codeburn/tests/cli-deepseek-v4-pricing.test.ts
ozymandiashh 986d72ce1e
Some checks failed
CI / semgrep (push) Has been cancelled
Tests / desktop (push) Has been cancelled
Tests / test-platforms (windows-latest) (push) Has been cancelled
Tests / test (22) (push) Has been cancelled
Tests / test (22.13.0) (push) Has been cancelled
Tests / test (24) (push) Has been cancelled
Tests / test (26) (push) Has been cancelled
Tests / test-platforms (macos-latest) (push) Has been cancelled
fix(pricing): restore the DeepSeek v4 and gpt-5.6-codex repricing invariants (#1134) (#1577)
* fix(pricing): restore the DeepSeek v4 and gpt-5.6-codex repricing invariants (#1134)

The 0.9.21 snapshot caught the 2026-08-24 repricings mid-transition and
relaxed two tests/models.test.ts invariants. Upstream has since synced:

- DeepSeek v4: LiteLLM now carries the official peak rates for both the
  bare and the deepseek/-namespaced rows (pro 1.32/3.96 per million,
  flash 0.30/1.20), so the stale hand-pinned MANUAL_ENTRIES (from before
  PR #27056 merged) are removed and prefixed-equals-bare is asserted
  again.
- gpt-5.6-codex / -max: still absent from LiteLLM, so their
  MANUAL_ENTRIES remain but now mirror the repriced gpt-5.6 base row
  verbatim (4/20 per million, tier block included). codex-equals-base
  is asserted again, and the long-context tier test now expects the
  codex SKUs to carry the base tier.

The refresh also exposed a pass-2 ordering defect in
scripts/bundle-litellm.mjs: a reseller row like
openrouter/deepseek/deepseek-v4-pro could claim the empty
deepseek/deepseek-v4-pro slot before the official row was reached (the
winner was decided purely by upstream JSON key order), pricing the
namespaced id at the resale rate. A prefixed row may now claim only a
stripped slot that is not itself an upstream entry name; multi-segment
ids that exist only as reseller rows keep resolving as before.

Bundled snapshot regenerated: 24 rows moved by upstream drift
(claude-sonnet-5-5 family added, deepseek-v4.1-flash repriced,
zai/glm-4.6 cache-write filled), plus the deepseek/codex corrections.
Token-priced calls re-price on read; no re-parse is needed.

* fix(pricing): repin cline-cli parse version and cover #1134 shadow bug

- session-cache.ts: bump the cline-cli parse version so cached estimated
  costs (e.g. offline DeepSeek v4.1 flash) re-price on read, since
  cline-cli is in REPORTED_COST_PROVIDERS.
- CHANGELOG.md: note the bundler fix also reprices zai/glm-4.6 from the
  vercel_ai_gateway resale row to the official row, and moves the two
  mistral embed models to the fallback table.
- bundle-litellm.test.ts: add a fixture covering a reseller-prefixed row
  that sorts before the official row it would otherwise shadow.

---------

Co-authored-by: Resham Joshi <65915470+iamtoruk@users.noreply.github.com>
2026-09-29 15:05:37 +02:00

