Focus streaming and Claude client tests#58
Merged
Conversation
i wanted to record a few but somehow caused a mass rerecord, doesnt matter since fresh vcrs are better
stream_test had 3 cases multi turn is delted since we kinda do that in handoff already split tool call and basic text into two tests makes it easier with the way that handoff works to do one test per file
remove prompt too long test since that is already done somewhere else udpated the error message from claude
![managerbot-app[bot]](https://avatars.githubusercontent.com/in/853044?s=60&v=4){kind=small}
There was a problem hiding this comment.
Reviewed Changes
Managerbot reviewed 6 out of 102 changed files in this pull request and generated 0 comments.
Files not reviewed (96)
- test/fixtures/handoff/stream_image_test/anthropic_apikey_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_image_test/anthropic_oauth_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_image_test/openai_apikey_completions_gpt-5.1.json
- test/fixtures/handoff/stream_image_test/openai_apikey_responses_gpt-5.4.json
- test/fixtures/handoff/stream_image_test/openai_oauth_codex_gpt-5.4.json
- test/fixtures/handoff/stream_reasoning_test/anthropic_apikey_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_reasoning_test/anthropic_oauth_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_reasoning_test/openai_apikey_completions_gpt-5.1.json
- test/fixtures/handoff/stream_reasoning_test/openai_apikey_responses_gpt-5.4.json
- test/fixtures/handoff/stream_reasoning_test/openai_oauth_codex_gpt-5.4.json
- test/fixtures/handoff/stream_test/anthropic_oauth_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_text_test/anthropic_apikey_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_text_test/anthropic_oauth_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_text_test/openai_apikey_completions_gpt-5.1.json
- test/fixtures/handoff/stream_text_test/openai_apikey_responses_gpt-5.4.json
- test/fixtures/handoff/stream_text_test/openai_oauth_codex_gpt-5.4.json
- test/fixtures/handoff/stream_tool_call_test/anthropic_apikey_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_tool_call_test/anthropic_oauth_messages_claude-sonnet-4-20250514.json
- test/fixtures/handoff/stream_tool_call_test/openai_apikey_completions_gpt-5.1.json
- test/fixtures/handoff/stream_tool_call_test/openai_apikey_responses_gpt-5.4.json
- test/fixtures/handoff/stream_tool_call_test/openai_oauth_codex_gpt-5.4.json
- test/fixtures/vcr_cassettes/integration/clients/claude_test_rb/test_throws_authentication_error.yml
- test/fixtures/vcr_cassettes/integration/clients/claude_test_rb/test_throws_bad_request_error.yml
- test/fixtures/vcr_cassettes/integration/clients/claude_test_rb/test_throws_not_found_error.yml
- test/fixtures/vcr_cassettes/integration/clients/claude_test_rb/test_throws_throws_prompt_too_long_.yml
- test/fixtures/vcr_cassettes/integration/clients/groq_test_rb/test_throws_authentication_error.yml
- test/fixtures/vcr_cassettes/integration/clients/groq_test_rb/test_throws_bad_request_error.yml
- test/fixtures/vcr_cassettes/integration/clients/groq_test_rb/test_throws_not_found_error.yml
- test/fixtures/vcr_cassettes/integration/clients/groq_test_rb/test_throws_rate_limit_error.yml
- test/fixtures/vcr_cassettes/integration/clients/openai_test_rb/test_embeddings_api.yml
- test/fixtures/vcr_cassettes/integration/clients/openai_test_rb/test_throws_authentication_error.yml
- test/fixtures/vcr_cassettes/integration/clients/openai_test_rb/test_throws_bad_request_error.yml
- test/fixtures/vcr_cassettes/integration/clients/openai_test_rb/test_throws_not_found_error.yml
- test/fixtures/vcr_cassettes/integration/clients/openai_test_rb/test_throws_rate_limit_error.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_anthropic_apikey_messages_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_anthropic_apikey_messages_none_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_openai_apikey_completions_none_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_openai_apikey_completions_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_openai_apikey_responses_none_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_openai_apikey_responses_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/cache_test_rb/test_live_cache_read_tokens_on_second_turn_openai_oauth_codex_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_image_test_rb/test_handoff_stream_image__anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_image_test_rb/test_handoff_stream_image__anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_image_test_rb/test_handoff_stream_image__openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_image_test_rb/test_handoff_stream_image__openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_image_test_rb/test_handoff_stream_image__openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_reasoning_test_rb/test_handoff_stream_reasoning__anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_reasoning_test_rb/test_handoff_stream_reasoning__anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_reasoning_test_rb/test_handoff_stream_reasoning__openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