Feature flags, all 2,081.

tengu_auto_mode_context_over_ceiling ◇ New telemetry fires when auto-mode context is too large and gets withheld entirely.never mined ·never mined never read tengu_auto_mode_context_static_over_budget ◇ Auto-mode classifier context now trims progressively to stay within a byte budget.never mined ·never mined never read tengu_auto_mode_context_withheld ◇ New telemetry fires when auto-mode context is too large and gets withheld entirely.never mined ·never mined never read tengu_auto_mode_decision ◇ Subagent results can be tagged to show which parts Claude Code wrote versus the model.never mined ·never mined never read tengu_auto_mode_denial_dialog_auto_denied ◇ Auto mode can show a prompt that denies itself after two minutes when you are away; off by default.never mined ·never mined never read tengu_auto_mode_denial_limit_exceeded ◇ More auto-mode permission events record whether the tool was from an MCP server.never mined ·never mined never read tengu_auto_mode_entry_warning_shown ◇ New automatic prompts appear: a first-time auto mode warning, a spending threshold dialog and a worktree tip.never mined ·never mined never read tengu_auto_mode_env_onboarding_later ◇ Auto-mode environment setup onboarding now waits for repeated denials before offering againnever mined ·never mined never read tengu_auto_mode_fallback_to_ask ◇ In auto mode, a question can be classified and handled instead of halting the run.never mined ·never mined never read tengu_auto_mode_git_state_probe ◇ Auto mode sessions now probe local git state and report telemetry about it.never mined ·never mined never read tengu_auto_mode_hook_allow_funneled ◇ Hook-approved tool calls could still be checked by the auto-mode classifier, but the flag is off.never mined ·never mined never read tengu_auto_mode_malformed_tool_input ◇ Auto-mode approval events now note whether the tool came from an MCP server.never mined ·never mined never read tengu_auto_mode_outcome ◇ Auto-mode fallback telemetry now records why a fallback model was used.never mined ·never mined never read tengu_auto_mode_outer_retry ◇ Auto mode retries instead of failing when the model that routes your turn is briefly unavailable.never mined ·never mined never read tengu_auto_mode_repo_visibility_lookup_failed ◇ An analytics event, not a feature flag. Claude Code logs it when it cannot determine a repository's visibility (public or private) from the GitHub API, with a reason field: gitlab, bitbucket or other_host for a non-GitHub host, parse_error or missing_fields for an unusable API response, http_error when the request fails, and policy_denied when the visibility probe is not allowed by policy.never mined ·never mined never read tengu_auto_mode_server_context_stale ◇ Auto mode now re-checks artifact facts to catch stale 'allow' verdicts from the server classifiernever mined ·never mined never read tengu_auto_mode_server_fallback_notice ◇ The auto-mode fallback warning can now appear inside SDK host apps that support it, when tengu_expressive_galaxy allowsnever mined ·never mined never read tengu_auto_mode_server_fallback_notice_closed ◇ The auto-mode server-fallback notice now records "unanswered" when it closes without a choice, and the dialog can be cancelled from outsidenever mined ·never mined never read tengu_auto_mode_setup_wizard_answers ◇ Auto-mode setup is one screen now instead of three separate questions.never mined ·never mined never read tengu_auto_mode_setup_wizard_shown ◇ Reopening the auto-mode wizard can no longer let a stray keypress confirm instantly.never mined ·never mined never read tengu_auto_mode_worktree_fast_path ◇ Auto mode could stop asking about sibling git worktrees of the same repo, but it is off.v2.1.227 → v2.1.308 ◆in the build AND v2.1.227 tengu_auto_notice_once ◇ Default false. In auto mode, when on, the recurring Auto Mode Active reminders are replaced by a single meta message, The user has asked you to work without stopping for clarifying questions. ..., added only when no auto mode reminder is found since the last auto mode exit. When off, the full or sparse auto mode reminder repeats every few turns.v2.1.138 or earlier → v2.1.144 ○gone AND v2.1.308 tengu_autocompact_offer_resolved ◇ No description from anybody.never mined ·never mined never read tengu_autofix_pr ◇ No description from anybody.never mined ·never mined never read tengu_autofix_pr_result ◇ An analytics event, not a feature flag. Claude Code logs it when an /autofix-pr run ends, with a result field: success (a cloud autofix session was spawned or one is already monitoring the