308 ◆in the build AND v2.1.284 tengu_vscode_review_upsell ◇ A resume-precheck gate is now passed to the VS Code extension, on by default.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.284 tengu_vscode_stored_startup_config ◇ The VS Code extension has two new remotely controlled settings, about stored startup configuration and Python, that are on by defaultv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_walnut_gable ◇ Publishing an artifact now strips all nested preview wrappers, not just the outermost one.v2.1.234 → v2.1.238 ○gone AND v2.1.239 tengu_walnut_prism ◇ Default false. When on (or when CLAUDE_CODE_OWNERSHIP_FRAME is true), system prompt wording shifts to ownership framing in the prompt variants that carry these sections: the opening line becomes You work alongside the user on software engineering tasks and own the outcome of what you take on. (or an output-style variant with the same framing), the confirm-before-risky-actions sentence drops approval in one context doesn't extend to the next, and the When a task has been agreed, the approval covers it end to end paragraph is left out.v2.1.161 → v2.1.215 ○gone AND v2.1.308 tengu_walnut_sconce ◇ An alternate PR-review description exists but you'll always see the original one.v2.1.218 → v2.1.267 ○gone AND v2.1.221 tengu_walnut_spire ◇ Plugin eval checks your credentials first and aborts instead of failing every case.v2.1.198 → v2.1.268 ○gone AND v2.1.235 tengu_walnut_tiller ◇ MCP tools that declare file inputs can now take local file paths, which Claude Code uploads and replaces with referencesv2.1.296 → v2.1.308 ◆in the build AND v2.1.296 tengu_warm_sunrise ◇ A find command containing -rm no longer counts as read-only, so Claude Code asks before running itv2.1.289 → v2.1.308 ◆in the build never read tengu_watchdog_skip_nonstreaming_fallback ◇ Default false. When on, a streaming request that the stream idle watchdog aborts is not retried as a non-streaming request. CLAUDE_CODE_REMOTE has the same effect, and CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK or tengu_disable_streaming_to_non_streaming_fallback disable the fallback for every stream failure.v2.1.211 → v2.1.308 ◆in the build AND v2.1.232 tengu_web_fetch_provenance_prompt ◇ WebFetch's permission logic is now a reusable function that can re-check permissions after a redirectnever mined ·never mined never read tengu_web_fetch_transport ◇ A new telemetry event records the outcome and duration of each raw WebFetch network requestnever mined ·never mined never read tengu_web_setup_push_offer ◇ A new dialog can offer to connect GitHub to claude.ai after a git push, not yet confirmed livev2.1.267 → v2.1.308 ◆in the build never read tengu_webagent_mcp_bridge ◇ The hearthbot chat bridge can now auto-allow many more read-only actions without a permission promptv2.1.273 → v2.1.274 ○gone AND v2.1.273 tengu_webfetch_deadline_ms ◇ WebFetch requests now enforce a timeout and fail with a clear deadline error if exceededv2.1.268 → v2.1.308 ◆in the build never read tengu_wif_user_oauth_refresh_token_cleared ◇ An analytics event, not a feature flag. Claude Code logs it, with no fields, after a workload identity federation token request fails with HTTP 400 or 401 and an invalid_grant body, and Claude Code removes the stored refresh_token from the cached credentials file because it is still the same token that was used.never mined ·never mined never read tengu_wiggly_dove ◇ A new x-claude-code-wiggly-dove request header can carry client version, permission mode, sandbox and git details, and is off by defaultv2.1.296 → v2.1.308 ◆in the build AND v2.1.296 tengu_wild_gosling ◇ A new remotely controlled switch is off by default and never applies to organisations under the HIPAA policyv2.1.290 → v2.1.308 ◆in the build AND v2.1.290 tengu_wild_tome ◇ Memory extraction gets a new 'relayFork' execution mode, off by defaultv2.1.271 → v2.1.308 ◆in the build AND v2.1.286 tengu_willow_crate ◇ Opening the diff panel records one event with your terminal width bucket.v2.1.228 → v2.1.259 ○gone AND v2.1.228 tengu_willow_mode ◇ No description from anybody.never mined ·never mined AND v2.1.110 tengu_willow_prism ◇ Default