Phase 3: usage screen

GET /usage serves the numbers behind Claude Code's /usage, read with the
CLI's own stored OAuth credentials (nothing to configure). The endpoint
is undocumented, so parsing is defensive -- the generic limits[] array
becomes labeled window bars, unknown kinds surface under their raw name,
and any failure degrades to an 'unavailable' snapshot with the reason.
One UsageProvider per paid service behind a caching monitor that
enforces the >=180s minimum poll regardless of phone refreshes; no
background polling at all. ureq (rustls) does the outbound call, with
the process-level CryptoProvider now chosen explicitly in main -- ureq
brings ring while axum-server brings aws-lc-rs, and with both in the
graph rustls refuses to guess.

App: a Usage screen off the session list -- per-window bars colored by
utilization with relative reset times. Verified live: 74%/26%/16%
windows rendered against the real endpoint.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw

server/Cargo.lock

@@ -2,6 +2,12 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.5"
@@ -23,6 +29,7 @@ dependencies = [
  "if-addrs",
  "qrcode",
  "rand",
+ "rustls",
  "serde",
  "serde_json",
  "sha2",
@@ -34,6 +41,7 @@ dependencies = [
  "tower",
  "tracing",
  "tracing-subscriber",
+ "ureq",
 ]
 
 [[package]]
@@ -337,6 +345,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "crc32fast"
+version = "1.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8498c871161e1742aaa9d52551b2d6ebdd4c3d45a3be423e3728f33b955be550"
+dependencies = [
+ "cfg-if",
+]
+
 [[package]]
 name = "crypto-common"
 version = "0.2.2"
@@ -406,6 +423,16 @@ version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d45db016d36b838f563236e9193d0ee6ce38f3f68b6c94e914b4929c96bbb890"
 
+[[package]]
+name = "flate2"
+version = "1.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -713,6 +740,16 @@ version = "0.3.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
 
+[[package]]
+name = "miniz_oxide"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
+dependencies = [
+ "adler2",
+ "simd-adler32",
+]
+
 [[package]]
 name = "mio"
 version = "1.2.2"
@@ -878,7 +915,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0283386ce02abc0151e1761d08802dfe86c173b0b494af5cbc086574e453da06"
 dependencies = [
  "aws-lc-rs",
+ "log",
  "once_cell",
+ "ring",
  "rustls-pki-types",
  "rustls-webpki",
  "subtle",
@@ -1020,6 +1059,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "simd-adler32"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
+
 [[package]]
 name = "slab"
 version = "0.4.12"
@@ -1300,6 +1345,41 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
 
+[[package]]
+name = "ureq"
+version = "3.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "972d7902c8735f2695410b8aed7df6ed12a47394aa1c8d7af49f0497b731a94d"
+dependencies = [
+ "base64",
+ "flate2",
+ "log",
+ "percent-encoding",
+ "rustls",
+ "rustls-pki-types",
+ "ureq-proto",
+ "utf8-zero",
+ "webpki-roots",
+]
+
+[[package]]
+name = "ureq-proto"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da5f78b09e6941e1a0f2e30e695e4b120377b54d5e0aec11b594bb57b3971613"
+dependencies = [
+ "base64",
+ "http",
+ "httparse",
+ "log",
+]
+
+[[package]]
+name = "utf8-zero"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8c0a043c9540bae7c578c88f91dda8bd82e59ae27c21baca69c8b191aaf5a6e"
+
 [[package]]
 name = "utf8parse"
 version = "0.2.2"
@@ -1324,6 +1404,15 @@ version = "0.11.1+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
 
+[[package]]
+name = "webpki-roots"
+version = "1.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7dcd9d09a39985f5344844e66b0c530a33843579125f23e21e9f0f220850f22a"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "windows-link"
 version = "0.2.1"

server/Cargo.toml

@@ -30,6 +30,14 @@ qrcode = { version = "0.14", default-features = false }
 # The wg0-bound listener needs the interface's address; the stdlib has no
 # getifaddrs. This is the smallest crate that wraps just that.
 if-addrs = "0.15"
+# Outbound HTTPS for the usage endpoint. A small blocking client fits an
+# every-few-minutes poll better than pulling in reqwest's tower stack;
+# rustls-backed like the rest of the TLS here.
+ureq = "3"
+# Direct dependency only to pick the process-level CryptoProvider in main:
+# ureq pulls rustls-with-ring, axum-server rustls-with-aws-lc-rs, and with
+# both in the graph rustls refuses to auto-select one.
+rustls = "0.23"
 
 [dev-dependencies]
 tempfile = "3"

server/src/main.rs

@@ -17,6 +17,7 @@ mod auth;
 mod config;
 mod routes;
 mod session;
+mod usage;
 
 use std::net::{IpAddr, SocketAddr};
 use std::path::{Path, PathBuf};
@@ -119,6 +120,13 @@ fn print_enrollment(host: IpAddr, port: u16, token: &str) -> Result<()> {
 
