One read of Claude Developer Platformapi-20260820T193728Z
49 pages moved out of 584 read.
Pages moved
49
significant first
Pages read
584
in this capture
Captured
19:37 UTC
Corpus hash
5658ae966f49
corpus-hash
What this read moved
26-49 of 49, page 2 of 2This capture is too large to show at once. Changes 26-49 of 49 are below, significant first; the rest are on the following screens.
agents-and-tools/tool-use/fine-grained-tool-streaming Changed · +1 / -1 lines
from line 18
1818
1919All models support fine-grained tool streaming on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). To use it, set `eager_input_streaming` to `true` on any user-defined tool where you want fine-grained streaming enabled, and enable streaming on your request.
2020
21The `eager_input_streaming` field is optional. Setting it to `true` turns on fine-grained streaming for that tool, and omitting it gives you standard buffered streaming, in which the API buffers and validates each parameter value before streaming it back. The exception is a request that still sends the legacy `fine-grained-tool-streaming-2025-05-14` beta header, which turns fine-grained streaming on for tools that leave the field unset. The per-tool field replaces that header, and an explicit `false` keeps buffered streaming for a tool even when a request still sends it. See [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference) for the field definition.
21The `eager_input_streaming` field is optional. Setting it to `true` turns on fine-grained streaming for that tool, and omitting it gives you standard buffered streaming, in which the API buffers and validates each parameter value before streaming it back. The exception is a request that still sends the legacy `fine-grained-tool-streaming-2025-05-14` beta header, which turns fine-grained streaming on for tools that leave the field unset. The per-tool field replaces that header, and an explicit `false` keeps buffered streaming for a tool even when a request still sends it. The legacy header cannot be combined with a [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) or [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolset entry: the API rejects a request that sends both, so remove the header and set `eager_input_streaming` on the user-defined tools that need it. See [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference) for the field definition.
2222
2323The following example turns on fine-grained streaming for a `make_file` tool and asks Claude for a long poem, so the tool input is large enough to watch it stream in:
2424
agents-and-tools/tool-use/handle-tool-calls Changed · +4 / -0 lines
from line 20
2020* `name`: The name of the tool being used.
2121* `input`: An object containing the input being passed to the tool, conforming to the tool's `input_schema`.
2222
23A `tool_use` block for a member of the [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) or [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolset also carries a `toolset_name` field (`"computer"` or `"browser"`). Its `name` is the member tool Claude is calling, such as `screenshot` or `navigate`, so dispatch those blocks on both fields.
24
2325<Accordion title="Example API response with a `tool_use` content block">
2426 ```json JSON
2527 {
from line 56
5456 * `tool_use_id`: The `id` of the tool use request this is a result for.
5557 * `content` (optional): The result of the tool, as a string (for example, `"content": "15 degrees"`), a list of nested content blocks (for example, `"content": [{"type": "text", "text": "15 degrees"}]`), or a list of document blocks (for example, `"content": [{"type": "document", "source": {"type": "text", "media_type": "text/plain", "data": "15 degrees"}}]`). These content blocks can use the `text`, `image`, `document`, or [`search_result`](https://platform.claude.com/docs/en/build-with-claude/search-results) types.
5658 * `is_error` (optional): Set to `true` if the tool execution resulted in an error.
59
60A `tool_result` that answers a computer use or browser use member block must also echo the same `toolset_name` value as the `tool_use` block; a member result that omits it is rejected. Its `content` is also narrower: a member result may contain only `text` and `image` blocks, and a browser use result may add one [`browser_state`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#track-tabs-and-page-state) block (the [tab-management members](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#tab-management-results) return only that block).
5761
5862<Note>
5963 **Important formatting requirements:**
agents-and-tools/tool-use/parallel-tool-use Changed · +3 / -1 lines
from line 23
2323}
2424```
2525
26The [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#batch-actions) and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#batch-actions) are stricter. When Claude returns several of their member tool calls in one turn (a batch action), run them sequentially in the order they appear and stop at the first failure; each tool defines the exact text to return for the calls you skip.
27
2628## Test parallel tool calls
2729
2830<Note>
from line 1569
15671569
15681570**4. Calls in a batch appear to depend on each other**
15691571
1570Execution order is your choice. If your tools have ordering dependencies, running the batch sequentially and stopping on the first failure is a valid strategy: return `is_error: true` for any call you didn't run. If you run in parallel and a call fails because its prerequisite hadn't completed, return `is_error: true` with the natural error message. Claude will reissue the call on the next turn. To reduce dependent calls appearing together, add this to your system prompt: "Only batch tool calls that are independent of each other."