PR), success_current_session (monitoring set up in the current session), deferred_to_pr_steward (PR Steward is already handling the PR), cancelled, or failed together with an error_code.never mined ·never mined never read tengu_autofix_pr_started ◇ An analytics event, not a feature flag. Claude Code logs it when an /autofix-pr run starts, with action set to start and has_pr_number, has_repo_path and has_repo_ref recording which of those inputs were given.never mined ·never mined never read tengu_ax_screen_reader ◇ The information Claude Code gives the auto mode safety check can now carry an extra marker, and a new prompt-screening step was addedv2.1.300 → v2.1.308 ◆in the build AND v2.1.295 tengu_ax_sr_arrow_nav ◇ Arrow-key navigation for screen-reader mode is gated off, so screen readers keep the existing behavior.v2.1.281 → v2.1.282 ○gone never read tengu_background ◇ No description from anybody.v2.1.287 ○gone never read tengu_basalt_3kr ◇ No description from anybody.never mined ·never mined never read tengu_basalt_loom ◇ Plan artifacts now have their own switch instead of riding along with an unrelated experiment.v2.1.223 → v2.1.237 ○gone AND v2.1.223 tengu_basalt_meadow ◇ Default false. When on, each prompt submission sends a tengu_render_glyph_cardinality telemetry event with the terminal renderer's style-pool size and glyph-atlas key count, plus the terminal program and a session-age bucket, and glyph-atlas recording stays on even when tengu_xterm_atlas_reset is off.v2.1.154 → v2.1.308 ◆in the build AND v2.1.308 tengu_basalt_scarp ◇ Default false. Takes effect only while tengu_basalt_spur is on, under the same provider conditions. When a forked request skips cache writes and its fork point is the same message as its main prompt-cache breakpoint, the breakpoint pinned at the fork point is placed one cacheable message earlier.v2.1.153 → v2.1.308 ◆in the build AND v2.1.248 tengu_basalt_spur ◇ Default false. Applies only when the provider is the first-party API, Anthropic on AWS or Google Cloud, or Foundry, and experimental betas are allowed (CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS unset, no HIPAA restriction). When on, the background memory-extraction (extract_memories) and auto-dream forks skip writing their new messages to the prompt cache, and request building can pin an extra cache breakpoint at the message a forked request branched from.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.248 tengu_bash_allowlist_strip_all ◇ Default false. Its value is recorded as stripAllBashFlag on the tengu_auto_mode_decision telemetry event sent when the auto mode classifier reviews a tool call; the fast-path and subagent-handoff decision events do not carry it, and no other code reads the flag in this version.v2.1.138 or earlier → v2.1.191 ○gone never read tengu_bash_ast_too_complex ◇ Bash's 'too complex to check' read-block guard now applies via a general table covering more refusal reasons, not just one hardcoded casenever mined ·never mined never read tengu_bash_command_clamp_denied ◇ If a clamped agent's permission check crashes, the shell command is denied rather than allowed.never mined ·never mined never read tengu_bash_dangerous_rm_too_complex ◇ The dangerous-rm safety check for bash commands can now be extended with an extra custom checknever mined ·never mined never read tengu_bash_security_check_triggered ◇ No description from anybody.never mined ·never mined never read tengu_bash_task_ack ◇ Backgrounded shell commands may return a structured task record instead of raw output.never mined ·never mined never read tengu_bash_task_delivered ◇ Finished background tasks now report whether their output was spliced back in or lost.never mined ·never mined never read tengu_bash_tool_command_executed ◇ Bash/PowerShell telemetry and sandbox checks now track whether the user typed the command directly.never mined ·never mined never read tengu_bash_tool_command_failed ◇ Bash tool telemetry now records a detailed breakdown of each command's shapenever mined ·never mined never read tengu_bedrock_upgrade_check ◇ Bedrock and Vertex now share one check for outdated pinned model variables.never mined ·never mined never read tengu_began_setup ◇ Onboarding now also treats a 'gateway' authentication setup as equivalent to OAuth for its flownever mined ·never mined never read tengu_bergotte_lantern ◇ No description from anybody.never mined ·never mined never read tengu_bg_adopt_upgrade_respawn ◇ Background sessions stop needlessly restarting when your running build is already newer.never mined ·never mined never read tengu_bg_agent_action ◇ Background-agent telemetry no longer records which agent template was usednever mined ·never mined never read tengu_bg_attach_outcome ◇ Background attach events now record cold starts, surface and first frame details.never mined ·never mined never read tengu_bg_attach_stall_ms ◇ Default 5000 (milliseconds). How long attaching to a background session may wait for it to redraw before Claude Code restarts the session with Session not responding; after two such restarts it gives up, prints Session keeps stalling at startup. and kills the session. 