Source: ai-research/claude-code-release-v2-1-{271,272,273}.md (fetched with gh release view on 2026-09-29) and raw/anthropic-watch-claude-code-tag-v2-1-{274,275,276,277,278}.md (watch feed) — anthropics/claude-code GitHub release notes, published 2026-09-14 to 2026-09-19 — plus the code.claude.com changelog snapshots ai-research/claude-code-docs-changelog-2026-09-18.md (v2.1.270–277, fetched 2026-09-18) and ai-research/claude-code-docs-changelog-2026-09-25.md (v2.1.278 entry, fetched 2026-09-25). No official W38 digest existed: code.claude.com/docs/en/whats-new/2026-w38 returned HTTP 404 on 2026-09-25.
Product: Claude Code · URL: https://github.com/anthropics/claude-code/releases · Date: 2026-09-14 → 2026-09-19
Eight releases (v2.1.271 through v2.1.278). Three changes reach beyond Claude Code’s own config: AGENTS.md is read when a project has no CLAUDE.md, skills and plugins enabled on claude.ai sync to terminal sessions, and auto mode’s classifier moves server-side by default for API, Enterprise and third-party-provider users, which the release note says “does not charge for classifier overhead”. Subagents gain omitClaudeMd and a reviewed hand-back call, the Monitor tool loses its no-timeout persistent option, and the deprecated TaskOutput tool is removed. Continues Week 37.
Key Takeaways
- AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change this under “Project instructions” in
/config; not yet on Bedrock, Vertex or Foundry (v2.1.277). See CLAUDE.md Primer. (Update 2026-09-29: per Claude Code’s memory docs, Bedrock and telemetry-off sessions load AGENTS.md from v2.1.281; Vertex and Foundry are not confirmed. See AGENTS.md.) - Auto mode defaults to the server-side classifier for Claude API and Enterprise users and on Bedrock, Vertex, Foundry and gateways;
CLAUDE_CODE_AUTO_MODE_SERVER=0opts out on Bedrock/Vertex/Foundry/gateways, a billed fallback warns, and/statusgains an “Auto mode server” row showing where the classifier runs (v2.1.278). This reverses v2.1.273 four days earlier, which had set Bedrock/Vertex/Foundry to the local classifier “for now”. See Auto Mode. - claude.ai skills and plugins sync to the terminal: those enabled on your claude.ai account load in terminal sessions signed in with it; opt out with
syncClaudeAiSkills: falseorsyncClaudeAiPlugins: false(v2.1.275). See Agent Skills. omitClaudeMdin agent frontmatter and--agentsJSON runs custom and plugin subagents without user, project and local CLAUDE.md files; managed policy files still load (v2.1.271). See Subagents.- Subagent output is fenced off twice over. In auto mode a subagent reports back through a dedicated hand-back call that the safety classifier reviews (v2.1.271), and subagent results reach the main agent under a header marking them as subagent output, indented, “so text in a subagent’s result cannot pass as the session’s own instructions” (v2.1.277).
- Monitor watches always have a deadline — at most 30 minutes, 10 in single-prompt
-pruns — and notify Claude to re-arm, replacing the no-timeoutpersistentoption (v2.1.271). See Monitor Tool. - The TaskOutput tool is gone (v2.1.277): Claude reads a background task’s output file with Read, and
taskOutputMaxCharsandTASK_MAX_OUTPUT_LENGTHno longer have any effect. - Fable always appears in
/modelon the Anthropic API, greyed out only when organization settings disable it (v2.1.277). - The context meter had counted advisor-tool turns at about twice their real size, so auto-compact fired at about half the real window — fixed (v2.1.273). See Advisor Tool.
