Feature flags, all 2,081.

tengu_1p_event_batch_config ◇ Default {}. Batch settings for Claude Code's first-party event logger: scheduledDelayMillis (falls back to OTEL_LOGS_EXPORT_INTERVAL, then 10000), maxExportBatchSize (default 200) and maxQueueSize (default 8192), plus skipAuth, maxAttempts, path and baseUrl passed to the exporter. When the value changes during a session, the logger is flushed and rebuilt with the new settings.never mined ·never mined AND v2.0.37 tengu_account_plugins_sync_enabled ◇ Plugins you enabled on claude.ai can be pulled to your machine, but only your account server can enable it.never mined ·never mined AND v2.1.308 tengu_account_skills_sync_enabled ◇ Account skills-sync eligibility logic generalized into a reusable descriptorv2.1.234 ○gone AND v2.1.235 tengu_adopt_claim ◇ Stale adopted session claims now return their data marked stale instead of being discardednever mined ·never mined never read tengu_adopt_link ◇ Adopting an agent's transcript now hard-links the file, copying only when linking is impossible.never mined ·never mined never read tengu_adopt_relink ◇ On startup, subagent transcripts stored as symlinks are converted to hard links or copies.never mined ·never mined never read tengu_advisor_unknown_content ◇ Advisor output you couldn't see now shows an error or a clear "declined to advise" message.never mined ·never mined never read tengu_agent_frontmatter_mode_widening_carry_ignored ◇ An agent definition's permissionMode can no longer widen the mode inherited from its parent context.never mined ·never mined never read tengu_agent_hooks_origin_untrusted ◇ Agents in untrusted folders can no longer define inline MCP servers; trust the project to allow it.never mined ·never mined never read tengu_agent_list_attach ◇ Default false. When CLAUDE_CODE_AGENT_LIST_IN_MESSAGES is unset or not a recognised boolean, true sends the Agent tool's list of agent types as agent_listing_delta attachments in the conversation (after the first, only the added and removed types) and leaves it out of the tool description. A truthy CLAUDE_CODE_DISABLE_ATTACHMENTS or CLAUDE_CODE_SIMPLE keeps the list in the description.v2.1.138 or earlier → v2.1.177 ○gone AND v2.1.178 tengu_agent_proxy_download_queue ◇ Download backlog on the agent proxy is now reported as a telemetry event.never mined ·never mined never read tengu_agent_proxy_failure_note ◇ Proxy connection failures during a command are summarised afterwards, grouped by host, with a curl pointer.never mined ·never mined never read tengu_agent_summary_skipped ◇ Background-agent summaries now get rejected outright if unparseable, with a running count of failuresnever mined ·never mined never read tengu_agent_tool_selected ◇ SDK result messages now include a summary of the subagents your session started.never mined ·never mined never read tengu_agent_worktree_cwd_escape_blocked ◇ Agent commands now have a concrete worktree boundary, so escapes get blocked with a clearer log line.never mined ·never mined never read tengu_agents_md_mod ◇ A new built-in agents-md plugin can load AGENTS.md as project instructions instead of, or alongside, CLAUDE.mdnever mined ·never mined AND v2.1.281 tengu_agentview_inherit_mode_demote ◇ A hidden --inherit-permission-mode flag lets a spawned session take its permission mode from whatever launched it.v2.1.257 → v2.1.308 ◆in the build AND v2.1.257 tengu_agile_glade ◇ Usage reports about individual features can now be thinned out or dropped per feature by a server setting, without a new releasev2.1.293 → v2.1.308 ◆in the build AND v2.1.293 tengu_alder_compass ◇ Default false. When on, the spinner tip rotation can include New to Claude Code? Run /powerup for a quick interactive tutorial. The tip is offered only to a user with fewer than 10 startups who has not unlocked any powerups.v2.1.139 → v2.1.308 ◆in the build AND v2.1.308 tengu_alder_wicket ◇ Default false. When on, the system prompt gets a # Delivering work section (section id scope_fidelity) telling the model to deliver what was asked at the intended scope, finish the whole task and say plainly what is missing. The section is also turned on by a truthy CLAUDE_CODE_ALDER_WICKET env var or a tengu_alder_wicket value of true in the cached client data.never mined ·never mined never read tengu_amber_anchor ◇ Default false. Enables installing the background daemon as a launchctl/systemd service: when off, claude daemon install, start and restart fail as disabled in this version, the claude daemon usage text says the daemon runs on demand, and daemon messages call it background service in place of daemon. When on and the daemon cold-start mode is ask (CLAUDE_CODE_DAEMON_COLD_START, the daemonColdStart setting, or the tengu_quiet_harbor flag), starting a background session with no daemon running can offer claude daemon install instead of starting one on demand, unless that prompt was dismissed or CLAUDE_CONFIG_DIR is set.