Merge pull request #1056 from avs-io/fix/1047-codex-activity-ids

fix(models): price Codex activity ids via the official underlying model

scripts/upgrade-path/run.mjs

@@ -33,7 +33,7 @@ const WORK = process.env['UPGRADE_PATH_WORK'] || join(tmpdir(), 'codeburn upgrad
 const OLD_SESSION_CACHE = 'session-cache.v7.json'
 const OLD_DAILY_CACHE = 'daily-cache.v17.json'
 const NEW_SESSION_CACHE_DIR = 'session-cache.v9'
-const NEW_DAILY_CACHE = 'daily-cache.v24.json'
+const NEW_DAILY_CACHE = 'daily-cache.v25.json'
 
 const HOME = join(WORK, 'user home')
 const PAYLOADS = join(WORK, 'payloads')

src/codex-cache.ts

@@ -40,7 +40,10 @@ import type { ParsedProviderCall } from './providers/types.js'
 // in `skills`. This file stores each call's `tools`/`toolSequence`/`skills`
 // verbatim (they are passed through on read, never re-derived), so v13 entries
 // keep the old, MCP- and skill-less attribution until they re-parse.
-export const CODEX_CACHE_VERSION = 14
+// v15: builtin alias prices `codex-auto-review` (#1047). Exact-hit cache
+// entries still hold the pre-alias $0; bump so unchanged rollouts reprice.
+// Must be max(main v14 #1092, this)+1 — #1092 spent v14 on MCP/skills.
+export const CODEX_CACHE_VERSION = 15
 export const CODEX_LEGACY_CACHE_FILE = 'codex-results.json'
 export function codexCacheFileName(version = CODEX_CACHE_VERSION): string {
   return `codex-results.v${version}.json`

src/codex-credits.ts

@@ -20,10 +20,19 @@ const CREDITS_PER_MILLION: Record<string, CodexCreditRate> = {
   'gpt-5.4-mini': { input: 18.75, cachedInput: 1.875, output: 113 },
 }
 
+// Activity surfaces keep their product id on the call (display stays
+// "Codex Auto Review"). Credits must follow the same underlying model
+// BUILTIN_ALIASES uses for USD. Keep this table in lockstep with
+// `codex-auto-review` in src/models.ts.
+const ACTIVITY_CREDIT_MODELS: Record<string, string> = {
+  'codex-auto-review': 'gpt-5.5',
+}
+
 /// Resolve the credit rate for a Codex model name, tolerating suffix variants
 /// (e.g. "gpt-5.5-codex"). Returns null when the model has no known credit rate.
 export function codexCreditRate(model: string): CodexCreditRate | null {
-  const m = model.toLowerCase()
+  const mapped = ACTIVITY_CREDIT_MODELS[model] ?? ACTIVITY_CREDIT_MODELS[model.toLowerCase()]
+  const m = (mapped ?? model).toLowerCase()
   if (m.includes('5.4') && m.includes('mini')) return CREDITS_PER_MILLION['gpt-5.4-mini']!
   if (m.includes('5.4')) return CREDITS_PER_MILLION['gpt-5.4']!
   if (m.includes('5.5')) return CREDITS_PER_MILLION['gpt-5.5']!

src/daily-cache.ts

@@ -6,6 +6,15 @@ import { join } from 'path'
 import { getCodeburnCacheDir } from './cache-dir.js'
 import type { DateRange, ProjectSummary } from './types.js'
 
