Feature flags, all 2,081.

tengu_remote_tool_classifier ◇ Tool calls and Bash can be routed to another machine over a device bridge.never mined ·never mined never read tengu_remote_tool_forward ◇ Tool calls and Bash can be routed to another machine over a device bridge.never mined ·never mined never read tengu_remote_tool_restart_adoption ◇ Resuming an MCP session can adopt tool calls a previous worker left in flight instead of re-issuing the interrupted turn.never mined ·never mined never read tengu_remote_tool_restart_adoption_unroutable ◇ Tool calls sent to remote hosts are tracked so a session restart can adopt them and explain whether the command actually ran.never mined ·never mined never read tengu_remote_tool_result_rendered ◇ Remote sessions now report once when they first show a tool result.never mined ·never mined never read tengu_remote_tool_serve ◇ Serving a remote tool call now records detailed timing for each stage of the replynever mined ·never mined never read tengu_remote_tool_serve_hook_held ◇ Hooks for tool calls served to a cloud session can be held instead of run, turning the call into an ask.never mined ·never mined never read tengu_remote_tool_served_preview ◇ Approval dialogs for forwarded edits now rebuild the diff against your local copy of the file.never mined ·never mined never read tengu_remote_tool_targets ◇ Tool calls and Bash can be routed to another machine over a device bridge.never mined ·never mined never read tengu_remote_tools_announce ◇ Tool announcements from an attached machine are size-checked and answered with a precise refusal reason.never mined ·never mined never read tengu_rename_full_session_fork ◇ Default false. When on, /rename without a name first asks a one-turn fork of the full session, with every tool denied, for a name, but only while the session's last saved request parameters are recent and match the current model. If that returns nothing, it falls back to the normal path, a separate model call given a text extract of the conversation.v2.1.147 → v2.1.308 ◆in the build never read tengu_repl_diff_panel_shown ◇ Opening the diff panel records one event with your terminal width bucket.never mined ·never mined never read tengu_repl_mcp_error_throw ◇ The gate behind MCP error-throwing now reads under the name tengu_tranquil_fern instead of tengu_repl_mcp_error_throwv2.1.217 → v2.1.274 ○gone AND v2.1.275 tengu_repo_text_file_size ◇ No description from anybody.never mined ·never mined never read tengu_report_findings_tool ◇ Two server-side switches that steered review behaviour are gone, so reviews no longer vary by remote config.v2.1.196 → v2.1.231 ○gone AND v2.1.232 tengu_request_user_dialog_implicit_cancel ◇ Bug fix: cancelling pending dialogs could log the wrong dialog type in telemetrynever mined ·never mined never read tengu_resume_model_restore ◇ Blocked model access now triggers a live re-check with the server before finalizing the blocknever mined ·never mined never read tengu_resume_open_live_bg ◇ --resume on a session running in the background now attaches to it and hands over your prompt instead of refusingv2.1.285 → v2.1.308 ◆in the build AND v2.1.285 tengu_resume_parked_permission ◇ Resuming could drop unanswered permission prompts instead of re-running the interrupted turn, but only with an env var set.never mined ·never mined never read tengu_resume_return_action ◇ Resuming a session can now reuse an already-computed summary instead of recalculating itnever mined ·never mined never read tengu_resume_stale_prompt_cancel ◇ On resume, cancelled leftover prompts are now reported by id to the headless loop.never mined ·never mined never read tengu_resume_stale_turn_suppressed ◇ The staleness cutoff for auto-resuming an interrupted turn is now configurable, defaulting to 6 hoursnever mined ·never mined never read tengu_retention_sweep ◇ Leftover temp files from interrupted plan writes are now cleaned up by the retention sweep.never mined ·never mined never read tengu_retire_chat_relay_artifact_backstop ◇ A chat relay flag no longer does anything; entrypoint alone decides that path.v2.1.203 → v2.1.247 ○gone AND v2.1.248 tengu_review_bughunter_config ◇ The cloud review poll timeout is no longer hardcoded at 30 minutes and now comes from remote config.