An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.251/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.251/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.251/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.248/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.248/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.246/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.242/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.239/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.236/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.234/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.232/model |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming /model after this was published.
the line in the docs`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. `applyFlagSetti… |
|
v2.1.206tengu_umber_kestrel |
Flag reading movedThe flag server now returns on for tengu_umber_kestrel, read as this account. | |
v2.1.239tengu_toasty_breeze |
Flag reading movedThe flag server now returns {"allowanceNote":"{percent} allowance left","budgetExhaustedCopy":"You've used this week's lower-priority allowance","cooloffMinutes":10,"enabled":true,"label":"Continue now at lower priority","noticeLine":"/low-priority to continue now at lower priority · uses your weekly limit","statusLine":"Lower priority until {reset}","version":3,"waitBanner":"Working at lower priority · waiting for capacity"} for tengu_toasty_breeze, read as this account. | |
v2.1.239tengu_toasty_breeze |
Flag reading movedThe flag server now returns {"allowanceNote":"{percent} allowance left","budgetExhaustedCopy":"You've used this week's lower-priority allowance","cooloffMinutes":10,"enabled":true,"label":"Continue now at lower priority","noticeLine":"/low-priority to continue now at lower priority · uses your weekly limit","statusLine":"Lower priority until {reset}","version":3,"waitBanner":"Working at lower priority · waiting for capacity"} for tengu_toasty_breeze, read as this account. | |
v2.1.248tengu_nifty_lemur |
Flag reading movedThe flag server now returns {"autoContinue":true,"enabled":true,"label":"Reset your session limit now","noticeLine":"/limit-reset to reset your session limit now · uses weekly limit · 1/week","spentLine":"Weekly reset used · available again {date}","successLine":"Session limit reset · next reset available {date} · your weekly limit still applies","unavailableLine":"Couldn't reset your session limit right now · try again in a moment","version":1} for tengu_nifty_lemur, read as this account. | |
v2.1.248tengu_nifty_lemur |
Flag reading movedThe flag server now returns {"autoContinue":true,"enabled":true,"label":"Reset your session limit now","noticeLine":"/limit-reset to reset your session limit now · uses weekly limit · 1/week","spentLine":"Weekly reset used · available again {date}","successLine":"Session limit reset · next reset available {date} · your weekly limit still applies","unavailableLine":"Couldn't reset your session limit right now · try again in a moment","version":1} for tengu_nifty_lemur, read as this account. | |
v2.1.251tengu_juniper_relay |
Flag reading movedThe flag server now returns on for tengu_juniper_relay, read as this account. | |
v2.1.223tengu_juniper_relay |
Flag reading movedThe flag server now returns on for tengu_juniper_relay, read as this account. | |
v2.1.229copy |
Documentation arrivedA small documentation edit on User identity and local data touched a line naming copy after this was published.
the line in the docs| `vm_bundles/` | Cached copy of the VM workspace bundle that Cowork sessions run in, plus the data disk the app creates to hold those sessions' home directories inside the VM. | |
|
v2.1.229link |
Documentation arrivedAnthropic's documentation has since written up link, on Triage requests.
the line in the docsAnswer requests in this channel from the team's triage runbook: <link to the runbook doc>. Read it before answering. If a request isn't covered there, mention <your on-call person's handle> so they can pick it up. |
|
v2.1.265wrap |
Documentation arrivedAnthropic's documentation has since written up wrap, on Triage requests.
the line in the docs```text wrap theme={null} |
|
v2.1.257auth |
Documentation arrivedA small documentation edit on Monitoring touched a line naming auth after this was published.
the line in the docs* When authenticated via OAuth, `user.email` is included in telemetry attributes, sent only to the OTel endpoint you configure, never to Anthropic. If this is a concern for your organization, work with your telemetry backend to filter or r… |
|
v2.1.259proactivity |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming proactivity after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.259list |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming list after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.265scope |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming scope after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.257scope |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming scope after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.251attach |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming attach after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.248restricted |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming restricted after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.248low |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming low after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.238status |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming status after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.238status |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming status after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.229/pr |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming /pr after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.229domain |
Documentation arrivedA small documentation edit on Customize Claude Tag touched a line naming domain after this was published.
the line in the docsThe Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… |
|
v2.1.242merge |
Documentation arrivedAnthropic's documentation has since written up merge, on Give Claude access to your tools.