+// Bumped to 25: `codex-auto-review` now prices as the recommended GPT-5.5
+// row (#1047). Days already finalized under v24 keep that id at $0
+// forever unless MIN_SUPPORTED_VERSION moves: the daily cache has no
+// per-provider invalidation. The Codex parse version and CODEX_CACHE_VERSION
+// move with this so the lower caches reprice first; this pass then re-derives
+// ALL days from the warm session cache (seconds, not a full re-parse).
+// adoptOlderDailyCaches keeps the superseded file as the baseline. v21 is
+// #946, v22 was this PR's earlier claim, v23 is #1075, v24 is #1090.
+//
 // Bumped to 20: the Codex fast-path read a nested
 // `base_instructions.provenance.model` out of `session_meta` as if it were
 // `payload.model` (#1040), so every call a rollout attributed from session
@@ -128,11 +137,10 @@ import type { DateRange, ProjectSummary } from './types.js'
 // window where neither existed). The daily cache has no per-provider
 // invalidation, so there is no way to tell those days apart from here -
 // raising MIN_SUPPORTED_VERSION forces the one-time re-derivation for
-// everyone, which is a lossless no-op for days already correct. #1056 also
-// claims 24 on its own branch (unmerged as of this writing); whichever lands
-// second takes the next number instead of reusing this one.
-export const DAILY_CACHE_VERSION = 24
-const MIN_SUPPORTED_VERSION = 24
+// everyone, which is a lossless no-op for days already correct.
+// v25: #1047 activity-id pricing. v24 on main already shipped #1090.
+export const DAILY_CACHE_VERSION = 25
+const MIN_SUPPORTED_VERSION = 25
 // Version-suffixed so different binaries each own a distinct file and never
 // clobber an incompatible schema. Bumping the version mints a fresh filename;
 // adoptOlderDailyCaches then unions days out of every previous file (including

src/models.ts

@@ -312,6 +312,16 @@ const BUILTIN_ALIASES: Record<string, string> = {
   'openclaw-auto':                 'claude-sonnet-4-5',
   'warp-auto-efficient':           'gpt-5.3-codex',
   'warp-auto-powerful':            'claude-opus-4-6',
+  // Codex activity ids are product surfaces, not subscription SKUs and not
+  // LiteLLM rows. OpenAI's tracker (openai/codex#32224) says auto review
+  // consumes normal model usage. Public evidence: review_model defaults to
+  // the session model; GPT-5.5 is the currently recommended review model.
+  // Price as that existing bundled row. Do not invent a rate. Do not treat
+  // the id as honestly $0 — it draws from the same credit pool. Display
+  // stays on autoModelNames (same class as cursor-auto / copilot-openai-auto).
+  // Only alias ids observed in Codex source / real rollouts. Do not infer
+  // `codex-code-review` from the activity name "code review".
+  'codex-auto-review':             'gpt-5.5',
   'grok-build':                    'grok-build-0.1',
   'GPT-5.3 Codex (low reasoning)': 'gpt-5.3-codex',
   'GPT-5.3 Codex (medium reasoning)': 'gpt-5.3-codex',
@@ -1017,6 +1027,7 @@ const autoModelNames: Record<string, string> = {
   'openclaw-auto': 'OpenClaw (auto)',
   'qwen-auto': 'Qwen (auto)',
   'kimi-auto': 'Kimi (auto)',
+  'codex-auto-review': 'Codex Auto Review',
 }
 
 const SHORT_NAMES: Record<string, string> = {

src/session-cache.ts

@@ -280,7 +280,7 @@ export const PROVIDER_PARSE_VERSIONS: Record<string, string> = {
   // session-meta-model-v1: parse large session_meta records structurally so a
   // nested base_instructions provenance.model cannot overwrite turn_context.
   // session-meta-fields-v1: the same depth-1 window for cwd/name/originator/
-  // session_id/forked_from_id/model_provider, not just model.
+  // session_id/forked_from_id/model_provider, not just model. (#1055)
   // codex-pricing-v1 (#1075): reasoning tokens are no longer added on top of
   // output, and cache_write_input_tokens moves out of the plain input bucket on
   // models with an explicit cache-write rate. The bucket move does NOT self-heal
@@ -294,7 +294,10 @@ export const PROVIDER_PARSE_VERSIONS: Record<string, string> = {
   // through the `exec` custom tool or the item model's `CommandExecution` item
   // were counted as Bash only. Cached sessions store tools/toolSequence/skills
   // verbatim, so they must re-parse to gain the attribution.
-  codex: 'mcp-attribution-v5-est-cost-active-timing-mcp-wait-rich-capture-v1-cross-provider-pr-v1-session-meta-model-v1-session-meta-fields-v1-codex-pricing-v1-codex-tps-v1-codex-mcp-skills-v1',
+  // activity-price-v1: `codex-auto-review` now prices via the recommended
+  // review model. session-cache.json would otherwise keep the pre-alias $0.
+  // Compose all four — a take-ours merge would drop #1075, #1079, or #1092.
+  codex: 'mcp-attribution-v5-est-cost-active-timing-mcp-wait-rich-capture-v1-cross-provider-pr-v1-session-meta-model-v1-session-meta-fields-v1-codex-pricing-v1-codex-tps-v1-codex-mcp-skills-v1-activity-price-v1',
   cursor: 'composer-anchored-crediting-v1-est-cost',
   'cursor-agent': 'workspaceless-transcript-v1',
   // source-provenance-v1 (#944): CLI sessions were misread as VS Code

