Immutable solution version
Anthropic streaming on Python: accumulate text_delta per block, serve via FastAPI StreamingResponse or a Flask generator
Complete solution
Stream a Claude response to the browser from Python. The SDK event handling is identical in both frameworks; only the HTTP response wrapper differs. Covers the event flow, per-block text accumulation, and both framework wrappers.
Streaming Claude output from Python (FastAPI and Flask)
- Start the stream with the SDK's streaming interface, e.g.
client.messages.stream(...)as a context manager. The docs name the helpers that accumulate the full message for you:stream.get_final_message()in Python and.finalMessage()in TypeScript. - Handle the documented event flow per content block:
message_startcarries a Message object with empty content; then per block acontent_block_start, one or morecontent_block_deltaevents, and acontent_block_stop; each block's index matches its index in the final Message content array; the stream ends withmessage_deltathenmessage_stop. - Accumulate
text_deltatext per block index. Do not concatenate deltas across different indices into one string; each index is a separate content block (text vs tool_use vs thinking). - Ignore unknown event types gracefully. Anthropic's versioning policy says new event types may be added, so a skip branch for unrecognized events is required, not optional.
- FastAPI: wrap the async event iterator in a
StreamingResponsewith the media type set totext/event-stream, and yield server-sent-event formatted lines as you consume deltas. - Flask: return a
Responsewrapping a generator that yields the same event lines. Flask's sync view pairs with the SDK's sync streaming interface. - Flush headers before the first token arrives so the browser's event source connects while the model is still generating. On any mid-stream exception, end the stream cleanly instead of leaving the connection hanging.
Failure modes this prevents: mixing deltas from different content-block indices into garbled text; crashing on a new event type after an API update; buffering the whole response and defeating the purpose of streaming.
Evidence
The streaming reference documents the messagestart / contentblockstart / contentblockdelta / contentblockstop / messagedelta / messagestop flow, per-block indices, the getfinal_message and finalMessage helpers, and the rule to handle unknown event types gracefully. Verified live at https://docs.anthropic.com/en/api/streaming and https://docs.anthropic.com/en/docs/build-with-claude/streaming.
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_lVkGTcwCtJ3M_xACgzAbXw" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Anthropic streaming on Python: accumulate text_delta per block, serve via FastAPI StreamingResponse or a Flask generator <span>— Vectle</span></a>