Feature flags, all 2,081.

tengu_mcp_server_policy_bypass_exempt ◇ The rule that exempts MCP server policy denials in remote bypass-permissions sessions behaves the same as beforev2.1.196 → v2.1.308 ◆in the build AND v2.1.288 tengu_mcp_singleton_unwrap ◇ MCP tool calls and resumed tasks now hold a guard on connection error tracking for as long as each call runsv2.1.141 → v2.1.308 ◆in the build AND v2.1.287 tengu_mcp_skills ◇ Prompt autocomplete no longer suggests MCP server URL templates for input like /server:...://v2.1.161 → v2.1.303 ○gone AND v2.1.282 tengu_mcp_skills_funnel ◇ Skills fetched from MCP servers now report extra usage stats back to Anthropic.never mined ·never mined never read tengu_mcp_startup_policy_seed ◇ Remote sessions can now seed MCP startup policy state behind a new gate.v2.1.191 → v2.1.308 ◆in the build AND v2.1.290 tengu_mcp_stateless_skip_init ◇ Default true. When on, a claude.ai connector (claudeai-proxy) with stateless: true connects statelessly: MCP initialize is answered from its cached init response when that parses and carries a supported protocol version (otherwise a real initialize runs), and when tengu_mcp_discover_projection_prior is not off, server/discover can be resolved from a cached projection. It also turns on the anthropic-mcp-client-capabilities and MCP-Protocol-Version request headers even when tengu_mcp_discover_projection_prior is off.v2.1.169 → v2.1.308 ◆in the build AND v2.1.308 tengu_mcp_step_up_auth_dialog ◇ Claude Code can offer to sign in to an MCP server again with wider permissions when a tool call is refused for missing scopev2.1.281 → v2.1.308 ◆in the build AND v2.1.288 tengu_mcp_strip_trailing_xml_tags ◇ MCP result post-processing still uses the same flag to decide whether to strip trailing XML-like tags.v2.1.186 → v2.1.308 ◆in the build AND v2.1.299 tengu_mcp_subagent_prompt ◇ Default false. Chooses the instructions Claude gets when an MCP tool result is too large and is saved to a file. Off gives the generic text (read it in chunks with offset and limit, then state how much was read); on gives format-specific steps (probe JSON with jq, slice long lines by character range, or read a stated number of lines per chunk) and suggests doing the reading in a subagent. MCP_TRUNCATION_PROMPT_OVERRIDE overrides it: legacy forces the generic text, any other non-empty value the new one.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_mcp_task_worker_wake ◇ The wake-up and retry steps for background MCP tasks now depend on a new remote switch that is off by defaultv2.1.285 → v2.1.308 ◆in the build AND v2.1.299 tengu_mcp_tasks ◇ Claude Code now checks a remote switch for an MCP tasks feature that stays off unless the server turns it onv2.1.285 → v2.1.296 ○gone AND v2.1.299 tengu_mcp_tool_call_auth_error ◇ A bug that could crash MCP auth-error logging with a stray exception has been fixednever mined ·never mined never read tengu_mcp_tool_search ◇ No description from anybody.never mined ·never mined never read tengu_mcp_tools_listed ◇ MCP tool-list telemetry now reports total, max, mean, and over-limit counts for tool description lengthsnever mined ·never mined never read tengu_mcp_tripwire ◇ MCP events are forwarded for logging with identifying fields stripped, and skipped entirely if analytics are off.never mined ·never mined never read tengu_mcp_url_elicitation ◇ MCP server configs accept a new bareElicitationCapability option that gives the server the plain elicitation capability instead of the legacy URL onev2.1.281 → v2.1.308 ◆in the build AND v2.1.300 tengu_media_byte_cap ◇ The size limit on images and media sent to the model now comes from new remote settings, with checks and a separate second limitv2.1.191 → v2.1.296 ○gone AND v2.1.299 tengu_media_byte_cap_stripped ◇ An analytics event, not a feature flag. Claude Code logs it when the image and document data in a request exceeds the media byte limit and it strips the oldest blocks: blocks inside tool results become [media removed: request limit], other blocks are dropped (a message left empty gets the placeholder). Fields are totalBytes, byteLimit, removedCount and removedBytes, and the removed