Feature flags, all 2,081.

tengu_toasty_fiddle ◇ No description from anybody.v2.1.305 → v2.1.308 ◆in the build never read tengu_toasty_hammock ◇ Claude Code contains a new remotely controlled switch and a new artifact entry for publishing edits, with no visible effect yetv2.1.299 → v2.1.308 ◆in the build never read tengu_toasty_thimble ◇ A short reminder can be slipped in after tool results, set by an environment variable or server config.never mined ·never mined never read tengu_toasty_thimble_applied ◇ Reminder text can be latched into a conversation once per model from server config or an env var.never mined ·never mined never read tengu_todo_tool ◇ No description from anybody.never mined ·never mined never read tengu_tombstone_persisted_removal ◇ Transcript compaction now keeps host-injected messages next to the conversation turn they belong tonever mined ·never mined never read tengu_tool_cgroup ◇ On Linux you can cap memory for shell commands so a runaway process cannot eat your machine.never mined ·never mined never read tengu_tool_cpu_by_phase ◇ Remote sessions now report per-phase CPU usage split between CLI and tool subprocesses.never mined ·never mined never read tengu_tool_result_dedup ◇ No description from anybody.never mined ·never mined never read tengu_tool_result_pairing_repaired ◇ Tool-result repair now detects and reports 'misplaced' tool results in debug outputnever mined ·never mined never read tengu_tool_result_persistence ◇ No description from anybody.never mined ·never mined never read tengu_tool_schema_sizes ◇ A new event breaks down tool schema sizes by category, deduplicated and capped at 512 hashes.never mined ·never mined never read tengu_tool_search_mode_decision ◇ An analytics event, not a feature flag. Claude Code logs it when it decides whether tool search is enabled for a request, from the main query path and from compaction. Fields include enabled, mode, reason (for example model_unsupported or no_tools_in_request), checkedModel, mcpToolCount and mcpNonBlocking.never mined ·never mined never read tengu_tool_search_unsupported_models ◇ Default null. A list of model name substrings for which tool search is treated as unsupported: a model whose name contains one (case-insensitive) does not get tool search and reports model_unsupported where that reason is used. A non-array value falls back to the built-in list claude-3-5-haiku, claude-3-haiku.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_tool_use_diff_computed ◇ Writing over a very large file skips diff computation, so it no longer stalls.never mined ·never mined never read tengu_tool_use_granted_in_config ◇ An analytics event, not a feature flag. Claude Code logs it when its permission check allows a tool use without asking the user, for example through an allow rule or, in auto mode, through the classifier. It carries the tool-use metadata fields plus, for shell commands, destructive_category, destructive_target_scope, git_destructive_target and permission_mode.never mined ·never mined never read tengu_tool_use_show_permission_request ◇ Auto-mode telemetry now tags MCP tool calls with which server they connect to and whether that's ambiguousnever mined ·never mined never read tengu_tool_use_success ◇ Bash tool telemetry now breaks commands into class, program name, subcommand, and pipe usage, behind a beta flagnever mined ·never mined never read tengu_tool_use_tool_result_mismatch_error ◇ Error reports about mismatched tool calls now scrub odd identifiers instead of sending them raw.never mined ·never mined never read tengu_transcript_compact_failed ◇ Transcript compaction now runs through the storage backend instead of editing files directlynever mined ·never mined never read tengu_transcript_id_scan_fallback ◇ Resuming a session by its id now works even when the usual lookup misses it.never mined ·never mined never read tengu_transcript_input_to_teammate ◇ The prompt input takes grouped inputs and two submit paths are less defensive.never mined ·never mined never read tengu_transcript_phantom_parent ◇ An analytics event, not a feature flag. Claude Code logs it while loading a transcript when the walk up the parentUuid chain from the last eligible message stops on a broken link. It carries total_offsets (indexed entries), walked_slots (entries visited) and reason, one of non_string_parent, unknown_parent or parent_cycle.never mined ·never mined never read tengu_transcript_write_failed ◇ An unrelated file write failure no longer degrades your session's transcript recording.never mined ·never mined never read tengu_transcript_writer_recovered ◇ An unrelated file write failure no longer degrades your session's transcript recording.never mined ·never mined never read tengu_tst_hint_m7r ◇ No description from anybody.never mined ·never mined never read tengu_tst_kx7 ◇ No description from anybody.never mined ·never mined never read tengu_tst_names_in_messages ◇ No description from anybody.never mined ·never mined never read tengu_tui_optout_reason ◇ Feedback typed when opting out of the new fullscreen terminal UI is now actually submitted, not just measuredv2.1.143 → v2.1.241 ○gone never read tengu_tui_refused ◇ /tui and /update now refuse to restart when it would lose session state, naming the exact blocker.never mined ·never mined never read tengu_turn_end ◇ Every turn now reports why it ended, how long it took and whether a goal was active.never mined ·never mined never read tengu_turn_first_text ◇ A new event tracks how long the first visible text of a turn takes, including time spent waiting on you.never mined ·never mined never read tengu_turn_handoff_run ◇ A new turn_handoff protocol lets a session pass an in-progress turn to a managed cloud worker to finishnever mined ·never mined never read tengu_turn_handoff_staged_files_wait ◇ Claude Code now waits for in-flight staged file operations to settle before handing off a turnnever mined ·never mined never read tengu_turn_tail_analysis_degraded ◇ A bad message no longer breaks turn analysis; failures are skipped and reported instead of passing silently.never mined ·never mined never read tengu_twinkling_globe ◇ New remote gate tengu_twinkling_globe controls whether Claude Code treats account policy limits as absent instead of fetching themnever mined ·never mined AND v2.1.308 tengu_ultraplan_prompt_identifier ◇ Default "simple_plan". Picks the ultraplan prompt variant: simple_plan, visual_plan or three_subagents_with_critique; an unknown value falls back to simple_plan. It also picks the dialog and command text, where three_subagents_with_critique shows a ~10-30 min estimate and the Advanced multi-agent plan mode. blurb; a launch that carries its own prompt identifier uses that instead.