Everything Anthropic has published that we can see: blog posts, release notes, changelog entries, incidents and deprecations. Their words, linked back to them, newest first.
1.4.0 (2026-09-04)
Full Changelog: v1.3.0...v1.4.0
Features
api: add Claude Tag category and user breakdowns to usage reports ( 9fce1e4 )
api: add named types for organization compliance settings state ( 1de1957 )
api: add support for sending a workspace ID on more endpoints ( d1d2c01 )
Bug Fixes
client: raise a clear error when an httpx object is passed instead of an httpx2 one ( 9447099 )
repair custom-code merge in messages resources ( #580 ) ( 85454ca )
Chores
examples: refresh platform model IDs ( #499 ) ( 182abb5 )
internal: bundle the mock server spec and update dev tooling ( f9b0cf2…
Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through
Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters
Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line
Added /skill-doctor to show which loaded skills go unused and what they cost in context, so you…
What's changed
Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through
Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters
Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line
Added /skill-doctor to show which loaded skills go unused and what they cost in…
Now tracking this page; changes will appear here as they happen. Latest announcements: 2026-06-05: Claude Opus 4.1 model; 2026-04-14: Claude Sonnet 4 and Claude Opus 4 models; 2026-02-19: Claude Haiku 3 model; 2025-12-19: Claude Haiku 3.5 model; 2025-10-28: Claude Sonnet 3.7 model; 2025-08-13: Claude Sonnet 3.5 models
What's changed
Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff
Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field
Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists
Added a text form of /advisor ( /advisor , /advisor <model> , /advisor off ) for the desktop app, Remote Control, and other headless ( -p /Agent SDK) sessions
Added…
Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff
Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field
Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists
Added a text form of /advisor (/advisor, /advisor , /advisor off) for the desktop app, Remote Control, and other headless (-p/Agent SDK) sessions
Added oidc.scope_on_refresh to the…
Sep 3 , 16:23 UTC
Resolved - The issue affecting Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 has been resolved. Impact has ended as of 9:16 PT / 16:16 UTC.
Sep 3 , 16:06 UTC
Monitoring - A fix has been deployed for Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and we are monitoring for recovery.
Sep 3 , 15:25 UTC
Update - The only affected models right now are Opus 4.8 and Opus 5. The rest of the models have recovered to baseline error rate.
Sep 3 , 14:49 UTC
Update - We are continuing to work on a fix for this issue.
Sep 3 , 13:50 UTC
Update - An exhaustive list of…
Sep 3 , 12:56 UTC
Resolved - This incident has been resolved.
Sep 3 , 12:47 UTC
Monitoring - A fix has been implemented and we are monitoring the results.
Sep 3 , 12:37 UTC
Investigating - We are investigating elevated errors on requests to Claude Sonnet 5. We will provide an update as soon as possible.
Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json); entries that name a command to run are skipped
Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding
Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge
Added --json to claude plugin validate for a machine-readable…
What's changed
Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json ); entries that name a command to run are skipped
Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding
Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge
Added --json to claude plugin validate for a…
Sep 2 , 21:44 UTC
Resolved - The issue affecting Claude Sonnet 5 has been resolved. Impact occurred from 2:05pm PT / 21:05 UTC to 2:19pm PT / 21:19 UTC.
Sep 2 , 21:17 UTC
Investigating - We are investigating elevated errors on requests to Claude Sonnet 5. We will provide an update as soon as possible.
Sep 2 , 01:24 UTC
Resolved - This issue has been resolved.
Sep 1 , 23:26 UTC
Monitoring - We have identified and resolved an issue where users who reached a balance of zero usage credits saw delays in the availability of newly purchased credits, resulting in some requests to the Claude API receiving 'credit balance is too low' errors erroneously. This affected credits purchased from 05:10am PT / 12:10 UTC to 2:35pm PT / 21:35 UTC. At this time, newly purchased credits should be available as expected and we are working to resolve any remaining impact.
Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255
Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied
What's changed
Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255
Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied
Sep 1 , 18:07 UTC
Resolved - This issue has been resolved.
Sep 1 , 17:52 UTC
Monitoring - We are seeing success rates recover across affected services. Core inference and the API are not impacted.
Sep 1 , 17:05 UTC
Investigating - We are investigating reports of degraded performance affecting some Claude services, including docs.claude.com. We are working to resolve these issues and will provide an update as soon as possible.
