1 files changed, 286 insertions, 0 deletions
diff --git a/src/core/metrics/cache-timer.ts b/src/core/metrics/cache-timer.ts
new file mode 100644
index 0000000..3d7270d
--- /dev/null
+++ b/src/core/metrics/cache-timer.ts
@@ -0,0 +1,286 @@
+import type { AgentEvent } from "@dispatch/wire";
+import type { MetricsRow } from "./types";
+
+/**
+ * Pure core for the **cache timer** — how long the prompt cache has sat idle
+ * between model requests. Anthropic's prompt cache (as used by the Claude Code
+ * subscription) expires 5 minutes after its last hit, so the gaps BETWEEN
+ * requests decide whether the next request reads from cache:
+ *
+ * - **step gap**: a step (one LLM round-trip) finished and its tools are
+ *   executing. Starts at `step-complete`; stops when the step's last tool
+ *   result arrives (the next request fires right after) or, failing that, when
+ *   anything from the next step shows up. Its final value is **stamped** on
+ *   that step (keyed by `stepId`).
+ * - **turn gap**: the turn ended (`done` / `error`) and the conversation is
+ *   waiting on the user. Stops when a new message is sent (locally, or a
+ *   `user-message` / `turn-start` from another client) and is stamped on that
+ *   turn (keyed by `turnId`).
+ *
+ * At most ONE gap runs at a time (`running`). Zero DOM, zero clock: every fold
+ * takes the current time as an argument.
+ */
+
+/** Prompt-cache time-to-live: 5 minutes (drives the badge colour). */
+export const CACHE_TTL_MS = 5 * 60 * 1000;
+
+/** The timer counts up to this, then reads "10+ min". */
+export const CACHE_TIMER_MAX_MS = 10 * 60 * 1000;
+
+/** Within this much of the TTL the timer warns (colour only). */
+const WARN_AT_MS = CACHE_TTL_MS - 60 * 1000;
+
+/** A step gap in progress: the step's tools are executing. */
+export interface RunningStepGap {
+  readonly kind: "step";
+  readonly turnId: string;
+  readonly stepId: string;
+  /** Epoch ms the step completed. */
+  readonly startedAt: number;
+  /** How many tool calls the step made (`0` → nothing to show; never stamped). */
+  readonly toolCount: number;
+  /** Tool calls still awaiting their result. */
+  readonly pending: ReadonlySet<string>;
+  /** Longest backend-reported tool `durationMs` seen so far for this step. */
+  readonly maxToolMs: number;
+}
+
+/** A turn gap in progress: the turn ended and nothing has been sent since. */
+export interface RunningTurnGap {
+  readonly kind: "turn";
+  /**
+   * The turn that ended, or `null` when seeded from the backend's
+   * `lastActivityAt` after a reload (no live `done` seen) — then it belongs to
+   * the most recent turn, resolved positionally / via `lastTurnId` on stop.
+   */
+  readonly turnId: string | null;
+  /** Epoch ms the turn ended. */
+  readonly startedAt: number;
+}
+
+export type RunningGap = RunningStepGap | RunningTurnGap;
+
+export interface CacheTimerState {
+  readonly running: RunningGap | null;
+  /** Stamped step gaps: `stepId` → elapsed ms. */
+  readonly stepStamps: ReadonlyMap<string, number>;
+  /** Stamped turn gaps: `turnId` → elapsed ms. */
+  readonly turnStamps: ReadonlyMap<string, number>;
+  /** Tool calls seen per step in the CURRENT turn (`stepId` → call ids). */
+  readonly calls: ReadonlyMap<string, ReadonlySet<string>>;
+  /** Tool results seen per step in the CURRENT turn (`stepId` → call ids). */
+  readonly results: ReadonlyMap<string, ReadonlySet<string>>;
+  /** Longest tool `durationMs` per step in the CURRENT turn. */
+  readonly toolMs: ReadonlyMap<string, number>;
+}
+
+export function initialCacheTimerState(): CacheTimerState {
+  return {
+    running: null,
+    stepStamps: new Map(),
+    turnStamps: new Map(),
+    calls: new Map(),
+    results: new Map(),
+    toolMs: new Map(),
+  };
+}
+
+function addTo(
+  map: ReadonlyMap<string, ReadonlySet<string>>,
+  key: string,
+  value: string,
+): ReadonlyMap<string, ReadonlySet<string>> {
+  const next = new Map(map);
+  next.set(key, new Set([...(map.get(key) ?? []), value]));
+  return next;
+}
+
+function withEntry(map: ReadonlyMap<string, number>, key: string, value: number) {
+  const next = new Map(map);
+  next.set(key, value);
+  return next;
+}
+
+/**
+ * Stop the running STEP gap (if any). A step that made tool calls is stamped
+ * with `max(wall-clock elapsed, longest backend tool duration)` — the backend
+ * figure keeps a late-join replay (whole step delivered in one burst, ~0
+ * elapsed) honest. A step with no tool calls is discarded.