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_astrolabe ◇ Default false. One of the switches that add the autonomy_append system prompt section ("You are operating autonomously...": proceed with reversible actions without asking, report findings without applying a fix when the user is only asking, finish the work before ending the turn). The section is added when tengu_amber_sextant is on (default true) and either the current model's settings turn it on or this check passes; the check passes when CLAUDE_CODE_AMBER_ASTROLABE is set, the client data key of this name is true, or this flag is on.v2.1.251 → v2.1.259 ○gone never read tengu_amber_creek ◇ Accepting fullscreen now runs as a trial, and two crashed launches disable it on that machine.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.239 tengu_amber_ferry ◇ A new mode, off unless switched on remotely, lets remote sessions start preparing a message's attachments before its files finish downloadingv2.1.286 → v2.1.308 ◆in the build AND v2.1.292 tengu_amber_flint ◇ Default true. A kill switch for agent teams: teams are enabled only when CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is set or --agent-teams is passed, and this flag is on. Turning it off disables teams even when they were requested.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.33 tengu_amber_heron ◇ Default false. When true, an Agent tool call that does not set run_in_background launches the subagent as a background task. An explicit run_in_background: false, an in-process teammate caller, or CLAUDE_CODE_DISABLE_BACKGROUND_TASKS keeps it synchronous.v2.1.186 → v2.1.197 ○gone AND v2.1.286 tengu_amber_kestrel ◇ Subagent launching gets a nesting-depth cap, a bypassable concurrency cap, and new teammate/model-inherit rulesv2.1.217 → v2.1.308 ◆in the build AND v2.1.284 tengu_amber_larch ◇ Before running a Bash command, Claude Code now also checks shell scripts written inline in it, such as heredocs or code passed with -cv2.1.288 → v2.1.308 ◆in the build AND v2.1.288 tengu_amber_lark ◇ The usage report's analysis now calculates the most sessions running at the same time, adds per-day and per-week detail, and blanks some recommendationsv2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.305 tengu_amber_lattice ◇ Default {}. Its plugins field is a list of plugin names (without the @marketplace suffix) whose hook commands are given the user's Anthropic credential in their environment: ANTHROPIC_AUTH_TOKEN set to the claude.ai OAuth access token when logged in that way, otherwise ANTHROPIC_API_KEY. It applies only to a plugin installed from one of Anthropic's official marketplaces, never when ANTHROPIC_UNIX_SOCKET is set, and subject to further provider and account checks.v2.1.144 → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_lynx ◇ The feedback dialog still skips one extra request when a server-side flag is on, the same as in the previous buildv2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.299 tengu_amber_moleskin ◇ Default null. A per-context-window version of tengu_amber_rokovoko, the fraction of the effective context window held in reserve when deciding to start precomputing a compaction summary in the background. The value is an object keyed by context-window size in tokens, or default, each entry {repl, sdk} with fractions from 0 up to but not including 1; sdk is used for queries whose source is sdk and repl for the rest. With null, a malformed table, or no entry for the current window and no default, the tengu_amber_rokovoko value is used.v2.1.179 → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_packet ◇ Claude Code can reuse a precomputed conversation summary instead of compacting fresh, gated offv2.1.198 → v2.1.308 ◆in the build AND v2.1.265 tengu_amber_prism ◇ Default false. When on and auto memory is enabled, the tool result Claude receives when the user rejects or cancels a tool call gets a note appended: the user's next message may contain a correction or preference, and Claude should consider saving it to memory for future sessions.