Fix Bedrock streaming dropping all chunks when Faraday env is nil

[chen-anders]

What this does

Fixes a bug where Bedrock ConverseStream responses come back completely empty (zero chunks, blank content, nil token counts) even though the HTTP request succeeds with status 200.

The Faraday 2 on_data callback gates chunk parsing on env&.status == 200. With the net_http adapter, env is nil during streaming (the status is not yet known when chunks arrive), so this condition is false for every chunk. Each valid AWS event-stream frame is then routed to the failed-response handler, which tries to JSON.parse binary eventstream bytes, fails, logs a "failed stream error chunk" debug line, and silently drops it. The result is an empty streamed response.

This affects any app on Faraday 2.x + the net_http adapter (Faraday's default) using Bedrock streaming.

Fix: invert the guard so a nil env (status unknown) falls through to normal chunk parsing, and only a present env reporting a non-200 status is treated as a failure. Applied in both spots that build the v2 on_data proc:

• RubyLLM::Streaming::FaradayHandlers.v2_on_data (shared SSE handler)
• RubyLLM::Protocols::Converse::Streaming#stream_response (Bedrock ConverseStream)

Reproduction

chat = RubyLLM.chat(model: "us.anthropic.claude-sonnet-4-6", provider: "bedrock", assume_model_exists: true)

# Non-streaming — works:
chat.ask("Say BANANA only.").content          # => "BANANA"

# Streaming — broken before this fix:
chunks = []
resp = chat.ask("Say BANANA only.") { |c| chunks << c }
chunks.size    # => 0   (expected: > 0)
resp.content   # => ""   (expected: "BANANA")

With Faraday 2.x + net_http, the debug log shows the data arriving fine ({"delta":{"text":"BANANA"}}, usage tokens, status 200) but every frame hitting "Failed Bedrock stream error chunk". After the fix: chunks.size => 5, resp.content => "BANANA", tokens populated.

Type of change

• Bug fix
• New feature
• Breaking change
• Documentation
• Performance improvement

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

• I ran overcommit --install and all hooks pass
• I tested my changes thoroughly
  • For provider changes: Re-recorded VCR cassettes with bundle exec rake vcr:record[provider_name]
  • Added unit tests covering nil-env / 200 / non-200 routing for both code paths (spec/ruby_llm/streaming_spec.rb, spec/ruby_llm/protocols/converse/streaming_spec.rb)
• I updated documentation if needed
• I didn't modify auto-generated files manually (models.json, aliases.json)

AI-generated code

• I used AI tools to help write this code
• I have reviewed and understand all generated code (required if above is checked)

API changes

• Breaking change
• New public methods/classes
• Changed method signatures
• No API changes

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 82.88%. Comparing base (80fe294) to head (a1093e9).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #813   +/-   ##
=======================================
  Coverage   82.88%   82.88%           
=======================================
  Files         142      142           
  Lines        6574     6574           
  Branches     1148     1148           
=======================================
  Hits         5449     5449           
- Misses        663      664    +1     
+ Partials      462      461    -1     

☔ View full report in Codecov by Harness.
📢 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.