+ */
+function stopStep(state: CacheTimerState, now: number): CacheTimerState {
+  const r = state.running;
+  if (r === null || r.kind !== "step") return state;
+  if (r.toolCount === 0) return { ...state, running: null };
+  const elapsed = Math.max(0, now - r.startedAt, r.maxToolMs);
+  return { ...state, running: null, stepStamps: withEntry(state.stepStamps, r.stepId, elapsed) };
+}
+
+/**
+ * Stop the running TURN gap (if any) and stamp it on its turn. A seeded gap
+ * (`turnId === null`) is stamped on `lastTurnId()` — the most recent turn's
+ * id — or dropped when that is unknown.
+ */
+export function stopTurnGap(
+  state: CacheTimerState,
+  now: number,
+  lastTurnId: () => string | undefined,
+): CacheTimerState {
+  const r = state.running;
+  if (r === null || r.kind !== "turn") return state;
+  const turnId = r.turnId ?? lastTurnId();
+  if (turnId === undefined) return { ...state, running: null };
+  const elapsed = Math.max(0, now - r.startedAt);
+  return { ...state, running: null, turnStamps: withEntry(state.turnStamps, turnId, elapsed) };
+}
+
+/** A turn ended: close any step gap, forget the turn's tool bookkeeping, start the turn gap. */
+function endTurn(state: CacheTimerState, turnId: string, now: number): CacheTimerState {
+  const s = stopStep(state, now);
+  return {
+    ...s,
+    running: { kind: "turn", turnId, startedAt: now },
+    calls: new Map(),
+    results: new Map(),
+    toolMs: new Map(),
+  };
+}
+
+/**
+ * Fold one live event into the cache-timer state at time `now`. `lastTurnId`
+ * resolves a seeded turn gap's turn when a new turn starts (see
+ * `stopTurnGap`); it is only called in that case.
+ */
+export function foldCacheTimerEvent(
+  state: CacheTimerState,
+  event: AgentEvent,
+  now: number,
+  lastTurnId: () => string | undefined,
+): CacheTimerState {
+  const r = state.running;
+  switch (event.type) {
+    case "user-message":
+    case "turn-start":
+      // A new turn is starting — the user (here or elsewhere) sent a message.
+      return stopTurnGap(state, now, lastTurnId);
+
+    case "tool-call": {
+      // A call from a DIFFERENT step means the next step is already streaming.
+      const s = r?.kind === "step" && r.stepId !== event.stepId ? stopStep(state, now) : state;
+      return { ...s, calls: addTo(s.calls, event.stepId, event.toolCallId) };
+    }
+
+    case "tool-result": {
+      const results = addTo(state.results, event.stepId, event.toolCallId);
+      const dur = event.durationMs ?? 0;
+      const toolMs =
+        dur > (state.toolMs.get(event.stepId) ?? 0)
+          ? withEntry(state.toolMs, event.stepId, dur)
+          : state.toolMs;
+      let s: CacheTimerState = { ...state, results, toolMs };
+      if (r?.kind === "step" && r.stepId === event.stepId) {
+        const pending = new Set(r.pending);
+        pending.delete(event.toolCallId);
+        s = { ...s, running: { ...r, pending, maxToolMs: Math.max(r.maxToolMs, dur) } };
+        // Every tool of the step has returned → the next request fires now.
