mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-08-21 22:44:31 +00:00
0bfdfa372a
A warm launch rewrote the entire session cache whenever any provider appended a few KB: on a 6 GB corpus that is a 155 MB stringify + fsync every run. The on-disk cache is now a version-suffixed directory holding one shard per provider plus a small envelope, and a save rewrites only the providers marked dirty. - Dirtiness is tracked per provider (markCacheDirty) instead of one global flag, so an appended Claude session no longer republishes Codex, Copilot and the rest. - Shards carry a nonce in their filename and the envelope is renamed last, so a save is published at a single point: readers never see a half-updated set, and a writer that loses the refresh ownership fence leaves the canonical shards untouched. - A shard that fails validation is treated as an absent provider rather than rejecting the whole cache, so one malformed turn costs one provider's re-parse instead of every provider's history. - v7 migrates losslessly: the blob is re-laid-out into shards and removed only once that save publishes. Nothing re-parses. - Cold-parse progress saves now trigger every N files parsed rather than every 5s, so a slow cold parse no longer rewrites the growing cache on a wall clock.
127 lines
4.2 KiB
TypeScript
127 lines
4.2 KiB
TypeScript
import { mkdir, mkdtemp, readFile, rm, stat, writeFile } from 'fs/promises'
|
|
import { tmpdir } from 'os'
|
|
import { join } from 'path'
|
|
|
|
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
|
|
|
|
import { clearSessionCache, parseAllSessions } from '../src/parser.js'
|
|
import { CACHE_VERSION, computeEnvFingerprint, type SessionCache } from '../src/session-cache.js'
|
|
import { readCacheOnDisk, writeCacheOnDisk } from './fixtures/session-cache-io.js'
|
|
import type { DateRange } from '../src/types.js'
|
|
|
|
let home: string
|
|
let cacheDir: string
|
|
|
|
beforeEach(async () => {
|
|
home = await mkdtemp(join(tmpdir(), 'codeburn-gemini-home-'))
|
|
cacheDir = await mkdtemp(join(tmpdir(), 'codeburn-gemini-cache-'))
|
|
process.env['HOME'] = home
|
|
process.env['CODEBURN_CACHE_DIR'] = cacheDir
|
|
})
|
|
|
|
afterEach(async () => {
|
|
clearSessionCache()
|
|
await rm(home, { recursive: true, force: true })
|
|
await rm(cacheDir, { recursive: true, force: true })
|
|
})
|
|
|
|
describe('Gemini session cache migration', () => {
|
|
it('reparses cached legacy aggregate Gemini entries into granular calls', async () => {
|
|
const chatsDir = join(home, '.gemini', 'tmp', 'project-a', 'chats')
|
|
await mkdir(chatsDir, { recursive: true })
|
|
const sessionPath = join(chatsDir, 'session-2026-05-16.json')
|
|
await writeFile(sessionPath, JSON.stringify({
|
|
sessionId: 'gemini-session-1',
|
|
startTime: '2026-05-16T10:00:00.000Z',
|
|
messages: [
|
|
{ id: 'u1', timestamp: '2026-05-16T10:00:00.000Z', type: 'user', content: 'work' },
|
|
{
|
|
id: 'g1',
|
|
timestamp: '2026-05-16T10:00:05.000Z',
|
|
type: 'gemini',
|
|
content: 'first',
|
|
model: 'gemini-3.1-pro-preview',
|
|
tokens: { input: 10, output: 5 },
|
|
},
|
|
{
|
|
id: 'g2',
|
|
timestamp: '2026-05-16T10:00:10.000Z',
|
|
type: 'gemini',
|
|
content: 'second',
|
|
model: 'gemini-3.1-pro-preview',
|
|
tokens: { input: 12, output: 6 },
|
|
},
|
|
],
|
|
}))
|
|
|
|
const fileStat = await stat(sessionPath)
|
|
await writeCacheOnDisk({
|
|
version: CACHE_VERSION,
|
|
providers: {
|
|
gemini: {
|
|
envFingerprint: computeEnvFingerprint('gemini'),
|
|
files: {
|
|
[sessionPath]: {
|
|
fingerprint: {
|
|
dev: fileStat.dev,
|
|
ino: fileStat.ino,
|
|
mtimeMs: fileStat.mtimeMs,
|
|
sizeBytes: fileStat.size,
|
|
},
|
|
mcpInventory: [],
|
|
turns: [{
|
|
timestamp: '2026-05-16T10:00:00.000Z',
|
|
sessionId: 'gemini-session-1',
|
|
userMessage: 'work',
|
|
calls: [{
|
|
provider: 'gemini',
|
|
model: 'gemini-3.1-pro-preview',
|
|
usage: {
|
|
inputTokens: 22,
|
|
outputTokens: 11,
|
|
cacheCreationInputTokens: 0,
|
|
cacheReadInputTokens: 0,
|
|
cachedInputTokens: 0,
|
|
reasoningTokens: 0,
|
|
webSearchRequests: 0,
|
|
cacheCreationOneHourTokens: 0,
|
|
},
|
|
speed: 'standard',
|
|
timestamp: '2026-05-16T10:00:00.000Z',
|
|
tools: [],
|
|
bashCommands: [],
|
|
skills: [],
|
|
deduplicationKey: 'gemini:gemini-session-1',
|
|
}],
|
|
}],
|
|
},
|
|
},
|
|
},
|
|
},
|
|
} as SessionCache)
|
|
|
|
const range: DateRange = {
|
|
start: new Date('2026-05-16T00:00:00.000Z'),
|
|
end: new Date('2026-05-16T23:59:59.999Z'),
|
|
}
|
|
|
|
const projects = await parseAllSessions(range, 'gemini')
|
|
const keys = projects.flatMap(project =>
|
|
project.sessions.flatMap(session =>
|
|
session.turns.flatMap(turn => turn.assistantCalls.map(call => call.deduplicationKey)),
|
|
),
|
|
)
|
|
|
|
expect(projects[0]!.totalApiCalls).toBe(2)
|
|
expect(keys).toEqual([
|
|
'gemini:gemini-session-1:g1',
|
|
'gemini:gemini-session-1:g2',
|
|
])
|
|
|
|
const savedCache = await readCacheOnDisk() as any
|
|
const savedKeys = savedCache.providers.gemini.files[sessionPath].turns.flatMap((turn: { calls: Array<{ deduplicationKey: string }> }) =>
|
|
turn.calls.map(call => call.deduplicationKey),
|
|
)
|
|
expect(savedKeys).toEqual(keys)
|
|
})
|
|
})
|