Release table
| Version | Date (UTC) | Shape |
|---|---|---|
| v2.1.271 | 2026-09-14 | omitClaudeMd, subagent hand-back, Monitor deadlines, fast mode in Remote sessions |
| v2.1.272 | 2026-09-15 | ”Bug fixes and reliability improvements” only |
| v2.1.273 | 2026-09-15 | Gateway hint headers, advisor context-meter fix, local classifier on 3P (reversed in 278) |
| v2.1.274 | 2026-09-17 | MCP v2 client default on 3P, CLAUDE_CODE_MCP_STARTUP_WAIT_MS, tool_use_id loop self-heal |
| v2.1.275 | 2026-09-17 | claude.ai skills/plugins sync, send-now key, npm plugins without install scripts |
| v2.1.276 | 2026-09-18 | Single fix: advisor_20260301 400 behind proxies (2.1.275 regression) |
| v2.1.277 | 2026-09-18 | AGENTS.md, TaskOutput removed, subagent-output header, Fable always listed |
| v2.1.278 | 2026-09-19 | Server-side auto-mode classifier by default; /status row |
Models and defaults
- Fable always listed in
/modelon the Anthropic API (v2.1.277). - Server-side auto-mode classifier default (v2.1.278); v2.1.273 had briefly done the opposite on Bedrock/Vertex/Foundry.
- Fast mode in Claude Code Remote sessions (cloud and self-hosted runners), where the organization allows it (v2.1.271).
modelPricingand the gatewaypricingblock accept amultiplierabove 1, up to 10, for internal chargeback markups (v2.1.271).- Subagents with
model: "opus"on Bedrock, Vertex or Foundry no longer leave the session’s model when the ID has no recognizable family (v2.1.274). --resumeno longer drops[1m]when the resumed session’s model family differs from the default (v2.1.271).- Advisor-tool turns counted at about 2x in the context meter — fixed (v2.1.273).
- The background Haiku auto-title request is removed from
claude -pruns launched outside an SDK or IDE (v2.1.277). - Dynamic workflows default to small on Pro plans, and the medium size guideline dropped from 15 to 10 agents (v2.1.271). See Dynamic Workflows.
New commands and features
- AGENTS.md support (v2.1.277).
- claude.ai skills and plugins sync (v2.1.275); sign-in with a Claude account also requests access to claude.ai plugins (v2.1.273); the new
ListPluginstool lists plugins enabled on the claude.ai account (v2.1.275). - Send-now key (ctrl+enter, or ctrl+x ctrl+s) interrupts the current turn and sends all queued messages at once; sent and queued messages show in gray until the model receives them (v2.1.275). The code.claude.com changelog snapshot of 2026-09-18 lists the key under v2.1.277 as well; the v2.1.277 GitHub notes do not.
/plugin install --marketplaceoffers to add the marketplace before installing (v2.1.275).- Fork a Remote Control session started with
claude --remote-controlor/remote-controlfrom the Claude app; the fork runs as a background session on your computer (v2.1.273). See Channels. - Mouse support in the fullscreen
/configpanel (v2.1.271); click-to-expand collapsed teammate and agent messages in fullscreen (v2.1.274); a critical memory-usage warning (v2.1.274). /mobileshows one QR code for claude.ai/mobile (v2.1.271).- Artifacts: Markdown files publish as styled document pages and a session can watch up to 10 artifacts, up from 5 (v2.1.271); artifact database updates can remove a single field (v2.1.273); the Artifact tool asks for a one-word tab icon instead of an emoji favicon (v2.1.275). See Artifacts.
claude mcp servesends a progress update every 30 seconds during a running tool call (v2.1.271).- Invisible Unicode formatting and tag characters are stripped from prompts, and the cleaned prompt is shown for review before it is sent (v2.1.277).
- Dynamic workflows pause at your usage limit and continue when it resets, instead of dropping agents (v2.1.271).
- Claude apps gateway sign-in shows the signed-in account when the gateway names it; you confirm it before the credential is saved, and
/statusshows it (v2.1.275). - VS Code: a Memory dialog where you can view, edit and delete a saved memory, and sending an attached image without typing any text (v2.1.275); a Sign out row in the panel menu (with
/logout), background shells and other running tasks in the agent map, each with a Stop (with/tasks), a Copy response button and/copy, and session cost and token usage in the Account & usage dialog where plan limits don’t apply (Vertex, Bedrock, Foundry, API key) (v2.1.277).