135 lines
4.7 KiB
TypeScript

import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { spawnSync } from 'node:child_process'
import { describe, expect, it } from 'vitest'
function runCli(args: string[], home: string) {
return spawnSync(process.execPath, ['--import', 'tsx', 'src/cli.ts', ...args], {
cwd: process.cwd(),
env: {
...process.env,
CLAUDE_CONFIG_DIR: join(home, '.claude'),
HOME: home, USERPROFILE: home,
TZ: 'UTC',
},
encoding: 'utf-8',
timeout: 30_000,
})
}
function userLine(content: string, timestamp: string): string {
return JSON.stringify({
type: 'user',
sessionId: 'deepseek-v4-session',
timestamp,
cwd: '/tmp/deepseek-v4-validation',
message: { role: 'user', content },
})
}
function assistantLine(model: string, timestamp: string, messageId: string, usage: Record<string, number>): string {
return JSON.stringify({
type: 'assistant',
sessionId: 'deepseek-v4-session',
timestamp,
cwd: '/tmp/deepseek-v4-validation',
message: {
id: messageId,
type: 'message',
role: 'assistant',
model,
content: [
{ type: 'text', text: 'updated pricing code' },
{ type: 'tool_use', id: `tu-${messageId}`, name: 'Edit', input: { file_path: '/tmp/deepseek-v4-validation/pricing.ts', old_string: 'old', new_string: 'new' } },
],
usage,
},
})
}
describe('CLI DeepSeek v4 Claude pricing regression', () => {
it('prices DeepSeek v4 Claude sessions even when the runtime LiteLLM cache lacks those models', async () => {
const home = await mkdtemp(join(tmpdir(), 'codeburn-deepseek-v4-cli-'))
try {
const projectDir = join(home, '.claude', 'projects', 'deepseek-v4-validation')
const cacheDir = join(home, '.cache', 'codeburn')
await mkdir(projectDir, { recursive: true })
await mkdir(cacheDir, { recursive: true })
await writeFile(join(cacheDir, 'litellm-pricing.json'), JSON.stringify({
timestamp: Date.now(),
data: {
'gpt-4o-mini': {
inputCostPerToken: 1.5e-7,
outputCostPerToken: 6e-7,
cacheWriteCostPerToken: 0,
cacheReadCostPerToken: 7.5e-8,
webSearchCostPerRequest: 0.01,
fastMultiplier: 1,
},
},
}))
await writeFile(
join(projectDir, 'session.jsonl'),
[
userLine('Use DeepSeek v4 through the Claude-compatible endpoint.', '2026-05-20T10:00:00.000Z'),
assistantLine('deepseek-v4-pro', '2026-05-20T10:01:00.000Z', 'deepseek-v4-pro', {
input_tokens: 2_477_914,
output_tokens: 762_994,
cache_read_input_tokens: 258_556_928,
cache_creation_input_tokens: 0,
}),
userLine('Validate the flash model path too.', '2026-05-20T10:02:00.000Z'),
assistantLine('deepseek-v4-flash', '2026-05-20T10:03:00.000Z', 'deepseek-v4-flash', {
input_tokens: 1_552_573,
output_tokens: 353_914,
cache_read_input_tokens: 48_388_608,
cache_creation_input_tokens: 0,
}),
].join('\n') + '\n',
)
const result = runCli([
'--format', 'json',
'--from', '2026-05-20',
'--to', '2026-05-20',
'--provider', 'claude',
], home)
expect(result.status, `stderr: ${result.stderr}`).toBe(0)
const report = JSON.parse(result.stdout) as {
overview: { cost: number; calls: number; tokens: { cacheRead: number } }
models: Array<{ name: string; cost: number; calls: number; inputTokens: number; outputTokens: number; cacheReadTokens: number }>
}
const pro = report.models.find(m => m.name === 'DeepSeek v4 Pro')
const flash = report.models.find(m => m.name === 'DeepSeek v4 Flash')
expect(report.overview.calls).toBe(2)
expect(report.overview.tokens.cacheRead).toBe(306_945_536)
// The bundled snapshot now carries DeepSeek's official peak pricing
// (#1134): $1.32/$3.96 per million on pro, $0.30/$1.20 on flash.
expect(report.overview.cost).toBeCloseTo(18.849608, 5)
expect(pro).toBeDefined()
expect(pro!.calls).toBe(1)
expect(pro!.inputTokens).toBe(2_477_914)
expect(pro!.outputTokens).toBe(762_994)
expect(pro!.cacheReadTokens).toBe(258_556_928)
expect(pro!.cost).toBeCloseTo(17.668808, 6)
expect(flash).toBeDefined()
expect(flash!.calls).toBe(1)
expect(flash!.inputTokens).toBe(1_552_573)
expect(flash!.outputTokens).toBe(353_914)
expect(flash!.cacheReadTokens).toBe(48_388_608)
expect(flash!.cost).toBeCloseTo(1.1808, 6)
} finally {
await rm(home, { recursive: true, force: true })
}
})
})