 #[tokio::main]
 async fn main() -> Result<()> {
+    // Both rustls crypto providers are in the dependency graph (ureq
+    // brings ring, axum-server brings aws-lc-rs), so rustls refuses to
+    // pick one itself; choose before anything touches TLS.
+    rustls::crypto::aws_lc_rs::default_provider()
+        .install_default()
+        .expect("no other TLS crypto provider is installed before main");
+
     tracing_subscriber::fmt().with_env_filter("info").init();
     let args = Args::parse();
 
@@ -174,13 +182,21 @@ async fn main() -> Result<()> {
         .await
         .context("failed to load TLS cert/key")?;
 
+    let monitor = Arc::new(usage::UsageMonitor::new(vec![Box::new(usage::ClaudeUsage {
+        credentials_path: std::env::home_dir()
+            .unwrap_or_else(|| PathBuf::from("/"))
+            .join(".claude/.credentials.json"),
+    })]));
+
     // The bearer-token middleware wraps the entire router -- routes and
     // fallback alike -- here and only here, so a new route can't forget
     // auth. Zero unauthenticated endpoints.
-    let app = routes::router(Arc::clone(&manager)).layer(axum::middleware::from_fn_with_state(
-        Arc::clone(&manager),
-        auth::require_token,
-    ));
+    let app = routes::router(Arc::clone(&manager))
+        .merge(routes::usage_router(monitor))
+        .layer(axum::middleware::from_fn_with_state(
+            Arc::clone(&manager),
+            auth::require_token,
+        ));
 
     let addr = SocketAddr::new(bind_ip, args.port);
     tracing::info!("serving https://{addr}");

server/src/routes.rs

@@ -14,10 +14,10 @@
 //! POST   /sessions/{id}/attachments    multipart image upload -> {id}, referenced by /message
 //! GET    /sessions/{id}/files/{name}   images the session produced or was sent
 //! DELETE /sessions/{id}                kill process, delete transcript + files
+//! GET    /usage                        cached usage windows per provider
 //! ```
 //!
-//! Later phases add: `GET /usage`, `GET|PUT /hosts` and `/models` -- see
-//! PLAN.md's table.
+//! Later phases add: `GET|PUT /hosts` and `/models` -- see PLAN.md's table.
 //!
 //! Everything here works purely in the common event model; nothing may
 //! branch on the session kind (that's what drivers are for).
@@ -26,6 +26,8 @@ use std::convert::Infallible;
 use std::path::PathBuf;
 use std::sync::Arc;
 
+use anyhow::Context;
+
 use axum::Router;
 use axum::extract::{Path as UrlPath, Query, State};
 use axum::http::{HeaderMap, StatusCode};
@@ -69,6 +71,8 @@ enum ApiError {
     UnknownRoute,
     #[error("{0}")]
     BadRequest(String),
+    #[error(transparent)]
+    Internal(#[from] anyhow::Error),
 }
 
 impl IntoResponse for ApiError {
@@ -76,6 +80,12 @@ impl IntoResponse for ApiError {
         let status = match self {
             Self::UnknownSession(_) | Self::UnknownRoute => StatusCode::NOT_FOUND,
             Self::BadRequest(_) => StatusCode::BAD_REQUEST,
+            Self::Internal(err) => {
+                // The only variant whose real cause isn't safe to hand
+                // back verbatim, and the only one worth a log line.
+                tracing::error!("{err:#}");
+                return StatusCode::INTERNAL_SERVER_ERROR.into_response();
+            }
         };
         (status, self.to_string()).into_response()
     }
@@ -186,6 +196,22 @@ async fn interrupt(
     Ok(StatusCode::NO_CONTENT)
 }
 
+/// Separate router because its state is the usage monitor, not the
+/// session manager; merged (and auth-wrapped) with the rest in `main`.
+pub fn usage_router(monitor: Arc<crate::usage::UsageMonitor>) -> Router {
+    Router::new().route("/usage", get(usage)).with_state(monitor)
+}
+
+async fn usage(
+    State(monitor): State<Arc<crate::usage::UsageMonitor>>,
+) -> Result<axum::Json<Vec<crate::usage::UsageSnapshot>>, ApiError> {
+    // The fetch is blocking by design (see `usage`); off the workers.
+    let snapshots = tokio::task::spawn_blocking(move || monitor.snapshots())
+        .await
+        .context("usage fetch panicked")?;
+    Ok(axum::Json(snapshots))
+}
+
 #[derive(Deserialize)]
 struct ModelRequest {
     model: String,