_reasoning_test_rb/test_handoff_stream_reasoning__openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_reasoning_test_rb/test_handoff_stream_reasoning__openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_test_rb/test_handoff_stream__anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_test_rb/test_handoff_stream__anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_test_rb/test_handoff_stream__openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_test_rb/test_handoff_stream__openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_test_rb/test_handoff_stream__openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_text_test_rb/test_handoff_stream_text__anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_text_test_rb/test_handoff_stream_text__anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_text_test_rb/test_handoff_stream_text__openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_text_test_rb/test_handoff_stream_text__openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_text_test_rb/test_handoff_stream_text__openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_tool_call_test_rb/test_handoff_stream_tool_call__anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_tool_call_test_rb/test_handoff_stream_tool_call__anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_tool_call_test_rb/test_handoff_stream_tool_call__openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_tool_call_test_rb/test_handoff_stream_tool_call__openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/handoff_stream_tool_call_test_rb/test_handoff_stream_tool_call__openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/prompt_too_long_test_rb/test_live_prompt_too_long_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/prompt_too_long_test_rb/test_live_prompt_too_long_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/prompt_too_long_test_rb/test_live_prompt_too_long_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/prompt_too_long_test_rb/test_live_prompt_too_long_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/prompt_too_long_test_rb/test_live_prompt_too_long_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_image_test_rb/test_live_image_streaming_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_image_test_rb/test_live_image_streaming_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_image_test_rb/test_live_image_streaming_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/stream_image_test_rb/test_live_image_streaming_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_image_test_rb/test_live_image_streaming_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_reasoning_test_rb/test_live_basic_thinking_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_reasoning_test_rb/test_live_basic_thinking_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_reasoning_test_rb/test_live_basic_thinking_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/stream_reasoning_test_rb/test_live_basic_thinking_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_reasoning_test_rb/test_live_basic_thinking_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_test_rb/test_live_multi_turn_tool_streaming_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_test_rb/test_live_multi_turn_tool_streaming_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_test_rb/test_live_multi_turn_tool_streaming_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/stream_test_rb/test_live_multi_turn_tool_streaming_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_test_rb/test_live_multi_turn_tool_streaming_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_text_test_rb/test_live_text_streaming_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_text_test_rb/test_live_text_streaming_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_text_test_rb/test_live_text_streaming_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/stream_text_test_rb/test_live_text_streaming_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_text_test_rb/test_live_text_streaming_openai_oauth_codex_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_tool_call_test_rb/test_live_basic_tool_call_anthropic_apikey_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_tool_call_test_rb/test_live_basic_tool_call_anthropic_oauth_messages_claude-sonnet-4-20250514.yml
- test/fixtures/vcr_cassettes/integration/live/stream_tool_call_test_rb/test_live_basic_tool_call_openai_apikey_completions_gpt-5_1.yml
- test/fixtures/vcr_cassettes/integration/live/stream_tool_call_test_rb/test_live_basic_tool_call_openai_apikey_responses_gpt-5_4.yml
- test/fixtures/vcr_cassettes/integration/live/stream_tool_call_test_rb/test_live_basic_tool_call_openai_oauth_codex_gpt-5_4.yml
Comments suppressed due to low confidence (0)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Goal
Focus and stabilize provider tests by simplifying streaming coverage and updating Claude client expectations.
Changes made to achieve the goal
Refactored streaming tests into smaller single-purpose cases, removed redundant prompt-length coverage, updated Claude error expectations, and refreshed recorded VCR fixtures for the affected tests.