mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-13 08:52:02 +00:00
35386e3f4a
* fix(complexity_router): keep Claude Code subagent and side-request traffic off other agents' tier pins Claude Code sends one x-claude-code-session-id for the main agent, every subagent and their side requests. In user_turn mode a subagent's new ask rewrote the parent's pin (#50099), and the agent progress summaries Claude Code fires during a subagent run rewrote the subagent's pin to the cheapest tier (#50444). Subagent requests now get their own tier pin keyed on session id plus x-claude-code-agent-id. Requests marked x-claude-code-request-class: auxiliary route as housekeeping, and only main and subagent turns may write a pin. Without the hint header, the summary and prompt-suggestion prompts are matched as housekeeping sentinels. * chore(ui): regenerate schema.d.ts for the housekeeping_patterns description * fix(complexity_router): let the request-class hint only mark housekeeping, not suppress pin writes A client-sent request class must not decide whether a decision is saved. Tagging a real ask as workflow or auxiliary dropped its routing decision, so later continuations replayed an older pin with the new history. The auxiliary hint now only routes the request through the housekeeping path, which is already never pinned and defers to custom classifiers and keyword rules. * test(complexity_router): cover the auxiliary hint on a prompt no sentinel matches --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| docker-entrypoint.d | ||
| litellm-dashboard | ||
| Dockerfile | ||
| nginx.conf | ||