Settings and environment variables
CLAUDE_CODE_GATEWAY_HINT_HEADERS=1opts in tox-claude-code-request-class,-agent-type,-prev-tool-durations,-compactionand-context-compactedrequest headers for LLM gateways (v2.1.273). See Claude Apps Gateway.CLAUDE_CODE_AUTO_MODE_SERVER: introduced as a=1opt-in on Bedrock/Vertex/Foundry (v2.1.273), flipped to default-on with=0to opt out (v2.1.278).CLAUDE_CODE_MCP_STARTUP_WAIT_MSbounds how long the first non-interactive turn waits for connecting MCP servers (0 = don’t wait) (v2.1.274).- OpenTelemetry:
claude_code.managed_settings_resolvedevent withOTEL_LOG_MANAGED_SETTINGS=1(v2.1.274); aneffortattribute on theclaude_code.llm_requesttrace span, matching theapi_requestevent (v2.1.274);OTEL_LOG_TOOL_DETAILS=1adds real agent, skill, plugin and MCP names to cost and token metrics (v2.1.273);OTEL_LOG_RAW_API_BODIES=file:gains anindex.jsonl(v2.1.274); startup warning whenotelHeadersHelperfails (v2.1.275). syncClaudeAiSkills,syncClaudeAiPlugins(v2.1.275).- Gateway:
CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1, for gateways whose only egress is a forward proxy — every outbound request hands the proxy the hostname instead of resolving it locally — and an optional upstreamheaders:map that sends static headers to a proxy you run in front of a provider (v2.1.277);CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS(in-flight requests finish for up to 25 seconds on SIGTERM) andstore.connect_timeout_seconds(v2.1.274);enduser.sub, the IdP subject, added to the telemetry Claude Desktop and Cowork send through a gateway, and a warning when a replica has more requests open than the 256 it sends upstream at once, with a startup log line showing that limit (v2.1.274). claude self-hosted-runner --drain-marker-fileand--host-config-snapshot disk|memory(v2.1.271).taskOutputMaxCharsandTASK_MAX_OUTPUT_LENGTHno longer have any effect (v2.1.277);taskOutputMaxCharshad been added only in v2.1.261 (Week 36).- Managed
allowManagedMcpServersOnly,deniedMcpServersanddisableClaudeAiConnectorsset via MDM ormanaged-settings.jsonare honoured when server-managed settings are also present (v2.1.273); an unreadable enterprisemanaged-mcp.jsonkeeps exclusive MCP control and warns (v2.1.271). - MCP v2 client and 2026-07-28 protocol negotiation are the default on Bedrock, Vertex, Foundry and telemetry-disabled installs, “as other installs already do”; opt out with
MCP_SDK_GENERATION=v1orMCP_PROTOCOL_NEGOTIATION=legacy(v2.1.274). See MCP 2026-07-28 Spec.
Hooks, MCP, plugins, skills and subagents
omitClaudeMd(v2.1.271).- Subagent hand-back call reviewed by the classifier in auto mode (v2.1.271); subagent-output header (v2.1.277).
- Monitor deadlines replace
persistent(v2.1.271); a script’s final output and its exit arrive as one notification, saving a model turn (v2.1.274). - The hook spinner names which SessionStart, UserPromptSubmit, PreToolUse or SessionEnd hook is running, with elapsed time, and Esc cancels a prompt waiting on SessionStart (v2.1.271). See Hooks.
- Stop prompt hooks’ repeat blocks name the condition with a 500-character label instead of re-sending the whole prompt (v2.1.274).
- SubagentStop hooks with a specific matcher no longer fire for subagents with an empty agent type (v2.1.275).
