yeejhyang 53dde30d4a

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

* fix(models): make request admission enqueue atomic

* test(models): cover atomic request admission FIFO entry

* docs(models): record atomic admission FIFO invariant

* fix(models): address request-admission review follow-ups

2026-09-16 22:07:42 +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): preserve FIFO across request-admission handoff (#5459)

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

assistant_payload_replay.py

refactor(provider): share assistant payload replay matching (#3307)

2026-05-29 23:05:59 +08:00

claude_provider.py

feat: static system prompt with DynamicContextMiddleware for prefix-cache optimization (#2801)

2026-05-09 09:27:02 +08:00

credential_loader.py

fix(models): reuse the Claude Code OAuth token read from a file descriptor (#5411)

2026-09-14 09:23:12 +08:00

factory.py

feat(models): pace shared RPM budgets before dispatch (#5432)

2026-09-15 07:14:35 +08:00

mindie_provider.py

fix(models): restore usage_metadata in MindIE tool-mode simulated streaming (#5195)

2026-09-05 14:10:18 +08:00

openai_codex_provider.py

chroe(2585): keep polishing the code of codex token usage (#2689)

2026-05-02 15:04:11 +08:00

patched_deepseek.py

refactor(provider): share assistant payload replay matching (#3307)

2026-05-29 23:05:59 +08:00

patched_mimo.py

refactor(provider): share assistant payload replay matching (#3307)

2026-05-29 23:05:59 +08:00

patched_minimax.py

feat: MiniMax provider for image/video/podcast skills + new music-generation skill (#3437)

2026-06-08 22:04:38 +08:00

patched_openai.py

refactor(provider): share assistant payload replay matching (#3307)

2026-05-29 23:05:59 +08:00

patched_stepfun.py

feat(models): add StepFun reasoning model adapter (#3461)

2026-06-09 18:01:43 +08:00

request_admission.py

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

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

vllm_provider.py

feat(models): support cumulative vLLM stream usage (#4537)

2026-07-28 19:56:40 +08:00