This commit addresses both P0 issues flagged in Greptile review to achieve
5/5 score (currently 4/5).
**P0 Issue #1: Responses API X-Initiator never set**
Root cause: The X-Initiator header was being set in validate_environment(),
which doesn't have access to the `input` parameter. The _get_input_from_params()
helper checked for `litellm_params.input`, but this attribute doesn't exist in
GenericLiteLLMParams - the `input` parameter is passed separately to
transform_responses_api_request().
Fix: Moved X-Initiator and vision header logic from validate_environment() to
transform_responses_api_request() where the `input` parameter is available.
This ensures the header is correctly set for Responses API requests.
Changes:
- Added transform_responses_api_request() override in
GithubCopilotResponsesAPIConfig that:
1. Calculates X-Initiator based on input analysis
2. Adds copilot-vision-request header if images detected
3. Calls parent to validate input and handle reasoning items
- Removed broken _get_input_from_params() helper
- Simplified validate_environment() docstring and removed duplicate logic
**P0 Issue #2: Integration test in wrong location**
Root cause: tests/llm_translation/test_github_copilot_billing.py makes real
network calls via litellm.completion(), violating the repository rule that
tests/llm_translation/ is for mock-only tests.
Fix: Moved test file to tests/llm_responses_api_testing/ which is the
designated directory for integration tests that make real API calls.
Impact:
- Responses API requests now correctly set X-Initiator header
- Multi-turn agentic workflows (Plan mode, tool calls, agent flows) will
only consume 1 premium request per session instead of 1 per turn
- Integration tests now in proper location per repository conventions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
fedfaefd81