valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Azure Responses API workaround (#3528)

Browse Source 
Azure Responses API doesn't work well with store:false and response
items.

If store = false and id is sent an error is thrown that ID is not found
If store = false and id is not sent an error is thrown that ID is
required

Add detection for Azure urls and add a workaround to preserve reasoning
item IDs and send store:true
This commit is contained in:
pakrym-oai
2025-09-12 13:52:15 -07:00
committed by GitHub
parent 5f6e95b592
commit e3c6903199
3 changed files with 239 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
codex-rs/core/src/client.rs
View File

@@ -193,6 +193,15 @@ impl ModelClient {
None
};
// In general, we want to explicitly send `store: false` when using the Responses API,
// but in practice, the Azure Responses API rejects `store: false`:
//
// - If store = false and id is sent an error is thrown that ID is not found
// - If store = false and id is not sent an error is thrown that ID is required
//
// For Azure, we send `store: true` and preserve reasoning item IDs.
let azure_workaround = self.provider.is_azure_responses_endpoint();
let payload = ResponsesApiRequest {
model: &self.config.model,
instructions: &full_instructions,
@@ -201,13 +210,19 @@ impl ModelClient {
tool_choice: "auto",
parallel_tool_calls: false,
reasoning,
store: false,
store: azure_workaround,
stream: true,
include,
prompt_cache_key: Some(self.conversation_id.to_string()),
text,
};
let mut payload_json = serde_json::to_value(&payload)?;
if azure_workaround {
attach_item_ids(&mut payload_json, &input_with_instructions);
}
let payload_body = serde_json::to_string(&payload_json)?;
let mut attempt = 0;
let max_retries = self.provider.request_max_retries();
@@ -220,7 +235,7 @@ impl ModelClient {
trace!(
"POST to {}: {}",
self.provider.get_full_url(&auth),
serde_json::to_string(&payload)?
payload_body.as_str()
);
let mut req_builder = self
@@ -234,7 +249,7 @@ impl ModelClient {
.header("conversation_id", self.conversation_id.to_string())
.header("session_id", self.conversation_id.to_string())
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload);
.json(&payload_json);
if let Some(auth) = auth.as_ref()
&& auth.mode == AuthMode::ChatGPT
@@ -431,6 +446,27 @@ struct ResponseCompletedOutputTokensDetails {
reasoning_tokens: u64,
}
fn attach_item_ids(payload_json: &mut Value, original_items: &[ResponseItem]) {
let Some(input_value) = payload_json.get_mut("input") else {
return;
};
let serde_json::Value::Array(items) = input_value else {
return;
};
for (value, item) in items.iter_mut().zip(original_items.iter()) {
if let ResponseItem::Reasoning { id, .. } = item {
if id.is_empty() {
continue;
}
if let Some(obj) = value.as_object_mut() {
obj.insert("id".to_string(), Value::String(id.clone()));
}
}
}
}
async fn process_sse<S>(
stream: S,
tx_event: mpsc::Sender<Result<ResponseEvent>>,

92
codex-rs/core/src/model_provider_info.rs
View File

@@ -162,6 +162,21 @@ impl ModelProviderInfo {
}
}
pub(crate) fn is_azure_responses_endpoint(&self) -> bool {
if self.wire_api != WireApi::Responses {
return false;
}
if self.name.eq_ignore_ascii_case("azure") {
return true;
}
self.base_url
.as_ref()
.map(|base| matches_azure_responses_base_url(base))
.unwrap_or(false)
}
/// Apply provider-specific HTTP headers (both static and environment-based)
/// onto an existing `reqwest::RequestBuilder` and return the updated
/// builder.
@@ -329,6 +344,18 @@ pub fn create_oss_provider_with_base_url(base_url: &str) -> ModelProviderInfo {
}
}
fn matches_azure_responses_base_url(base_url: &str) -> bool {
let base = base_url.to_ascii_lowercase();
const AZURE_MARKERS: [&str; 5] = [
"openai.azure.",
"cognitiveservices.azure.",
"aoai.azure.",
"azure-api.",
"azurefd.",
];
AZURE_MARKERS.iter().any(|marker| base.contains(marker))
}
#[cfg(test)]
mod tests {
use super::*;
@@ -419,4 +446,69 @@ env_http_headers = { "X-Example-Env-Header" = "EXAMPLE_ENV_VAR" }
let provider: ModelProviderInfo = toml::from_str(azure_provider_toml).unwrap();
assert_eq!(expected_provider, provider);
}
#[test]
fn detects_azure_responses_base_urls() {
fn provider_for(base_url: &str) -> ModelProviderInfo {
ModelProviderInfo {
name: "test".into(),
base_url: Some(base_url.into()),
env_key: None,
env_key_instructions: None,
wire_api: WireApi::Responses,
query_params: None,
http_headers: None,
env_http_headers: None,
request_max_retries: None,
stream_max_retries: None,
stream_idle_timeout_ms: None,
requires_openai_auth: false,
}
}
let positive_cases = [
"https://foo.openai.azure.com/openai",
"https://foo.openai.azure.us/openai/deployments/bar",
"https://foo.cognitiveservices.azure.cn/openai",
"https://foo.aoai.azure.com/openai",
"https://foo.openai.azure-api.net/openai",
"https://foo.z01.azurefd.net/",
];
for base_url in positive_cases {
let provider = provider_for(base_url);
assert!(
provider.is_azure_responses_endpoint(),
"expected {base_url} to be detected as Azure"
);
}
let named_provider = ModelProviderInfo {
name: "Azure".into(),
base_url: Some("https://example.com".into()),
env_key: None,
env_key_instructions: None,
wire_api: WireApi::Responses,
query_params: None,
http_headers: None,
env_http_headers: None,
request_max_retries: None,
stream_max_retries: None,
stream_idle_timeout_ms: None,
requires_openai_auth: false,
};
assert!(named_provider.is_azure_responses_endpoint());
let negative_cases = [
"https://api.openai.com/v1",
"https://example.com/openai",
"https://myproxy.azurewebsites.net/openai",
];
for base_url in negative_cases {
let provider = provider_for(base_url);
assert!(
!provider.is_azure_responses_endpoint(),
"expected {base_url} not to be detected as Azure"
);
}
}
}