vibe-action 0.0.4

Command router — execute shell commands and LLM prompts via simple YAML actions.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

//! LLM provider configuration for model inference.
//! Defines connection parameters and model settings for code analysis.

use serde::Deserialize;
use serde::Serialize;

/// Role of a cluster node by model size.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
#[serde(rename_all = "lowercase")]
pub enum ClusterRole {
    /// Small model for simple tasks (e.g., 3b).
    Small,
    /// Medium model for general tasks (e.g., 7-14b).
    Medium,
    /// Large model for complex tasks (e.g., 14b+).
    Large,
}

/// Configuration for a single LLM provider connection.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ClusterConfig {
    /// Provider run: "ollama", "deepseek", "qwen".
    pub provider: String,
    /// API endpoint URL.
    pub host: String,
    /// Model name to use for inference.
    pub model: String,
    /// Role of this node: small, medium, or large.
    #[serde(default)]
    pub role: Option<ClusterRole>,
    /// Request timeout in seconds.
    pub timeout_secs: u64,
    /// Temperature for generation (0.0-2.0, lower = more deterministic).
    pub temperature: f32,
    /// Seed for reproducible outputs.
    pub seed: u64,
    /// Context window size in tokens.
    pub num_ctx: usize,
    /// Maximum tokens to predict/generate.
    pub num_predict: usize,
    /// API key for cloud providers (not needed for Ollama).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub api_key: Option<String>,
    /// Number of parallel connections to this provider (default 1).
    pub parallel: usize,
}

impl Default for ClusterConfig {
    /// Creates default Ollama configuration.
    fn default() -> Self {
        Self {
            provider: "ollama".to_string(),
            host: "http://localhost:11434".to_string(),
            model: "qwen2.5-coder:14b-instruct".to_string(),
            role: Some(ClusterRole::Medium),
            timeout_secs: 60,
            temperature: 0.1,
            seed: 42,
            num_ctx: 4096,
            num_predict: 2048,
            api_key: None,
            parallel: 1,
        }
    }
}