Messages changedapi/beta/messages
Nearest release: v2.1.315, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+218added
Lines−50removed
From line
137
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits33to this page, all time
The whole hunk
from line 137, old and new numbered
/
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 137
137137
138138 - `"analytics-usage-cost-2026-08-24"`
139139
140 - `"experimental-claude-tag-2026-10-21"`
141
140142- `"anthropic-user-profile-id": optional string`
141143
142144 The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization.
from line 1038
10361038
10371039 - `BetaEncryptedCodeExecutionResultBlockParam object`
10381040
1039 Code execution result with encrypted stdout for PFC + web_search results.
1041 The output and exit code of Python code that Claude ran with the code execution tool, with standard output in encrypted form, sent back in a later request.
10401042
10411043 - `type: "encrypted_code_execution_result"`
10421044
from line 1574
15721574
15731575 - `BetaCodeExecutionTool20260120 object`
15741576
1575 Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
1577 A `tools` entry for the code execution tool, version `code_execution_20260120`. It adds REPL state persistence to version `code_execution_20250825`.
15761578
1579 REPL state persistence applies with programmatic tool calling. With it, the Python interpreter state, such as variable bindings, persists across requests that reuse the container.
1580
1581 See the [code execution tool guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool?sdk_languages=http#tool-versions) to learn what each tool version adds.
1582
15771583 - `type: "code_execution_20260120"`
15781584
15791585 - `name: "code_execution"`
from line 4226
42204226
42214227 - `BetaCodeExecutionTool20260120 object`
42224228
4223 Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
4229 A `tools` entry for the code execution tool, version `code_execution_20260120`. It adds REPL state persistence to version `code_execution_20250825`.
42244230
4231 REPL state persistence applies with programmatic tool calling. With it, the Python interpreter state, such as variable bindings, persists across requests that reuse the container.
4232
4233 See the [code execution tool guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool?sdk_languages=http#tool-versions) to learn what each tool version adds.
4234
42254235 - `BetaCodeExecutionTool20260521 object`
42264236
42274237 Code execution tool with REPL state persistence.
from line 4926
49164926
49174927 - `BetaEncryptedCodeExecutionResultBlock object`
49184928
4919 Code execution result with encrypted stdout for PFC + web_search results.
4929 The output and exit code of Python code that Claude ran with the code execution tool, with standard output in encrypted form.
49204930
4931 The API returns this block in place of `code_execution_result` when the code called the web search tool.
4932
4933 See the [programmatic tool calling guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling?sdk_languages=http) to learn more about programmatic tool calling.
4934
49214935 - `type: "encrypted_code_execution_result"`
49224936
49234937 default: encrypted_code_execution_result
from line 5492
54785492
54795493 - `BetaCodeExecutionTool20260120 object`
54805494
5481 Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
5495 A `tools` entry for the code execution tool, version `code_execution_20260120`. It adds REPL state persistence to version `code_execution_20250825`.
54825496
5497 REPL state persistence applies with programmatic tool calling. With it, the Python interpreter state, such as variable bindings, persists across requests that reuse the container.
5498
5499 See the [code execution tool guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool?sdk_languages=http#tool-versions) to learn what each tool version adds.
5500
54835501 - `type: "code_execution_20260120"`
54845502
54855503 - `name: "code_execution"`
from line 7020
70027020
70037021 - `response_inclusion: optional "full" or "excluded"`
70047022
7005 How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn.
7006
7007 - `"full"`
7008
7009 - `"excluded"`
7010
7011 - `strict: optional boolean`
7012
7013 When true, guarantees schema validation on tool names and inputs
7014
7015 - `url_sources: optional BetaWebFetchURLSources or null`
7016
7017 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
7018
7019 - `use_cache: optional boolean`
7020
7021 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
7022
7023 - `BetaAdvisorTool20260301 object`
7024
7025 - `type: "advisor_20260301"`
7026
7027 - `model: Model`
7028
7029 The model that will complete your prompt.
7030
7031 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
7032
7033 - `"claude-haiku-5-5"`
7034
7035 Fastest model for high-volume, real-time tasks
7036
7037 - `"claude-sonnet-5-5"`
7038
7039 Efficient model for coding and agents
7040
7041 - `"claude-fable-5-1"`
7042
7043 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
7044
7045 - `"claude-opus-5-5"`
7046
7047 Powerful intelligence for coding, knowledge work, and long-running agents
7048
7049
7023 How this tool's result blocks appear in the
No line in this hunk matches that.