tests/codex-credits.test.ts

@@ -17,6 +17,12 @@ describe('codexCreditRate', () => {
     expect(codexCreditRate('gpt-4o')).toBeNull()
     expect(codexCreditRate('claude-opus-4-8')).toBeNull()
   })
+
+  it('resolves the auto-review activity id to the same rate as GPT-5.5', () => {
+    expect(codexCreditRate('codex-auto-review')).toEqual(codexCreditRate('gpt-5.5'))
+    expect(codexCreditRate('codex-auto-review')).not.toBeNull()
+    expect(codexCreditRate('CODEX-AUTO-REVIEW')).toEqual(codexCreditRate('gpt-5.5'))
+  })
 })
 
 describe('codexCredits', () => {
@@ -45,4 +51,8 @@ describe('codexCredits', () => {
   it('returns null for an unknown model', () => {
     expect(codexCredits('gpt-4o', { inputTokens: 1_000_000, cachedReadTokens: 0, outputTokens: 0 })).toBeNull()
   })
+
+  it('charges auto-review at the GPT-5.5 credit rate, not null', () => {
+    expect(codexCredits('codex-auto-review', { inputTokens: 1_000_000, cachedReadTokens: 0, outputTokens: 0 })).toBe(125)
+  })
 })

tests/models.test.ts

@@ -653,6 +653,8 @@ describe('Cursor model variants resolve to pricing', () => {
     ['claude-4.6-haiku', 'claude-haiku-4-5'],
     // Cursor auto proxy
     ['cursor-auto', 'claude-sonnet-4-5'],
+    // Codex activity surface (official rate card, observed raw id)
+    ['codex-auto-review', 'gpt-5.5'],
     // OpenAI variants Cursor emits
     ['gpt-5', 'gpt-5'],
     ['gpt-5-fast', 'gpt-5'],
@@ -688,6 +690,29 @@ describe('Cursor model variants resolve to pricing', () => {
   })
 })
 
+describe('Codex activity ids (#1047)', () => {
+  it('keeps the activity label instead of collapsing to the underlying model name', () => {
+    expect(getShortModelName('codex-auto-review')).toBe('Codex Auto Review')
+  })
+
+  it('prices as the exact bundled GPT-5.5 object, not an invented rate', () => {
+    expect(getModelCosts('codex-auto-review')).toBe(getModelCosts('gpt-5.5'))
+    const auto = calculateCost('codex-auto-review', 1_000_000, 1_000_000, 0, 0, 0)
+    const gpt55 = calculateCost('gpt-5.5', 1_000_000, 1_000_000, 0, 0, 0)
+    expect(auto).toBeGreaterThan(0)
+    expect(auto).toBe(gpt55)
+  })
+
+  it('does not invent a family or an unobserved sibling id', () => {
+    expect(getModelCosts('codex-code-review')).toBeNull()
+    expect(getModelCosts('codex-cloud-task')).toBeNull()
+    expect(getModelCosts('codex-automation')).toBeNull()
+    expect(getModelCosts('code-review')).toBeNull()
+    expect(getModelCosts('auto-review')).toBeNull()
+    expect(calculateCost('codex-code-review', 1_000_000, 1_000_000, 0, 0, 0)).toBe(0)
+  })
+})
+
 describe('Cursor house model pricing', () => {
   const cases: Array<[string, { input: number; output: number; cacheWrite: number; cacheRead: number }]> = [
     ['composer-2.5', { input: 0.5, output: 2.5, cacheWrite: 0.5, cacheRead: 0.2 }],

tests/providers/codex.test.ts

@@ -1,9 +1,11 @@
 import { describe, it, expect, beforeEach, afterEach } from 'vitest'
-import { mkdtemp, mkdir, writeFile, rm } from 'fs/promises'
+import { mkdtemp, mkdir, writeFile, rm, stat } from 'fs/promises'
 import { join } from 'path'
 import { tmpdir } from 'os'
 
