kshitijk4poor 43de1ca8c2 refactor: remove _nr_to_assistant_message shim + fix flush_memories guard ... NormalizedResponse and ToolCall now have backward-compat properties so the agent loop can read them directly without the shim: ToolCall: .type, .function (returns self), .call_id, .response_item_id NormalizedResponse: .reasoning_content, .reasoning_details, .codex_reasoning_items This eliminates the 35-line shim and its 4 call sites in run_agent.py. Also changes flush_memories guard from hasattr(response, 'choices') to self.api_mode in ('chat_completions', 'bedrock_converse') so it works with raw boto3 dicts too. WS1 items 3+4 of Cycle 2 (#14418).		2026-04-23 02:30:05 -07:00
..
__init__.py	feat: add transport types + migrate Anthropic normalize path	2026-04-20 23:06:00 -07:00
test_bedrock_transport.py	feat: add BedrockTransport + wire all Bedrock transport paths	2026-04-21 20:58:37 -07:00
test_chat_completions.py	feat: add ChatCompletionsTransport + wire all default paths	2026-04-21 20:50:02 -07:00
test_codex_transport.py	feat: add ResponsesApiTransport + wire all Codex transport paths	2026-04-21 19:48:56 -07:00
test_transport.py	fix(agent): accept empty content with stop_reason=end_turn as valid anthropic response	2026-04-22 14:26:23 -07:00
test_types.py	refactor: remove _nr_to_assistant_message shim + fix flush_memories guard	2026-04-23 02:30:05 -07:00