1572Execution order is your choice. If your tools have ordering dependencies, running the batch sequentially and stopping on the first failure is a valid strategy (and the required one for the [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#batch-actions) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#batch-actions) tools): return `is_error: true` for any call you didn't run. If you run in parallel and a call fails because its prerequisite hadn't completed, return `is_error: true` with the natural error message. Claude will reissue the call on the next turn. To reduce dependent calls appearing together, add this to your system prompt: "Only batch tool calls that are independent of each other."
15711573
15721574## Next steps
15731575
agents-and-tools/tool-use/programmatic-tool-calling Changed · +1 / -0 lines
from line 1367
13671367The following tools cannot be called programmatically:
13681368
13691369* Tools provided by an [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector)
1370* The [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801`), whose `allowed_callers` field accepts only `"direct"`
13701371
13711372### Message formatting restrictions
13721373
agents-and-tools/tool-use/server-tools Changed · +1 / -1 lines
from line 1102
11021102 Fix the most common tool-use errors with symptom-to-fix diagnostic tables.
11031103 </Card>
11041104
1105 <Card title="Web search tool" icon="browser" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool">
1105 <Card title="Web search tool" icon="magnifying-glass" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool">
11061106 Search the web and cite results.
11071107 </Card>
11081108
agents-and-tools/tool-use/strict-tool-use Changed · +2 / -0 lines
from line 380
380380 </Step>
381381</Steps>
382382
383The [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolset entries (`computer_toolset_20260801` and `browser_toolset_20260801`) don't accept `strict: true`; a request that sets it on either entry is rejected.
384
383385## Common use cases
384386
385387<AccordionGroup>
agents-and-tools/tool-use/tool-search-tool Changed · +2 / -0 lines
from line 593
593593* Never set `defer_loading: true` on the tool search tool itself.
594594* Keep your 3–5 most frequently used tools non-deferred so Claude can call them without searching first.
595595
596The computer use and browser use toolsets (`computer_toolset_20260801` and `browser_toolset_20260801`) take `defer_loading` per member tool inside the entry's `configs` object, not on the entry itself; a request that sets it at the entry level is rejected. Because a toolset defers and expands as a unit, `defer_loading` must resolve to the same value on every enabled member, and when Claude discovers the toolset through search, every enabled member loads at once. See [Client toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#client-toolsets) for the `configs` format.
597
596598Both tool search variants (`regex` and `bm25`) search tool names, descriptions, argument names, and argument descriptions.
597599
598600Internally, the API excludes deferred tools from the system-prompt prefix. When Claude discovers a deferred tool through tool search, the API appends a `tool_reference` block inline in the conversation, then expands it into the full tool definition before passing it to Claude. The prefix is untouched, so prompt caching is preserved. The grammar for [strict mode](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) (the rules that constrain tool-call output to match your schemas) builds from the full toolset, so `defer_loading` and strict mode compose without grammar recompilation.
agents-and-tools/tool-use/troubleshooting-tool-use Changed · +1 / -1 lines
from line 74
7474 </Card>
7575
7676 <Card title="Tool reference" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference">
77 Full directory of Anthropic-schema tools and their version strings.
77 Full directory of Anthropic-provided tools and their version strings.
7878 </Card>
7979</CardGroup>
8080
agents-and-tools/tool-use/web-fetch-tool Changed · +1 / -1 lines
from line 50
50504. Claude analyzes the fetched content and provides a response with optional citations.
5151
5252<Note>
53 The web fetch tool currently does not support websites dynamically rendered with JavaScript.
53 The web fetch tool currently does not support websites dynamically rendered with JavaScript. For pages that need a real browser (JavaScript rendering, clicking, or filling forms), consider the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), a client tool where your application drives the browser and returns page text or screenshots to Claude as tool results.
5454</Note>
5555
5656### When Claude fetches
api/overview Changed · +1 / -1 lines
from line 152
152152Every SDK provides an auto-paginating iterator that follows `next_page` for you. In Python and TypeScript, you get it by iterating the list result directly. The other SDKs provide the iterator through a separate method. SDK auto-pagination is forward-only; to go back a page, read `prev_page` from the response and pass it back as the `page` parameter yourself. See [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for language-specific details.