 import { createCodexProvider } from '../../src/providers/codex.js'
+import { clearCodexMemCaches, CODEX_CACHE_VERSION, codexCacheFileName } from '../../src/codex-cache.js'
+import { calculateCost } from '../../src/models.js'
 import type { ParsedProviderCall } from '../../src/providers/types.js'
 
 let tmpDir: string
@@ -1317,3 +1319,77 @@ describe('codex provider - forked session dedupe', () => {
     expect(tokens).toBe(300)
   })
 })
+
+describe('codex auto-review pricing (#1047)', () => {
+  it('parses auto-review as itself and prices it as GPT-5.5', async () => {
+    const filePath = await writeSession(tmpDir, '2026-04-14', 'rollout-auto-review.jsonl', [
+      sessionMeta({ session_id: 'sess-auto', model: 'codex-auto-review' }),
+      userMessage('review the PR'),
+      tokenCount({
+        timestamp: '2026-04-14T10:01:00Z',
+        last: { input: 1_000_000, output: 1_000_000 },
+        total: { total: 2_000_000 },
+      }),
+    ])
+    const provider = createCodexProvider(tmpDir)
+    const calls: ParsedProviderCall[] = []
+    for await (const call of provider.createSessionParser({ path: filePath, project: 'test', provider: 'codex' }, new Set()).parse()) {
+      calls.push(call)
+    }
+    expect(calls).toHaveLength(1)
+    expect(calls[0]!.model).toBe('codex-auto-review')
+    expect(calls[0]!.costUSD).toBe(calculateCost('gpt-5.5', 1_000_000, 1_000_000, 0, 0, 0))
+  })
+
+  it('discards a warm v11 versioned $0 exact hit so unchanged rollouts reprice', async () => {
+    const cacheDir = join(tmpDir, 'cache')
+    await mkdir(cacheDir, { recursive: true })
+    const prev = process.env['CODEBURN_CACHE_DIR']
+    process.env['CODEBURN_CACHE_DIR'] = cacheDir
+    try {
+      const filePath = await writeSession(tmpDir, '2026-04-14', 'rollout-stale-auto.jsonl', [
+        sessionMeta({ session_id: 'sess-stale-auto', model: 'codex-auto-review' }),
+        userMessage('review the PR'),
+        tokenCount({
+          timestamp: '2026-04-14T10:01:00Z',
+          last: { input: 1_000_000, output: 1_000_000 },
+          total: { total: 2_000_000 },
+        }),
+      ])
+      const st = await stat(filePath)
+      // Main's #1075 already owns v11. A colliding v11 $0 file must not be
+      // treated as current after this PR takes v12.
+      expect(CODEX_CACHE_VERSION).toBeGreaterThan(11)
+      await writeFile(join(cacheDir, codexCacheFileName(11)), JSON.stringify({
+        version: 11,
+        files: {
+          [filePath]: {
+            mtimeMs: st.mtimeMs,
+            sizeBytes: st.size,
+            project: 'test',
+            calls: [{
+              model: 'codex-auto-review',
+              costUSD: 0,
+              inputTokens: 1_000_000,
+              outputTokens: 1_000_000,
+              deduplicationKey: 'stale',
+            }],
+          },
+        },
+      }))
+      clearCodexMemCaches()
+      const provider = createCodexProvider(tmpDir)
+      const calls: ParsedProviderCall[] = []
+      for await (const call of provider.createSessionParser({ path: filePath, project: 'test', provider: 'codex' }, new Set()).parse()) {
+        calls.push(call)
+      }
+      expect(calls).toHaveLength(1)
+      expect(calls[0]!.costUSD).toBeGreaterThan(0)
+      expect(calls[0]!.costUSD).toBe(calculateCost('gpt-5.5', 1_000_000, 1_000_000, 0, 0, 0))
+    } finally {
+      clearCodexMemCaches()
+      if (prev === undefined) delete process.env['CODEBURN_CACHE_DIR']
+      else process.env['CODEBURN_CACHE_DIR'] = prev
+    }
+  })
+})