codeburn/packages/cli/tests/codex-throughput-cache-invalidation.test.ts
iamtoruk 8ec2753cbd feat(cli): rehome codex tool-excluded active throughput
The second half of #940 (@ozymandiashh): upstream `main` measures Codex
throughput — a task's wall time minus its recorded tool wait, divided across
the task's calls by generated tokens — and none of it exists on this branch.
Added on one side only, so a `main` merge would land `src/codex-throughput.ts`
at a path npm workspaces does not build.

Rehomed against main as it ships today, with one deliberate divergence from
#940, which the maintainer decided: main's resume design wins.

  - Timing state is captured ONLY at a `task_started` boundary, where every
    per-task accumulator is provably empty, and a task's calls are buffered
    until its window is known. No recorded call is ever mutated after it has
    been handed to the host. #940's alternative — threading the open task
    window through the serialized state and back-patching earlier-pass calls
    via applyCodexTimingPatches — is dropped in full.

  - The branch's Phase-4 token-decode resume is untouched: it stays any-offset
    and round-trip proven. Marrying the two needed one adaptation, since core
    decodes records and never sees bytes: the decoder now reports its last
    task_started as a `checkpoint` (record index + call count + state), and the
    CLI turns that index into a byte offset and replays only the calls before
    it, letting the still-open task re-derive. A pass that crosses no boundary
    keeps the previous one; a cold decode of a file with no task_started at all
    falls back to end-of-file with `taskOpen: false`, so a task_complete whose
    window this pass never saw attributes nothing rather than spreading a whole
    task's active time over part of its tokens.

Restores the three fad84662 review fixes that #940 reverted: the discovery
fast path already short-circuits on cachedProject before isValidCodexSession
(unchanged here, verified); payload-level `duration_ms` outranks any nested one
(`timingDuration ?? timingNumber('duration_ms')`), so a duration buried in an
oversized mcp_tool_call_end's invocation.arguments can no longer inflate tool
wait; and MIN_WIDE stays 90 with the Tok/s column behind a showTps gate rather
than jumping to 130 and costing 90-129 column terminals their two-column
dashboard. Also ports the fork-suppressed-task_started regression test and the
depth-1 payloadString helper (main 1d36f444/497f6556), which the branch lacked.

Scope discipline: main's codex pricing work (billableOutputTokens, #1078) is
NOT dragged along — that is #1083 — and neither are its unported parser
changes (custom-tool transport, exact token counts and MCP names on oversized
lines), so cost, calls and tokens are untouched. Verified on a 1326-session
real corpus: codex totals byte-identical to the base branch, with 1302 of 1328
model slices now carrying timing (36.5 Tok/s on GPT-5.5).

CODEX_CACHE_VERSION takes 12, clear of main's ladder (11 as of #1078) so a
cache written by either line can never be read as current by the other, and
the codex parse version bumps in lockstep so session-cache.json cannot keep
serving timing-less turns without invoking the parser.
2026-08-21 13:37:22 -07:00