153153
154154<Note>
155 Some list endpoints use a different cursor scheme. The [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Models API](https://platform.claude.com/docs/en/api/models/list), and several [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) endpoints take `after_id` and `before_id` query parameters instead of `page`. Their responses return `has_more`, `first_id`, and `last_id` instead of `next_page`. The [Files API](https://platform.claude.com/docs/en/build-with-claude/files) also uses that scheme when a request includes the `files-api-2025-04-14` beta header; without the header, `GET /v1/files` takes `page` and returns `next_page`. The [Skills API](https://platform.claude.com/docs/en/build-with-claude/skills-guide) list endpoints, `GET /v1/skills` and `GET /v1/skills/{skill_id}/versions`, take `page` and return `next_page`; requests that include the `skills-2025-10-02` beta header also receive a `has_more` Boolean alongside `next_page`. See the reference page for each endpoint for its exact pagination fields.
155 Some list endpoints use a different cursor scheme. The [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Models API](https://platform.claude.com/docs/en/api/models/list), and several [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) endpoints take `after_id` and `before_id` query parameters instead of `page`. Their responses return `has_more`, `first_id`, and `last_id` instead of `next_page`. See the reference page for each endpoint for its exact pagination fields.
156156</Note>
157157
158158## Rate limits and availability
build-with-claude/claude-in-amazon-bedrock Changed · +1 / -0 lines
from line 361
361361* API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
362362* Claude Managed Agents
363363* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
364* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Amazon Bedrock; the beta computer use tool versions remain available)
364365
365366## Regions
366367
build-with-claude/claude-in-microsoft-foundry Changed · +1 / -0 lines
from line 643
643643* Models API
644644* Message Batches API
645645* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
646* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Microsoft Foundry; the beta computer use tool versions remain available)
646647
647648### Additional features not supported when hosted on Azure
648649
build-with-claude/claude-on-amazon-bedrock-legacy Changed · +1 / -0 lines
from line 737
737737* Claude Managed Agents
738738* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
739739* Automatic prompt caching (the [top-level `cache_control` field](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching); use [explicit cache breakpoints](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#explicit-cache-breakpoints) instead)
740* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Amazon Bedrock; the beta computer use tool versions remain available)
740741
741742### PDF support on Bedrock
742743
build-with-claude/claude-on-vertex-ai Changed · +1 / -0 lines
from line 362
362362* API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
363363* Claude Managed Agents
364364* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
365* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Google Cloud; the beta computer use tool versions remain available)
365366
366367### Context window
367368
build-with-claude/claude-platform-on-aws Changed · +1 / -0 lines
from line 560
560560The following capabilities are not currently available on Claude Platform on AWS:
561561
562562* **HIPAA readiness:** Anthropic's HIPAA-ready program is not available. See [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
563* **Computer use and browser use toolsets:** `computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Claude Platform on AWS. The beta [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) tool versions remain available.
563564
564565- **Admin API:** Workspace endpoints (create, get, list, update, and archive on `/v1/organizations/workspaces`) are available. Other Admin API endpoints (organization members, workspace members, invites, API keys, usage reports, cost reports, rate limit reports, and external keys) are not currently available. Manage [CMEK](https://platform.claude.com/docs/en/manage-claude/cmek) keys in the Claude Console instead. View usage and cost data in the [Claude Console](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#using-the-claude-console) instead. AWS IAM manages organization membership.
565566- **Workspace member management:** Adding or removing users from individual workspaces is not available. AWS IAM policies on workspace ARNs control access.
build-with-claude/pdf-support Changed · +2 / -0 lines
from line 941
941941 ```
942942
943943 ```php PHP
944 // The PHP SDK exposes the Files API under the beta namespace; field names can differ from other SDKs.
945 // The PHP SDK supports file_id document and image sources only through $client->beta->messages with the files beta.
944946 use Anthropic\Core\FileParam;
945947
946948 $client = new Client();
build-with-claude/prompt-engineering/claude-prompting-best-practices Changed · +1 / -1 lines
from line 828
828828 * "Review progress.txt, tests.json, and the git logs."
829829 * "Manually run through a fundamental integration test before moving on to implementing new features."
830830
8315. **Provide verification tools:** As the length of autonomous tasks grows, Claude needs to verify correctness without continuous human feedback. Tools like Playwright MCP server or computer use capabilities for testing UIs are helpful.
8315. **Provide verification tools:** As the length of autonomous tasks grows, Claude needs to verify correctness without continuous human feedback. Tools that let Claude verify UI work are helpful, such as the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), or a browser automation MCP server.