What's changed
Added Claude Fable 5.1 ( claude-fable-5-1 ), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads
Added "Time format" ( timeFormat ) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps
Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected
Added CLAUDE_CODE_SUBAGENT_MODEL_FORCE to apply CLAUDE_CODE_SUBAGENT_MODEL (or the main…
Added Claude Fable 5.1 (claude-fable-5-1), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads
Added "Time format" (timeFormat) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps
Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected
Added CLAUDE_CODE_SUBAGENT_MODEL_FORCE to apply CLAUDE_CODE_SUBAGENT_MODEL (or the main model) to every…
Sep 1 , 16:22 UTC
Resolved - This issue has been resolved.
Sep 1 , 16:02 UTC
Investigating - We are investigating elevated errors affecting Claude for Microsoft Office 365. We will provide an update as soon as possible.
Aug 31 , 20:36 UTC
Resolved - The issue affecting Claude Code has been resolved. Impact occurred from 16∶55 to 19∶16 UTC.
Aug 31 , 19:21 UTC
Investigating - We are investigating reports of degraded performance affecting Claude in Slack, Claude Code on the web, and Code Review. We will provide an update as soon as possible.
Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs
Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet
Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded
Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit
What's changed
Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs
Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet
Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded
Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit
Aug 31 , 17:52 UTC
Resolved - This issue has been resolved.
Aug 31 , 17:32 UTC
Monitoring - We have seen success rates return to normal for requests on Claude.ai and are monitoring closely.
Aug 31 , 17:23 UTC
Investigating - We are investigating reports of elevated errors affecting chats on claude.ai. We will provide an update as soon as possible.
On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems. We are conducting an in-depth analysis of both incidents, and planning to work with METR for an independent review. In the meantime, we’re sharing some of the changes we’ve made over the past month.
Aug 28 , 20:21 UTC
Resolved - The issue affecting Claude Cowork and Claude Code on the web has been resolved.
Aug 28 , 18:21 UTC
Monitoring - A mitigation has been applied for the issue affecting Claude Cowork and Claude Code on the web, and we are monitoring for recovery. Sessions that disconnected earlier can be retried
Aug 28 , 17:22 UTC
Identified - We have identified an issue with an upstream cloud provider affecting Claude Cowork and Claude Code on the web. Some sessions may fail to start or disconnect mid-task; affected sessions can be retried. We are in contact with the provider and…
Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost
Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)
Added a Spend limit bar to /usage and a rate_limits.spend_limit status line field for developers behind a Claude apps gateway with spend limits
Added a per-session prompt-cache line to /cost (hit ratio, misses, tokens re-cached, warm/cold) and a matching…
What's changed
Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost
Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)
Added a Spend limit bar to /usage and a rate_limits.spend_limit status line field for developers behind a Claude apps gateway with spend limits
Added a per-session prompt-cache line to /cost (hit ratio, misses, tokens re-cached, warm/cold)…
What's changed
Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ), keeps file tools inside the working directory, refuses bypassPermissions , and ignores user, project and local settings files
Added experimental.cacheTtl ( "5m" or "1h" ) to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured
Added claude self-hosted-runner --client-label <label> (or SELF_HOSTED_RUNNER_CLIENT_LABEL ) to override the label the runner registers with (default: hostname)
Added…
Added --restricted (or CLAUDE_CODE_RESTRICTED=1): removes the built-in tools that run commands or code and WebFetch (unless named in --tools), keeps file tools inside the working directory, refuses bypassPermissions, and ignores user, project and local settings files
Added experimental.cacheTtl ("5m" or "1h") to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured
Added claude self-hosted-runner --client-label (or SELF_HOSTED_RUNNER_CLIENT_LABEL) to override the label the runner registers with (default: hostname)
Added server-managed settings…
1.2.0 (2026-08-27)
Full Changelog: v1.1.0...v1.2.0
Features
api: beta files/skills namespaces use GA shapes; drop dated beta header pins ( 9df4565 )
Bug Fixes
aws,bedrock: sign raw request bytes so binary file uploads work ( #531 ) ( f50e910 )
ci: resolve assignment aliases in detect-breaking-changes ( f2c4925 )
sessions: make event accumulator forward-compatible with new event types ( #533 ) ( cbbaf6e )
tools: let read return a view_range of a file over the size cap ( #538 ) ( b68e876 )
tools: preserve exact file bytes in the agent toolset and memory tool (no newline translation) ( #540 ) (…
We’re opening a research preview of the Model Hardware Standard (MHS), a shared specification for AI agents to safely operate physical devices, to a first group of scientific research labs and advanced manufacturers.
