Follow Discord
Sweep 30 Oct 2026 · 21:36Z Build v2.1.315 533 read Stable v2.1.308 Latest v2.1.314 Next v2.1.315 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One capture · claude-code

One read of Claude Code CLIclaude-code-20261028T170702Z

4 pages moved out of 228 read.

Pages moved 4 significant first
Pages read 228 in this capture
Captured 17:07 UTC
Corpus hash aea3d9f5787d corpus-hash

What this read moved

1-4 of 4

claude-apps-gateway-config Changed · +5 / -3 lines

from line 417
417417 
418418```yaml theme={null}
419419models:
420 - id: claude-opus-restricted # a custom id, not a built-in model name
420 - id: restricted-claude-opus-4-8 # a custom id, not a built-in model name
421421 upstream_model:
422422 bedrock-isolated: us.anthropic.claude-opus-4-8 # the only upstream that serves it
423423```
from line 871
871871 policies:
872872 - match: { groups: [restricted-projects] }
873873 cli:
874 availableModels: [claude-opus-restricted]
874 availableModels: [restricted-claude-opus-4-8]
875875 enforceAvailableModels: true
876 model: claude-opus-restricted
876 model: restricted-claude-opus-4-8
877 env:
878 ANTHROPIC_DEFAULT_OPUS_MODEL: restricted-claude-opus-4-8 # opus and Default resolve to the ID too
877879```
878880 
879881#### Matcher values that stop the gateway at boot

errors Changed · +4 / -4 lines

#### Waiting for API response

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 481
481481 
482482As of v2.1.198, the usual spinner tip is suppressed during retries. Once the error reason is revealed, if the failure is a 529 overload the line below the countdown also names where to check service status: `status.claude.com` on the Anthropic API, or the provider or gateway host named in the message on other configurations.
483483 
484If no data arrives on the response stream for 20 seconds while a request is still pending, the spinner shows `Waiting for API response · will retry in … · check your network` before any retry has started. The request hasn't failed yet: the countdown runs to the point where Claude Code aborts the stalled connection. After the abort, what you see depends on how far the response had got:
484#### Waiting for API response
485485 
486The `Waiting for API response · will retry in … · check your network` banner means that Claude Code has waited at least 20 seconds without receiving any data for a request. The request hasn't failed yet: the countdown runs to the point where Claude Code aborts the stalled connection. If the abort happens:
487 
486488* Before Claude has completed a block of text or a tool call, or started one after finishing its thinking, Claude Code retries the request or ends the turn with an error. [Automatic retries](#automatic-retries) says which stalls it retries and how many times.
487489* After Claude has completed a block of text or a tool call, or started one after finishing its thinking, but before Claude has finished the response, Claude Code keeps what Claude completed, continues the turn from any tool calls Claude finished, and shows [The response above may be incomplete](#the-response-above-may-be-incomplete). In a non-interactive session, and for a subagent's response in any session, Claude Code may first prompt Claude to continue the response; that entry says when it does and when you still see the notice there.
488490* After Claude finished the response, Claude Code ends the turn normally.
489491 
490The banner clears on its own once data resumes or a retry succeeds. If it reappears on every attempt, treat it as a [network issue](#unable-to-connect-to-api). Before v2.1.185, the banner appeared after 10 seconds with different wording.
492The banner clears on its own once data resumes or a retry succeeds. If it reappears on every attempt, treat it as a [network issue](#unable-to-connect-to-api). If you connect through a gateway, see [The waiting banner comes and goes behind a gateway](#waiting-banner-behind-a-gateway). Before v2.1.185, the banner appeared after 10 seconds with different wording.
491493 
492While Claude is consulting the [advisor](https://code.claude.com/docs/en/advisor.md), the banner appears after 90 seconds without data instead of 20, because a long advisor review can send nothing for well over 20 seconds. Before v2.1.214, the 20-second threshold applied during advisor calls too, so the banner appeared during advisor reviews even when nothing was wrong.
493 
494494#### The waiting banner comes and goes behind a gateway
495495 
496496If the `Waiting for API response` banner comes and goes while Claude thinks and you connect through a gateway, [update Claude Code](https://code.claude.com/docs/en/setup.md#update-claude-code) to v2.1.309 or later. The banner appears after 45 seconds without data on these connections:
from line 2513
25132513 
25142514### tool\_use.name over 200 characters
25152515 
2516A tool call in the conversation history carries a name longer than the 200 characte
2516A tool call in the conversation history carries a name longer than the 200 characters the API accepts in a request:
2517 
2518```text theme={null}
2519API Error: 400 ... tool_use.name: String should have at most 200 characters
2520```
2521 
2522Claude Code cuts such a name to 200 characters when the response arrives and when it loads a saved conversation, so the call fails with a [`No such tool available

