Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One capture · api

One read of Claude Developer Platformapi-20261021T220722Z

82 pages moved out of 808 read.

Pages moved 82 significant first
Pages read 808 in this capture
Captured 22:07 UTC
Corpus hash dd90a8d0c9c2 index-hash

What this read moved

76-82 of 82, page 4 of 4

This capture is too large to show at once. Changes 76-82 of 82 are below, significant first; the rest are on the following screens.

managed-agents/migration Changed · +1 / -1 lines

from line 1157
11571157 
11581158 agent = client.beta.agents.create(
11591159 name: "weather-agent",
1160 model: "claude-opus-5-5",
1160 model: Anthropic::Beta::BetaManagedAgentsModel::CLAUDE_OPUS_5_5,
11611161 system_: "You are a concise weather assistant.",
11621162 tools: [
11631163 {

managed-agents/quickstart Changed · +2 / -2 lines

from line 100
100100 
101101 <Tab title="Java">
102102 ```groovy Gradle
103 implementation("com.anthropic:anthropic-java:3.0.0")
103 implementation("com.anthropic:anthropic-java:3.1.0")
104104 ```
105105 </Tab>
106106 
from line 343
343343 
344344 agent = client.beta.agents.create(
345345 name: "Coding Assistant",
346 model: "claude-opus-5-5",
346 model: Anthropic::Beta::BetaManagedAgentsModel::CLAUDE_OPUS_5_5,
347347 system_: "You are a helpful coding assistant. Write clean, well-documented code.",
348348 tools: [{type: "agent_toolset_20260401"}]
349349 )

managed-agents/self-hosted-sandboxes-workers Changed · +1 / -1 lines

from line 453
453453 
454454 ```bash
455455 #!/bin/bash
456 # spawn.sh: called once per claimed work item
456 # spawn.sh: called once for each claimed work item
457457 # The claimed work item arrives as JSON on stdin.
458458 ANTHROPIC_WORK_SECRET="$(jq -r '.secret // empty')"
459459 export ANTHROPIC_WORK_SECRET

managed-agents/tools-web-restrictions Changed · +2 / -0 lines

from line 23
2323 
2424Your organization's web search settings on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console also apply to `web_search` in a session. If an administrator disables web search, `web_search` calls return an error result to the agent, and the session continues. If the organization restricts web search domains, the agent receives only the search results that both the organization's domain restrictions and the agent's per-tool lists allow.
2525 
26Your organization's web fetch settings on the same page also apply to `web_fetch` in a session. If an administrator turns off web fetch, `web_fetch` calls return an error result to the agent, and the session continues. If the organization sets allowed or blocked domains for web fetch, a URL must pass the organization's list and the agent's per-tool lists, and so must any URL a redirect leads to. A `web_fetch` call for a URL that any of them excludes also returns an error result to the agent.
27 
2628## Set domain lists on an agent
2729 
2830The following example creates an agent that limits `web_search` to two sites and blocks one host for `web_fetch`. It also sets `user_location` (java, php: `userLocation`; csharp, go: `UserLocation`) and `max_content_tokens` (java, php: `maxContentTokens`; csharp, go: `MaxContentTokens`), which [Settings](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions#settings) describes. The response echoes the `configs` (csharp, go: `Configs`) array.

models/fable-5-1/migration-guide Changed · +1 / -2 lines

from line 956
956956 ```
957957 
958958 ```bash CLI
959 ant beta:messages create \
960 --beta thinking-binding-controls-2026-08-01 <<'YAML'
959 ant beta:messages create --beta thinking-binding-controls-2026-08-01 <<'YAML'
961960 model: claude-fable-5-1
962961 max_tokens: 16000
963962 thinking:

models/fable-5-1/whats-new-fable-5-1 Changed · +2 / -1 lines

from line 93
9393 ```
9494 
9595 ```bash CLI
96 ant beta:messages create --beta mid-conversation-output-config-2026-07-01 <<'YAML'
96 ant beta:messages create \
97 --beta mid-conversation-output-config-2026-07-01 <<'YAML'
9798 model: claude-fable-5-1
9899 max_tokens: 4096
99100 output_config:

test-and-evaluate/strengthen-guardrails/reduce-latency Changed · +1 / -1 lines

from line 187
187187 
188188 # For time-sensitive applications, use Claude Haiku 5.5 at low effort
189189 message = client.messages.create(
190 model: "claude-haiku-5-5",
190 model: Anthropic::Model::CLAUDE_HAIKU_5_5,
191191 max_tokens: 1024,
192192 output_config: { effort: :low },
193193 messages: [{ role: "user", content: "Summarize this customer feedback in 2 sentences: [feedback text]" }]
Feedback