+        if (pending.size === 0) s = stopStep(s, now);
+      }
+      return s;
+    }
+
+    case "step-complete": {
+      const s = stopStep(stopTurnGap(state, now, lastTurnId), now);
+      const calls = s.calls.get(event.stepId) ?? new Set<string>();
+      const done = s.results.get(event.stepId) ?? new Set<string>();
+      const pending = new Set([...calls].filter((id) => !done.has(id)));
+      return {
+        ...s,
+        running: {
+          kind: "step",
+          turnId: event.turnId,
+          stepId: event.stepId,
+          startedAt: now,
+          toolCount: calls.size,
+          pending,
+          maxToolMs: s.toolMs.get(event.stepId) ?? 0,
+        },
+      };
+    }
+
+    case "text-delta":
+    case "reasoning-delta":
+    case "reasoning-end":
+    case "provider-retry":
+      // Output (or a retry) from the next request: the gap is over.
+      return r?.kind === "step" ? stopStep(state, now) : state;
+
+    case "usage":
+      return r?.kind === "step" && event.stepId !== undefined && event.stepId !== r.stepId
+        ? stopStep(state, now)
+        : state;
+
+    case "done":
+    case "error":
+      return endTurn(state, event.turnId, now);
+
+    default:
+      return state;
+  }
+}
+
+/**
+ * Seed a turn gap from an authoritative "last activity" timestamp (the
+ * backend's `lastActivityAt`, for a conversation that is idle — e.g. after a
+ * reload, when no live `done` was seen). Never overrides a running step gap;
+ * a running turn gap keeps the LATER start. Non-finite input is ignored.
+ */
+export function seedTurnGap(state: CacheTimerState, at: number): CacheTimerState {
+  if (!Number.isFinite(at)) return state;
+  const r = state.running;
+  if (r === null) return { ...state, running: { kind: "turn", turnId: null, startedAt: at } };
+  if (r.kind === "turn" && at > r.startedAt) return { ...state, running: { ...r, startedAt: at } };
+  return state;
+}
+
+// ── View ──────────────────────────────────────────────────────────────────────
+
+/** Formatted cache-timer view: label + colour severity + capped flag. */
+export interface CacheTimerView {
+  /** `"m:ss"` up to 10 minutes, then `"10+ min"`. */
+  readonly label: string;
+  /** Colour by the 5-minute cache TTL (maps to DaisyUI `badge-{level}`). */
+  readonly level: "success" | "warning" | "error";
+  /** Whether the 10-minute display cap was reached (a live timer may stop ticking). */
+  readonly capped: boolean;
+}
+
+/**
+ * Build the view for `elapsedMs`. Colour tracks the cache TTL: success under
+ * 4 min, warning in the last minute, error once the cache has likely expired.
+ * Negative / non-finite elapsed (clock skew) clamps to `0:00`.
+ */
+export function viewCacheTimer(elapsedMs: number): CacheTimerView {
+  const ms = Number.isFinite(elapsedMs) && elapsedMs > 0 ? elapsedMs : 0;
+  const level = ms >= CACHE_TTL_MS ? "error" : ms >= WARN_AT_MS ? "warning" : "success";
+  if (ms >= CACHE_TIMER_MAX_MS) return { label: "10+ min", level, capped: true };
+  const totalSeconds = Math.floor(ms / 1000);
+  const minutes = Math.floor(totalSeconds / 60);
+  const seconds = totalSeconds % 60;
+  return { label: `${minutes}:${seconds.toString().padStart(2, "0")}`, level, capped: false };
+}
+
+/**
+ * Index of the most recent turn's metrics row — the LAST `turn-metrics` row,
+ * provided no user message follows it. Where a SEEDED turn gap (no `turnId`)
+ * renders. `null` when there is no such row.
+ */
+export function lastTurnRowIndex(rows: readonly MetricsRow[]): number | null {
+  for (let i = rows.length - 1; i >= 0; i--) {
+    const row = rows[i];
+    if (row === undefined) continue;
+    if (row.kind === "turn-metrics") return i;
+    if (row.kind === "group" && row.group.kind === "single" && row.group.chunk.role === "user") {
+      return null;
+    }
+  }
+  return null;
+}