# Claude Code v2.1.178 > Claude Code v2.1.178, released 15 Jun 2026 (2026-06-15). 21 entries read out of the shipped bundle. Unofficial, and not affiliated with Anthropic. Web version: https://changelogs.core-directive.com/v/2.1.178 This release replaces the explicit TeamCreate/TeamDelete tools with a simpler named-agent model, introduces a standalone `/design-login` command for design-system access independent of the main session token, and adds `isolation: "remote"` support to the Agent tool for cloud-hosted subagents. Fable 5 usage credits receive a significant UX overhaul, and the code-review skill gains a new CLAUDE.md conventions angle. ## New Features ### /design-login — Standalone Design-System Authorization **What** A new slash command that authorizes design-system (claude.ai/design) access independently of the main session login. This is especially useful when Claude Code authenticates via an API key or provider token rather than a claude.ai subscription. **Usage** `/design-login` **Details** - Opens a browser OAuth consent page specific to design-system scopes (`user:design:read`, `user:design:write`) - On SSH or remote sessions (where a browser can't reach the local listener), the flow falls back to a manual code-paste method - The credential is stored as a separate `designOauth` entry in settings, entirely separate from the main session token — signing out of claude.ai does not invalidate the design credential - The credential auto-refreshes; if a refresh fails the command re-prompts - Requires `CLAUDE_CODE_DESIGN_OAUTH_CLIENT_ID` to be set (or a build that includes the registered client id) - A 5-minute browser-authorization timeout applies; after that, the manual `/design-login` flow is suggested **Evidence** Design OAuth lock and flow (search for `"Design login"`, `".design_oauth_refresh.lock"`, `"design login — approving opens a browser OAuth consent"`) ### Agent Tool: `isolation: "remote"` — Cloud-Hosted Subagents **What** The Agent tool's `isolation` parameter now accepts `"remote"` in addition to `"worktree"`. This launches the agent in a remote cloud (CCR) environment, always as a background task. **Usage** `// In a skill or agent prompt instructing Agent tool use: isolation: "remote"` **Details** - Always runs in the background; you are notified when it completes - Remote agents run against the repository's default branch if the current local branch is not pushed to origin - Not available in all contexts: if CCR is unavailable, the tool reports `[remote agent] isolation:'remote' is unavailable` - A local agent context or no git root causes automatic fallback to other isolation modes **Evidence** Remote agent branch check (search for `"[remote agent] local branch '"`, `"isolation:'remote' is unavailable"`, `"CLAUDE_CODE_REMOTE_SESSION_ID"`) ### `/thinking` Command: `thinking_display` Parameter **What** The `/thinking` command (which sets maximum thinking tokens) now accepts an optional `thinking_display` argument to set the thinking display mode for the rest of the session. **Usage** `/thinking 10000 summarized /thinking 10000 omitted /thinking 10000 (keeps the session-start --thinking-display value) /thinking 0 (disables extended thinking)` **Details** - `summarized` — shows collapsed thinking summaries - `omitted` — hides thinking blocks entirely - Passing `null` clears back to the API default - When omitted the display mode from session start (`--thinking-display`) is preserved **Evidence** Schema update for `set_max_thinking_tokens` (search for `"thinking_display optionally sets the thinking display mode"`, `"thinking_display"`) ## Improvements ### Named-Teammate Agent Swarms (TeamCreate/TeamDelete Removed) The explicit `TeamCreate` and `TeamDelete` tools have been removed. Multi-agent coordination is now done entirely through the `Agent` tool's `name` parameter — no separate team-creation step is needed. Before (v2.1.177): `// 1. Call TeamCreate to set up the team // 2. Call Agent with team_name + name to spawn a teammate // 3. Call TeamDelete when done` After (v2.1.178): `// Just call Agent with a name parameter Agent({ name: "researcher", prompt: "..." })` **Details** - Agent swarms remain gated by the same feature flag as before - The `team_name` field in `TeammateIdle` hook events is now deprecated (marked `@deprecated`) — sessions have a single implicit team; the field will be removed in a future release - System prompt guidance now reads: "If this plan can be broken down into multiple independent tasks, consider spawning named teammates with the Agent tool (pass a `name`) to parallelize the work." - "main" is now a reserved recipient name for SendMessage — it routes a message directly to the main conversation **Evidence** Removal of TeamCreate/TeamDelete tools (search for `"TeamCreate"` absent from new file; guidance string search for `"spawning