832832
8338336. **Encourage complete usage of context:** Prompt Claude to efficiently complete components before moving on:
834834
build-with-claude/prompt-engineering/prompting-claude-opus-4-8 Changed · +1 / -1 lines
from line 157
157157
158158## Computer use
159159
160[Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
160On the Claude API, Claude Opus 4.8 supports the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Opus 4.8 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
161161
162162For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.
163163
build-with-claude/prompt-engineering/prompting-claude-sonnet-5 Changed · +1 / -1 lines
from line 153
153153
154154## Computer use
155155
156Claude Sonnet 5 supports the `computer_20251124` tool version. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
156On the Claude API, Claude Sonnet 5 supports the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Sonnet 5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
157157
158158For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.
159159
build-with-claude/search-results Changed · +1 / -1 lines
from line 2159
21592159 Ground Claude's responses in your source documents. Citations return the exact passages that support each claim, so you can verify answers and surface sources to your users.
21602160 </Card>
21612161
2162 <Card title="Web search tool" icon="browser" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool">
2162 <Card title="Web search tool" icon="magnifying-glass" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool">
21632163 Give Claude access to current web content with cited sources, optional dynamic filtering, and domain controls.
21642164 </Card>
21652165
build-with-claude/vision-coordinates Changed · +2 / -0 lines
from line 448
448448
449449If you cannot pre-resize (for example, when the image comes from an upstream system you can't modify), use the resize helper from [Resize your image before uploading](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates#resize-your-image-before-uploading) to recover the dimensions Claude saw, then map the coordinates Claude returns into normalized coordinates or back onto your original image. Claude resizes oversized images rather than rejecting them, up to the API's [request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits). Beyond those limits the request fails with a validation error instead. Pass the tier limits that match the model you called: the wrong tier's limits recover the wrong resized dimensions and silently shift every coordinate. This approach requires knowing the pixel dimensions of the image you uploaded, so it does not apply to PDF uploads.
450450
451Screenshots and zoom images that you return to the [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#handle-coordinate-scaling-for-higher-resolutions) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#targets-and-coordinates) toolsets are an exception to automatic resizing. The API rejects a `tool_result` image that exceeds the model's limits with a validation error instead of resizing it. Resize those images in your application before returning them, then scale the coordinates Claude returns back to your screen's dimensions.
452
451453<CodeGroup>
452454 ```bash cURL
453455 # This local coordinate conversion makes no API request, so there's nothing
build-with-claude/working-with-messages Changed · +4 / -0 lines
from line 1046
10461046 Control desktop computer environments with the Messages API.
10471047 </Card>
10481048
1049 <Card title="Browser use tool" icon="browser" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool">
1050 Let Claude navigate, read, and interact with webpages in a browser you run.
1051 </Card>
1052
10491053 <Card title="Structured outputs" icon="code-brackets" href="https://platform.claude.com/docs/en/build-with-claude/structured-outputs">
10501054 Get guaranteed, schema-validated JSON output from Claude.
10511055 </Card>
manage-claude/cmek Changed · +1 / -0 lines
from line 127
127127| | Structured outputs (not available for Claude Fable 5 or Claude Mythos models in CMEK organizations) |
128128| | Advisor tool |
129129| | Computer use |
130| | Browser use |
130131| | Context management |
131132
132133## Limited preservation outside your key
managed-agents/files Changed · +3 / -1 lines
from line 71
7171 ```
7272
7373 ```php PHP
74 // The PHP SDK exposes the Files API under the beta namespace; field names can differ from other SDKs.
7475 $file = $client->beta->files->upload(
7576 FileParam::fromResource(fopen($csvPath, 'r'), filename: 'data.csv', contentType: 'text/csv'),
7677 );
from line 538
537538
538539## Listing and downloading session files
539540
540Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Filtering by `scope_id` requires the `managed-agents-2026-04-01` beta header, so the list examples use the `beta` files namespace and pass that header explicitly. Downloading a file doesn't require a beta header.
541Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Filtering by `scope_id` requires the `managed-agents-2026-04-01` beta header, so the list examples use the `beta` files namespace and pass that header explicitly.
541542
542543<CodeGroup>
543544 ```bash cURL
from line 651
650651 ```
651652
652653 ```php PHP
654 // The PHP SDK exposes the Files API under the beta namespace; field names can differ from other SDKs.
653655 // List files associated with a session
654656 $files = $client->beta->files->list(
655657 scopeID: 'sesn_abc123',