From 41debc4f60404adafa911b05ff5eafc39231f1c8 Mon Sep 17 00:00:00 2001
From: Brummel <mould@mycelium.de>
Date: Mon, 18 May 2026 18:31:35 +0200
Subject: [PATCH] feat: CLI suggest/eval/index; Mode C baseline runnable

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 src/bin/alpha_id.rs | 108 +++++++++++++++++++++++++++++++++++++++++++-
 tests/cli_tests.rs  |  14 ++++++
 2 files changed, 120 insertions(+), 2 deletions(-)
 create mode 100644 tests/cli_tests.rs

diff --git a/src/bin/alpha_id.rs b/src/bin/alpha_id.rs
index 9738ab8..2e98150 100644
--- a/src/bin/alpha_id.rs
+++ b/src/bin/alpha_id.rs
@@ -1,3 +1,107 @@
-fn main() {
-    println!("alpha-id CLI — see `alpha-id --help`");
+use alpha_id::eval::{inject_errors, recall_at_k};
+use alpha_id::model::{Config, Filter, Mode};
+use alpha_id::pipeline::Pipeline;
+use clap::{Parser, Subcommand};
+use std::io::Read;
+
+#[derive(Parser)]
+#[command(name = "alpha-id")]
+struct Cli {
+    #[arg(long, default_value = "config/default.toml", global = true)]
+    config: String,
+    #[command(subcommand)]
+    cmd: Cmd,
+}
+
+#[derive(Subcommand)]
+enum Cmd {
+    /// Build indexes (lexical now; embeddings added in Phase A)
+    Index { #[arg(long)] sample: Option<usize>, #[arg(long)] full: bool, #[arg(long)] confirm: bool },
+    /// Suggest ICD codes for a dictation (FILE or - for stdin)
+    Suggest {
+        input: String,
+        #[arg(long, default_value = "c")] mode: String,
+        #[arg(long, default_value_t = 10)] top: usize,
+        #[arg(long)] billable_only: bool,
+        #[arg(long)] valid_only: bool,
+        #[arg(long)] exclude_exotic: bool,
+        #[arg(long)] chapters: Option<String>,
+        #[arg(long)] json: bool,
+    },
+    /// Run the eval harness
+    Eval {
+        #[arg(long, default_value = "c")] mode: String,
+        #[arg(long, default_value_t = 200)] cases: usize,
+        #[arg(long, default_value_t = 42)] seed: u64,
+    },
+}
+
+fn read_input(arg: &str) -> String {
+    if let Ok(v) = std::env::var("ALPHA_ID_STDIN") { return v; }
+    if arg == "-" {
+        let mut s = String::new();
+        std::io::stdin().read_to_string(&mut s).ok();
+        s
+    } else {
+        std::fs::read_to_string(arg).unwrap_or_default()
+    }
+}
+
+fn main() {
+    let cli = Cli::parse();
+    let cfg = Config::load(&cli.config).expect("config");
+    match cli.cmd {
+        Cmd::Index { sample, full, confirm } => {
+            let p = Pipeline::load(&cfg).expect("load");
+            eprintln!("Loaded {} entries, {} ICD metas. (sample={:?} full={} confirm={})",
+                p.entries.len(), p.meta.len(), sample, full, confirm);
+        }
+        Cmd::Suggest { input, mode, top, billable_only, valid_only, exclude_exotic, chapters, json } => {
+            let p = Pipeline::load(&cfg).expect("load");
+            let m: Mode = mode.parse().expect("mode");
+            let filter = Filter {
+                billable_only, valid_only, exclude_exotic,
+                chapters: chapters.map(|c| c.split(',').map(|s| s.trim().to_string()).collect()),
+            };
+            let text = read_input(&input);
+            let res = p.suggest(&text, m, &filter, top);
+            if json {
+                println!("{}", serde_json::to_string_pretty(&res).unwrap());
+            } else {
+                for s in &res.suggestions {
+                    println!("{:<8} {:>5.3}  {}", s.icd_code, s.score, s.description);
+                }
+                eprintln!("[{} segments, mode {}, {} ms, degraded={}]",
+                    res.diagnostics.segment_count, res.diagnostics.mode,
+                    res.diagnostics.millis, res.diagnostics.degraded);
+            }
+        }
+        Cmd::Eval { mode, cases, seed } => {
+            let p = Pipeline::load(&cfg).expect("load");
+            let m: Mode = mode.parse().expect("mode");
+            let mut sum = 0.0;
+            let mut billable_sum = 0.0;
+            let mut billable_n: f64 = 0.0;
+            let billable: Vec<_> = p.entries.iter().enumerate()
+                .filter(|(_, e)| e.valid)
+                .filter(|(_, e)| {
+                    alpha_id::corpus::primary_code(e)
+                        .and_then(|c| p.meta.get(c))
+                        .map(|mt| mt.para295 == "P").unwrap_or(false)
+                })
+                .take(cases).collect();
+            for (k, (_, e)) in billable.iter().enumerate() {
+                let code = alpha_id::corpus::primary_code(e).unwrap().to_string();
+                let noisy = inject_errors(&e.text, 0.15, seed.wrapping_add(k as u64));
+                let res = p.suggest(&noisy, m, &Filter::default(), 10);
+                let preds: Vec<String> = res.suggestions.iter().map(|s| s.icd_code.clone()).collect();
+                sum += recall_at_k(&preds, &code, 10);
+                billable_sum += recall_at_k(&preds, &code, 10);
+                billable_n += 1.0;
+            }
+            let n = billable.len().max(1) as f64;
+            println!("mode={} cases={} Recall@10={:.3} BillableRecall@10={:.3}",
+                mode, billable.len(), sum / n, billable_sum / billable_n.max(1.0));
+        }
+    }
 }
diff --git a/tests/cli_tests.rs b/tests/cli_tests.rs
new file mode 100644
index 0000000..f479763
--- /dev/null
+++ b/tests/cli_tests.rs
@@ -0,0 +1,14 @@
+use std::process::Command;
+
+#[test]
+fn cli_suggest_outputs_json_with_codes() {
+    let out = Command::new(env!("CARGO_BIN_EXE_alpha-id"))
+        .args(["suggest", "--mode", "c", "--json", "-"])
+        .arg("--config").arg("config/default.toml")
+        .env("ALPHA_ID_STDIN", "Diabetes mellitus Typ 2")
+        .output().unwrap();
+    assert!(out.status.success(), "stderr: {}", String::from_utf8_lossy(&out.stderr));
+    let s = String::from_utf8_lossy(&out.stdout);
+    assert!(s.contains("\"icd_code\""));
+    assert!(s.contains("E11"));
+}