AWS bedrock documentation change
Summary
Replaced curly apostrophes with straight apostrophes throughout the document and fixed minor typo ('off' to 'off')
Security assessment
Changes are purely typographical and formatting updates with no modifications to security-related content, features, or configurations. The updates focus on punctuation consistency and minor text corrections without introducing, modifying, or removing any security controls, vulnerabilities, or security-relevant functionality.
Diff
diff --git a/bedrock/latest/userguide/claude-messages-extended-thinking.md b/bedrock/latest/userguide/claude-messages-extended-thinking.md index f115843e3..0ba6f5f6f 100644 --- a//bedrock/latest/userguide/claude-messages-extended-thinking.md +++ b//bedrock/latest/userguide/claude-messages-extended-thinking.md @@ -20 +20 @@ Best practicesHow extended thinking worksHow to use extended thinkingExtended th -Extended thinking gives Claude enhanced reasoning capabilities for complex tasks, while providing varying levels of transparency into its step-by-step thought process before it delivers its final answer. Whenever you enable Claude’s thinking mode, you will need to set a budget for the maximum number of tokens that Claude can use for its internal reasoning process. +Extended thinking gives Claude enhanced reasoning capabilities for complex tasks, while providing varying levels of transparency into its step-by-step thought process before it delivers its final answer. Whenever you enable Claude's thinking mode, you will need to set a budget for the maximum number of tokens that Claude can use for its internal reasoning process. @@ -127 +127 @@ When extended thinking is turned on, Claude creates `thinking` content blocks wh -Here’s an example of the default response format: +Here's an example of the default response format: @@ -144 +144 @@ Here’s an example of the default response format: -For more information about the response format of extended thinking, see Anthropic’s Messages API [Request and Response](./model-parameters-anthropic-claude-messages-request-response.html). +For more information about the response format of extended thinking, see Anthropic's Messages API [Request and Response](./model-parameters-anthropic-claude-messages-request-response.html). @@ -156 +156 @@ The value of `budget_tokens` must be set to a value less than `max_tokens`. Howe -With extended thinking enabled, the Messages API for Claude 4 models returns a summary of Claude’s full thinking process. Summarized thinking provides the full intelligence benefits of extended thinking, while preventing misuse. +With extended thinking enabled, the Messages API for Claude 4 models returns a summary of Claude's full thinking process. Summarized thinking provides the full intelligence benefits of extended thinking, while preventing misuse. @@ -160 +160 @@ Here are some important considerations for summarized thinking: - * You’re charged for the full thinking tokens generated by the original request, not the summary tokens. + * You're charged for the full thinking tokens generated by the original request, not the summary tokens. @@ -179 +179 @@ You can stream extended thinking responses using server-sent events (SSE). When -Here’s how to handle streaming with thinking using **InvokeModelWithResponseStream** : +Here's how to handle streaming with thinking using **InvokeModelWithResponseStream** : @@ -389 +389 @@ The API response will now only include text -During tool use, you must pass thinking blocks back to the API, and you must include the complete unmodified block back to the API. This is critical for maintaining the model’s reasoning flow and conversation integrity. +During tool use, you must pass thinking blocks back to the API, and you must include the complete unmodified block back to the API. This is critical for maintaining the model's reasoning flow and conversation integrity. @@ -397 +397 @@ While you can omit `thinking` blocks from prior `assistant` role turns, we sugge - * Use the relevant thinking blocks necessary to preserve the model’s reasoning + * Use the relevant thinking blocks necessary to preserve the model's reasoning @@ -406 +406 @@ When Claude invokes tools, it is pausing its construction of a response to await - * **Reasoning continuity** : The thinking blocks capture Claude’s step-by-step reasoning that led to tool requests. When you post tool results, including the original thinking ensures Claude can continue its reasoning from where it left off. + * **Reasoning continuity** : The thinking blocks capture Claude's step-by-step reasoning that led to tool requests. When you post tool results, including the original thinking ensures Claude can continue its reasoning from where it left off. @@ -408 +408 @@ When Claude invokes tools, it is pausing its construction of a response to await - * **Context maintenance** : While tool results appear as user messages in the API structure, they’re part of a continuous reasoning flow. Preserving thinking blocks maintains this conceptual flow across multiple API calls. + * **Context maintenance** : While tool results appear as user messages in the API structure, they're part of a continuous reasoning flow. Preserving thinking blocks maintains this conceptual flow across multiple API calls. @@ -421 +421 @@ When providing thinking blocks, the entire sequence of consecutive thinking bloc -Interleaved thinking is made available to you as a ‘Beta Service’ as defined in the AWS Service Terms. It is subject to your Agreement with AWS and the AWS Service Terms, and the applicable model EULA. +Interleaved thinking is made available to you as a 'Beta Service' as defined in the AWS Service Terms. It is subject to your Agreement with AWS and the AWS Service Terms, and the applicable model EULA. @@ -663 +663 @@ This behavior is consistent whether using regular thinking or interleaved thinki -In older Claude models (before Claude 3.7 Sonnet), if the sum of prompt tokens and max_tokens exceeded the model’s context window, the system would automatically adjust max_tokens to fit within the context limit. This meant you could set a large max_tokens value and the system would silently reduce it as needed. With Claude 3.7 and 4 models, `max_tokens` (which includes your thinking budget when thinking is enabled) is enforced as a strict limit. The system now returns a validation error if prompt tokens + max_tokens exceeds the context window size. +In older Claude models (before Claude 3.7 Sonnet), if the sum of prompt tokens and max_tokens exceeded the model's context window, the system would automatically adjust max_tokens to fit within the context limit. This meant you could set a large max_tokens value and the system would silently reduce it as needed. With Claude 3.7 and 4 models, `max_tokens` (which includes your thinking budget when thinking is enabled) is enforced as a strict limit. The system now returns a validation error if prompt tokens + max_tokens exceeds the context window size. @@ -692 +692 @@ Given the context window and `max_tokens` behavior with extended thinking Claude - * Be aware that previous thinking blocks don’t accumulate in your context window. This change has been made to provide more predictable and transparent behavior, especially as maximum token limits have increased significantly. + * Be aware that previous thinking blocks don't accumulate in your context window. This change has been made to provide more predictable and transparent behavior, especially as maximum token limits have increased significantly.