0 turns the restart off; any other value is raised to at least 2000, or 12000 when a background-session launcher is configured.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_bg_attach_upgrade ◇ Default true. Gates the background-session supervisor's prewarming: restarting idle background sessions whose recorded Claude Code version is stale onto the running version, in one delayed burst once the supervisor is ready and up to tengu_bg_prewarm_per_sweep (default 3) per periodic sweep while memory is not low. Sessions launched in exec mode are skipped and a session on a newer version is not downgraded. Turning it off stops prewarming; the sweep still restarts sessions in its pinned set.v2.1.162 → v2.1.308 ◆in the build never read tengu_bg_binary_takeover ◇ The background daemon can now retire a same-version instance; build is 2.1.248.v2.1.152 → v2.1.308 ◆in the build AND v2.1.248 tengu_bg_classifier_config ◇ Background classifier gets a new, currently inactive setting to control how much recent conversation text it quotesv2.1.138 or earlier → v2.1.308 ◆in the build never read tengu_bg_classify ◇ A new 'Projects' recap mode for the background classifier can summarize thread status, currently unread/offnever mined ·never mined never read tengu_bg_daemon_binary_takeover ◇ The background daemon can now retire a same-version instance; build is 2.1.248.never mined ·never mined never read tengu_bg_daemon_spawn_failed ◇ An analytics event, not a feature flag. Claude Code logs it when it fails to spawn the background daemon: when spawning a transient daemon with daemon run --origin transient errors, when a configured agent launcher's daemon never becomes reachable, and when the daemon's upgrade self-respawn fails to spawn. Fields include errno_enoent, errno_eacces, errno, launcher_configured, failed_stage or respawn depending on the site.v2.1.138 or earlier → v2.1.241 ○gone never read tengu_bg_daemon_spawn_reinstall_wait ◇ Starting the background helper during an npm reinstall now waits and retries instead of failing.never mined ·never mined never read tengu_bg_dispatch_fallback ◇ Background dispatch failures now distinguish a daemon that started but couldn't launch Claude Code.never mined ·never mined never read tengu_bg_dispatch_rejected ◇ The background daemon now records why it refused a queued dispatch file.never mined ·never mined never read tengu_bg_imark_malformed ◇ Background sessions now send readiness marks so attaching knows when a session is actually interactive.never mined ·never mined never read tengu_bg_leftarrow_inprocess ◇ Backgrounding no longer claims artifact comment monitors will stop; it says they keep auto-replying here.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.296 tengu_bg_low_mem_mb ◇ Low-memory threshold in MiB for background sessions, code default 1024; 0 or less turns the check off. Outside macOS the machine counts as low on memory when the system memory reading is below the threshold; on macOS the value only switches the check on and macOS's critical memory-pressure level decides. While memory is low, the background-session supervisor retires settled workers sooner and before spawning a new session, stops prewarming, keeps no pre-started spare, and a worker that crashes before starting reports possibly low memory.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.232 tengu_bg_prewarm_burst_concurrency ◇ Background session prewarm now checks the concurrency limit instead of the delay value.v2.1.206 → v2.1.308 ◆in the build AND v2.1.248 tengu_bg_prewarm_burst_delay_ms ◇ Default 15000 (milliseconds). How long the background-session supervisor waits, once it is ready, before its prewarm burst: restarting idle background sessions on a stale Claude Code version onto the running one, tengu_bg_prewarm_burst_concurrency (default 3) at a time. The burst is skipped if the supervisor is shutting down, the concurrency is 0 or less, or tengu_bg_attach_upgrade is off.v2.1.206 → v2.1.308 ◆in the build AND v2.1.248 tengu_bg_prewarm_per_sweep ◇ The kite network transport is on by default