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_ultraplan_stopped ◇ An analytics event, not a feature flag. Claude Code logs it when a running remote agent task that is an ultraplan session is stopped (marked killed), with duration_ms measured from when polling of that task started; it also clears the stored ultraplanSessionUrl.never mined ·never mined never read tengu_ultraplan_timeout_seconds ◇ Default 5400. Seconds Claude Code polls a cloud ultraplan session for an approved plan before failing with no approval after N minutes or, if no plan was ever pending, ExitPlanMode never reached after N minutes.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_ultrareview_awareness_shown ◇ Code review and post-commit tips can point you at a deeper cloud review, off by default.never mined ·never mined never read tengu_ultrareview_post ◇ Code review findings can be posted straight back to your GitHub pull request as a comment.never mined ·never mined never read tengu_umber_petrel ◇ Default false. When on, auto memory is turned off for sessions whose model matches an entry in the tengu_sepia_cormorant model list, unless auto memory has been explicitly forced on or off.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_update_bg_respawn ◇ /update and /restart no longer mention artifact comment monitoring in their refusal messagesnever mined ·never mined never read tengu_update_refused ◇ /tui and /update now refuse to restart when it would lose session state, naming the exact blocker.never mined ·never mined never read tengu_use_file_checkpoints ◇ No description from anybody.never mined ·never mined never read tengu_valiant_lantern ◇ 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 AND v2.1.302 tengu_validated_clover ◇ A new internal check called tengu_validated_clover appeared in Claude Code's code, but what it does isn't known yetnever mined ·never mined AND v2.1.308 tengu_vast_puddle ◇ No description from anybody.v2.1.295 → v2.1.308 ◆in the build never read tengu_vast_sunset ◇ No description from anybody.v2.1.299 → v2.1.308 ◆in the build never read tengu_velvet_anchor ◇ No description from anybody.never mined ·never mined never read tengu_velvet_hammer ◇ Default false. When true, or when the per-model variant tengu_velvet_hammer_<bucket> is true for the current model (the bucket is a model family such as opus, sonnet or haiku; the base bucket uses the plain name), the Edit tool skips its "File has not been read yet. Read it first before writing to it." rejection, so a file that was never read, or was only partially read, can be edited.v2.1.166 → v2.1.195 ○gone AND v2.1.308 tengu_velvet_harbor_owl ◇ A startup banner pitching Claude Enterprise to org admins exists but no one sees it by default.v2.1.238 → v2.1.308 ◆in the build AND v2.1.308 tengu_velvet_marble ◇ No description from anybody.v2.1.307 → v2.1.308 ◆in the build AND v2.1.308 tengu_velvet_moth ◇ Default 0.2. Probability that the memory survey opens for an assistant message that cites a memory with an eligible citation sentence (at most 250 characters), once the survey is otherwise enabled (tengu_dunwich_bell on, product feedback allowed, CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY unset, among other checks); each message is considered once. 1 always opens it for an eligible message and 0 never does.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.308 tengu_verified_vs_assumed ◇ Default false. When on, the # Doing tasks section of the system prompt gains the line When reporting results, be accurate about what you verified vs. what you assumed., which tells the model to distinguish what it confirmed by running a command or reading a file from what it believes but did not check, and not to assert assumptions as facts.v2.1.138 or earlier → v2.1.308 ◆in the build never read tengu_vertex_fallback_check ◇ No description from anybody.never mined ·never mined never read tengu_vertex_upgrade_check ◇ An analytics event, not a feature flag. Claude Code logs it at the start of a check for newer default models on Vertex, when the provider is vertex, CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST is unset, and at least one pinned model tier is found to check. It carries stale_tiers, the number of such tiers; each tier whose default model has a Vertex id is then probed and reported separately as tengu_vertex_probe_result.never mined ·never mined never read tengu_vinteuil_phrase ◇ No description from anybody.never mined ·never mined never read tengu_violin_ ◇ Remote sessions started from the desktop app now need a second flag as well.never mined ·never mined never read tengu_violin_plan_classifier ◇ A new flag will control whether plan mode gets classifier-based permission checksv2.1.267 → v2.1.308 ◆in the build never read 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_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_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_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_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_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_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_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_witty_firefly ◇ No description from anybody.v2.1.301 → v2.1.306 ○gone AND v2.1.308 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_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_wondrous_haven ◇ No description from anybody.v2.1.295 → v2.1.308 ◆in the build never read 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_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_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_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_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_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