fast-mode Changed · +10 / -8 lines

from line 4
44 
55> [!NOTE]
66>
7> Fast mode is in [research preview](#research-preview). The feature, pricing, and availability may change based on feedback.
7> Fast mode for Claude Opus 5.5 is available, and fast mode for Claude Opus 5 and Claude Opus 4.8 is in [research preview](#research-preview).
88 
99Fast mode is a high-speed configuration for Claude Opus, making the model up to 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interactive work like rapid iteration or live debugging, and toggle it off when cost matters more than latency.
1010 
from line 16
1616 
1717* Use `/fast` to toggle on fast mode in the Claude Code CLI. The [VS Code extension](https://code.claude.com/docs/en/vs-code.md) offers a **Toggle fast mode** command when the selected model supports fast mode. Claude Code saves that toggle to your [`fastMode` setting](#toggle-fast-mode).
1818* Fast mode pricing per MTok input/output is \$8/\$40 on Opus 5.5 and \$10/\$50 on Opus 5 and Opus 4.8.
19* Available to Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and on Claude Console. Team and Enterprise organizations need an Owner to enable it first, and Console organizations need access provisioned first, both described under [Requirements](#requirements).
19* Available to Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and on Claude Console. Team and Enterprise organizations need an Owner to enable it first, and Console organizations need access provisioned first to use it with Opus 5 or Opus 4.8. [Requirements](#requirements) describes both.
2020* For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits.
2121 
2222## Toggle fast mode
from line 115
115115 
116116Fast mode requires all of the following:
117117 
118* **Anthropic API or subscription only**: fast mode is available through the Anthropic Console API and for Claude subscription plans using usage credits. It is not available on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Console organizations must also have [fast mode access provisioned](#enable-fast-mode-for-your-organization).
118* **Anthropic API or subscription only**: fast mode is available through the Anthropic Console API and for Claude subscription plans using usage credits. It is not available on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Console organizations must also have [fast mode access provisioned](#enable-fast-mode-for-your-organization) to use it with Opus 5 or Opus 4.8.
119119* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](https://code.claude.com/docs/en/costs.md#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's included usage. Until they're on, `/fast` reports "Fast mode requires usage credits". How you turn them on depends on your plan:
120120 * On Pro and Max, turn them on in the **Usage credits** section of [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` to open that page.
121121 * On Team and Enterprise, a member with billing access turns them on for the organization at [**Organization settings > Usage**](https://claude.ai/admin-settings/usage), and a member without it runs `/usage-credits` to send the organization's admins a request.
from line 125
125125> Fast mode usage draws directly from usage credits, even if you have remaining usage on your plan.
126126 
127127* **Paid Console organization**: Claude Console accounts don't use usage credits, and your organization pays for fast mode per token with the rest of its API usage. On the Console's free Evaluation plan, `/fast` shows "Fast mode unavailable during evaluation. Please purchase credits." To clear it, purchase credits in your [Console billing settings](https://platform.claude.com/settings/billing).
128 
129 Fast mode with Opus 5.5 also depends on your organization's [usage tier](https://platform.claude.com/docs/en/api/rate-limits).
128130* **Owner enablement for Team and Enterprise**: fast mode is disabled by default for Team and Enterprise organizations. An Owner must explicitly [enable fast mode](#enable-fast-mode-for-your-organization) before users can access it.
129131 
130132> [!NOTE]
from line 142
140142 
141143Where you enable fast mode depends on which product your organization uses:
142144 
143* **Console** (API customers): an admin enables it in [Claude Code preferences](https://platform.claude.com/claude-code/preferences). Fast mode is in [research preview](#research-preview), so your organization must also have fast mode access provisioned before fast mode requests succeed. To get access, contact your account manager or join the waitlist, as described in [fast mode on the Claude API](https://platform.claude.com/docs/en/build-with-claude/fast-mode).
144 
145 Without provisioned access, the API rejects each fast mode request with a 429, and Claude Code treats each rejection as a [fast mode rate limit](#handle-rate-limits). Unlike a rate limit's cooldown, the rejections continue until access is provisioned.
145* **Console** (API customers): an admin enables it in [Claude Code preferences](https://platform.claude.com/claude-code/preferences)
146146* **Claude AI** (Team and Enterprise): an Owner enables it at [**Organization settings > Claude Code**](https://claude.ai/admin-settings/claude-code)
147147 
148Console organizations that use Claude Opus 5 or Claude Opus 4.8 also need provisioned access, as described in [fast mode on the Claude API](https://platform.claude.com/docs/en/build-with-claude/fast-mode). Without that access, fast mode requests on those models hit the [fast mode rate limit](#handle-rate-limits) and fall back to standard speed until access is provisioned.
149 
148150Another option to disable fast mode entirely is to set `CLAUDE_CODE_DISABLE_FAST_MODE=1`. See [Environment variables](https://code.claude.com/docs/en/env-vars.md).
149151 
150152### Use fast mode behind proxies and LLM gateways
from line 199
197199 
198200## Handle rate limits
199201 
200Fast mode has separate rate limits from standard Opus. All supported Opus models share one fast mode rate limit pool: usage on any of them draws from the same limits. When you hit the fast mode rate limit:
202Fast mode has separate rate limits from standard Opus; for Console organizations, the Claude Platform's [rate limits](https://platform.claude.com/docs/en/api/rate-limits) page describes them. When you hit the fast mode rate limit:
201203 
2022041. Fast mode automatically falls back to standard speed
2032052. The `↯` icon turns gray to indicate cooldown
from line 215
213215 
214216## Research preview
215217 
216Fast mode is a research preview feature. This means:
218Fast mode for Claude Opus 5 and Claude Opus 4.8 is a research preview feature, which means:
217219 
218220* The feature may change based on feedback
219221* Availability and pricing are subject to change

