feat(agent): aggregate Claude usage from local transcripts (#49) #51

Merged
maximus merged 3 commits from issue-49-claude-usage-aggregate into main 2026-10-04 19:29:38 +00:00
2 changed files with 155 additions and 27 deletions
Showing only changes of commit c888f7c633 - Show all commits

View file

@ -431,16 +431,20 @@ describe("at most 12 models per day", () => {
// --- Frozen days and the scan threshold ---------------------------------------- // --- Frozen days and the scan threshold ----------------------------------------
describe("frozen days", () => { describe("frozen days", () => {
const FROZEN = { // What the agent hands over: a contiguous frozen run from the window start
"2026-10-01": { // through 2026-10-01, empty days included.
const FROZEN = {};
for (const day of windowDays("2026-10-04")) {
if (day > "2026-10-01") break;
FROZEN[day] = { models: {}, projects: {} };
}
FROZEN["2026-10-01"] = {
models: { "claude-opus-5-5": { input: 7, output: 7, cacheCreation: 7, cacheRead: 7, requests: 7 } }, models: { "claude-opus-5-5": { input: 7, output: 7, cacheCreation: 7, cacheRead: 7, requests: 7 } },
projects: { alpha: { work: 21, cacheRead: 7, requests: 7 } }, projects: { alpha: { work: 21, cacheRead: 7, requests: 7 } },
},
"2026-09-30": { models: {}, projects: {} },
}; };
it("opens no file whose mtime day is before the threshold (spy on file opening)", async () => { it("opens no file whose mtime day is before the threshold (spy on file opening)", async () => {
// Threshold = day after the most recent frozen day = 2026-10-02. // Threshold = oldest open day = day after the frozen run = 2026-10-02.
const old = writeTranscript( const old = writeTranscript(
"a/old.jsonl", "a/old.jsonl",
[line({ ts: "2026-10-02T15:00:00Z", output: 5 })], // would count if opened [line({ ts: "2026-10-02T15:00:00Z", output: 5 })], // would count if opened
@ -544,10 +548,78 @@ describe("frozen days", () => {
expect(dayOf(r, "2026-09-30").models).toEqual({}); expect(dayOf(r, "2026-09-30").models).toEqual({});
expect(r.openDays["2026-10-01"]).toBeUndefined(); expect(r.openDays["2026-10-01"]).toBeUndefined();
expect(r.openDays["2026-09-30"]).toBeUndefined(); expect(r.openDays["2026-09-30"]).toBeUndefined();
expect(Object.keys(r.openDays)).toHaveLength(28); expect(Object.keys(r.openDays)).toEqual(["2026-10-02", "2026-10-03", "2026-10-04"]);
expect(r.projects).toEqual([{ name: "alpha", work: 21 + 1 + 3, cacheRead: 7, requests: 8 }]); expect(r.projects).toEqual([{ name: "alpha", work: 21 + 1 + 3, cacheRead: 7, requests: 8 }]);
}); });
it("a frozen day in the future never hides an open day's files", async () => {
const file = writeTranscript(
"a/open.jsonl",
[line({ ts: "2026-10-03T15:00:00Z", output: 3 })],
"2026-10-03T16:00:00Z",
);
const opened = [];
const r = await aggregate({
root: tmpDir,
today: "2026-10-04",
homedir: HOME,
frozenDays: { "2026-11-15": { models: {}, projects: {} } },
openFile: (f, o) => {
opened.push(f);
return fs.createReadStream(f, o);
},
});
expect(opened).toEqual([file]);
expect(r.openDays["2026-10-03"].models["claude-opus-5-5"].output).toBe(3);
});
it("a gap in the frozen run keeps the open day before the gap scanned", async () => {
// 10-03 open, 10-04 (today) frozen: the oldest open day sets the threshold.
const file = writeTranscript(
"a/open.jsonl",