- Hook-driven sessions such as an active
/goalcompact instead of ending with “Prompt is too long”, and an active/goalsurvives--resumeafter compaction (v2.1.274). See Scheduled Tasks. - Auto mode: per-command
allowed_domainsfor Bash, PowerShell and Monitor with sandboxing — the hosts a command needs are reviewed with it and opened for it alone (v2.1.271). - Plugins:
claude plugin install/update --accept-command <sha256>accepts exactly the command a previous--jsonrun displayed, instead of-y(v2.1.271); npm-source plugins fetched withnpm pack --ignore-scriptsand integrity-verified, so install scripts no longer run (v2.1.275); plugin and marketplace clones leave Git LFS files as pointers (v2.1.274); a top-level$schemainhooks/hooks.jsonno longer shows “unknown key” (v2.1.274). See Plugins and Marketplaces. "type": "sdk"MCP entries in.mcp.json, settings, plugins and agent files are skipped with a warning (v2.1.274).- MCP: Streamable HTTP tool calls no longer time out at about 5 minutes despite a longer per-server timeout (v2.1.274); 403
insufficient_scopenames the missing permissions (v2.1.274); a notification pointing at/mcpwhen a server disconnects mid-session and reconnection gives up (v2.1.273); prompts and resources not refreshing when a server sends list-changed notifications without declaringlistChanged(v2.1.274); tool search matches bare MCP tool names (v2.1.271);list_changedtight-loop CPU fix (v2.1.271). - Skills synced from claude.ai move to the recoverable trash after sign-out (v2.1.271) or when the organization turns Skills off (v2.1.273).
/update-configwritesEdit(path)rules instead ofWrite(path)rules, which file permission checks don’t match (v2.1.275).
Breaking and behaviour changes
- TaskOutput tool removed (v2.1.277).
- Monitor
persistentoption replaced by deadline-and-re-arm (v2.1.271). - Local-session artifact watching: a new version published elsewhere no longer starts a turn; Claude learns of it from a later Artifact tool result (v2.1.274).
/code-reviewuses leaner inline review prompts for models without tuned settings instead of spawning many review subagents (v2.1.274)./statusreads “Cloud sessions”, and messaging says “cloud session” instead of “Claude Code on the web” (v2.1.274).- Scheduled and Run-now routine runs save data to, and republish, artifacts you can edit without asking; public artifacts, first publishes and deletes still ask (v2.1.275).
- A
sandbox.excludedCommandsglob must match every part of a compound command (v2.1.277). - v2.1.273 reverted the v2.1.268 change that applied Read and Edit deny rules to Bash lines the checker can’t analyze (
eval,env -C); such commands prompt again instead of being denied.
Notable fixes
- Sessions stuck endlessly retrying “unexpected tool_use_id” 400 errors: transcripts now self-heal where possible (v2.1.274).
- Being logged out when an older Claude Code build, such as an IDE extension’s bundled CLI, runs on the same machine (v2.1.277).
claude -pand Agent SDK sessions hanging with no result after an internal error now exit with code 1 (v2.1.277). See Agent SDK.- Messages typed while Claude works sometimes ignored by the model (v2.1.277).
- Sandboxed Bash on Linux reporting exit 0 for failed commands under zsh (v2.1.275).
/rewindin a forked or background session restoring zero-filled files (v2.1.275).- Security (v2.1.271): a cached organization policy reused after switching accounts, organizations or API keys; org policy fetched through, and rejected by, third-party local proxies set via
ANTHROPIC_UNIX_SOCKET; cloud sessions rejecting every subagent tool call (“failed schema validation”) after the worker restarted. - Bash permission checks (v2.1.271): missing the file
fmt,columnand similar commands read when it follows an unrecognized option; skipping files a wildcard expands to in a pattern or option value (grep -v dir/* file); shell variable declaration flags misrepresenting the command. /tuirefusing to restart because of a finished agent-team teammate (v2.1.273), see Agent Teams; saved scheduled tasks running in the wrong session after.claude/scheduled_tasks.jsonwas copied into another folder such as a new worktree (v2.1.273).--forward-subagent-textstream-json and SDK output dropping the messages of subagents spawned by acontext: forkskill; fullscreen freezing or blanking when scrolling past a large file diff; a stray</ccmemory>closing tag in responses (v2.1.275).- v2.1.276: every request failing with
400 … Input tag 'advisor_20260301'whenANTHROPIC_BASE_URLpoints at a proxy or gateway (2.1.275 regression).