named teammates with the"`; reserved name message search for `"SendMessage routes it to the main conversation"`) ### Code Review: CLAUDE.md Conventions Angle Added **What** The code review skill (`/code-review`) now runs a dedicated "conventions" finder angle that checks changed code against the CLAUDE.md files governing those files. **Details** - Looks at user-level `~/.claude/CLAUDE.md`, repo-root `CLAUDE.md`, and any ancestor-directory `CLAUDE.md` or `CLAUDE.local.md` relevant to changed files - Only flags a violation when the exact rule can be quoted and the exact violating line identified — no vague style inferences - Total finder angles increase: high effort goes from 7 to 8 independent angles; max effort goes from 9 to 10 - Cleanup/altitude/conventions candidates share the same finding shape; correctness bugs always rank higher when output cap forces a cut **Evidence** Updated phase header strings (search for `"3 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle"`, `"Pin the diff command, changed files, applicable CLAUDE.md files, and conventions"`) ### Fable 5 Usage Credits UX Overhaul **What** The model selector and status messages around Fable 5's usage credits are significantly improved with clearer state communication. **Details** - The model entry now dynamically shows either "Draws from usage credits" or "Included with your plan until [date]" depending on account state - New `fableOverageConsent` consent flow: users are asked to explicitly enable usage credits before Fable 5 draws from them - Consent is stored per organization UUID or account UUID in local settings - Improved error messages distinguish between: credits not yet enabled, monthly limit reached (admin-adjustable vs. self-adjustable), credits unavailable for the account, and organization policy disabling credits - A configurable bridge dialog timeout: `CLAUDE_CODE_FABLE_BRIDGE_DIALOG_TIMEOUT_MS` (default 60,000 ms) **Evidence** Fable model description function (search for `"Draws from usage credits"`, `"Included with your plan until"`, `"fableOverageConsent"`, `"CLAUDE_CODE_FABLE_BRIDGE_DIALOG_TIMEOUT_MS"`) ### DesignSync: Works Without a claude.ai Session Login **What** DesignSync (and the DesignSync tool) now works even when the session authenticates with an API key or provider token, as long as a design credential has been stored via `/design-login`. **Details** - Previously, design access required expanding the main OAuth token with design scopes — impossible with API keys - Now there is a separate credential slot (`designOauth`) checked independently of the main session token - Error messages are updated to reflect this: the new message for needing authorization is "Run /design-login to authorize it with your claude.ai account — this works even when this session authenticates with an API key or a provider token." - The DesignSync tool description is updated to note the `(or, for sessions without one, a dedicated design authorization from /design-login)` path **Evidence** DesignSync error message (search for `"DesignSync needs design-system authorization. Run /design-login"`, `"designOauth"`) ### Foundry Deployment Capability Detection **What** When running against an Azure AI Foundry deployment, Claude Code now detects unsupported capabilities at runtime and degrades gracefully instead of failing. **Details** - Detects when Foundry returns a 400 error indicating features are unavailable (tool search, structured outputs, web search) - Capabilities detected from Foundry error messages: `tool_search_server`, `tool_search`, `structured_outputs`, `web_search` - On subsequent requests, the unsupported capabilities are stripped from the request (e.g. `defer_loading` and `strict` fields removed from tool definitions) - Web search unavailability is reported as: "Web search is not available on this Foundry deployment." - Tool search unavailability shows: "Tool search disabled: Foundry deployment for '…'" **Evidence** Foundry capability detection (search for `"[foundry-capabilities] deployment"`, `"retry:foundry-capability-strip:"`, `"fail:foundry-purpose-request"`, `"not supported in your workspace"`) ### Artifact Tool: HTML Skeleton Wrapping at Publish Time **What** The Artifact tool now wraps content in a `……` skeleton automatically at publish time, so content files should be written without those outer tags. **Details** - Write the page content directly (body content, CSS, scripts) — no ``, ``, ``, or `` tags of your own - Unless the user specifies a location, the recommended place for artifact files is the scratchpad directory listed in the system prompt - All other existing rules (self-contained, no external resources, responsive, favicon) are unchanged **Evidence** Updated Artifact tool description (search for `"wrapped in a"`, `""`, `"write the page content directly"`) ### Skill Directory