110 lines
5.3 KiB
TypeScript

// Regression for the stale-cache path of the codex active-timing port (same
// class as #478/#618). Two caches serve a codex session without ever invoking
// the decoder: session-cache.json (per provider, gated by envFingerprint) and
// codex-results.json (per file, gated by CODEX_CACHE_VERSION). A user upgrading
// into this change has both warm and both timing-less, so unless BOTH gates
// move, the dashboard's Tok/s column stays empty on every unchanged session
// forever. This drives the full parseAllSessions pipeline against caches seeded
// exactly as the pre-change release left them.
//
// Revert-proof: drop the `-active-timing-v1` suffix from the codex entry in
// PROVIDER_PARSE_VERSIONS and the seeded fingerprint matches again, the stale
// section is served, and the assertion below fails.
import { describe, it, expect, beforeEach, afterAll, vi } from 'vitest'
import { mkdir, rm, readFile, writeFile } from 'fs/promises'
import { createHash } from 'crypto'
import { join } from 'path'
import { clearSessionCache, parseAllSessions } from '../src/parser.js'
import { sessionCachePath } from '../src/session-cache.js'
const testRoot = vi.hoisted(() => {
const root = `${process.env['TMPDIR'] || '/tmp'}/codex-timing-stale-${process.pid}-${Date.now()}`
process.env['HOME'] = `${root}/home`
process.env['USERPROFILE'] = `${root}/home`
process.env['CODEX_HOME'] = `${root}/codex`
return root
})
const CODEX_HOME = join(testRoot, 'codex')
const CACHE_DIR = join(testRoot, 'cache')
// computeEnvFingerprint('codex') as the pre-change release computed it: the
// same CODEX_HOME, the same parse version minus this change's suffix.
const PRE_CHANGE_PARSE_VERSION = 'mcp-attribution-v2-est-cost-rich-capture-v1-cross-provider-pr-v1'
function preChangeFingerprint(): string {
const parts = [`CODEX_HOME=${CODEX_HOME}`, `parser=${PRE_CHANGE_PARSE_VERSION}`]
return createHash('sha256').update(parts.join('\0')).digest('hex').slice(0, 16)
}
beforeEach(() => {
process.env['HOME'] = join(testRoot, 'home')
process.env['USERPROFILE'] = join(testRoot, 'home')
process.env['CODEX_HOME'] = CODEX_HOME
process.env['CODEBURN_CACHE_DIR'] = CACHE_DIR
})
afterAll(async () => {
await rm(testRoot, { recursive: true, force: true })
})
function timingTotals(projects: Awaited<ReturnType<typeof parseAllSessions>>): number[] {
return projects.flatMap(p => p.sessions.flatMap(s => Object.values(s.modelBreakdown).map(m => m.activeDurationMs ?? 0)))
}
describe('codex active-timing invalidates both stale caches', () => {
it('re-parses an unchanged codex file cached by the pre-change release', async () => {
const sessionDir = join(CODEX_HOME, 'sessions', '2026', '04', '14')
await mkdir(sessionDir, { recursive: true })
await mkdir(CACHE_DIR, { recursive: true })
const lines = [
JSON.stringify({ type: 'session_meta', timestamp: '2026-04-14T10:00:00Z', payload: { session_id: 'sess-timing-stale', model: 'gpt-5.5', cwd: '/Users/test/proj', originator: 'codex_cli_rs' } }),
JSON.stringify({ type: 'event_msg', timestamp: '2026-04-14T10:00:00Z', payload: { type: 'task_started' } }),
JSON.stringify({ type: 'response_item', timestamp: '2026-04-14T10:00:01Z', payload: { type: 'message', role: 'user', content: [{ type: 'input_text', text: 'run it' }] } }),
JSON.stringify({ type: 'event_msg', timestamp: '2026-04-14T10:00:08Z', payload: { type: 'token_count', info: { last_token_usage: { input_tokens: 300, output_tokens: 100 }, total_token_usage: { total_tokens: 400 } } } }),
JSON.stringify({ type: 'event_msg', timestamp: '2026-04-14T10:00:10Z', payload: { type: 'task_complete', duration_ms: 10_000 } }),
]
await writeFile(join(sessionDir, 'rollout-timing-stale.jsonl'), lines.join('\n') + '\n')
// Run 1: cold cache, current code. Timing present (sanity).
clearSessionCache()
const fresh = await parseAllSessions(undefined, 'codex')
expect(timingTotals(fresh)).toEqual([10_000])
// Rewrite both caches as the pre-change release left them: the old provider
// envFingerprint, the old codex-results version, and cached calls/turns
// with no timing at all. The rollout file itself is untouched, so nothing
// but the two version gates can trigger a re-parse.
const cachePath = sessionCachePath()
const cache = JSON.parse(await readFile(cachePath, 'utf8'))
cache.providers.codex.envFingerprint = preChangeFingerprint()
for (const f of Object.values(cache.providers.codex.files) as any[]) {
for (const turn of f.turns) {
for (const call of turn.calls) {
delete call.activeDurationMs
delete call.activeGeneratedTokens
delete call.toolWaitMs
}
}
}
await writeFile(cachePath, JSON.stringify(cache))
const codexCachePath = join(CACHE_DIR, 'codex-results.json')
const codexCache = JSON.parse(await readFile(codexCachePath, 'utf8'))
codexCache.version = 8
for (const f of Object.values(codexCache.files) as any[]) {
for (const call of f.calls ?? []) {
delete call.activeDurationMs
delete call.activeGeneratedTokens
delete call.toolWaitMs
}
}
await writeFile(codexCachePath, JSON.stringify(codexCache))
clearSessionCache()
const second = await parseAllSessions(undefined, 'codex')
expect(timingTotals(second)).toEqual([10_000])
})
})