codeburn/tests/cli-model-savings.test.ts
Justin Gheorghe 8ded6ad6fd feat(cli): track local-model cost savings against a paid baseline (#421)
Add a new `localModelSavings` config and `codeburn model-savings` CLI
that maps a local-model name (e.g. llama3.1:8b) to a paid baseline
(e.g. gpt-4o). The local call still costs $0; the new `savingsUSD`
field tracks the counterfactual spend avoided by running locally and
is reported separately from `costUSD` everywhere a number is shown.

* Parser normalization (`applyLocalModelSavings`) runs on Claude
  parse, direct provider calls, and the cached-call path. It forces
  `costUSD` to 0 and attaches `savingsUSD` + `savingsBaselineModel`
  + `isLocalSavings` on the `ParsedApiCall`. Local-savings wins for
  actual cost even when the same model is also in `modelAliases`.
* Session, project, day, model, category, activity, skill, and
  subagent rollups all carry `savingsUSD` alongside `costUSD`.
* `status --format json` adds `today.savings` and `month.savings`.
* `status --format menubar-json` adds a `current.localModelSavings`
  block (totalUSD, calls, byModel, byProvider) plus savings on
  topModels, topProjects, topSessions, topActivities, and history
  daily entries. Schema fields default-decode for backward compat.
* `report --format json` adds savings across overview/daily/
  projects/models/activities/skills/subagents/topSessions, with
  the active paid baseline name on each model row.
* `models` command gains a `Saved` column on table/markdown/CSV
  and a `savingsUSD`/`savingsBaselineModel` pair in JSON. Default
  `--min-cost 0.01` filter now ORs in `savingsUSD >= minCost` so
  local models with $0 actual cost but >0 savings still surface.
* CSV/JSON exports add a `Saved (CODE)` column on summary/daily/
  models/projects/sessions.
* Dashboard TUI shows a green 'saved $X by local models' footer
  line in the overview when any savings are present.
* macOS Swift payload gains a `LocalModelSavings` Codable block
  and savings fields on every model/activity/session/daily
  struct. Hero shows a green leaf 'Saved $X' caption, models
  section gets a green `Saved` column. `swift build` clean.
* GNOME indicator adds 'saved $X' to the hero meta line and a
  `codeburn-model-saved` column to the model row.
* Daily cache schema bumped to v8 (`savingsUSD` on day/model/
  category/provider). `savingsConfigHash` invalidates the cache
  when the user changes their baseline mapping so historical
  saved-spend numbers never lie about a stale baseline.
* Defensive `Object.hasOwn` lookup in `getLocalSavingsBaseline`
  blocks the prototype-pollution test that previously surfaced via
  the savings path with a hostile `__proto__` model name.
* New tests (5 files, 25 tests, 549 lines) cover pricing helpers,
  end-to-end parser normalization, day aggregator savings,
  menubar payload savings, CLI set/list/remove, and
  daily-cache hash invalidation. Existing tests for daily-cache
  / day-aggregator / models-report updated for the new fields.
  Full vitest suite: 1028/1028 passing across 73 test files.
  `tsc --noEmit` clean. `npm run build` clean.
  (Note: `mac/Tests` has a pre-existing `no such module 'Testing'`
  environment error on the installed Swift toolchain, confirmed
  on `main` before this PR; not caused by these changes.)
2026-06-01 11:06:39 +03:00

76 lines
2.6 KiB
TypeScript

import { mkdtemp, readFile, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { spawnSync } from 'node:child_process'
import { describe, it, expect } from 'vitest'
const CLI_TIMEOUT_MS = 10_000
function runCli(args: string[], home: string) {
return spawnSync(process.execPath, ['--import', 'tsx', 'src/cli.ts', ...args], {
cwd: process.cwd(),
env: {
...process.env,
HOME: home,
USERPROFILE: home,
HOMEPATH: home,
HOMEDRIVE: '',
},
encoding: 'utf-8',
})
}
function readConfig(home: string): Promise<Record<string, unknown>> {
return readFile(join(home, '.config', 'codeburn', 'config.json'), 'utf-8')
.then(raw => JSON.parse(raw) as Record<string, unknown>)
}
describe('codeburn model-savings command', () => {
it('saves, lists, and removes a local-model savings mapping', async () => {
const home = await mkdtemp(join(tmpdir(), 'codeburn-cli-savings-'))
try {
const set = runCli(['model-savings', 'llama3.1:8b', 'gpt-4o'], home)
expect(set.status).toBe(0)
expect(set.stdout).toContain('llama3.1:8b -> gpt-4o')
const saved = await readConfig(home)
expect(saved.localModelSavings).toEqual({ 'llama3.1:8b': 'gpt-4o' })
const list = runCli(['model-savings', '--list'], home)
expect(list.status).toBe(0)
expect(list.stdout).toContain('llama3.1:8b -> gpt-4o')
const remove = runCli(['model-savings', '--remove', 'llama3.1:8b'], home)
expect(remove.status).toBe(0)
const after = await readConfig(home)
expect(after.localModelSavings).toBeUndefined()
} finally {
await rm(home, { recursive: true, force: true })
}
}, CLI_TIMEOUT_MS)
it('warns when the same model is also configured in modelAliases', async () => {
const home = await mkdtemp(join(tmpdir(), 'codeburn-cli-savings-'))
try {
expect(runCli(['model-alias', 'llama3.1:8b', 'gpt-4o'], home).status).toBe(0)
const set = runCli(['model-savings', 'llama3.1:8b', 'gpt-4o'], home)
expect(set.status).toBe(0)
expect(set.stdout).toContain('savings take precedence')
} finally {
await rm(home, { recursive: true, force: true })
}
}, CLI_TIMEOUT_MS)
it('rejects a remove for an unknown mapping', async () => {
const home = await mkdtemp(join(tmpdir(), 'codeburn-cli-savings-'))
try {
const result = runCli(['model-savings', '--remove', 'unknown:1b'], home)
expect(result.status).toBe(1)
expect(result.stderr).toContain('No savings mapping found')
} finally {
await rm(home, { recursive: true, force: true })
}
}, CLI_TIMEOUT_MS)
})