Files
llmx/codex-rs/core/src/client_common.rs

85 lines
2.8 KiB
Rust
Raw Normal View History

feat: support the chat completions API in the Rust CLI (#862) This is a substantial PR to add support for the chat completions API, which in turn makes it possible to use non-OpenAI model providers (just like in the TypeScript CLI): * It moves a number of structs from `client.rs` to `client_common.rs` so they can be shared. * It introduces support for the chat completions API in `chat_completions.rs`. * It updates `ModelProviderInfo` so that `env_key` is `Option<String>` instead of `String` (for e.g., ollama) and adds a `wire_api` field * It updates `client.rs` to choose between `stream_responses()` and `stream_chat_completions()` based on the `wire_api` for the `ModelProviderInfo` * It updates the `exec` and TUI CLIs to no longer fail if the `OPENAI_API_KEY` environment variable is not set * It updates the TUI so that `EventMsg::Error` is displayed more prominently when it occurs, particularly now that it is important to alert users to the `CodexErr::EnvVar` variant. * `CodexErr::EnvVar` was updated to include an optional `instructions` field so we can preserve the behavior where we direct users to https://platform.openai.com if `OPENAI_API_KEY` is not set. * Cleaned up the "welcome message" in the TUI to ensure the model provider is displayed. * Updated the docs in `codex-rs/README.md`. To exercise the chat completions API from OpenAI models, I added the following to my `config.toml`: ```toml model = "gpt-4o" model_provider = "openai-chat-completions" [model_providers.openai-chat-completions] name = "OpenAI using Chat Completions" base_url = "https://api.openai.com/v1" env_key = "OPENAI_API_KEY" wire_api = "chat" ``` Though to test a non-OpenAI provider, I installed ollama with mistral locally on my Mac because ChatGPT said that would be a good match for my hardware: ```shell brew install ollama ollama serve ollama pull mistral ``` Then I added the following to my `~/.codex/config.toml`: ```toml model = "mistral" model_provider = "ollama" ``` Note this code could certainly use more test coverage, but I want to get this in so folks can start playing with it. For reference, I believe https://github.com/openai/codex/pull/247 was roughly the comparable PR on the TypeScript side.
2025-05-08 21:46:06 -07:00
use crate::error::Result;
use crate::models::ResponseItem;
use futures::Stream;
use serde::Serialize;
use std::collections::HashMap;
use std::pin::Pin;
use std::task::Context;
use std::task::Poll;
use tokio::sync::mpsc;
/// API request payload for a single model turn.
#[derive(Default, Debug, Clone)]
pub struct Prompt {
/// Conversation context input items.
pub input: Vec<ResponseItem>,
/// Optional previous response ID (when storage is enabled).
pub prev_id: Option<String>,
/// Optional initial instructions (only sent on first turn).
pub instructions: Option<String>,
/// Whether to store response on server side (disable_response_storage = !store).
pub store: bool,
/// Additional tools sourced from external MCP servers. Note each key is
/// the "fully qualified" tool name (i.e., prefixed with the server name),
/// which should be reported to the model in place of Tool::name.
pub extra_tools: HashMap<String, mcp_types::Tool>,
}
#[derive(Debug)]
pub enum ResponseEvent {
OutputItemDone(ResponseItem),
Completed { response_id: String },
}
#[derive(Debug, Serialize)]
pub(crate) struct Reasoning {
pub(crate) effort: &'static str,
#[serde(skip_serializing_if = "Option::is_none")]
pub(crate) summary: Option<Summary>,
}
/// A summary of the reasoning performed by the model. This can be useful for
/// debugging and understanding the model's reasoning process.
#[derive(Debug, Serialize)]
#[serde(rename_all = "lowercase")]
pub(crate) enum Summary {
Auto,
#[allow(dead_code)] // Will go away once this is configurable.
Concise,
#[allow(dead_code)] // Will go away once this is configurable.
Detailed,
feat: support the chat completions API in the Rust CLI (#862) This is a substantial PR to add support for the chat completions API, which in turn makes it possible to use non-OpenAI model providers (just like in the TypeScript CLI): * It moves a number of structs from `client.rs` to `client_common.rs` so they can be shared. * It introduces support for the chat completions API in `chat_completions.rs`. * It updates `ModelProviderInfo` so that `env_key` is `Option<String>` instead of `String` (for e.g., ollama) and adds a `wire_api` field * It updates `client.rs` to choose between `stream_responses()` and `stream_chat_completions()` based on the `wire_api` for the `ModelProviderInfo` * It updates the `exec` and TUI CLIs to no longer fail if the `OPENAI_API_KEY` environment variable is not set * It updates the TUI so that `EventMsg::Error` is displayed more prominently when it occurs, particularly now that it is important to alert users to the `CodexErr::EnvVar` variant. * `CodexErr::EnvVar` was updated to include an optional `instructions` field so we can preserve the behavior where we direct users to https://platform.openai.com if `OPENAI_API_KEY` is not set. * Cleaned up the "welcome message" in the TUI to ensure the model provider is displayed. * Updated the docs in `codex-rs/README.md`. To exercise the chat completions API from OpenAI models, I added the following to my `config.toml`: ```toml model = "gpt-4o" model_provider = "openai-chat-completions" [model_providers.openai-chat-completions] name = "OpenAI using Chat Completions" base_url = "https://api.openai.com/v1" env_key = "OPENAI_API_KEY" wire_api = "chat" ``` Though to test a non-OpenAI provider, I installed ollama with mistral locally on my Mac because ChatGPT said that would be a good match for my hardware: ```shell brew install ollama ollama serve ollama pull mistral ``` Then I added the following to my `~/.codex/config.toml`: ```toml model = "mistral" model_provider = "ollama" ``` Note this code could certainly use more test coverage, but I want to get this in so folks can start playing with it. For reference, I believe https://github.com/openai/codex/pull/247 was roughly the comparable PR on the TypeScript side.
2025-05-08 21:46:06 -07:00
}
#[derive(Debug, Serialize)]
pub(crate) struct Payload<'a> {
pub(crate) model: &'a str,
#[serde(skip_serializing_if = "Option::is_none")]
pub(crate) instructions: Option<&'a String>,
// TODO(mbolin): ResponseItem::Other should not be serialized. Currently,
// we code defensively to avoid this case, but perhaps we should use a
// separate enum for serialization.
pub(crate) input: &'a Vec<ResponseItem>,
pub(crate) tools: &'a [serde_json::Value],
pub(crate) tool_choice: &'static str,
pub(crate) parallel_tool_calls: bool,
pub(crate) reasoning: Option<Reasoning>,
#[serde(skip_serializing_if = "Option::is_none")]
pub(crate) previous_response_id: Option<String>,
/// true when using the Responses API.
pub(crate) store: bool,
pub(crate) stream: bool,
}
pub(crate) struct ResponseStream {
pub(crate) rx_event: mpsc::Receiver<Result<ResponseEvent>>,
}
impl Stream for ResponseStream {
type Item = Result<ResponseEvent>;
fn poll_next(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
self.rx_event.poll_recv(cx)
}
}