feature-availability Changed · +2 / -2 lines

from line 86
8686 <tr>
8787 <td>[Fast mode](https://code.claude.com/docs/en/fast-mode.md)</td>
8888 <td>✓ ([Owner-enabled](https://code.claude.com/docs/en/fast-mode.md#enable-fast-mode-for-your-organization) on Team and Enterprise)</td>
89 <td>✓ (provisioned organizations)</td>
89 <td>✓ (Opus 5 and 4.8 need provisioning)</td>
9090 <td>✗</td>
9191 <td>✗</td>
9292 <td>✗</td>
from line 281
281281 
282282**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription).
283283 
284Everything in [CLI capabilities that vary by provider](#cli-capabilities-that-vary-by-provider) is available, except that [fast mode](https://code.claude.com/docs/en/fast-mode.md) requires [provisioned access](https://code.claude.com/docs/en/fast-mode.md#enable-fast-mode-for-your-organization). [Server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md) that you configure in a claude.ai Team or Enterprise organization don't reach a session that authenticates with a Console API key. See [Platform availability](https://code.claude.com/docs/en/server-managed-settings.md#platform-availability) for how to cover those sessions.
284Everything in [CLI capabilities that vary by provider](#cli-capabilities-that-vary-by-provider) is available, except that [fast mode](https://code.claude.com/docs/en/fast-mode.md) with Claude Opus 5 or Claude Opus 4.8 requires [provisioned access](https://code.claude.com/docs/en/fast-mode.md#enable-fast-mode-for-your-organization). [Server-managed settings](https://code.claude.com/docs/en/server-managed-settings.md) that you configure in a claude.ai Team or Enterprise organization don't reach a session that authenticates with a Console API key. See [Platform availability](https://code.claude.com/docs/en/server-managed-settings.md#platform-availability) for how to cover those sessions.
285285 
286286**Partial support:**
287287 
Feedback