apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-07 23:02:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add support for v1/responses API (#622)

Browse source 
* making first commit. still need to work on streaming respones

* making first commit. still need to work on streaming respones

* stream buffer implementation with tests

* adding grok API keys to workflow

* fixed changes based on code review

* adding support for bedrock models

* fixed issues with translation to claude code

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
This commit is contained in:
Salman Paracha 2025-12-03 14:58:26 -08:00 • committed by GitHub
parent b01a81927d
commit a448c6e9cb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
38 changed files with 7015 additions and 2955 deletions
Download patch file Download diff file Expand all files Collapse all files

11
crates/brightstaff/src/handlers/router.rs
View file

@ -3,7 +3,7 @@ use common::configuration::{ModelAlias, ModelUsagePreference};
use common::consts::{ARCH_IS_STREAMING_HEADER, ARCH_PROVIDER_HINT_HEADER};
use hermesllm::apis::openai::ChatCompletionsRequest;
use hermesllm::clients::endpoints::SupportedUpstreamAPIs;
use hermesllm::clients::SupportedAPIs;
use hermesllm::clients::SupportedAPIsFromClient;
use hermesllm::{ProviderRequest, ProviderRequestType};
use http_body_util::combinators::BoxBody;
use http_body_util::{BodyExt, Full};
@ -39,7 +39,7 @@ pub async fn router_chat(
let mut client_request = match ProviderRequestType::try_from((
&chat_request_bytes[..],
&SupportedAPIs::from_endpoint(request_path.as_str()).unwrap(),
&SupportedAPIsFromClient::from_endpoint(request_path.as_str()).unwrap(),
)) {
Ok(request) => request,
Err(err) => {
@ -58,7 +58,7 @@ pub async fn router_chat(
let resolved_model = if let Some(model_aliases) = model_aliases.as_ref() {
if let Some(model_alias) = model_aliases.get(&model_from_request) {
debug!(
"Model Alias: 'From {}' -> 'To{}'",
"Model Alias: 'From {}' -> 'To {}'",
model_from_request, model_alias.target
);
model_alias.target.clone()
@ -91,10 +91,11 @@ pub async fn router_chat(
Ok(
ProviderRequestType::MessagesRequest(_)
| ProviderRequestType::BedrockConverse(_)
| ProviderRequestType::BedrockConverseStream(_),
| ProviderRequestType::BedrockConverseStream(_)
| ProviderRequestType::ResponsesAPIRequest(_),
) => {
// This should not happen after conversion to OpenAI format
warn!("Unexpected: got MessagesRequest after converting to OpenAI format");
warn!("Unexpected: got non-ChatCompletions request after converting to OpenAI format");
let err_msg = "Request conversion failed".to_string();
let mut bad_request = Response::new(full(err_msg));
*bad_request.status_mut() = StatusCode::BAD_REQUEST;

4
crates/brightstaff/src/main.rs
View file

@ -6,7 +6,7 @@ use brightstaff::router::llm_router::RouterService;
use brightstaff::utils::tracing::init_tracer;
use bytes::Bytes;
use common::configuration::Configuration;
use common::consts::{CHAT_COMPLETIONS_PATH, MESSAGES_PATH};
use common::consts::{CHAT_COMPLETIONS_PATH, MESSAGES_PATH, OPENAI_RESPONSES_API_PATH};
use http_body_util::{combinators::BoxBody, BodyExt, Empty};
use hyper::body::Incoming;
use hyper::server::conn::http1;
@ -123,7 +123,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
async move {
match (req.method(), req.uri().path()) {
(&Method::POST, CHAT_COMPLETIONS_PATH | MESSAGES_PATH) => {
(&Method::POST, CHAT_COMPLETIONS_PATH | MESSAGES_PATH | OPENAI_RESPONSES_API_PATH) => {
let fully_qualified_url =
format!("{}{}", llm_provider_url, req.uri().path());
router_chat(req, router_service, fully_qualified_url, model_aliases)