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_quartz ◇ No description from anybody.never mined ·never mined never read tengu_amber_quill ◇ Default false. Turns on context-aware tips when the allow_context_tips policy permits them: every few turns a classifier side query picks one tip from a list of situation-matched entries (at most 3 per session) and shows it. While on, the spinner drops its built-in /clear and /btw hints and clears the regular spinner tip, unless CLAUDE_CODE_FORCE_TIP_ID or a spinnerTipsOverride is set.v2.1.191 → v2.1.211 ○gone never read tengu_amber_quill_moth ◇ Publishing an artifact can carry a template choice, switched off here, plus new edit attribution.v2.1.221 → v2.1.272 ○gone AND v2.1.221 tengu_amber_redwood2 ◇ You can now set when auto-compaction kicks in with a new --autocompact flag, and /autocompact works for everyone.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.221 tengu_amber_redwood3 ◇ You can now set when auto-compaction kicks in with a new --autocompact flag, and /autocompact works for everyone.v2.1.154 → v2.1.308 ◆in the build AND v2.1.221 tengu_amber_relay ◇ Default false. When on, session persistence is enabled for Remote Control connections from both the interactive session and the SDK: the local transcript is synced to the remote session and later internal events are written to it as they happen. The interactive session can also enable persistence through other conditions when the flag is off.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_rokovoko ◇ Default 0.2. The fraction of the effective context window held in reserve when deciding to start precomputing a compaction summary in the background: precompute arms once the context reaches the effective window minus this fraction of it, or the auto-compact threshold if that is lower. A value that is not a number from 0 up to but not including 1 falls back to 0.2. A matching entry in tengu_amber_moleskin takes precedence.v2.1.142 → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_sentinel ◇ Default false. Gates the Monitor tool, which streams each output line of a background command to Claude as a notification; the tool is enabled only when this flag and a second runtime check both pass. When on, monitors declared by plugins are also started, the Bash and scheduled-task tool instructions point Claude at Monitor for waiting on a condition, and a Bash command with a long leading sleep is blocked.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.98 tengu_amber_sextant ◇ Autonomous-operation guidance now checked with a second condition that takes message state as inputv2.1.169 → v2.1.308 ◆in the build AND v2.1.275 tengu_amber_tally ◇ Default {}. Configures a warning shown when an inactive conversation is continued after its prompt cache has likely expired, or with a different model: the cost of re-sending the context is estimated as a percentage of the 5-hour usage limit from creditsPerMillionTokens (per model) and fiveHourCredits (per rate-limit tier), and if it reaches minPercent (default 5) a dialog offers Resume or Start a new conversation. With the default {} those two required maps are missing and no warning is shown. Setting newConversationPointer to false also drops the reminder that points a conversation started this way at the earlier transcript.v2.1.282 → v2.1.308 ◆in the build AND v2.1.308 tengu_amber_tollgate ◇ A new gate can block plugin install links, requiring /plugin install to be typed manually insteadv2.1.275 → v2.1.308 ◆in the build AND v2.1.275 tengu_amber_wren ◇ Default {}. Object of default file reading limits used by the Read tool and other file reads: maxSizeBytes (default 262144), maxTokens (default 25000; CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS above 0 takes precedence), includeMaxSizeInPrompt (when true, the Read prompt says files larger than the size limit return an error) and targetedRangeNudge (when true, the Read prompt tells the model to read only the part of a file it needs instead of recommending reading the whole file). Numbers that are not positive and finite fall back to the defaults, and the result is cached for the session.v2.1.138 or earlier → v2.1.267 ○gone AND v2.1.75 tengu_anchor_tide ◇ Default false. Sets where the cursor lands when stepping back through prompt history: off places it at the start of the recalled prompt, on places it at the end.v2.1.152 → v2.1.156 ○gone AND v2.1.308 tengu_ant_attribution_header_new ◇ No description from anybody.never mined ·never mined never read tengu_ant_yolo_equiv_strip_config ◇ No description from anybody.v2.1.169 → v2.1.308 ◆in the build never read tengu_api_cache_breakpoints ◇ An analytics event, not a feature flag. Claude Code logs it after placing prompt cache markers on the messages for an API request, with totalMessageCount, cachingEnabled, skipCacheWrite, forkPointPinned and markerCount; a caller can turn the event off for a given request.never mined ·never mined never read tengu_api_no_response_timeout ◇ Hung requests are aborted when headers never arrive, and you can tune the window.never mined ·never mined never read tengu_api_query ◇ Query and