totals also include blocks dropped by the media count limit in the same pass.never mined ·never mined never read tengu_medlar_quoin ◇ Artifact reply posts can now declare which earlier reply they continuev2.1.235 → v2.1.272 ○gone AND v2.1.235 tengu_mellow_beacon ◇ A server-controlled setting can make some background requests to the model point back to the reply they came fromv2.1.288 → v2.1.308 ◆in the build AND v2.1.288 tengu_mellow_heron ◇ Claude Code can now track prompts that were merged or queued together, for rewinding and spotting unanswered turns, when a switch is onv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_mellow_hollerith ◇ New built-in 'Claude Test' plugin runs plain-language specs against your local dev server in a real browser and reports PASS/FAILv2.1.274 → v2.1.295 ○gone AND v2.1.300 tengu_melodic_ember ◇ A check in the plugin and hook area now depends on a remote switch, with a new step for VS Code making sure hook registration is not pendingv2.1.299 → v2.1.308 ◆in the build AND v2.1.304 tengu_melodic_octopus ◇ When --worktree uses a pull or merge request number, Claude Code fetches the full PR reference and refuses if it can't tell which commit is meantv2.1.300 → v2.1.308 ◆in the build AND v2.1.302 tengu_melodic_wolf ◇ Subagent results can be tagged to show which parts Claude Code wrote versus the model.v2.1.242 → v2.1.308 ◆in the build AND v2.1.277 tengu_mem_push_delete_mode ◇ Default corroborate. How a memory store sync push treats a previously synced file that is now missing locally: immediate deletes it remotely on that push, never never deletes it (and skips the mass-delete hold check), and corroborate deletes it only after it has been missing on at least 2 walks at least 30000 ms apart. Other flag values mean corroborate; a set CLAUDE_CODE_MEMORY_PUSH_DELETE_MODE overrides the flag.v2.1.212 → v2.1.308 ◆in the build AND v2.1.308 tengu_memdir_accessed ◇ Memory file access reporting now notes the file kind and how it reached the model.never mined ·never mined never read tengu_memdir_disabled ◇ Auto-memory loading is now skipped when a permissions setting fences reads outside the working directorynever mined ·never mined never read tengu_memdir_file_edit ◇ Editing files in your memory directory now clears stale caches right away, so changes take effect sooner.never mined ·never mined never read tengu_memdir_file_lint ◇ Memory files can be checked after a write for oversize, split files and bad descriptions.never mined ·never mined never read tengu_memdir_file_write ◇ Editing files in your memory directory now clears stale caches right away, so changes take effect sooner.never mined ·never mined never read tengu_memdir_index_assembled ◇ A memory index can be generated by scanning recent files rather than read from a stored index.never mined ·never mined never read tengu_memdir_pin_write ◇ Memory files marked pinned would be injected into every conversation instead of waiting to be recalled.never mined ·never mined never read tengu_memdir_pinned_injected ◇ Adding pinned: true to a memory file's frontmatter would apply it to every session automatically.never mined ·never mined never read tengu_memdir_prefetch_blocking_wait ◇ Your turn can pause up to two seconds waiting for memory directory files to load first.never mined ·never mined never read tengu_memdir_write_lint ◇ A new check can refuse or clean memory files containing invisible characters or tag-like text; it falls back to off unless enabled remotelyv2.1.284 → v2.1.308 ◆in the build AND v2.1.284 tengu_memoized_owl ◇ The fixed browser setup reply in the desktop app and on claude.ai is now controlled by a newly named switch, so any earlier rollout starts overv2.1.301 → v2.1.308 ◆in the build AND v2.1.301 tengu_memoized_turtle ◇ No description from anybody.v2.1.295 → v2.1.308 ◆in the build AND v2.1.308 tengu_memory_bulk_inflate ◇ Team memory bulk-inflate telemetry now only fires for non-account memory, plus a new bail-outv2.1.161 → v2.1.308 ◆in the build AND v2.1.275 tengu_memory_store_resync_interval_minutes ◇ Default 60. Minutes between periodic resyncs of the team and user memory stores, used as the base interval for