Stream Anthropic responses uncompressed

[xymbol]

What this does

Net::HTTP requests gzip and auto-inflates by default. Cloudflare gzips Anthropic's SSE with infrequent deflate flushes, batching chunk delivery into 2 bursts and pushing first-chunk arrival to ~15s on a 22s response.

Setting Accept-Encoding: identity on streaming requests bypasses Net::HTTP's inflater. Scoped to Anthropic streaming; non-streaming responses still benefit from gzip.

Measured on claude-haiku-4-5, 1500-word completion. Sparkline: each char = 1s, digit = chunks delivered, _ = zero.

	TTFT	chunks/sec
before	15.1s	9____9
after	1.17s	84528454645464555__92

Type of change

• Bug fix

Scope check

• I read the Contributing Guide
• This aligns with RubyLLM's focus on LLM communication
• This isn't application-specific logic that belongs in user code
• This benefits most users, not just my specific use case

Quality check

• Existing Anthropic cassettes replay clean with the patched code — VCR's default matcher is [:method, :uri], and Net::HTTP still inflates a recorded gzipped response on its own. Re-recording with rake vcr:record[anthropic] is optional and not included here; the only load-bearing diff would be the Accept-Encoding request header value.
• New spec at spec/ruby_llm/providers/anthropic/streaming_spec.rb asserts the request header (fails without the fix, passes with).
• No documentation changes needed.

AI-generated code

• I used AI tools to help diagnose and write this
• I have reviewed and understand all generated code

API changes

• No API changes

Related

anthropics/anthropic-sdk-ruby#182 — the official Anthropic Ruby SDK has the same Net::HTTP auto-inflate bug and applies the same one-header fix (Accept-Encoding: identity) on its streaming endpoints.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 87.06%. Comparing base (4942d6c) to head (5f7a121).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #771   +/-   ##
=======================================
  Coverage   87.05%   87.06%           
=======================================
  Files         119      119           
  Lines        5594     5596    +2     
  Branches     1407     1407           
=======================================
+ Hits         4870     4872    +2     
  Misses        724      724           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.