apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-07-05 15:52:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix more

Browse source
This commit is contained in:
Adil Hafeez 2025-07-10 16:23:40 -07:00
parent 31c21a5491
commit d994a4c8f5
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
4 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
crates/llm_gateway/src/stream_context.rs
View file

@ -344,7 +344,7 @@ impl HttpContext for StreamContext {
info!( info!(
"on_http_request_body: provider: {}, model requested (in body): {}, model selected: {}", "on_http_request_body: provider: {}, model requested (in body): {}, model selected: {}",
self.llm_provider().provider_interface, self.llm_provider().name,
model_requested, model_requested,
model_name.unwrap_or(&"None".to_string()), model_name.unwrap_or(&"None".to_string()),
); );

8
crates/llm_gateway/tests/integration.rs
View file

@ -266,7 +266,7 @@ fn llm_gateway_bad_request_to_open_ai_chat_completions() {
.expect_get_buffer_bytes(Some(BufferType::HttpRequestBody)) .expect_get_buffer_bytes(Some(BufferType::HttpRequestBody))
.returning(Some(incomplete_chat_completions_request_body)) .returning(Some(incomplete_chat_completions_request_body))
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: openai, model requested (in body): gpt-1, model selected: gpt-4")) .expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: open-ai-gpt-4, model requested (in body): gpt-1, model selected: gpt-4"))
.expect_send_local_response( .expect_send_local_response(
Some(StatusCode::BAD_REQUEST.as_u16().into()), Some(StatusCode::BAD_REQUEST.as_u16().into()),
None, None,
@ -432,7 +432,7 @@ fn llm_gateway_override_model_name() {
.returning(Some(chat_completions_request_body)) .returning(Some(chat_completions_request_body))
// The actual call is not important in this test, we just need to grab the token_id // The actual call is not important in this test, we just need to grab the token_id
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: openai, model requested (in body): gpt-1, model selected: gpt-4")) .expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: open-ai-gpt-4, model requested (in body): gpt-1, model selected: gpt-4"))
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_metric_record("input_sequence_length", 29) .expect_metric_record("input_sequence_length", 29)
@ -481,7 +481,7 @@ fn llm_gateway_override_use_default_model() {
// The actual call is not important in this test, we just need to grab the token_id // The actual call is not important in this test, we just need to grab the token_id
.expect_log( .expect_log(
Some(LogLevel::Info), Some(LogLevel::Info),
Some("on_http_request_body: provider: openai, model requested (in body): gpt-1, model selected: gpt-4"), Some("on_http_request_body: provider: open-ai-gpt-4, model requested (in body): gpt-1, model selected: gpt-4"),
) )
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
@ -529,7 +529,7 @@ fn llm_gateway_override_use_model_name_none() {
.returning(Some(chat_completions_request_body)) .returning(Some(chat_completions_request_body))
// The actual call is not important in this test, we just need to grab the token_id // The actual call is not important in this test, we just need to grab the token_id
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: openai, model requested (in body): none, model selected: gpt-4")) .expect_log(Some(LogLevel::Info), Some("on_http_request_body: provider: open-ai-gpt-4, model requested (in body): none, model selected: gpt-4"))
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Debug), None) .expect_log(Some(LogLevel::Debug), None)
.expect_metric_record("input_sequence_length", 29) .expect_metric_record("input_sequence_length", 29)

6
demos/use_cases/preference_based_routing/arch_config_rendered.yaml
View file

@ -15,14 +15,14 @@ llm_providers:
name: openai/gpt-4o name: openai/gpt-4o
provider_interface: openai provider_interface: openai
routing_preferences: routing_preferences:
- description: b - description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
name: code understanding name: code generation
- access_key: $OPENAI_API_KEY - access_key: $OPENAI_API_KEY
model: gpt-4.1 model: gpt-4.1
name: openai/gpt-4.1 name: openai/gpt-4.1
provider_interface: openai provider_interface: openai
routing_preferences: routing_preferences:
- description: a - description: understand and explain existing code snippets, functions, or libraries
name: code understanding name: code understanding
tracing: tracing:
random_sampling: 100 random_sampling: 100

2
demos/use_cases/preference_based_routing/hurl_tests/simple.hurl
View file

@ -13,7 +13,7 @@ Content-Type: application/json
HTTP 200 HTTP 200
[Asserts] [Asserts]
header "content-type" == "application/json" header "content-type" == "application/json"
jsonpath "$.model" matches /^gpt-4o-mini/ jsonpath "$.model" matches /^gpt-4.1/
jsonpath "$.usage" != null jsonpath "$.usage" != null
jsonpath "$.choices[0].message.content" != null jsonpath "$.choices[0].message.content" != null
jsonpath "$.choices[0].message.role" == "assistant" jsonpath "$.choices[0].message.role" == "assistant"