the stale-store check and the resync timer. A non-numeric, 0 or negative value turns periodic resync off, values below 1 are raised to 1, and CLAUDE_CODE_DISABLE_MEMORY_PERIODIC_RESYNC turns it off regardless of this flag.v2.1.178 → v2.1.308 ◆in the build never read tengu_memory_stream_list ◇ Default true. When on, memory store sync first tries to list a store's entries through the backend's metadata stream (exportMetadata), falling back to the paged list call when that fails. Off, or with CLAUDE_CODE_DISABLE_MEMORY_STREAM_LIST set, every listing uses the paged list.v2.1.210 → v2.1.308 ◆in the build AND v2.1.210 tengu_memory_sync_ro_unsaved ◇ A sync that runs out of time now reports as timed out rather than failed.never mined ·never mined never read tengu_memory_threshold_crossed ◇ Memory-pressure warning now shows separate 'high' and 'critical' banners instead of one combined onenever mined ·never mined never read tengu_memory_toggled ◇ An analytics event, not a feature flag. Claude Code logs it when /pause-memory pauses or resumes memory for the session; the field toggled_off is true when memory was paused.never mined ·never mined never read tengu_memory_tools_version_conflict ◇ Memory writes will need the version token from your last read, forcing a read before overwriting.never mined ·never mined never read tengu_memory_undo_attempt ◇ No description from anybody.never mined ·never mined never read tengu_memory_undo_failure ◇ No description from anybody.never mined ·never mined never read tengu_memory_undo_success ◇ No description from anybody.never mined ·never mined never read tengu_mermaid_mod ◇ Mermaid flowcharts and sequence diagrams in replies now render as text art in the terminalnever mined ·never mined AND v2.1.277 tengu_merry_popcorn ◇ Claude Code can now label each approval of a tool call as coming from a person, a classifier, a mode or a hookv2.1.288 → v2.1.308 ◆in the build AND v2.1.288 tengu_merry_tide ◇ One tool can now be offered when an extra condition holds and a remote switch is on, and the shared tool description needs that same conditionv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_mid_conv_system_fallback_retry ◇ An analytics event, not a feature flag. Claude Code logs it when the API rejects a request carrying mid-conversation role:"system" messages or per-turn statements and Claude Code retries without them; the fields are per_turn_effort, misplaced, and, when a misplaced system message was found, misplaced_index, wire_message_count and message_count.never mined ·never mined never read tengu_mighty_flask ◇ No description from anybody.v2.1.296 → v2.1.308 ◆in the build never read tengu_migrate_bypass_permissions_accepted ◇ An analytics event, not a feature flag. Claude Code logs it at startup when it migrates the old global bypassPermissionsModeAccepted value: it may write skipDangerousModePermissionPrompt: true to user settings, then removes the old key from the global config.never mined ·never mined never read tengu_mill_orange ◇ Chinese, Japanese and Korean messages without spaces could trigger memory recall, but that branch is off here.v2.1.219 → v2.1.308 ◆in the build AND v2.1.221 tengu_mint_lanes ◇ Default false. Turns on kind lanes in the slash command menu, as does CLAUDE_CODE_ENABLE_MENU_KIND_LANES: each command row gets a kind label (info commands show as config, action shows nothing) and a [source] tag, and uses the command's menuDescription when it has one.v2.1.163 → v2.1.308 ◆in the build AND v2.1.163 tengu_misty_anchor ◇ Cloud sessions can fetch a server-built memory block into the system prompt, off in this build.v2.1.246 → v2.1.308 ◆in the build AND v2.1.271 tengu_misty_aurora ◇ In remote sessions, a permission request left unanswered long enough can be declined automatically, with Claude told not to retryv2.1.292 → v2.1.308 ◆in the build AND v2.1.292 tengu_misty_sunbeam ◇ When a PDF has too many pages to read at once, Claude Code can read the first pages and report the total instead of failingv2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_misty_twilight ◇ New helper can abort leftover elicitation watchdogs, controlled by the tengu_misty_twilight