everywhere, and CLAUDE_CODE_HARBOR_KITE=0 now really turns it off.v2.1.163 → v2.1.308 ◆in the build AND v2.1.248 tengu_bg_pty_unavailable ◇ An analytics event, not a feature flag. Claude Code logs it when a background session cannot be started because no pseudo-terminal spawner is available, marking the job crashed with the detail Bun.Terminal unavailable (running under Node?); it carries the job's short id.never mined ·never mined never read tengu_bg_ptyhost_zombie ◇ Background sessions whose terminal process died are now killed and marked failed instead of hanging.never mined ·never mined never read tengu_bg_retire_grace_bridged_min ◇ A prompt-and-context experiment switch was renamed and four other switches disappeared entirely.v2.1.149 → v2.1.245 ○gone never read tengu_bg_retired ◇ A background worker can now be retired purely for running a stale CLI version, with new retirement causes recorded.never mined ·never mined never read tengu_bg_revival_guard ◇ Default true. Applies when a background session's worker process crashes and is respawned. When on, a respawn that resumes a transcript with messages also gets CLAUDE_CODE_RESUME_PROMPT set (if not already set) to a note saying the session was restarted automatically and Claude should re-verify anything time-sensitive, plus CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS of one hour for sessions with interactive lineage, and each scheduled respawn first reads the session's record on disk and is skipped when that record already shows a finished state with no queued prompt. When off, only CLAUDE_CODE_RESUME_INTERRUPTED_TURN=1 is set on such a respawn and the on-disk check is not made.v2.1.211 → v2.1.308 ◆in the build never read tengu_bg_roster_orphan_adopted ◇ Recovering a stray background agent entry now records that it happened, so gaps are traceable.never mined ·never mined never read tengu_bg_session_id_taken ◇ Background sessions that hit an already-claimed session id now fail with a clear dimmed notice.never mined ·never mined never read tengu_bg_spare_claim_fail ◇ Background session records can be flagged as spare, but nothing in this build decides when a spare gets spawned.never mined ·never mined never read tengu_bg_spare_enable ◇ Default true. Lets the background-session dispatcher keep a warm spare worker process started ahead of time (not on Windows) and hand it to the next dispatched session whose launch mode is not exec, provided the spare was started by the same Claude Code version. Turning it off disposes any existing spare and stops spares from being started or claimed.v2.1.138 or earlier → v2.1.308 ◆in the build never read tengu_bg_spawn_cwd_gone ◇ An analytics event, not a feature flag. Claude Code logs it when a background session cannot start because its working directory no longer exists or is not accessible, with the job's short id, the attempt number and via. With via of dispatch the daemon refuses the job; with cold, spare or boot the spawn path marks the job crashed and it is not respawned.never mined ·never mined never read tengu_bg_state_read_recovered ◇ Background state reads retry on transient errors instead of failing immediately.never mined ·never mined never read tengu_bg_state_read_transient ◇ Background job state read failures now report themselves once per job instead of silently falling back to a cache.never mined ·never mined never read tengu_bg_worker_ctty ◇ Daemon-mode background workers now try to claim a controlling terminal at startup.v2.1.251 → v2.1.308 ◆in the build AND v2.1.251 tengu_bg_worker_exit ◇ A background worker that dies before starting is reported as a crash, not silence.never mined ·never mined never read tengu_billiard_aviary ◇ Default false. When on, auto memory switches to a variant stored in a tiny_memory directory instead of memory under the project's folder in ~/.claude/projects/ (when no memory directory override is set), with its own memory prompt; it also changes several other memory code paths, for example adding a created date default to the frontmatter of memory files.v2.1.138 or earlier → v2.1.190 ○gone AND v2.1.94 tengu_binary_balloon ◇ Remote sessions can send tool descriptions straight from a recorded snapshot instead of rebuilding them, behind tengu_binary_balloonv2.1.281 → v2.1.308 ◆in the build AND v2.1.281 tengu_binary_content_persisted ◇ Files Claude saves from web fetches, artifacts and binary tool output are now tracked in session state.never mined ·never mined never read tengu_binary_download_success ◇ Updates can arrive as a compressed build, so downloads get smaller with no setting to change.never