Wenchao An c1f9064e9b

fix(models): route managed OpenAI GPT-6 presets through Responses (#7870) ...

* fix(models): route managed OpenAI GPT-6 presets through Responses

* test(memory): pin capacity scenarios to a stable clock

* fix(models): honor Flash mode for managed OpenAI GPT-6

* fix(models): reconcile preset effort with explicit reasoning contracts

* test(memory): share the fixed clock with updater capacity tests

* fix(models): normalize GPT-6 reasoning overrides and sampling

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-11-05 14:30:42 +08:00

..

__init__.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)

2026-03-14 22:55:52 +08:00

AGENTS.md

fix(models): route managed OpenAI GPT-6 presets through Responses (#7870)

2026-11-05 14:30:42 +08:00

assistant_payload_replay.py

fix(runtime): harden model response recovery at provider boundaries (#5080)

2026-09-18 07:29:34 +08:00

claude_provider.py

fix(models): honor HTTP-date Retry-After hints in Claude retries (#7295)

2026-10-23 15:21:44 +08:00

credential_loader.py

fix(models): fall through an unusable credential source instead of ending the lookup (#7140)

2026-10-20 10:30:52 +08:00

factory.py

fix(models): route managed OpenAI GPT-6 presets through Responses (#7870)

2026-11-05 14:30:42 +08:00

mindie_provider.py

fix(mindie): decode escaped newlines correctly inside tilde-fenced code blocks (#7285)

2026-10-24 11:41:35 +08:00

openai_codex_provider.py

fix(models): honor HTTP-date Retry-After hints in Claude retries (#7295)

2026-10-23 15:21:44 +08:00

patched_deepseek.py

feat(models): add managed Kimi K3.1 Pro capabilities (#7566)

2026-10-27 14:57:29 +08:00

patched_mimo.py

refactor(models): give reasoning capture plumbing a single owner (#6639)

2026-10-11 10:53:00 +08:00

patched_minimax.py

feat(models): register managed models with provider presets (#6757)

2026-10-13 08:14:23 +08:00

patched_openai.py

fix(config): correct Gemini official endpoint reasoning example (#6161)

2026-10-02 22:32:21 +08:00

patched_stepfun.py

refactor(models): give reasoning capture plumbing a single owner (#6639)

2026-10-11 10:53:00 +08:00

reasoning_capture.py

refactor(models): give reasoning capture plumbing a single owner (#6639)

2026-10-11 10:53:00 +08:00

reasoning.py

feat(models): add declarative reasoning capability contract (#5780)

2026-09-24 20:39:30 +08:00

request_admission.py

fix(models): preserve FIFO across request-admission handoff (#5459)

2026-09-16 22:07:42 +08:00

selection.py

feat(models): add scoped model controls to Web chats (#7249)

2026-10-22 08:08:23 +08:00

vllm_provider.py

fix(vllm): normalize thinking switches without mutating request bodies (#6496)

2026-10-08 20:41:40 +08:00