flagv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_mocha_barista ◇ /schedule now always documents one-time runs and how to re-arm one that already fired.v2.1.138 or earlier → v2.1.245 ○gone AND v2.1.246 tengu_mode_cycle ◇ Changing permission mode now clears the leftover exit banner.never mined ·never mined never read tengu_model_capability_from_client_data ◇ Claude can narrate what it's about to do and post progress updates; set CLAUDE_CODE_TURN_UPDATES.v2.1.305 → v2.1.306 ○gone never read tengu_model_capability_off_from_client_data ◇ No description from anybody.v2.1.295 → v2.1.303 ○gone never read tengu_model_catalog_compare ◇ Model catalog comparison telemetry now records which catalog the models came from and accounts for session-masked ids.never mined ·never mined never read tengu_model_proposed_goals_changed ◇ A "Claude-proposed goals" setting in the config panel controls whether Claude suggests session goals.never mined ·never mined never read tengu_modular_mochi ◇ Destructive MCP calls under remote auto mode can now be allowed by either the existing gate or a new flag.v2.1.259 → v2.1.308 ◆in the build AND v2.1.295 tengu_modular_seal ◇ Claude Code can now count Claude's refusals since the conversation was last summarised, behind a setting that is off by defaultv2.1.295 → v2.1.308 ◆in the build AND v2.1.295 tengu_moonlit_island ◇ Claude Code can mark a round of polled events as declared and hand them to Claude in one message, but only behind a remote switchv2.1.293 → v2.1.308 ◆in the build AND v2.1.293 tengu_moonlit_lagoon ◇ A timing check used while Claude Code is idle or waiting on you now first consults a server-controlled switchv2.1.287 → v2.1.308 ◆in the build AND v2.1.287 tengu_moonlit_lobster ◇ Changing the model now refreshes the data Claude Code loaded at startup, as part of reworked model-switch handlingv2.1.285 → v2.1.287 ○gone AND v2.1.285 tengu_moonlit_panda ◇ Cloud sessions could delay starting language servers until needed, but the gate is off here.v2.1.246 → v2.1.308 ◆in the build AND v2.1.246 tengu_moonlit_toucan ◇ Claude Code now counts turns since a person last wrote and can act once a limit is reached, but this is off unless switched on remotelyv2.1.296 → v2.1.308 ◆in the build AND v2.1.296 tengu_morning_brief_config ◇ Default null. An object whose skillPrompt string replaces the built-in prompt of the /morning skill when, after trimming, it is 500 to 50000 characters long. A valid CLAUDE_CODE_MORNING_BRIEF_PROMPT takes precedence, and the flag is not read when the entrypoint is remote_cowork or remote_trigger.v2.1.207 ○gone AND v2.1.207 tengu_morning_brief_skill ◇ Default false. Enables the /morning skill (render a morning brief as an HTML artifact, or set it up as a recurring weekday task) when CLAUDE_CODE_IS_COWORK is true and the entrypoint is not remote_cowork or remote_trigger. A true CLAUDE_CODE_ENABLE_MORNING_BRIEF enables the skill in those sessions and entrypoints regardless of this flag.v2.1.207 ○gone AND v2.1.207 tengu_moss_anchor ◇ The built-in fallback for starting sessions in auto mode switched from off to on, so it applies unless the server turns it offv2.1.152 → v2.1.308 ◆in the build AND v2.1.302 tengu_mossy_crown ◇ A new accessFallbackModels setting lists models Claude Code may fall back to when the main model can't be usedv2.1.292 → v2.1.308 ◆in the build AND v2.1.299 tengu_mossy_gray ◇ A limit set at 2000 for every provider can now be removed by a server-side switch when Claude Code runs interactivelyv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_mossy_lantern ◇ Tools added or removed mid-conversation can be surfaced to the model, but the beta capability is gated off by default.v2.1.257 → v2.1.268 ○gone AND v2.1.308 tengu_mossy_thrush ◇ When a further server-side switch is on, the changed-file check can judge files through an outputs link and count each outcomev2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_mossy_wirth ◇ Reading project files can return an uploaded PDF or Word file itself, and writes can check a version first; both are off unless switched on remotelyv2.1.299 → v2.1.308 ◆in the build AND v2.1.299 tengu_moth_copse ◇ Default false. When true, Claude Code takes the memory stores code paths that a non-empty CLAUDE_MEMORY_STORES environment variable turns on; for example, AutoMem memory entries are filtered out of the loaded memory files. One check differs: only the environment variable, not this flag, makes files the memory mode when no earlier choice applies.