mined ·never mined never read tengu_binary_lollipop ◇ Claude Code now contains the name of a new server-controlled switch, but nothing yet shows what it controlsv2.1.290 → v2.1.308 ◆in the build never read tengu_binary_music ◇ Users with a one-million-token context can be offered a choice of when auto-compact kicks in, from 300k to 900k tokensv2.1.300 → v2.1.308 ◆in the build AND v2.1.301 tengu_birch_compass ◇ Default false. When on, the usage limits view adds a cost breakdown panel that scans local session files (showing Scanning local sessions… meanwhile) and, for a day or week window, lists the behaviours above a percentage threshold plus agents, skills and plugins, with tips. If any session file is over 200MB it shows Cannot compute breakdown instead.v2.1.138 or earlier → v2.1.148 ○gone AND v2.1.108 tengu_birch_kettle ◇ Default false. Enables the bundled claude-code-docs skill, which answers questions about Claude Code's own commands, flags, settings, hooks and other features, can be invoked by the user with a [question] argument, and is allowed Read, Grep, Glob and WebFetch limited to code.claude.com and platform.claude.com. The skill is enabled only when this flag is on and its registration was not marked disabled.v2.1.154 → v2.1.308 ◆in the build AND v2.1.308 tengu_birch_lantern ◇ Default "off". Picks how /powerup is advertised in a session where the first-run onboarding was shown: "banner" shows an info notice ("New here? Type /powerup for a 5-minute tour..."), "step" adds a "Learn the moves" step after onboarding that can launch the tour, and any other value shows neither. CLAUDE_CODE_POWERUP_ONBOARDING set to banner or step overrides the flag.v2.1.181 → v2.1.308 ◆in the build AND v2.1.181 tengu_bison_cairn ◇ Default false. When on, the system prompt includes the # Delivering work section (guidance on doing the requested scope, handling uncertainty mid-task and proceeding after the user reaffirms a request). The section is also included when the cached client data has tengu_bison_cairn: true, for models with the fable_5_1_prompt_bundle capability (except under certain entrypoints), and for models with the opus_5_prompt_bundle capability while tengu_fennel_godwit is off; CLAUDE_CODE_BISON_CAIRN set to a true or false value overrides all of these.never mined ·never mined AND v2.1.217 tengu_bracken_sluice ◇ A read-only subagent that analyses one artifact comment thread exists but stays off.v2.1.227 → v2.1.308 ◆in the build AND v2.1.227 tengu_bramble_lintel ◇ When a pass that saves memories from your conversation stops early, the next pass looks at the same turns againv2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.305 tengu_brass_condor_loupe ◇ A remote-config gate decides whether an internal UI element shows a summary view or stays hidden.v2.1.257 → v2.1.267 ○gone AND v2.1.257 tengu_brass_kite ◇ A tool lets Claude offer one-time Claude in Chrome setup through a card after a Chrome tool finds the extension is not connectednever mined ·never mined AND v2.1.290 tengu_brass_lantern ◇ New startup telemetry tracks managed-config readiness and an optional live identity checkv2.1.271 → v2.1.289 ○gone never read tengu_brass_plover ◇ Artifacts can show who else is viewing live, but only if you set an environment variable.v2.1.251 → v2.1.308 ◆in the build AND v2.1.251 tengu_brass_sled ◇ Default false. When on, the PowerShell tool's prompt gets a "Developer tools verified on this machine's PATH" line listing the build and dev tools Claude Code detected, telling Claude that a tool missing from the list is likely not installed and should be checked with Get-Command first; on Windows it adds a note that the MSVC toolchain (cl, nmake, msbuild) is only on PATH inside a Visual Studio developer shell. The line is left out when no tools were detected.v2.1.198 → v2.1.308 ◆in the build AND v2.1.308 tengu_breezy_crescent ◇ Monitor tool watches can now be capped with an auto-expiring timeout instead of running foreverv2.1.268 → v2.1.308 ◆in the build AND v2.1.287 tengu_breezy_diffie ◇ Handling of repeated 404s while polling a cloud /code-review session is now controlled by a gate, with clearer error messagesv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_breezy_fairy ◇ Session device-binding can now request an elevated security tier, retrying without it if the server rejects the requestv2.1.274 → v2.1.308 ◆in the build AND v2.1.277 tengu_breezy_haven ◇ Claude Code keeps reading input during slow input hooks, and withdraws pending permission requests when you press Stop or the session endsv2.1.295 → v2.1.308 ◆in the build AND v2.1.295