apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-07-02 15:51:02 +02:00
Code Issues Projects Releases Packages Wiki Activity

Add support for Amazon Bedrock Converse and ConverseStream (#588)

Browse source 
* first commit to get Bedrock Converse API working. Next commit support for streaming and binary frames

* adding translation from BedrockBinaryFrameDecoder to AnthropicMessagesEvent

* Claude Code works with Amazon Bedrock

* added tests for openai streaming from bedrock

* PR comments fixed

* adding support for bedrock in docs as supported provider

* cargo fmt

* revertted to chatgpt models for claude code routing

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
Co-authored-by: Adil Hafeez <adil.hafeez@gmail.com>
This commit is contained in:
Salman Paracha 2025-10-22 11:31:21 -07:00 • committed by GitHub
parent ba826b1961
commit 9407ae6af7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
35 changed files with 7362 additions and 1493 deletions
Download patch file Download diff file Expand all files Collapse all files

25
crates/hermesllm/src/transforms/mod.rs Normal file
View file

@ -0,0 +1,25 @@
//! API transformation modules
//!
//! This module provides organized transformations between the two main LLM API formats:
//! - `/v1/chat/completions` (OpenAI format)
//! - `/v1/messages` (Anthropic format)
//!
//! Provider-specific transformations (Bedrock, Groq, etc.) are handled internally
//! by the gateway, but the external API surface remains these two standard formats.
//! The transformations are split into logical modules for maintainability.
pub mod lib;
pub mod request;
pub mod response;
// Re-export commonly used items for convenience
pub use lib::*;
pub use request::*;
pub use response::*;
// ============================================================================
// CONSTANTS
// ============================================================================
/// Default maximum tokens when converting from OpenAI to Anthropic and no max_tokens is specified
pub const DEFAULT_MAX_TOKENS: u32 = 4096;