mirror of
https://github.com/katanemo/plano.git
synced 2026-07-14 16:22:12 +02:00
fb0581fd39
* pushing draft PR * transformations are working. Now need to add some tests next * updated tests and added necessary response transformations for Anthropics' message response object * fixed bugs for integration tests * fixed doc tests * fixed serialization issues with enums on response * adding some debug logs to help * fixed issues with non-streaming responses * updated the stream_context to update response bytes * the serialized bytes length must be set in the response side * fixed the debug statement that was causing the integration tests for wasm to fail * fixing json parsing errors * intentionally removing the headers * making sure that we convert the raw bytes to the correct provider type upstream * fixing non-streaming responses to tranform correctly * /v1/messages works with transformations to and from /v1/chat/completions * updating the CLI and demos to support anthropic vs. claude * adding the anthropic key to the preference based routing tests * fixed test cases and added more structured logs * fixed integration tests and cleaned up logs * added python client tests for anthropic and openai * cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo * fixing the tests. python dependency order was broken * updated the openAI client to fix demos * removed the raw response debug statement * fixed the dup cloning issue and cleaned up the ProviderRequestType enum and traits * fixing logs * moved away from string literals to consts * fixed streaming from Anthropic Client to OpenAI * removed debug statement that would likely trip up integration tests * fixed integration tests for llm_gateway * cleaned up test cases and removed unnecessary crates * fixing comments from PR * fixed bug whereby we were sending an OpenAIChatCompletions request object to llm_gateway even though the request may have been AnthropicMessages --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-4.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-9.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-10.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-41.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-136.local>
31 lines
1.7 KiB
Rust
31 lines
1.7 KiB
Rust
pub const RATELIMIT_SELECTOR_HEADER_KEY: &str = "x-arch-ratelimit-selector";
|
|
pub const SYSTEM_ROLE: &str = "system";
|
|
pub const USER_ROLE: &str = "user";
|
|
pub const TOOL_ROLE: &str = "tool";
|
|
pub const ASSISTANT_ROLE: &str = "assistant";
|
|
pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
|
pub const DEFAULT_TARGET_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
|
pub const API_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
|
pub const MODEL_SERVER_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
|
pub const MODEL_SERVER_NAME: &str = "model_server";
|
|
pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
|
|
pub const MESSAGES_KEY: &str = "messages";
|
|
pub const ARCH_PROVIDER_HINT_HEADER: &str = "x-arch-llm-provider-hint";
|
|
pub const CHAT_COMPLETIONS_PATH: &str = "/v1/chat/completions";
|
|
pub const MESSAGES_PATH: &str = "/v1/messages";
|
|
pub const HEALTHZ_PATH: &str = "/healthz";
|
|
pub const X_ARCH_STATE_HEADER: &str = "x-arch-state";
|
|
pub const X_ARCH_API_RESPONSE: &str = "x-arch-api-response-message";
|
|
pub const X_ARCH_TOOL_CALL: &str = "x-arch-tool-call-message";
|
|
pub const X_ARCH_FC_MODEL_RESPONSE: &str = "x-arch-fc-model-response";
|
|
pub const ARCH_FC_MODEL_NAME: &str = "Arch-Function";
|
|
pub const REQUEST_ID_HEADER: &str = "x-request-id";
|
|
pub const TRACE_PARENT_HEADER: &str = "traceparent";
|
|
pub const ARCH_INTERNAL_CLUSTER_NAME: &str = "arch_internal";
|
|
pub const ARCH_UPSTREAM_HOST_HEADER: &str = "x-arch-upstream";
|
|
pub const ARCH_MODEL_PREFIX: &str = "Arch";
|
|
pub const HALLUCINATION_TEMPLATE: &str =
|
|
"It seems I'm missing some information. Could you provide the following details ";
|
|
pub const OTEL_COLLECTOR_HTTP: &str = "opentelemetry_collector_http";
|
|
pub const OTEL_POST_PATH: &str = "/v1/traces";
|
|
pub const LLM_ROUTE_HEADER: &str = "x-arch-llm-route";
|