Scoping **What** Skills can now be scoped to a specific directory subtree. When a scoped and unscoped variant of the same skill exist, the Skill tool picks the most-specific matching directory. **Details** - Skill names with a directory scope appear as `apps/web:deploy` (directory prefix + colon + skill name) - The Skill tool prompt now instructs the model: "When a skill name has both a scoped and an unscoped variant, pick by the files you are working on: if the files are under a variant's directory, invoke that variant (most specific directory wins)" - Marketplace plugin entries can declare specific skill subdirectory paths relative to the plugin root **Evidence** Skill tool prompt update (search for `"Some skills are scoped to a directory"`, `"most specific directory wins"`); plugin schema (search for `"Path to a skill directory, relative to the plugin root"`) ### Scratchpad Directory Always Enabled **What** The Scratchpad Directory section is now always included in the system prompt when a scratchpad is available. It was previously gated by the `tengu_scratch` feature flag. **Details** - Workers can read and write to the scratchpad without permission prompts - The section is only added when a scratchpad directory is actually configured and not already present in the system prompt - The `# Scratchpad Directory` marker is used to detect duplicate inclusion **Evidence** Removal of `tengu_scratch` flag check (search for `"# Scratchpad Directory"`, `"Twf"`); old code checked `pz5()` which called `Y$("tengu_scratch", !1)`) - Flag `tengu_scratch`: Off in both readings (read for one account on one subscription tier against v2.1.178; this account: off, anonymous baseline: off, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release. ### Remote Control Diagnostics Improvements **What** The Remote Control eligibility check (shown in `claude doctor` and related diagnostics) now shows more granular, correctly-labeled status for each check. **Details** - Each check now shows a positive or negative label depending on its state, e.g. "Connected to the Anthropic API (api.anthropic.com)" vs. "Not connected to the Anthropic API (api.anthropic.com)" - A new explicit org policy check: "Org policy allows Remote Control (allow_remote_control)" / "Org policy does not allow Remote Control" / "Org policy could not be verified" - The rollout gate check now distinguishes between "rollout not enabled for this account" and "could not be verified for this account" (no server response) - Remote Control is now blocked with a clearer message when the organization's compliance policy disallows it **Evidence** Updated diagnostics function (search for `"Connected to the Anthropic API (api.anthropic.com)"`, `"Org policy allows Remote Control (allow_remote_control)"`, `"Remote Control rollout enabled for this account"`) ### agent-proxy Replaces egress-gateway **What** Internal proxy component renamed from "egress-gateway" to "agent-proxy". All log messages now use the `[agent-proxy]` prefix. **Details** - All `[egress-gateway]` log strings are replaced with `[agent-proxy]` - No behavior change; this is a rename that aligns with the component's role in agent communication **Evidence** Log string comparison (search for `"[agent-proxy] enabled on 127.0.0.1:"`, `"[agent-proxy] tunnel protocol v2 negotiated"`) ### Tool Call Empty-Input Repair **What** When a tool is called with an empty input object `{}` but the tool has required parameters, a helpful error message is now generated that shows the minimal valid call shape. **Details** - Controlled by the `teasel_cove` field in the `juniper_shoal` server config (feature flag) - The error message format: "The [tool] tool was called with an empty input object ({}), but it has required parameters: `param1`, `param2`. Minimal valid call shape: {…}. Re-issue the call with real values for each required parameter." - Works for Zod-validated tool schemas (ZodObject inputs) **Evidence** New function generating the repair message (search for `"tool was called with an empty input object ({})"`; `"teasel_cove"` in juniper_shoal config) ### Hyperlink Scheme Allowlist **What** Clickable hyperlinks in the UI are now filtered through a scheme allowlist. Links with non-allowlisted schemes are silently rejected rather than dispatched. **Details** - Allowed schemes: `https:`, `http:`, `vscode:`, `vscode-insiders:`, `cursor:`, `windsurf:`, `zed:`, `jetbrains:`, `idea:`, `slack:`, `linear:`, `notion:`, `figma:` - Non-allowlisted schemes produce a warning log: "[hyperlink] refusing to dispatch clicked link with non-allowlisted scheme" - `file:` URLs are allowed but resolve to local filesystem paths only **Evidence** Allowlist constant (search for `"[hyperlink] refusing to dispatch clicked link with non-allowlisted scheme"`, `"windsurf:"`, `"figma:"`) ### NotebookEdit Permission