Commit graph

2 commits

Author SHA1 Message Date
kshitijk4poor
08e2a1a51e fix(anthropic): omit tool-streaming beta on MiniMax endpoints
MiniMax's Anthropic-compatible endpoints reject requests that include
the fine-grained-tool-streaming beta header — every tool-use message
triggers a connection error (~18s timeout). Regular chat works fine.

Add _common_betas_for_base_url() that filters out the tool-streaming
beta for Bearer-auth (MiniMax) endpoints while keeping all other betas.
All four client-construction branches now use the filtered list.

Based on #6528 by @HiddenPuppy.
Original cherry-picked from PR #6688 by kshitijk4poor.
Fixes #6510, fixes #6555.
2026-04-09 17:53:52 -07:00
kshitij
22d1bda185 fix(minimax): correct context lengths, model catalog, thinking guard, aux model, and config base_url
Cherry-picked from PR #6046 by kshitijk4poor with dead code stripped.

- Context lengths: 204800 → 1M (M1) / 1048576 (M2.5/M2.7) per official docs
- Model catalog: add M1 family, remove deprecated M2.1 and highspeed variants
- Thinking guard: skip extended thinking for MiniMax (Anthropic-compat endpoint)
- Aux model: MiniMax-M2.7-highspeed → MiniMax-M2.7 (same model, half price)
- Config base_url: honour model.base_url for API-key providers (fixes China users)
- Stripped unused get_minimax_max_output() / _MINIMAX_MAX_OUTPUT (no consumer)

Fixes #5777, #4082, #6039. Closes #3895.
2026-04-08 02:20:46 -07:00