Merge pull request #3341 from ultraworkers/fix/rebase-on-main

feat(team): team enhancements, subagentModel, parallel tool exec (fixed from #3250)
This commit is contained in:
Bellman authored and GitHub committed 2026-10-13 09:13:47 +09:00
commit 734558eb31
26 files changed
+3944 -1165

No files matched your search

+9 -5
View File
@@ -683,13 +683,15 @@ pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
max_output_tokens: 8_192,
context_window_tokens: 131_072,
}),
"qwen-max" => Some(ModelTokenLimit {
max_output_tokens: 8_192,
// Qwen models via DashScope / OpenAI-compat
"qwen3.6-35b-fast" | "qwen3-235b-a22b" | "qwen-max" | "qwen-plus" | "qwen-turbo"
| "qwen-qwq" => Some(ModelTokenLimit {
max_output_tokens: 16_384,
context_window_tokens: 131_072,
}),
"qwen-plus" => Some(ModelTokenLimit {
max_output_tokens: 8_192,
context_window_tokens: 131_072,
"glm-5.1-fast" => Some(ModelTokenLimit {
max_output_tokens: 16_384,
context_window_tokens: 200_000,
}),
// Groq compound systems are exposed through an OpenAI-compatible API
// but cap completions at 8,192 output tokens. Without this metadata
@@ -699,6 +701,8 @@ pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
max_output_tokens: 8_192,
context_window_tokens: 131_072,
}),
// Unknown models return None so preflight skips the context-window
// check and lets the API enforce its own limits.
_ => None,
}
}