result telemetry now carry a proactivity level field from your session.never mined ·never mined never read tengu_api_subagent_model_not_found ◇ A subagent failing on a missing model now tells you exactly which model was sent.never mined ·never mined never read tengu_api_success ◇ API success and error telemetry now includes your session's proactivity level.never mined ·never mined never read tengu_api_unrecognized_model ◇ You get a one-time warning line if a query names a model Claude Code does not recognise.never mined ·never mined never read tengu_artifact_ask ◇ Artifact publishing now recognizes a "still settling" server state and retries instead of failingnever mined ·never mined never read tengu_artifact_ask_granted ◇ Claude Code now logs telemetry when it asks for, and receives, permission to publish an artifactnever mined ·never mined never read tengu_artifact_five_class_asks ◇ Pinning someone else's artifact can now be auto-allowed instead of prompting, under an experimentnever mined ·never mined never read tengu_artifact_foreign_read_unasked ◇ A new unified consent system governs sensitive artifact actions like delete and access changesnever mined ·never mined never read tengu_artifact_hljs_highlight ◇ Artifact syntax highlighting and mermaid diagrams are now always on; three other gates were renamed and stay off.v2.1.212 → v2.1.238 ○gone AND v2.1.239 tengu_artifact_legacy_verb ◇ A telemetry event records which legacy artifact verb was steered onto the new schema.never mined ·never mined never read tengu_artifact_mcp_list ◇ MCP tool calls to artifact servers now pass through argument-rewriting and result-observing hooksnever mined ·never mined never read tengu_artifact_mcp_switch ◇ MCP config building gets a new caching layer, currently unread/offnever mined ·never mined never read tengu_artifact_mermaid_diagrams ◇ Artifact syntax highlighting and mermaid diagrams are now always on; three other gates were renamed and stay off.v2.1.202 → v2.1.238 ○gone AND v2.1.239 tengu_artifact_preview ◇ An artifact preview action would screenshot a page locally at several widths, but it cannot run here.never mined ·never mined never read tengu_artifact_publish ◇ Artifact publishing can copy files from other artifacts server-side, but it's off by default.never mined ·never mined never read tengu_artifact_reject_breaker ◇ The Artifact tool stops looping after three identical failures and reports the problem to you.never mined ·never mined never read tengu_artifact_thumb_direct ◇ Default false. Turns on thumbnail capture for the inline upload lane: artifact publishing starts a thumbnail capture of the page there, skipped when the Chrome preflight fails or the page is too large. The signed upload lane captures a thumbnail whenever the server provides a thumbnail upload URL, regardless of the flag; with the flag on, a failed signed PUT that falls back to inline keeps that running capture for the fallback instead of cancelling it with the reason index_put_failed.v2.1.208 → v2.1.210 ○gone never read tengu_artifact_tool_recovered ◇ New telemetry tracks when the artifact tool disappears and reappears mid-session.never mined ·never mined never read tengu_artifact_tool_withheld ◇ New telemetry tracks when the artifact tool disappears and reappears mid-session.never mined ·never mined never read tengu_artifact_toolset ◇ Artifact tool messages now describe actions as unified list/read calls with a scope, not old per-type namesnever mined ·never mined never read tengu_artifact_verify ◇ Claude could read console errors and failed loads from real viewers of an artifact, but it's switched off.never mined ·never mined never read tengu_artifact_verify_republish ◇ Claude could read console errors and failed loads from real viewers of an artifact, but it's switched off.never mined ·never mined never read tengu_ashen_kelp ◇ No description from anybody.v2.1.138 or earlier → v2.1.140 ○gone AND v2.1.132 tengu_ask_user_question_completed ◇ AskUserQuestion now logs detailed completion stats and shows a transcript line for itself againnever mined ·never mined never read tengu_assistant_output_harness_content ◇ Claude's own replies are scanned for text imitating internal control markup, and matches counted only.never mined ·never mined never read tengu_async_goblet ◇ SDK-hosted sessions can now upload attachments, with a clearer message when files stay local.v2.1.234 → v2.1.308 ◆in the build AND v2.1.234 tengu_async_snowglobe ◇ Claude Code recognises a new local memory import background task and reads a stale note setting for memory from remote settingsnever mined ·never mined AND v2.1.286 tengu_at_mention_peer_ ◇ Typing @name could message another live Claude session; the feature