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.217 tengu_moth_lantern ◇ Default false. When on and CLAUDE_MEMORY_STORES is unset or blank, a saved org memory store selection for the current account (orgMemorySelection) is sent when Claude Code requests the org memory credential, and cached store-picker data is returned alongside the org memory mounts. When off, a saved selection is sent only if it is public_projects.v2.1.213 → v2.1.217 ○gone AND v2.1.213 tengu_mulberry_fog ◇ No description from anybody.never mined ·never mined never read tengu_mutable_teapot ◇ Claude Code can now remove ask rules that come from MCP server policy before sending your permission rules to the auto mode classifiernever mined ·never mined AND v2.1.282 tengu_nankeen_kestrel ◇ Windows sandbox TLS interception could use a persistent managed certificate authority, but that path is disabled here.v2.1.212 → v2.1.308 ◆in the build AND v2.1.221 tengu_native_auto_updater_skipped_unverified_release ◇ Auto-update telemetry now reports a release skipped for failing verification as its own outcome.never mined ·never mined never read tengu_native_auto_updater_success ◇ Auto-update telemetry now reports a release skipped for failing verification as its own outcome.never mined ·never mined never read tengu_native_auto_updater_up_to_date ◇ Auto-update telemetry now reports a release skipped for failing verification as its own outcome.never mined ·never mined never read tengu_native_cdn_dark_read_failure ◇ No description from anybody.never mined ·never mined never read tengu_native_cursor ◇ Default false. When true, Claude Code uses the terminal's native cursor, the same as setting CLAUDE_CODE_NATIVE_CURSOR, provided the DECSTBM renderer is not in use; the result is cached for the process. CLAUDE_CODE_ACCESSIBILITY and one other internal condition turn the native cursor on without this flag. On Windows the same switches also feed a second terminal setup check that does not look at the DECSTBM renderer.v2.1.163 → v2.1.308 ◆in the build AND v2.1.308 tengu_neapolitan ◇ The checks deciding whether subagents are offered remote isolation gained two new conditions at the frontv2.1.178 → v2.1.308 ◆in the build AND v2.1.288 tengu_new_init ◇ No description from anybody.never mined ·never mined never read tengu_nifty_finch ◇ Claude Code can now work out an alternate model to suggest from the current one, behind a server switchv2.1.286 → v2.1.308 ◆in the build AND v2.1.286 tengu_nifty_lemur ◇ Five analytics events cover the weekly limit-reset flow.v2.1.248 → v2.1.308 ◆in the build AND v2.1.308 tengu_nimble_wren ◇ The built-in web-fetch helper now uses Haiku when certain model and provider checks pass, and is told not to retry sites that refuse itv2.1.300 → v2.1.308 ◆in the build AND v2.1.302 tengu_noble_mountain ◇ Write tool now accepts file_text, file_content, and path as aliases for content and file_path, rewriting input before plugin hooks see itv2.1.280 → v2.1.308 ◆in the build AND v2.1.280 tengu_noble_snowflake ◇ A new telemetry event, tengu_bridge_transcript_deferral, reports each stage of Remote Control's deferred transcript uploadv2.1.281 → v2.1.308 ◆in the build AND v2.1.281 tengu_noble_wozniak ◇ When the agents view opens, background housekeeping can now wait until you have trusted the folder instead of starting straight awayv2.1.300 → v2.1.308 ◆in the build AND v2.1.300 tengu_non_deferrable_builtins ◇ Default null. A list of tool names that tool search does not defer, so they are loaded with the request. The value may be a plain array or an object keyed by model name substring with a * fallback; it is merged with a non_deferrable_builtins list from another config source, and its entries also feed a set of MCP server names alongside the always-allow rules.v2.1.176 → v2.1.308 ◆in the build AND v2.1.308