server/src/usage.rs

@@ -0,0 +1,255 @@
+//! Usage-limit reporting -- the same numbers as Claude Code's `/usage`.
+//!
+//! Polls `https://api.anthropic.com/api/oauth/usage` with the OAuth access
+//! token from Claude Code's local credential store. The endpoint is
+//! undocumented and has changed before, so everything here is best-effort:
+//! every field is optional, and failure degrades to an "unavailable"
+//! snapshot with the reason, never an error that breaks the screen.
+//!
+//! Two rules learned from others hitting this endpoint (see PLAN.md's
+//! references): send `User-Agent: claude-code/<version>` (without it,
+//! requests land in an aggressively rate-limited bucket) and poll no more
+//! often than every 180 s. The cache below enforces the latter across any
+//! number of phone refreshes; there is no background poll at all -- the
+//! screen's fetch is the trigger, so no session activity means no traffic.
+//!
+//! One [`UsageProvider`] per paid service, so a second service later is a
+//! new impl behind the same snapshot shape, not a parallel screen.
+
+use std::path::PathBuf;
+use std::sync::Mutex;
+use std::time::{Duration, Instant};
+
+use serde::Serialize;
+use serde_json::Value;
+
+const USAGE_URL: &str = "https://api.anthropic.com/api/oauth/usage";
+const MIN_POLL_INTERVAL: Duration = Duration::from_secs(180);
+/// Matched to the CLI version the wire formats were pinned against.
+const USER_AGENT: &str = "claude-code/2.1.237";
+
+/// One rate-limit window, as the phone renders it: a labeled bar.
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageWindow {
+    pub label: String,
+    /// 0-100.
+    pub percent: f64,
+    /// ISO-8601, as the API sends it; absent for windows that never reset.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub resets_at: Option<String>,
+    /// Whether this window is currently the binding one.
+    pub active: bool,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageSnapshot {
+    pub provider: String,
+    pub available: bool,
+    pub windows: Vec<UsageWindow>,
+    /// Why `available` is false, written for the screen.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub error: Option<String>,
+    /// Epoch seconds the numbers were fetched (they can be up to the poll
+    /// interval old).
+    pub fetched_at: f64,
+}
+
+pub trait UsageProvider: Send + Sync {
+    fn name(&self) -> &'static str;
+    /// Blocking -- call off the async workers.
+    fn fetch(&self) -> UsageSnapshot;
+}
+
+/// Reads the numbers behind Claude Code's `/usage` using its own stored
+/// credentials -- nothing to configure, and it reports on exactly the
+/// account the local CLI runs as.
+pub struct ClaudeUsage {
+    pub credentials_path: PathBuf,
+}
+
+impl ClaudeUsage {
+    fn unavailable(&self, error: String) -> UsageSnapshot {
+        UsageSnapshot {
+            provider: self.name().to_string(),
+            available: false,
+            windows: Vec::new(),
+            error: Some(error),
+            fetched_at: crate::session::now(),
+        }
+    }
+
+    fn access_token(&self) -> Result<String, String> {
+        let text = std::fs::read_to_string(&self.credentials_path).map_err(|err| {
+            format!(
+                "couldn't read {} ({err}) -- is Claude Code logged in on this machine?",
+                self.credentials_path.display()
+            )
+        })?;
+        serde_json::from_str::<Value>(&text)
+            .ok()
+            .and_then(|creds| {
+                creds.get("claudeAiOauth")?.get("accessToken")?.as_str().map(String::from)
+            })
+            .ok_or_else(|| {
+                "credential file has no claudeAiOauth.accessToken -- log in with `claude` once"
+                    .to_string()
+            })
+    }
+}
+
+impl UsageProvider for ClaudeUsage {
+    fn name(&self) -> &'static str {
+        "claude"
+    }
+
+    fn fetch(&self) -> UsageSnapshot {
+        let token = match self.access_token() {
+            Ok(token) => token,
+            Err(error) => return self.unavailable(error),
+        };
+        let text = match ureq::get(USAGE_URL)
+            .header("Authorization", &format!("Bearer {token}"))
+            .header("anthropic-beta", "oauth-2025-04-20")
+            .header("User-Agent", USER_AGENT)
+            .call()
+            .and_then(|mut response| response.body_mut().read_to_string())
+        {
+            Ok(text) => text,
+            Err(err) => {
+                // The error string can embed the URL but never the token.
+                return self.unavailable(format!("usage endpoint unreachable: {err}"));
+            }
+        };
+        let body: Value = match serde_json::from_str(&text) {
+            Ok(body) => body,
+            Err(err) => return self.unavailable(format!("usage endpoint sent non-JSON: {err}")),
+        };
+        UsageSnapshot {
+            provider: self.name().to_string(),
+            available: true,