false. Turns on the Agent tool's cost steer for pro subscribers when CLAUDE_CODE_AGENT_COST_STEER is neither a true nor a false value: the Agent tool prompt gains the paragraph Do not spawn agents unless the user asks. and drops the bullet about launching several agents in one message, and the initial agent listing omits its concurrency note.v2.1.138 or earlier → v2.1.139 ○gone never read tengu_willow_tern ◇ A writing-style prompt block can be forced on with an environment variable; otherwise it stays off.v2.1.248 → v2.1.294 ○gone AND v2.1.247 tengu_willow_tern_applied ◇ A writing-style prompt block can be forced on with an environment variable; otherwise it stays off.never mined ·never mined never read tengu_windows_credman ◇ Several internal services now receive login credentials directly instead of grabbing whatever token is lying around.never mined ·never mined AND v2.1.269 tengu_wise_bear_copy ◇ Usage-limit reset messages now map limit types to session, weekly, or model-based reset scopesv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_wise_comet ◇ Manual compaction now decides whether to strip thinking blocks, gated for adaptive thinking only.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260 tengu_wise_kite ◇ Claude Code has a new feature switch that is controlled from Anthropic's servers and falls back to offv2.1.287 → v2.1.308 ◆in the build AND v2.1.287 tengu_wise_star ◇ A flag decides whether the file-delivery tool is held back from the initial tool list.v2.1.248 → v2.1.258 ○gone AND v2.1.248 tengu_witty_firefly ◇ No description from anybody.v2.1.301 → v2.1.306 ○gone AND v2.1.308 tengu_witty_hearth ◇ With CLAUDE_CODE_PEWTER_OWL_TOOL set, three tools can now leave out a response ID depending on a remotely controlled switchv2.1.290 → v2.1.308 ◆in the build AND v2.1.293 tengu_witty_kay ◇ Two new feature switch names were added to an existing list of switch namesv2.1.307 → v2.1.308 ◆in the build AND v2.1.307 tengu_witty_wand ◇ Model effort level can now be set per-model via a gated remote-configured tablev2.1.283 → v2.1.308 ◆in the build never read tengu_wobbly_dahl ◇ Claude Code can tell the model the user pays per token and what a Bash call costs, but both notes fall back to offv2.1.290 → v2.1.308 ◆in the build AND v2.1.290 tengu_wobbly_fern ◇ If a request is too big, you're told whether dropping attachments or compacting would help.v2.1.229 → v2.1.308 ◆in the build never read tengu_wobbly_pinwheel ◇ Scripted sessions now get a stream-json status message whenever the permission mode changes.v2.1.234 → v2.1.308 ◆in the build AND v2.1.234 tengu_wondrous_acorn ◇ A new tether subsystem recreates a thinking thread when the server drops earlier thinking due to a prefix mismatchv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_wondrous_haven ◇ No description from anybody.v2.1.295 → v2.1.308 ◆in the build never read tengu_woolly_forest ◇ The check for preparing compaction ahead of time was reorganized, and a separate server-controlled switch was added beside itv2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_woolly_owl ◇ A remote bridge session's /clear command can now automatically dismiss a local dialog blocking itv2.1.265 → v2.1.308 ◆in the build never read tengu_woolly_parsnip ◇ Auto mode now stops itself instead of looping forever when safety checks keep failingv2.1.280 → v2.1.284 ○gone AND v2.1.285 tengu_worker_owner_rows_killswitch ◇ Spawned background agents can now be given a relayed summary of the project owner's recent 'timeline' postsv2.1.267 → v2.1.308 ◆in the build AND v2.1.267 tengu_worker_permission_mode_restore ◇ Resuming a session that was in plan mode now puts you back in plan mode.never mined ·never mined never read tengu_workflow_authoring_skill_autoload ◇ A bundled workflow-authoring skill loads itself when you mention workflows, and multi-agent runs need your ask.never mined ·never mined never read tengu_workflow_launched ◇ Internal renaming of the local-workflow launch tool's code, no behavior changenever mined ·never mined never read tengu_workflow_saved ◇ Your saved workflows can be listed and stored through a storage backend rather than plain files.never mined ·never mined