the line in the docs**Security Guidance** is off by default. Add it directly on a scope, or turn it on in a bundle's **Plugins** tab, and new threads in covered channels pick it up. The plugin flags problems and suggests fixes; it doesn't block a commit or a … |
|
v2.1.232default |
Documentation arrivedAnthropic's documentation has since written up default, on Give Claude access to your tools.
the line in the docs**Security Guidance** is off by default. Add it directly on a scope, or turn it on in a bundle's **Plugins** tab, and new threads in covered channels pick it up. The plugin flags problems and suggests fixes; it doesn't block a commit or a … |
|
v2.1.232default |
Documentation arrivedAnthropic's documentation has since written up default, on Give Claude access to your tools.
the line in the docs**Security Guidance** is off by default. Add it directly on a scope, or turn it on in a bundle's **Plugins** tab, and new threads in covered channels pick it up. The plugin flags problems and suggests fixes; it doesn't block a commit or a … |
|
v2.1.246files |
Documentation arrivedAnthropic's documentation has since written up files, on Give Claude access to your tools.
the line in the docsAnthropic's **Security Guidance** [plugin](https://code.claude.com/docs/en/plugins) has Claude review the code it writes. With the plugin on in a channel, Claude is warned about risky patterns as it edits files, and the plugin reviews the … |
|
v2.1.265Code |
Documentation arrivedAnthropic's documentation has since written up Code, on Give Claude access to your tools.
the line in the docs### Code review with the Security Guidance plugin |
|
v2.1.248restricted |
Documentation arrivedAnthropic's documentation has since written up restricted, on Give Claude access to your tools.
the line in the docsA Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan… |
|
v2.1.257auto |
Documentation arrivedAnthropic's documentation has since written up auto, on Give Claude access to your tools.
the line in the docsA Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan… |
|
v2.1.251auto |
Documentation arrivedAnthropic's documentation has since written up auto, on Give Claude access to your tools.
the line in the docsA Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan… |
|
v2.1.248auto |
Documentation arrivedAnthropic's documentation has since written up auto, on Give Claude access to your tools.
the line in the docsA Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan… |
|
v2.1.265scope |
Documentation arrivedAnthropic's documentation has since written up scope, on Give Claude access to your tools.
the line in the docsA connection grants access; a plugin teaches Claude how to use it well. A plugin is a packaged set of skills: reusable instructions for working with a specific tool or following a specific process. Attach a plugin to the same Access bundle… |
|
v2.1.257scope |
Documentation arrivedAnthropic's documentation has since written up scope, on Give Claude access to your tools.
the line in the docsA connection grants access; a plugin teaches Claude how to use it well. A plugin is a packaged set of skills: reusable instructions for working with a specific tool or following a specific process. Attach a plugin to the same Access bundle… |
|
v2.1.251attach |
Documentation arrivedAnthropic's documentation has since written up attach, on Give Claude access to your tools.
the line in the docsA Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan… |
|
v2.1.248low |
Documentation arrivedAnthropic's documentation has since written up low, on Give Claude access to your tools.
the line in the docsA connection grants access; a plugin teaches Claude how to use it well. A plugin is a packaged set of skills: reusable instructions for working with a specific tool or following a specific process. Attach a plugin to the same Access bundle… |
|
v2.1.246files |
Documentation arrivedA small documentation edit on Changelog touched a line naming files after this was published.
the line in the docsA Windows update released September 8, 2026 (including KB5124008) stops Cowork from reaching your files when it runs on your Windows PC, so tasks fail or the workspace does not start. This affects Cowork on third-party inference deployment… |
|
v2.1.242cloud |
Documentation arrivedA small documentation edit on Changelog touched a line naming cloud after this was published.
the line in the docsA Windows update released September 8, 2026 (including KB5124008) stops Cowork from reaching your files when it runs on your Windows PC, so tasks fail or the workspace does not start. This affects Cowork on third-party inference deployment… |
|
v2.1.242cloud |
Documentation arrivedA small documentation edit on Changelog touched a line naming cloud after this was published.
the line in the docsA Windows update released September 8, 2026 (including KB5124008) stops Cowork from reaching your files when it runs on your Windows PC, so tasks fail or the workspace does not start. This affects Cowork on third-party inference deployment… |
|
v2.1.242cloud |
Documentation arrivedA small documentation edit on Changelog touched a line naming cloud after this was published.
the line in the docsA Windows update released September 8, 2026 (including KB5124008) stops Cowork from reaching your files when it runs on your Windows PC, so tasks fail or the workspace does not start. This affects Cowork on third-party inference deployment… |