AWS bedrock documentation change
Summary
Added 'See also' section with security-related links and updated tool use reference
Security assessment
Added links to 'Thinking encryption' documentation which explicitly mentions encrypted-thinking and redaction behavior (security features). While not fixing vulnerabilities, this adds references to security documentation.
Diff
diff --git a/bedrock/latest/userguide/claude-messages-extended-thinking.md b/bedrock/latest/userguide/claude-messages-extended-thinking.md index 5950ce8a5..57b23ba13 100644 --- a//bedrock/latest/userguide/claude-messages-extended-thinking.md +++ b//bedrock/latest/userguide/claude-messages-extended-thinking.md @@ -10,0 +11,9 @@ Best practicesHow extended thinking worksHow to use extended thinkingExtended th +###### See also + + * [Thinking encryption](./claude-messages-thinking-encryption.html) – encrypted-thinking and redaction behavior specific to Claude 3.7 Sonnet. + + * [Differences in thinking across model versions](./claude-messages-thinking-differences.html) – differences in how Claude 3.7 Sonnet and Claude 4 models return thinking output. + + + + @@ -221 +230 @@ When using streaming with thinking enabled, you might notice that text sometimes -Extended thinking can be used alongside [Tool use](./model-parameters-anthropic-claude-messages-tool-use.html) allowing Claude to reason through tool selection and results processing. When using extended thinking with tool use, be aware of the following limitations: +Extended thinking can be used alongside [Anthropic Claude tool use](./model-parameters-anthropic-claude-messages-tool-use.html) allowing Claude to reason through tool selection and results processing. When using extended thinking with tool use, be aware of the following limitations: @@ -719 +728 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Tool use +Messages API