Tranquil-Flow 1d38b0f888 fix(agent): comprehensive DeepSeek V4 support — context windows, thinking mode, reasoning replay ... Unifies approaches from PRs #14952, #14958, #15325, #15228, #15354 into a single cohesive implementation: - Add 1M context window entries for V4 models (deepseek-v4-pro, deepseek-v4-flash, deepseek-chat, deepseek-reasoner) - Plumb thinking.type toggle and reasoning_effort mapping for native DeepSeek API (only "high" and "max" are valid) - Strip incompatible sampling params when thinking is enabled - Inject reasoning_content="" on all assistant messages for DeepSeek replay (scoped to api.deepseek.com and OpenRouter) - Fix _extract_reasoning isinstance checks for empty strings - Preserve empty-string reasoning_content in normalize_response - Add _copy_reasoning_content_for_api call in _handle_max_iterations Fixes #15353. Supersedes #14952, #14958, #15325, #15228, #15354.		2026-04-25 10:16:34 +10:00
..
__init__.py	feat: add BedrockTransport + wire all Bedrock transport paths	2026-04-21 20:58:37 -07:00
anthropic.py	refactor: remove _nr_to_assistant_message shim + fix flush_memories guard	2026-04-23 02:30:05 -07:00
base.py	feat: add transport ABC + AnthropicTransport wired to all paths	2026-04-21 01:27:01 -07:00
bedrock.py	feat: add BedrockTransport + wire all Bedrock transport paths	2026-04-21 20:58:37 -07:00
chat_completions.py	fix(agent): comprehensive DeepSeek V4 support — context windows, thinking mode, reasoning replay	2026-04-25 10:16:34 +10:00
codex.py	feat: add ResponsesApiTransport + wire all Codex transport paths	2026-04-21 19:48:56 -07:00
types.py	fix: add extra_content property to ToolCall for Gemini thought_signature (#14488)	2026-04-23 23:45:07 +05:30