llama-stack-mirror/tests/integration/responses
Omar Abdelwahab 3d02349783 test: Keep skip marker for MCP auth tests (recordings needed)
After attempting local recording generation, encountered multiple environment issues:
1. Client/server version mismatches (0.3.x vs 0.4.0.dev0)
2. LlamaStackClient API changes (provider_data parameter removed)
3. Dev server network constraints (HTTP 426 errors with OpenAI API)

Server logs from CI confirmed recordings are needed:
- RuntimeError: Recording not found for request hash: 56ddb450d...
- Tests with authorization parameter create different OpenAI request hashes

Local recording generation requires complex environment setup that matches CI.
Requesting reviewer assistance to generate recordings via CI infrastructure.
2025-11-13 19:58:31 -08:00
..
fixtures fix(tests): add OpenAI client connection cleanup to prevent CI hangs (#4119) 2025-11-12 12:17:13 -05:00
recordings feat: split API and provider specs into separate llama-stack-api pkg (#3895) 2025-11-13 11:51:17 -08:00
__init__.py feat(tests): introduce a test "suite" concept to encompass dirs, options (#3339) 2025-09-05 13:58:49 -07:00
conftest.py feat(tests): enable MCP tests in server mode (#4146) 2025-11-13 07:23:23 -08:00
helpers.py feat(responses)!: improve responses + conversations implementations (#3810) 2025-10-15 09:36:11 -07:00
streaming_assertions.py feat(responses)!: add in_progress, failed, content part events (#3765) 2025-10-10 07:27:34 -07:00
test_basic_responses.py feat(tests): enable MCP tests in server mode (#4146) 2025-11-13 07:23:23 -08:00
test_conversation_responses.py test: Add timeout to test_conversation_error_handling to prevent CI hang 2025-11-13 18:46:27 -08:00
test_file_search.py feat(tests): enable MCP tests in server mode (#4146) 2025-11-13 07:23:23 -08:00
test_mcp_authentication.py test: Keep skip marker for MCP auth tests (recordings needed) 2025-11-13 19:58:31 -08:00
test_tool_responses.py Merge branch 'main' into add-mcp-authentication-param 2025-11-13 09:42:35 -08:00