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.259 tengu_review_remote_github_access_probe ◇ PR reviews stop right away with advice if your GitHub account cannot see the repo.never mined ·never mined never read tengu_review_workflow_routing ◇ Two server-side switches that steered review behaviour are gone, so reviews no longer vary by remote config.v2.1.160 → v2.1.231 ○gone AND v2.1.232 tengu_rewind_first_message ◇ Default false. Changes the SDK rewind_conversation control request: when false, the rewind is anchored at the nearest assistant message before the target and fails with no preceding assistant if there is none. When true, it is anchored at the nearest user or assistant message before the target, that error is not returned (so the first message can be the target), and the anchor is persisted with { rewound: true }.v2.1.191 → v2.1.245 ○gone AND v2.1.308 tengu_ripgrep_availability ◇ An analytics event, not a feature flag. Claude Code logs it after its first-use test of ripgrep, which runs rg --version and passes when it exits 0 with output starting ripgrep . Fields: working (1 or 0) and using_system (1 when the system ripgrep is in use). Nothing is logged when the test throws.v2.1.242 → v2.1.247 ○gone never read tengu_ripgrep_eagain_retry ◇ An analytics event, not a feature flag. Claude Code logs it, with no fields, when a ripgrep run fails with an EAGAIN error and it retries the search in single-threaded mode (-j 1).v2.1.242 → v2.1.247 ○gone never read tengu_rl_checkpoint_auto_continue_cancelled_by_slash ◇ Typing a slash after a rate-limit checkpoint clears the prefilled "continue" so your command runs cleanly.never mined ·never mined never read tengu_rl_checkpoint_auto_continue_cancelled_by_upsell ◇ Hitting a rate-limit checkpoint can prefill "continue" for you, cancelled if you upgrade instead.never mined ·never mined never read tengu_rl_checkpoint_auto_continue_queued ◇ Hitting a five-hour limit could queue your turn to resume automatically at reset, currently off.never mined ·never mined never read tengu_rl_checkpoint_copy_shown ◇ Hitting a five-hour limit could queue your turn to resume automatically at reset, currently off.never mined ·never mined never read tengu_rosy_donut ◇ A new internal flag, on by default, gates some turn and line attribution behavior.v2.1.257 → v2.1.308 ◆in the build AND v2.1.257 tengu_rosy_finch ◇ An MCP tool call's timeout can now pause while it waits on a question to you, but only if this is switched on remotelyv2.1.305 → v2.1.308 ◆in the build AND v2.1.305 tengu_rosy_flute ◇ WebFetch now measures how often the same web page is fetched again, without changing what it returnsv2.1.281 → v2.1.308 ◆in the build AND v2.1.307 tengu_rosy_pine ◇ A prompt can offer to continue a resumed old session on a newer model of the same family; it is off unless switched on remotelyv2.1.286 ○gone AND v2.1.286 tengu_rosy_wren ◇ Spawned teammates only hear about the shared task list when they actually have task tools.v2.1.234 → v2.1.267 ○gone never read tengu_russet_linnet ◇ Default false. When on, the Skill tool's prompt uses the shorter Invoke a skill. text in place of the default Execute a skill within the main conversation text. Setting CLAUDE_CODE_SKILL_DESC_REFRAME to true turns this on regardless of the flag.v2.1.196 → v2.1.215 ○gone AND v2.1.196 tengu_russet_pergola ◇ A productivity-skills switch is named in the artifact code but nothing reads it.v2.1.277 → v2.1.304 ○gone never read tengu_russet_plover ◇ Artifact syntax highlighting and mermaid diagrams are now always on; three other gates were renamed and stay off.v2.1.239 → v2.1.250 ○gone AND v2.1.240 tengu_russet_whimbrel ◇ No description from anybody.v2.1.295 → v2.1.308 ◆in the build AND v2.1.308 tengu_rustling_crescent ◇ Claude Code can list the subagents that ran earlier in a session, off unless CLAUDE_CODE_SUBAGENT_HISTORY is set or it is switched on remotelyv2.1.307 → v2.1.308 ◆in the build AND v2.1.307 tengu_rustling_orbit ◇ A missing policy-limits response with no cache no longer counts as a failure; the session runs with no restrictions instead.v2.1.259 → v2.1.308 ◆in the build AND v2.1.304 tengu_rustling_pixel ◇ Claude Code can now keep extended-thinking content across any model switch, not just upgradesv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_rustling_sunset ◇ Claude Code can now show a heartbeat message while waiting on a rate-limit retryv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_sable_orrery ◇ Behind a server-controlled switch, the auto mode startup dialog now changes some state before it shows and restores it afterv2.1.305 → v2.1.308 ◆in the build AND v2.1.305 tengu_sable_thrush ◇ Claude Code now spots server-tagged narration thinking, but the display change stays off by default.v2.1.240 → v2.1.250 ○gone AND v2.1.251 tengu_saddle_lantern ◇ The memory prompt variant and the skill-suggestion rollout are now fields on the process config.v2.1.260 → v2.1.306 ○gone AND v2.1.248 tengu_saffron_anchor ◇ A prompt-and-context experiment switch was renamed and four other switches disappeared entirely.v2.1.179 → v2.1.245 ○gone AND v2.1.246 tengu_saffron_credits_only_tiers ◇ No description from anybody.v2.1.190 → v2.1.308 ◆in the build AND v2.1.190 tengu_saffron_ferry ◇ Claude Code reads a new on/off switch from the server, and treats it as on when the server sends nothingv2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_saffron_kite ◇ A new gate can now trigger remote-session notifications on its ownv2.1.275 → v2.1.308 ◆in the build never read tengu_saffron_ladder ◇ The remote setting behind the Fable upgrade offer now only turns a fixed "Upgrade to Max" option on or off, with no custom textv2.1.216 → v2.1.308 ◆in the build AND v2.1.282 tengu_saffron_lattice ◇ Whether a model needs consent or usage credits can now be decided per model rather than for the whole planv2.1.170 → v2.1.308 ◆in the build AND v2.1.299 tengu_saffron_picker_dim ◇ Default false. When on, and the cached extra-usage disabled reason is org_level_disabled or overage_not_provisioned (along with further account checks), model picker options whose value is a Fable model are shown disabled with the label Fable (disabled), and their description can gain a requires usage credits note.v2.1.190 → v2.1.308 ◆in the build AND v2.1.190 tengu_saffron_wren ◇ Goals now nudge Claude every 30 minutes when background shells or agents are blocking evaluation.v2.1.234 → v2.1.308 ◆in the build AND v2.1.269 tengu_sage_compass ◇ No description from anybody.never mined ·never mined AND v2.1.98 tengu_sage_compass2 ◇ An internal advisor model concept exists, with sub-agents told never to consult it, and only runs under first-party auth plus a flag.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.282 tengu_salt_marsh ◇ Memory citations can now be tagged inline with markupv2.1.205 → v2.1.308 ◆in the build AND v2.1.275 tengu_sandbox_disabled_commands ◇ No description from anybody.never mined ·never mined never read tengu_sandbox_scrub_removed_non_symlink ◇ The sandbox startup sweep records whether the denied thing it deleted was a file or directory.v2.1.242 → v2.1.247 ○gone never read tengu_sandbox_scrub_spared_unreachable ◇ Sandbox cleanup keeps symlinks you retargeted yourself, denying the new target instead of deleting the link.v2.1.247 ○gone never read tengu_satchel_banjo ◇ The dialog for buying extra usage now reads an offer, a remaining monthly bundle cap and custom discount tiers sent from the serverv2.1.217 → v2.1.308 ◆in the build AND v2.1.304 tengu_satin_quoll ◇ No description from anybody.never mined ·never mined never read tengu_scalable_quiche ◇ Artifacts could keep being watched even when your session is not running, but that is off.v2.1.227 → v2.1.238 ○gone AND v2.1.239 tengu_scheduled_task_fire ◇ Scheduled-task telemetry now hashes task IDs instead of sending them rawnever mined ·never mined never read tengu_scheduled_task_missed ◇ Scheduled-task telemetry now hashes task IDs instead of sending them rawnever mined ·never mined never read tengu_scratch ◇ Claude may soon be told to use a per-session scratchpad directory for temp files instead of /tmp.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.252 tengu_sdk_malformed_input ◇ Odd or damaged input frames on remote connections are now fixed up or quietly dropped instead of erroring out.never mined ·never mined never read tengu_sdk_mcp_manifests ◇ SDK-registered in-process MCP servers can now skip a round-trip handshake at session startv2.1.265 → v2.1.308 ◆in the build AND v2.1.288 tengu_sdk_memory_summary ◇ SDK memory usage sampling for child processes now runs asynchronously and in parallelnever mined ·never mined never read tengu_sdk_oauth_refresh_unfulfilled ◇ An SDK host can now refuse to refresh your login token and say why.never mined ·never mined never read tengu_sdk_result ◇ SDK session-result telemetry now includes the user message id being processed at session end.never mined ·never mined never read tengu_sdk_session_crash ◇ SDK session crash telemetry now logs the actual error that caused the crashnever mined ·never mined never read tengu_sdk_workspace_trust ◇ SDK/host initialize can now grant directory trust programmatically via a validated workspaceTrust optionnever mined ·never mined never read tengu_sedge_lantern ◇ /recap and the Session