Starting today, 10,000 scientists around the world can get Claude at no cost to start. Verified principal investigators qualify for a Claude Team subscription plan and then add their research team to Standard seats for free, or Premium seats for $15 per month, for up to a year.
Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting)
Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones
Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost levers (caching…
What's changed
Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting)
Added {id, text, cooldownSessions, priority} entries, tipsFile , and label to spinnerTipsOverride , so organizations can rotate their own tips alongside the built-in ones
Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost…
Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main)), since they also match options inserted before the subcommand
Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules
Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM
Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress
Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string)…
What's changed
Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main) ), since they also match options inserted before the subcommand
Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules
Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM
Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress
Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a…
Aug 24 , 20:26 UTC
Resolved - This issue has been resolved.
Aug 24 , 20:11 UTC
Monitoring - We have identified and resolved an issue which resulted in errors when attempting to access Claude.ai, including logging in via subscriptions for Claude Code. Errors occurred between 1:00pm (20:00 UTC) through 1:08pm PT (20:08 UTC). We are monitoring closely to ensure no further issues.
Aug 24 , 17:16 UTC
Resolved - This issue has been resolved.
Aug 24 , 17:12 UTC
Investigating - From 9:02–9:08am PT / 16:02–16:08 UTC) users experienced issues when logging into Claude.ai, including for connecting Claude Code with subscription. At this time, this issue has been resolved, but we are continuing to investigate a potential issue impacting users of the Claude.ai desktop application.
Aug 24 , 08:30 UTC
Resolved - This issue has been resolved. From 9:50pm PT / 04:50 UTC through 00:36am PT / 07:36 UTC, users saw elevated errors on requests to Claude models, including Claude Opus 5 and Fable 5.
Aug 24 , 07:47 UTC
Update - At this time, we have seen errors stabilize on Opus 5 and Fable 5, and are working to fully resolve success rates on all affected models. We will provide an update as soon as possible.
Aug 24 , 06:42 UTC
Update - We are continuing to work to resolve issues causing elevated requests on multiple models. We will provide an update as soon as possible.
Aug 24…
1.0.0 (2026-08-20)
Full Changelog: v0.125.0...v1.0.0
⚠ BREAKING CHANGES
client: upgrade to httpx2 and some minor breaking changes. See MIGRATION.md for details
Features
client: upgrade to httpx2 and some minor breaking changes. See MIGRATION.md for details ( 33e2967 )
Bug Fixes
beta: stop warning about output_format= on the parse/stream/tool_runner helpers ( 59bf261 )
Chores
streaming: restore the original event imports in lib/streaming/_types.py ( 87e9e01 )
Documentation
examples: use adaptive thinking in thinking examples ( b5870af )
Aug 20 , 19:42 UTC
Resolved - This issue has been resolved.
Aug 20 , 19:16 UTC
Investigating - We are investigating elevated errors on requests to some Claude models. We will provide additional updates as soon as possible.
Aug 20 , 19:01 UTC
Resolved - This issue has been resolved.
Aug 20 , 18:32 UTC
Investigating - We are investigating elevated errors affecting Google connectors (Sheets, Docs, Slides, and Chat) and custom Google integrations on Claude.ai. Core functionality is not affected. We will provide an update as soon as possible.
0.124.0 (2026-08-19)
Full Changelog: v0.123.0...v0.124.0
Features
api: Files and Skills APIs are now GA; add computer use and browser use toolsets ( 9a09e84 )
0.123.0 (2026-08-18)
Full Changelog: v0.122.0...v0.123.0
Features
api: additions to files and memory stores ( 09ce187 )
api: updates to skill, files, and user profiles ( c6cbffd )
client: add helpers for accessing the workspace ID in response headers ( f79882b )
Bug Fixes
api: remove unsupported mid_conv_system content block ( 6f15b8d )
client: compute platform headers without spawning a subprocess ( baca9f4 )
client: export custom status errors from _exceptions. all ( #459 ) ( 2950ec4 )
client: export ServiceUnavailableError and DeadlineExceededError from the package root ( #468 ) ( 0dcd06d…
Aug 19 , 11:02 UTC
Resolved - This incident has been resolved.
