mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-06 02:41:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(anthropic): cap max_tokens at 65536 for Qwen models via DashScope

Browse source 
DashScope's Anthropic-compatible endpoint enforces max_tokens ∈ [1, 65536].
Adding "qwen3" to _ANTHROPIC_OUTPUT_LIMITS prevents 400 errors that were
misclassified as context overflow, triggering premature compression.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
B1GGersnow 2026-04-25 00:37:54 +08:00 • committed by Teknium
parent 83bbe9b458
commit dc63ad0ad2
1 changed files with 3 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
agent/anthropic_adapter.py
View file

@ -105,6 +105,9 @@ _ANTHROPIC_OUTPUT_LIMITS = {
"claude-3-haiku": 4_096,
# Third-party Anthropic-compatible providers
"minimax": 131_072,
# Qwen models via DashScope Anthropic-compatible endpoint
# DashScope enforces max_tokens ∈ [1, 65536]
"qwen3": 65_536,
}
# For any model not in the table, assume the highest current limit.