collet 0.1.1

Relentless agentic coding orchestrator with zero-drop agent loops
Documentation 
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160

use super::content::Content;
use serde::{Deserialize, Serialize};
use std::sync::Arc;

/// OpenAI-compatible chat completion request.
#[derive(Debug, Serialize)]
pub struct ChatRequest {
    pub model: String,
    pub messages: Vec<Message>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tools: Option<Arc<Vec<serde_json::Value>>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tool_choice: Option<String>,
    pub max_tokens: u32,
    pub stream: bool,
    /// Sampling temperature. Omitted when `None`.
    /// Silently dropped by the caller for reasoning models.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub temperature: Option<f32>,
    /// Thinking/reasoning budget tokens. Omitted when `None`.
    /// Only included by the caller when the model profile has supports_reasoning = true.
    /// Takes priority over `reasoning_effort` when both are set.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub thinking_budget_tokens: Option<u32>,
    /// Reasoning effort level (low | medium | high). Omitted when `None`.
    /// Ignored if `thinking_budget_tokens` is set.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub reasoning_effort: Option<String>,
}

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Message {
    pub role: String,
    pub content: Option<Content>,
    /// Reasoning/thinking content returned by reasoning models.
    /// Present in non-streaming responses when the model uses chain-of-thought.
    /// Content may be null while reasoning_content holds the actual output.
    #[serde(default, skip_serializing_if = "Option::is_none")]
    pub reasoning_content: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tool_calls: Option<Vec<ToolCall>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tool_call_id: Option<String>,
}

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ToolCall {
    pub id: String,
    #[serde(rename = "type")]
    pub call_type: String,
    pub function: FunctionCall,
}

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct FunctionCall {
    pub name: String,
    pub arguments: String,
}

/// Tool request structs — deserialized only in debug builds by
/// `tools::registry::all_tool_definitions` for schema validation.
#[cfg(debug_assertions)]
#[derive(Debug, Serialize, Deserialize)]
pub struct ToolDefinition {
    #[serde(rename = "type")]
    pub tool_type: String,
    pub function: FunctionDefinition,
}

#[cfg(debug_assertions)]
#[derive(Debug, Serialize, Deserialize)]
pub struct FunctionDefinition {
    pub name: String,
    pub description: String,
    pub parameters: serde_json::Value,
}

/// OpenAI-compatible chat completion response.
#[derive(Debug, Deserialize)]
pub struct ChatResponse {
    pub id: String,
    pub choices: Vec<Choice>,
    #[serde(default)]
    pub usage: Option<Usage>,
}

#[derive(Debug, Deserialize)]
pub struct Choice {
    pub index: u32,
    pub message: Message,
    pub finish_reason: Option<String>,
}

#[derive(Debug, Deserialize)]
pub struct Usage {
    pub prompt_tokens: u32,
    pub completion_tokens: u32,
    pub total_tokens: u32,
    /// Cached prompt tokens (OpenAI: prompt_tokens_details.cached_tokens,
    /// some providers: top-level cached_tokens field).
    #[serde(default)]
    pub cached_tokens: u32,
    /// Nested details object used by OpenAI-compatible APIs.
    #[serde(default)]
    pub prompt_tokens_details: Option<PromptTokensDetails>,
}

/// OpenAI `usage.prompt_tokens_details` sub-object.
#[derive(Debug, Deserialize, Default)]
pub struct PromptTokensDetails {
    #[serde(default)]
    pub cached_tokens: u32,
}

/// Streaming chunk format (SSE).
#[derive(Debug, Deserialize)]
pub struct ChatChunk {
    pub id: String,
    pub choices: Vec<ChunkChoice>,
    /// Usage is included in the final chunk by some providers.
    #[serde(default)]
    pub usage: Option<Usage>,
}

#[derive(Debug, Deserialize)]
pub struct ChunkChoice {
    pub index: u32,
    pub delta: Delta,
    pub finish_reason: Option<String>,
}

#[derive(Debug, Deserialize)]
pub struct Delta {
    #[serde(default)]
    pub role: Option<String>,
    #[serde(default)]
    pub content: Option<Content>,
    /// Reasoning/thinking content (OpenAI o-series and compatible providers).
    #[serde(default)]
    pub reasoning_content: Option<String>,
    #[serde(default)]
    pub tool_calls: Option<Vec<DeltaToolCall>>,
}

#[derive(Debug, Deserialize)]
pub struct DeltaToolCall {
    pub index: u32,
    #[serde(default)]
    pub id: Option<String>,
    #[serde(default)]
    pub function: Option<DeltaFunction>,
}

#[derive(Debug, Deserialize)]
pub struct DeltaFunction {
    #[serde(default)]
    pub name: Option<String>,
    #[serde(default)]
    pub arguments: Option<String>,
}