is off by default.never mined ·never mined never read tengu_atomic_ocean ◇ The gzip decision now records exactly why it skipped, though compression stays off without a server value.v2.1.236 → v2.1.287 ○gone AND v2.1.300 tengu_attach_serve_link ◇ New 'Remote Control' system lets a cloud session dispatch tool execution to your local computernever mined ·never mined never read tengu_attachment_file_too_large ◇ An analytics event, not a feature flag. Claude Code logs it when an @-mentioned file is larger than the attachment size limit and its extension is not in an exempt set, in which case the file is not attached; fields are size_bytes and mode.never mined ·never mined never read tengu_attempt_decision_shadow ◇ Claude Code now carries new rules for retrying failed API calls, which run alongside the current ones only to compare decisionsv2.1.284 → v2.1.308 ◆in the build AND v2.1.284 tengu_attention_budget_cycle ◇ A per-session attention budget with up and down shortcuts is built but completely unreachable.never mined ·never mined never read tengu_auq_park_interrupted_at_stream_close ◇ Closing the control stream while a question waits can now cancel the turn, but that path stays off.never mined ·never mined never read tengu_auq_park_preserve_reverted ◇ Questions left open when the stream closes could stay answerable, but that behaviour is switched off for you today.never mined ·never mined never read tengu_auq_park_preserved_at_shutdown ◇ Questions left open when the stream closes could stay answerable, but that behaviour is switched off for you today.never mined ·never mined never read tengu_auto_background_agents ◇ Default false. When true, or when CLAUDE_AUTO_BACKGROUND_TASKS is truthy, a subagent started in the foreground by the Agent tool is moved to the background automatically after 120000 ms (2 minutes) if it is still running. When both are off, no automatic backgrounding timer is set.v2.1.138 or earlier → v2.1.177 ○gone never read tengu_auto_compact_config ◇ No description from anybody.never mined ·never mined never read tengu_auto_default_nudge_resolved ◇ Saying yes to the auto-mode prompt now actually saves auto as your default permission mode.never mined ·never mined never read tengu_auto_default_nudge_shown ◇ Dialog view events are recorded once per showing rather than on every redraw.never mined ·never mined never read tengu_auto_dream_completed ◇ An analytics event, not a feature flag. Claude Code logs it when a background auto-dream memory consolidation run finishes, with token usage (cache_read, cache_created, output), sessions_reviewed, daily_logs_found, files_touched_count and team_memory_enabled.never mined ·never mined never read tengu_auto_dream_failed ◇ An analytics event, not a feature flag. Claude Code logs it when a background auto-dream memory consolidation run throws an error other than a user abort, with phase (fork while the consolidation agent runs, completion during the bookkeeping after it) and error_class.never mined ·never mined never read tengu_auto_dream_fired ◇ An analytics event, not a feature flag. Claude Code logs it when an auto-dream memory consolidation run starts after its time and session gates pass, with hours_since (hours since the last consolidation, rounded), sessions_since (sessions to review) and team_memory_enabled.never mined ·never mined never read tengu_auto_dream_toggled ◇ New internal function lets code programmatically edit the auto-memory and auto-dream settingsnever mined ·never mined never read tengu_auto_memory_toggled ◇ New internal function lets code programmatically edit the auto-memory and auto-dream settingsnever mined ·never mined never read tengu_auto_mode_availability_changed ◇ Claude Code now tracks whether auto mode's availability changes during a session, not just at startupnever mined ·never mined never read tengu_auto_mode_beta_latch ◇ The automatic retry that would drop a rejected classifier beta can never trigger in this build.never mined ·never mined never read tengu_auto_mode_classifier_queue ◇ Default false. When on, auto mode's permission-classifier calls are queued and run one at a time per agent (the main session is one queue); if the permission mode changed while a call waited so the auto decision no longer applies, the decision is dropped: the tool call is denied in dontAsk mode or where permission prompts are unavailable, and otherwise the user is asked. The env var CLAUDE_CODE_AUTO_MODE_CLASSIFIER_QUEUE, when set, takes precedence over the flag.v2.1.218 → v2.1.220 ○gone AND v2.1.308 tengu_auto_mode_config ◇ Auto-mode permission checks can score risk 0-100 instead of yes/no, but only for configured models.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.307