Rules Now Filter by Path **What** The `NotebookEdit` tool now supports `ruleContentField: "notebook_path"`, meaning permission rules can match against the notebook path specifically. **Details** - Previously, permission rules for `NotebookEdit` did not have a path-based content field - Now, rules like `NotebookEdit(path/to/notebook.ipynb)` will correctly match the notebook path **Evidence** Schema change for NotebookEdit tool definition (search for `"notebook_path"` in context of `ruleContentField`) ### Periodic Memory Store Resync **What** Memory stores are now periodically resynced in the background instead of relying solely on event-driven pushes. **Details** - Controlled by the `tengu_memory_store_resync_interval_minutes` feature flag (minimum interval enforced) - Can be disabled entirely with `CLAUDE_CODE_DISABLE_MEMORY_PERIODIC_RESYNC=true` - A timer re-arms after each sync to schedule the next one; the mechanism uses `unref()` so it doesn't block process exit **Evidence** New periodic resync logic (search for `"memory-watcher: stale-store check failed:"`, `"CLAUDE_CODE_DISABLE_MEMORY_PERIODIC_RESYNC"`, `"tengu_memory_store_resync_interval_minutes"`) ### TODO Reminder Mode Control **What** The TODO reminder behavior can now be controlled via a new environment variable or feature flag. **Usage** `CLAUDE_CODE_TODO_REMINDER_MODE=off claude # disable TODO reminders CLAUDE_CODE_TODO_REMINDER_MODE=baseline claude # default behavior` **Details** - Env var takes precedence over the `tengu_soft_slate_nudge` feature flag - Feature flag values: `"baseline"` (default) or `"off"` - When set to `"off"`, TODO nudges are suppressed **Evidence** New function reading the mode (search for `"CLAUDE_CODE_TODO_REMINDER_MODE"`, `"tengu_soft_slate_nudge"`) - Flag `tengu_soft_slate_nudge`: Not enough to say (read for one account on one subscription tier against v2.1.178; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release. ## Bug Fixes - Bash prompt rule denials are now classified as `safetyCheck` type (rather than `other`) with `classifierApprovable: false`, ensuring auto-mode cannot override safety denials. (search for `"Denied by Bash prompt rule"`) - Precomputed compact is now correctly gated: it can activate for non-user-query sources that have a precomputed swap available, fixing cases where compaction would not trigger when it should. (search for `"precomputed compact: arm gated"`) - WIF (Workload Identity Federation) token refresh now checks sibling-process-rotated tokens before performing a new refresh grant, avoiding redundant token rotations in multi-process scenarios. (search for `"wif: adopting sibling-rotated access token from credentials file"`) - Agent list attachment is no longer gated by `tengu_agent_list_attach` — the check that previously required the feature flag is removed, making agent context more consistently available. (search for `"tengu_agent_list_attach"` absent from new code) - Design OAuth credential error messages are improved: the `expand_failed` case now includes guidance to run `/design-login` as an alternative, rather than only suggesting `/login`. (search for `"Could not add design scopes to the token"`, `"or run /design-login to authorize design access separately"`) - Flag `tengu_agent_list_attach`: Off in both readings (read for one account on one subscription tier against v2.1.178; this account: off, anonymous baseline: off, compiled default: not a boolean we can read) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release. ## New Environment Variables | Variable | Purpose | |---|---| | `CLAUDE_CODE_SESSION_ID` | Identifies the current session (must start with `cse_` or `session_`) | | `CLAUDE_CODE_TODO_REMINDER_MODE` | Set to `off` or `baseline` to control TODO nudges | | `CLAUDE_CODE_FABLE_BRIDGE_DIALOG_TIMEOUT_MS` | Timeout for the Fable usage-credits consent dialog (default 60000 ms) | | `CLAUDE_CODE_DIAGNOSTICS_FILE` | Path for writing diagnostics output | | `CLAUDE_CODE_REPO_CHECKOUTS` | Controls repository checkout behavior for remote agents | | `CLAUDE_SESSION_INGRESS_TOKEN_FILE` | Path to a session ingress token file | | `CLAUDE_CODE_DESIGN_OAUTH_CLIENT_ID` | Override the registered Design OAuth client ID | | `CLAUDE_CODE_DISABLE_MEMORY_PERIODIC_RESYNC` | Set to disable periodic memory store resyncs | ## Notes The removal of `TeamCreate` and `TeamDelete` is a breaking change for any workflow that explicitly called those tools. Update to use the `Agent` tool's `name` parameter directly. The `team_name` field in `TeammateIdle` hook event payloads is deprecated and will be removed in a future release. The Artifact tool's content model changed: files should no longer include ``, ``, ``, or `` tags — the tool wraps the content in a skeleton automatically. Existing artifact files that include these tags may render with duplicate structure.