+            windows: parse_windows(&body),
+            error: None,
+            fetched_at: crate::session::now(),
+        }
+    }
+}
+
+/// Pulls the `limits` array apart, defensively: entries with no percent
+/// are skipped, unknown kinds keep their raw name as the label rather
+/// than being dropped -- a new window appearing should show up, not
+/// vanish.
+fn parse_windows(body: &Value) -> Vec<UsageWindow> {
+    let Some(limits) = body.get("limits").and_then(Value::as_array) else {
+        return Vec::new();
+    };
+    limits
+        .iter()
+        .filter_map(|limit| {
+            let percent = limit.get("percent")?.as_f64()?;
+            let kind = limit.get("kind").and_then(Value::as_str).unwrap_or("unknown");
+            let scope_model = limit
+                .get("scope")
+                .and_then(|scope| scope.get("model"))
+                .and_then(|model| model.get("display_name"))
+                .and_then(Value::as_str);
+            let label = match (kind, scope_model) {
+                ("session", _) => "5-hour window".to_string(),
+                ("weekly_all", _) => "Weekly (all models)".to_string(),
+                ("weekly_scoped", Some(model)) => format!("Weekly ({model})"),
+                (other, Some(model)) => format!("{other} ({model})"),
+                (other, None) => other.to_string(),
+            };
+            Some(UsageWindow {
+                label,
+                percent,
+                resets_at: limit
+                    .get("resets_at")
+                    .and_then(Value::as_str)
+                    .map(String::from),
+                active: limit.get("is_active").and_then(Value::as_bool).unwrap_or(false),
+            })
+        })
+        .collect()
+}
+
+/// The cache in front of whatever providers exist: at most one real fetch
+/// per provider per [`MIN_POLL_INTERVAL`], no matter how often the phone
+/// asks.
+pub struct UsageMonitor {
+    providers: Vec<Box<dyn UsageProvider>>,
+    cache: Mutex<Vec<(Instant, UsageSnapshot)>>,
+}
+
+impl UsageMonitor {
+    pub fn new(providers: Vec<Box<dyn UsageProvider>>) -> Self {
+        Self { providers, cache: Mutex::new(Vec::new()) }
+    }
+
+    /// Blocking -- call via `spawn_blocking`.
+    pub fn snapshots(&self) -> Vec<UsageSnapshot> {
+        let mut cache = self.cache.lock().unwrap();
+        self.providers
+            .iter()
+            .enumerate()
+            .map(|(i, provider)| {
+                if let Some((fetched, snapshot)) = cache.get(i)
+                    && fetched.elapsed() < MIN_POLL_INTERVAL
+                {
+                    return snapshot.clone();
+                }
+                let snapshot = provider.fetch();
+                match cache.get_mut(i) {
+                    Some(slot) => *slot = (Instant::now(), snapshot.clone()),
+                    None => cache.push((Instant::now(), snapshot.clone())),
+                }
+                snapshot
+            })
+            .collect()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn parses_the_limits_array_defensively() {
+        // Trimmed from a live 2026-08-24 response.
+        let body: Value = serde_json::from_str(
+            r#"{"limits":[
+                {"kind":"session","group":"session","percent":70,"severity":"normal","resets_at":"2026-08-25T04:29:59+00:00","scope":null,"is_active":true},
+                {"kind":"weekly_all","group":"weekly","percent":25,"resets_at":"2026-08-28T21:59:59+00:00","is_active":false},
+                {"kind":"weekly_scoped","percent":15,"resets_at":"2026-08-28T21:59:59+00:00","scope":{"model":{"id":null,"display_name":"Fable"}},"is_active":false},
+                {"kind":"mystery_new_window","percent":5},
+                {"kind":"broken_entry_without_percent"}
+            ]}"#,
+        )
+        .expect("json");
+        let windows = parse_windows(&body);
+        assert_eq!(windows.len(), 4);
+        assert_eq!(windows[0].label, "5-hour window");
+        assert_eq!(windows[0].percent, 70.0);
+        assert!(windows[0].active);
+        assert_eq!(windows[1].label, "Weekly (all models)");
+        assert_eq!(windows[2].label, "Weekly (Fable)");
+        // Unknown kinds surface under their raw name instead of vanishing.
+        assert_eq!(windows[3].label, "mystery_new_window");
+        assert_eq!(windows[3].resets_at, None);
+    }
+
+    #[test]
+    fn missing_credentials_degrade_to_unavailable() {
+        let provider = ClaudeUsage { credentials_path: PathBuf::from("/nonexistent/creds.json") };
+        let snapshot = provider.fetch();
+        assert!(!snapshot.available);
+        assert!(snapshot.error.expect("reason").contains("logged in"));
+    }
+
+    #[test]
+    fn an_empty_or_alien_body_yields_no_windows() {
+        assert!(parse_windows(&serde_json::json!({})).is_empty());
+        assert!(parse_windows(&serde_json::json!({"limits": "what"})).is_empty());
+    }
+}