codewhale-tui 0.9.3

Terminal UI for open-source and open-weight coding models
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

//! Recursive Language Model (RLM) loop — paper-spec Algorithm 1.
//!
//! Implements Zhang, Kraska & Khattab (arXiv:2512.24601, §2 Algorithm 1):
//!
//! ```text
//! state ← InitREPL(prompt=P)
//! state ← AddFunction(state, sub_RLM)
//! hist ← [Metadata(state)]
//! while True:
//!     code ← LLM(hist)
//!     (state, stdout) ← REPL(state, code)
//!     hist ← hist ∥ code ∥ Metadata(stdout)
//!     if state[Final] is set:
//!         return state[Final]
//! ```
//!
//! Invariants:
//! - `P` is held only as a REPL variable (`context` / `ctx`); never
//!   appears in the root LLM's window.
//! - The root LLM receives small metadata messages — length, preview,
//!   helper list, prior-round summary.
//! - Code rounds and sub-LLM calls travel over a single stdin/stdout
//!   pipe to a long-lived Python subprocess. No HTTP sidecar.

use crate::models::Usage;

pub mod bridge;
pub mod prompt;
pub mod session;
pub mod turn;

pub use bridge::RlmBridge;
pub use prompt::rlm_system_prompt;
pub use turn::{RlmTermination, RlmTurnResult, run_rlm_turn, run_rlm_turn_with_root};

fn add_usage_with_prompt_cache(total: &mut Usage, delta: &Usage) {
    total.input_tokens = total.input_tokens.saturating_add(delta.input_tokens);
    total.output_tokens = total.output_tokens.saturating_add(delta.output_tokens);
    total.prompt_cache_hit_tokens =
        add_optional_usage(total.prompt_cache_hit_tokens, delta.prompt_cache_hit_tokens);
    total.prompt_cache_miss_tokens = add_optional_usage(
        total.prompt_cache_miss_tokens,
        delta.prompt_cache_miss_tokens,
    );
    total.prompt_cache_write_tokens = add_optional_usage(
        total.prompt_cache_write_tokens,
        delta.prompt_cache_write_tokens,
    );
    total.reasoning_tokens = add_optional_usage(total.reasoning_tokens, delta.reasoning_tokens);
    total.reasoning_replay_tokens =
        add_optional_usage(total.reasoning_replay_tokens, delta.reasoning_replay_tokens);
    if let Some(delta_server) = delta.server_tool_use.as_ref() {
        let total_server = total.server_tool_use.get_or_insert_default();
        total_server.code_execution_requests = add_optional_usage(
            total_server.code_execution_requests,
            delta_server.code_execution_requests,
        );
        total_server.tool_search_requests = add_optional_usage(
            total_server.tool_search_requests,
            delta_server.tool_search_requests,
        );
    }
}

fn add_optional_usage(total: Option<u32>, delta: Option<u32>) -> Option<u32> {
    match (total, delta) {
        (Some(total), Some(delta)) => Some(total.saturating_add(delta)),
        (None, Some(delta)) => Some(delta),
        (Some(total), None) => Some(total),
        (None, None) => None,
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn add_usage_with_prompt_cache_preserves_cache_counts() {
        let mut total = Usage {
            input_tokens: 100,
            output_tokens: 10,
            prompt_cache_hit_tokens: Some(80),
            prompt_cache_miss_tokens: Some(20),
            ..Usage::default()
        };
        let delta = Usage {
            input_tokens: 50,
            output_tokens: 5,
            prompt_cache_hit_tokens: Some(30),
            prompt_cache_miss_tokens: Some(20),
            reasoning_tokens: Some(4),
            reasoning_replay_tokens: Some(3),
            server_tool_use: Some(crate::models::ServerToolUsage {
                code_execution_requests: Some(2),
                tool_search_requests: Some(1),
            }),
            ..Usage::default()
        };

        add_usage_with_prompt_cache(&mut total, &delta);

        assert_eq!(total.input_tokens, 150);
        assert_eq!(total.output_tokens, 15);
        assert_eq!(total.prompt_cache_hit_tokens, Some(110));
        assert_eq!(total.prompt_cache_miss_tokens, Some(40));
        assert_eq!(total.reasoning_tokens, Some(4));
        assert_eq!(total.reasoning_replay_tokens, Some(3));
        assert_eq!(
            total.server_tool_use,
            Some(crate::models::ServerToolUsage {
                code_execution_requests: Some(2),
                tool_search_requests: Some(1),
            })
        );
    }
}