never read tengu_workflow_schema_lint_enforce ◇ The workflow check for agent output formats that can never be met behaves the same as in the previous buildv2.1.260 → v2.1.308 ◆in the build AND v2.1.305 tengu_workflows_enabled ◇ One helper now decides whether workflows are off, covering the setting, env var and remote gate.v2.1.146 → v2.1.308 ◆in the build AND v2.1.284 tengu_worktree_detection ◇ An extra pass-through step was added to the internal chain that reports git worktree detection timingnever mined ·never mined never read tengu_worktree_kept ◇ Leaving a worktree warns about possible unpushed commits instead of claiming zero.never mined ·never mined never read tengu_worktree_mode ◇ No description from anybody.never mined ·never mined AND v2.1.51 tengu_worktree_removed ◇ Worktree cleanup aborts rather than deleting a tree whose state it cannot safely determine.never mined ·never mined never read tengu_worktree_resume_root_rejected ◇ Resuming into a missing worktree now warns you, and headless runs exit with an error instead of continuing.never mined ·never mined never read tengu_worktree_stale_lock_released ◇ An analytics event, not a feature flag. Claude Code logs it after a sweep that releases stale liveness locks on its own git worktrees, when at least one release was attempted. It carries attempted, the number of locks it tried to release in that sweep.never mined ·never mined never read tengu_woven_harbor ◇ Cloud sessions from review or plan sources can use a newer creation endpoint allowing --project grouping.v2.1.227 → v2.1.241 ○gone AND v2.1.224 tengu_woven_parcel ◇ No description from anybody.v2.1.305 → v2.1.306 ○gone never read tengu_write_tool_not_read_hypothetical ◇ Remotely served edits are less likely to be blocked by the read-before-write rule.never mined ·never mined never read tengu_xterm_atlas_reset ◇ Default true. Enables proactive glyph atlas resets in the terminal renderer on xterm.js terminals: once 2000 distinct styled glyph keys have been recorded (and 2000 ms have passed since the last reset), and when the terminal regains focus, Claude Code writes the escape sequence \x1B]104;255\x07 and clears its glyph record. When off, glyph recording also stops unless tengu_basalt_meadow is on.v2.1.154 → v2.1.308 ◆in the build AND v2.1.308 tengu_year_end_2025_campaign_promo ◇ No description from anybody.never mined ·never mined never read tengu_zany_flask ◇ Attachment uploads now have separate remote settings for preview and scaled copies, and Claude is told when an image went out scaled downv2.1.287 → v2.1.308 ◆in the build AND v2.1.292 tengu_zany_melody ◇ A server-controlled switch tied to session check-ins now has a different name; its built-in value is still onv2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_zany_pike ◇ After over 65 minutes idle, Claude Code can ask to clear older tool results from the conversation, keeping the last 5; off by defaultnever mined ·never mined AND v2.1.284 tengu_zesty_pearl ◇ On WSL, deny, ask and edit permission rules can also be checked against the other mount spelling of a path, when a switch is onv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_zinc_harbor ◇ Background tasks left running after their owning agent disappears are now automatically stoppedv2.1.275 → v2.1.308 ◆in the build AND v2.1.275 tengu_zippy_gosling ◇ Default 0 (off). Idle threshold in milliseconds for an interval poller used by several background checks, including policy limits polling. When it is a positive number, no main-loop query is running, and more time than that has passed since the later of the last user interaction and the last API completion, a poll tick is postponed until the next user interaction, at most 3 ticks in a row; a non-number, zero or negative value turns the postponement off.v2.1.261 → v2.1.308 ◆in the build AND v2.1.308 tengu_zippy_harbor ◇ Six features controlled from Anthropic's servers are now checked early at startup, and five are off unless switched on remotelyv2.1.300 → v2.1.308 ◆in the build never read tengu_zippy_spindle ◇ New unreleased mechanism lets a fresh prompt abort a running turn early to run soonerv2.1.271 → v2.1.308 ◆in the build AND v2.1.271