apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-08 15:22:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

adding support for claude code routing (#575)

Browse source 
* fixed for claude code routing. first commit

* removing redundant enum tags for cache_control

* making sure that claude code can run via the archgw cli

* fixing broken config

* adding a README.md and updated the cli to use more of our defined patterns for params

* fixed config.yaml

* minor fixes to make sure PR is clean. Ready to ship

* adding claude-sonnet-4-5 to the config

* fixes based on PR

* fixed alias for README

* fixed 400 error handling tests, now that we write temperature to 1.0 for GPT-5

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
This commit is contained in:
Salman Paracha 2025-09-29 19:23:08 -07:00 • committed by GitHub
parent 03c2cf6f0d
commit f00870dccb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 903 additions and 106 deletions
Download patch file Download diff file Expand all files Collapse all files

367
crates/hermesllm/src/apis/anthropic.rs
View file

File diff suppressed because one or more lines are too long

9
crates/hermesllm/src/apis/openai.rs
View file

@ -88,6 +88,7 @@ pub struct ChatCompletionsRequest {
pub prediction: Option<StaticContent>,
// pub reasoning_effect: Option<bool>, // GOOD FIRST ISSUE: Future support for reasoning effects
pub response_format: Option<Value>,
pub reasoning_effort: Option<String>, // e.g., "none", "low", "medium", "high"
// pub safety_identifier: Option<String>, // GOOD FIRST ISSUE: Future support for safety identifiers
pub seed: Option<i32>,
pub service_tier: Option<String>,
@ -116,6 +117,13 @@ impl ChatCompletionsRequest {
self.max_tokens = None;
}
}
pub fn fix_temperature_if_gpt5(&mut self) {
let model = self.model.as_str();
if model.starts_with("gpt-5") {
self.temperature = Some(1.0);
}
}
}
// ============================================================================
@ -598,6 +606,7 @@ impl TryFrom<&[u8]> for ChatCompletionsRequest {
let mut req: ChatCompletionsRequest = serde_json::from_slice(bytes).map_err(OpenAIStreamError::from)?;
// Use the centralized suppression logic
req.suppress_max_tokens_if_o3();
req.fix_temperature_if_gpt5();
Ok(req)
}
}