[line({ ts: "2026-10-03T15:00:00Z", output: 3 })],
"2026-10-03T16:00:00Z",
);
const frozenDays = {};
for (const day of windowDays("2026-10-04")) {
if (day !== "2026-10-03") frozenDays[day] = { models: {}, projects: {} };
}
const opened = [];
const r = await aggregate({
root: tmpDir,
today: "2026-10-04",
homedir: HOME,
frozenDays,
openFile: (f, o) => {
opened.push(f);
return fs.createReadStream(f, o);
},
});
expect(opened).toEqual([file]);
expect(Object.keys(r.openDays)).toEqual(["2026-10-03"]);
expect(r.openDays["2026-10-03"].models["claude-opus-5-5"].output).toBe(3);
});
it("every day frozen: no file is opened", async () => {
writeTranscript("a/x.jsonl", [line({ ts: "2026-10-04T15:00:00Z" })], "2026-10-04T16:00:00Z");
const frozenDays = {};
for (const day of windowDays("2026-10-04")) frozenDays[day] = { models: {}, projects: {} };
const opened = [];
const r = await aggregate({
root: tmpDir,
today: "2026-10-04",
homedir: HOME,
frozenDays,
openFile: (f, o) => {
opened.push(f);
return fs.createReadStream(f, o);
},
});
expect(opened).toEqual([]);
expect(Object.keys(r.openDays)).toEqual([]);
expect(r.days).toHaveLength(WINDOW_DAYS);
});
it("re-reads frozen counters defensively (bad numbers -> 0, junk ignored)", async () => { it("re-reads frozen counters defensively (bad numbers -> 0, junk ignored)", async () => {
const r = await aggregate({ const r = await aggregate({
root: tmpDir, root: tmpDir,
@ -634,3 +706,50 @@ describe("robustness", () => {
); );
}); });
}); });
// --- Names that collide with Object.prototype ------------------------------------
describe("prototype-shaped names", () => {
const PROTO_KEYS = ["work", "cacheRead", "requests", "input", "output", "cacheCreation"];
function prototypeIsClean() {
for (const k of PROTO_KEYS) {
expect(Object.prototype.hasOwnProperty.call(Object.prototype, k)).toBe(false);
expect(Object.prototype.hasOwnProperty.call(Object, k)).toBe(false);
}
}
it("projects named __proto__ and constructor are counted, Object.prototype untouched", async () => {
writeTranscript(
"a/x.jsonl",
[
line({ ts: "2026-10-03T15:00:00Z", cwd: `${HOME}/claude-code/__proto__`, output: 5 }),
line({ ts: "2026-10-03T16:00:00Z", cwd: `${HOME}/claude-code/constructor`, output: 7 }),
line({ ts: "2026-10-03T17:00:00Z", model: "constructor", output: 2 }),
],
"2026-10-04T12:00:00Z",
);
const r = await aggregate({ root: tmpDir, today: "2026-10-04", homedir: HOME });
prototypeIsClean();
const byName = Object.fromEntries(r.projects.map((p) => [p.name, p]));
expect(Object.keys(byName).sort()).toEqual(["__proto__", "alpha", "constructor"].sort());
expect(Object.getOwnPropertyDescriptor(byName, "__proto__").value.work).toBe(1 + 5);
expect(byName.constructor.work).toBe(1 + 7);
expect(dayOf(r, "2026-10-03").models.constructor.output).toBe(2);
expect(JSON.parse(JSON.stringify(r.days)).length).toBe(WINDOW_DAYS);
});
it("a __proto__ key in a frozen day stays a plain project", async () => {
const frozenDays = JSON.parse(
'{"2026-10-01":{"models":{},"projects":{"__proto__":{"work":4,"cacheRead":0,"requests":1},"constructor":{"work":6,"cacheRead":0,"requests":1}}}}',
);
const r = await aggregate({ root: tmpDir, today: "2026-10-04", homedir: HOME, frozenDays });
prototypeIsClean();
expect(r.projects.map((p) => [p.name, p.work]).sort()).toEqual(
[
["__proto__", 4],
["constructor", 6],
].sort(),
);
});
});