Aug 19 , 10:33 UTC
Monitoring - A fix has been implemented and we are monitoring the results.
Aug 19 , 09:42 UTC
Identified - We have identified the cause of elevated errors on requests to Claude Opus 5 and Claude Haiku 4.5 and are working on a fix. We will provide an update as soon as possible.
Aug 18 , 19:01 UTC
Resolved - The issue affecting Claude Opus 5 has been resolved. Impact occurred from 16:11 to 18:23 UTC.
Aug 18 , 18:26 UTC
Monitoring - A fix has been implemented and we are monitoring the results.
Aug 18 , 17:12 UTC
Update - We are investigating elevated errors on requests to Claude Opus 5. We will provide an update as soon as possible.
Aug 18 , 16:20 UTC
Update - We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, and other Claude models. We will provide an update as soon as possible.
Aug…
Aug 17 , 15:29 UTC
Resolved - This incident has been resolved.
Aug 17 , 14:39 UTC
Monitoring - A fix has been implemented and we are monitoring the results.
Aug 17 , 14:25 UTC
Update - Claude Opus 5 is operational. Claude Sonnet 5 is degraded. We are investigating.
Aug 17 , 13:56 UTC
Investigating - We are investigating elevated errors on requests to Claude Opus 5. We will provide an update as soon as possible.
Aug 16 , 22:34 UTC
Resolved - The issue affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork has been resolved.
Aug 16 , 22:22 UTC
Monitoring - A fix has been deployed for the issue affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork and we are monitoring for recovery.
Aug 16 , 22:02 UTC
Update - We are investigating reports of degraded performance affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork. We will provide an update as soon as possible.
Aug 16 , 21:58 UTC
Investigating - We…
Aug 15 , 00:27 UTC
Resolved - The issue affecting Claude services has been resolved. Impact occurred from 20:00 Aug 14, 2026 to 00:11 Aug 15 , 2026 UTC.
Aug 15 , 00:21 UTC
Update - We have identified the cause of the issue affecting Claude services and are working on a fix. We will provide an update as soon as possible.
Aug 15 , 00:20 UTC
Update - We have identified the cause of the issue affecting claude.ai and are working on a fix. We will provide an update as soon as possible.
Aug 14 , 23:57 UTC
Identified - We have identified the cause of elevated errors on requests to Claude Fable 5 and…
Aug 14 , 21:58 UTC
Resolved - The issue affecting the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 20:14 to 20:38 UTC.
Aug 14 , 20:44 UTC
Monitoring - A fix has been deployed for the issue affecting the Claude API, Claude Code, and Claude Cowork and we are monitoring for recovery.
Aug 14 , 20:44 UTC
Identified - We have identified the cause of the issue affecting the Claude API, Claude Code, and Claude Cowork and are working on a fix. We will provide an update as soon as possible.
Aug 14 , 20:30 UTC
Investigating - We are investigating reports of degraded…
In this article, we share answers to some of the questions we’ve received about how our chosen watermarking method works, whether it affects Claude’s outputs, and why we’re making this change.
Aug 14 , 10:53 UTC
Resolved - The issue resulting in users being unable to reach status.claude.com has been resolved.
Aug 14 , 07:58 UTC
Investigating - We are aware of issues with reaching status.claude.com, specifically regarding an invalid certificate issues. We are working to resolve these issues as soon as possible.
Aug 14 , 00:51 UTC
Resolved - The issue affecting Claude services has been resolved. Impact occurred from 23:42 to 00:50 UTC.
Aug 14 , 00:36 UTC
Investigating - We are investigating degraded performance in Claude Code on the Web sessions and related products (Cowork Remote, Routines, Claude Code Mobile)
Released and preview models from Anthropic's own docs. A dash means they haven't published that number.
Anthropic prices run from $1.00 to $10.00 per million input tokens across 8 models. The Anthropic price page works out what your own usage would cost on each one.
Something broken? Is Claude down shows what Anthropic's status page has posted and when.
Where this comes from
We read Anthropic's own feeds every fifteen minutes and store what's new. Nothing here is rewritten, and nothing comes from a rumour account or a reposted screenshot.