Try It
- Repos shared with other coding agents such as Codex CLI:^[inferred] keep one AGENTS.md; Claude Code now reads it when no CLAUDE.md exists.
- After v2.1.275, check
/skillsin a terminal signed in with your claude.ai account: skills enabled on claude.ai should now appear there too. - Auto mode with sandboxing: give Bash commands that need one host a per-command
allowed_domainsentry instead of widening the global network rules. - Check
/statusfor the “Auto mode server” row to confirm whether your classifier runs server-side. - Scripts that used Monitor
persistent: trueneed a re-arm loop; watches now end within 30 minutes. - Scripts that called TaskOutput should read the background task’s output file instead.
- Reviewer or linter subagents that don’t need project context: add
omitClaudeMd: trueto their frontmatter to save tokens. - If you don’t want claude.ai skills in the terminal, set
syncClaudeAiSkills: false. - Air-gapped or proxy-only deployments: confirm the server-side classifier’s calls get through your proxy before upgrading to v2.1.278; if they don’t, set
CLAUDE_CODE_AUTO_MODE_SERVER=0. - Watch for the billed-fallback warning in the first sessions after upgrading, especially on Bedrock, Vertex and Foundry.
Open Questions
- v2.1.272 is unitemized (“Bug fixes and reliability improvements”).
- Why did v2.1.273 set third-party providers to the local classifier “for now”, only for v2.1.278 to reverse it four days later? No rationale is given. The linked page (
code.claude.com/docs/en/auto-mode-classifier-billing) was not fetched. - What triggers a billed fallback? v2.1.278 says Claude Code warns on one, but neither the release note nor the changelog entry names the conditions.
- When will AGENTS.md support reach Bedrock, Vertex and Foundry? The note says “not yet”. Partly answered 2026-09-29: Bedrock from v2.1.281 per the memory docs; Vertex and Foundry still unconfirmed.
- How does AGENTS.md interact with a CLAUDE.md that imports it? The note covers only the no-CLAUDE.md case. Answered 2026-09-29 (memory docs): Claude reads the CLAUDE.md and gets AGENTS.md through the import, never twice.
- Does AGENTS.md follow CLAUDE.md’s hierarchy (user, project and subdirectory files), or is only a project-root AGENTS.md read? Not stated. Answered 2026-09-29 (memory docs): it follows the hierarchy. Every
AGENTS.mdand.claude/AGENTS.mdin the working directory and above loads at start, and a subdirectory’s loads on demand. - Does
omitClaudeMdalso skip AGENTS.md when a project uses it in place of CLAUDE.md? Not stated. Partly answered 2026-09-29: the memory docs say subagents that “skip project instructions” skip AGENTS.md too, without namingomitClaudeMd. See AGENTS.md. - Does fast mode in Remote sessions give the same speed-up as in local sessions? v2.1.271 says only that the host’s setting or
/fastapplies where the organization allows it.
Related
- What’s New — Week 37 — the preceding digest (
claude plugin eval). - What’s New — Week 39 — the following digest (Claude Opus 5.5).
- Auto Mode — server-side classifier default.
- Monitor Tool — deadline-and-re-arm behaviour.
- Subagents —
omitClaudeMd, hand-back call, output header. - CLAUDE.md Primer — AGENTS.md fallback.
- Agent Skills — claude.ai skill sync.
- CLI Reference — flags and settings named here.