recap settings entry now work for everyone without an experiment flag.v2.1.138 or earlier → v2.1.222 ○gone AND v2.1.223 tengu_sedge_lantern_config ◇ /recap and the Session recap settings entry now work for everyone without an experiment flag.v2.1.138 or earlier → v2.1.308 ◆in the build never read tengu_sedge_lantern_holdback ◇ Default false. When on, the away summary (session recap) is turned off unless CLAUDE_CODE_ENABLE_AWAY_SUMMARY is set to a true value, and the Session recap toggle is hidden from the settings list.v2.1.138 or earlier → v2.1.144 ○gone never read tengu_select_stray_click_dropped ◇ Clicking a menu right after focusing the terminal no longer picks an option you never aimed at.never mined ·never mined never read tengu_send_file ◇ Sending files between sessions now fails with a clear "not available in this session" message.v2.1.227 → v2.1.308 ◆in the build AND v2.1.290 tengu_send_user_file ◇ Under zero data retention, the file-send tool no longer appears at all.v2.1.142 → v2.1.308 ◆in the build AND v2.1.300 tengu_sepia_cormorant ◇ Default null. A list of model name substrings: when the session's current model contains one (case-insensitive) and tengu_umber_petrel is also on, auto memory defaults to off for that model and its status reads unavailable for current model with the toggle disabled. CLAUDE_CODE_DISABLE_AUTO_MEMORY set to a false value still forces auto memory on; a non-array or empty value has no effect.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_sepia_moth ◇ A precompute-compaction toggle is gated off by default and has no effect even if saved.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.300 tengu_sequential_cloud ◇ Claude Code can ping Anthropic's servers to keep a one-hour prompt cache alive during idle pauses, but it is off unless switched on remotelyv2.1.286 → v2.1.308 ◆in the build AND v2.1.286 tengu_sequential_puffin ◇ Resuming a session another process still controls can decline the takeover and tell you why.v2.1.232 → v2.1.308 ◆in the build AND v2.1.232 tengu_sequential_summit ◇ No description from anybody.v2.1.301 → v2.1.303 ○gone AND v2.1.308 tengu_serene_teacup ◇ A new step at session start refreshes an internal setting called the atis pinv2.1.282 → v2.1.308 ◆in the build AND v2.1.282 tengu_serene_teapot ◇ Claude Code no longer opens the server notification stream for claude.ai connectors, and answers that request itself with a 405v2.1.281 → v2.1.308 ◆in the build AND v2.1.281 tengu_serialized_petal ◇ A new setting controlled from Anthropic's servers is a number that is 0 unless the server sets it and two conditions are metv2.1.302 → v2.1.308 ◆in the build AND v2.1.302 tengu_served_unattended_consent ◇ A new config toggle lets you accept or decline whether cloud sessions may run commands unattended on your machine.never mined ·never mined never read tengu_server_classifier_no_result_latched ◇ An analytics event, not a feature flag. Claude Code logs it when the server-side auto mode classifier (the arbiter) returns no classification result and auto mode switches to classifying locally for the rest of the session, with the fields isSubagent and reason (the no-result reason such as server_unsupported, or other).never mined ·never mined never read tengu_session_deep_search_toggled ◇ No description from anybody.never mined ·never mined never read tengu_session_file_read ◇ An analytics event, not a feature flag. Claude Code logs it when the Read tool returns a text file's content, with the fields totalLines, readLines, totalBytes, readBytes, offset, limit and ext when present, messageID when present, and is_session_transcript (whether the file is classified as a session transcript).never mined ·never mined never read tengu_session_forked_branches_fetched ◇ An analytics event, not a feature flag. After loading a list of session logs, Claude Code counts the logs per session key and logs this event when any key has more than one, with the fields total_sessions, sessions_with_branches, max_branches_per_session, avg_branches_per_session and total_transcript_count.never mined ·never mined never read tengu_session_index ◇ No description from anybody.never mined ·never mined never read tengu_session_memory_accessed ◇ No description from anybody.never mined ·never mined never read tengu_session_memory_deleted ◇ Rating a session memory bad now just records the rating instead of deleting the memory.never mined ·never mined never read tengu_session_memory_loaded ◇ No description from anybody.never mined ·never mined never read