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

+43
View File
@@ -180,6 +180,49 @@ impl ApiError {
}
}
/// HTTP status code for an `Api` error, if any. Used by callers (e.g. the
/// sub-agent provider chain) to decide whether to advance to the next
/// configured model — a 404 "model not found" on the primary should fall
/// through to the next fallback rather than killing the whole chain.
#[must_use]
pub fn status_code(&self) -> Option<reqwest::StatusCode> {
match self {
Self::Api { status, .. } => Some(*status),
Self::RetriesExhausted { last_error, .. } => last_error.status_code(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Http(_)
| Self::Io(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. }
| Self::RequestBodySizeExceeded { .. } => None,
}
}
/// Response body (best-effort) for an `Api` error, if any.
#[must_use]
pub fn response_body(&self) -> Option<&str> {
match self {
Self::Api { body, .. } => Some(body.as_str()),
Self::RetriesExhausted { last_error, .. } => last_error.response_body(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Http(_)
| Self::Io(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. }
| Self::RequestBodySizeExceeded { .. } => None,
}
}
#[must_use]
pub fn safe_failure_class(&self) -> &'static str {
match self {
+3 -2
View File
@@ -30,8 +30,9 @@ pub use providers::openai_compat::{
};
pub use providers::{
detect_provider_kind, max_tokens_for_model, max_tokens_for_model_with_override,
model_family_identity_for, model_family_identity_for_kind, provider_diagnostics_for_model,
resolve_model_alias, ProviderDiagnostics, ProviderKind,
model_family_identity_for, model_family_identity_for_kind, model_token_limit,
provider_diagnostics_for_model, resolve_model_alias, ModelTokenLimit, ProviderDiagnostics,
ProviderKind,
};
pub use sse::{parse_frame, SseParser};
pub use types::{
+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,
}
}