View file

@ -18,9 +18,13 @@
// are deduplicated on (message.id, requestId) across ALL files, keeping the // are deduplicated on (message.id, requestId) across ALL files, keeping the
// line with the largest output_tokens. // line with the largest output_tokens.
// * THE SCAN THRESHOLD. Frozen days are never recomputed. A file whose mtime // * THE SCAN THRESHOLD. Frozen days are never recomputed. A file whose mtime
// (Toronto day) is before the day after the most recent frozen day cannot // (Toronto day) is before the oldest open day of the window cannot hold a
// hold a line on an open day, so it is not even opened: this is what keeps // line on an open day, so it is not even opened: this is what keeps a run
// a run from re-reading ~210 MB of transcripts every time. // from re-reading ~210 MB of transcripts every time. The threshold comes
// from the open days, never from the frozen keys: a stray frozen day (in
// the future, or after a gap) must not hide an open day's files.
// * NO PROTOTYPE. Names read from transcripts or the state file key plain
// maps built by dict(), so `__proto__` or `constructor` stay ordinary keys.
const fs = require("node:fs"); const fs = require("node:fs");
const os = require("node:os"); const os = require("node:os");
@ -136,6 +140,13 @@ function count(value) {
return Number.isSafeInteger(value) && value >= 0 ? value : 0; return Number.isSafeInteger(value) && value >= 0 ? value : 0;
} }
// Every map keyed by a name read from a transcript or the state file (model,
// project, day) has no prototype: a project named `__proto__` or
// `constructor` is then a plain key, never a write into Object.prototype.
function dict() {
return Object.create(null);
}
function emptyModel() { function emptyModel() {
return { input: 0, output: 0, cacheCreation: 0, cacheRead: 0, requests: 0 }; return { input: 0, output: 0, cacheCreation: 0, cacheRead: 0, requests: 0 };
} }
@ -179,7 +190,7 @@ function capModels(models) {
(a < b ? -1 : a > b ? 1 : 0) (a < b ? -1 : a > b ? 1 : 0)
); );
}); });
const out = {}; const out = dict();
for (const name of names.slice(0, MAX_MODELS_PER_DAY - 1)) out[name] = models[name]; for (const name of names.slice(0, MAX_MODELS_PER_DAY - 1)) out[name] = models[name];
const other = emptyModel(); const other = emptyModel();
if (hasOther) addModel(other, models[OTHER_MODEL]); if (hasOther) addModel(other, models[OTHER_MODEL]);
@ -191,8 +202,8 @@ function capModels(models) {
// Frozen days come from the agent's state file: re-read through the same // Frozen days come from the agent's state file: re-read through the same
// counters, never trusted verbatim. // counters, never trusted verbatim.
function normalizeDay(day) { function normalizeDay(day) {
const models = {}; const models = dict();
const projects = {}; const projects = dict();
const srcModels = day && typeof day.models === "object" && day.models ? day.models : {}; const srcModels = day && typeof day.models === "object" && day.models ? day.models : {};
const srcProjects = const srcProjects =
day && typeof day.projects === "object" && day.projects ? day.projects : {}; day && typeof day.projects === "object" && day.projects ? day.projects : {};
@ -294,7 +305,7 @@ async function aggregate({
} = {}) { } = {}) {
if (!isDay(today)) throw new Error("aggregate: today must be a YYYY-MM-DD date"); if (!isDay(today)) throw new Error("aggregate: today must be a YYYY-MM-DD date");
const frozen = {}; const frozen = dict();
if (frozenDays && typeof frozenDays === "object") { if (frozenDays && typeof frozenDays === "object") {
for (const [day, value] of Object.entries(frozenDays)) { for (const [day, value] of Object.entries(frozenDays)) {
if (isDay(day)) frozen[day] = value; if (isDay(day)) frozen[day] = value;
@ -305,15 +316,13 @@ async function aggregate({
const windowStart = window[0]; const windowStart = window[0];
const openDayList = window.filter((d) => !Object.prototype.hasOwnProperty.call(frozen, d)); const openDayList = window.filter((d) => !Object.prototype.hasOwnProperty.call(frozen, d));
// Scan threshold: the day after the most recent frozen day. Floored at the // Scan threshold: the oldest open day of the window. With the agent's
// window start — a file last written before the window cannot hold a line // contiguous frozen prefix this is the day after the most recent frozen day;
// inside it. // computed from the open days rather than from the frozen keys, so a frozen
const frozenList = Object.keys(frozen).sort(); // day in the future or a gap in the frozen run can never push the threshold
let threshold = windowStart; // past an open day and silently empty it. A file last written before the
if (frozenList.length) { // window cannot hold a line inside it. Every day frozen: nothing to read.
const afterFrozen = shiftDay(frozenList[frozenList.length - 1], 1); const threshold = openDayList.length ? openDayList[0] : shiftDay(today, 1);
if (afterFrozen > threshold) threshold = afterFrozen;
}
// (message.id, requestId) -> best line so far. // (message.id, requestId) -> best line so far.
const requests = new Map(); const requests = new Map();
@ -383,8 +392,8 @@ async function aggregate({
// Open days: every non-frozen day of the window, empty ones included, so // Open days: every non-frozen day of the window, empty ones included, so
// the caller can freeze them all (an unfrozen empty day would hold the // the caller can freeze them all (an unfrozen empty day would hold the
// threshold back and every run would re-read the whole window). // threshold back and every run would re-read the whole window).
const openDays = {}; const openDays = dict();
for (const day of openDayList) openDays[day] = { models: {}, projects: {} }; for (const day of openDayList) openDays[day] = { models: dict(), projects: dict() };
for (const r of requests.values()) { for (const r of requests.values()) {
const bucket = openDays[r.day]; const bucket = openDays[r.day];
if (!bucket.models[r.model]) bucket.models[r.model] = emptyModel(); if (!bucket.models[r.model]) bucket.models[r.model] = emptyModel();
@ -399,7 +408,7 @@ async function aggregate({
// Merged 30-day series and project totals over the window. // Merged 30-day series and project totals over the window.
const days = []; const days = [];
const projectTotals = {}; const projectTotals = dict();
for (const date of window) { for (const date of window) {
const source = Object.prototype.hasOwnProperty.call(frozen, date) const source = Object.prototype.hasOwnProperty.call(frozen, date)
? normalizeDay(frozen[date]) ? normalizeDay(frozen[date])