Merge pull request #1053 from avs-io/fix/967-models-display-merge

fix(models): resolve and merge raw ids in models report

src/audit-report.ts

@@ -1,4 +1,4 @@
-import { billableOutputTokens, getModelCosts, sanitizeModelForDisplay, type ModelCosts } from './models.js'
+import { billableOutputTokens, fallbackRawModelDisplayName, getModelCosts, getShortModelName, sanitizeModelForDisplay, type ModelCosts } from './models.js'
 import { getProvider } from './providers/index.js'
 import { formatCost, formatTokens } from './format.js'
 import { renderTable, type TableColumn } from './text-table.js'
@@ -112,8 +112,8 @@ export async function aggregateAudit(projects: ProjectSummary[]): Promise<AuditR
     const entry = {
       displayName: p?.displayName ?? name,
       formatModel: p
-        ? (m: string) => sanitizeModelForDisplay(p.modelDisplayName(m))
-        : sanitizeModelForDisplay,
+        ? (m: string) => sanitizeModelForDisplay(fallbackRawModelDisplayName(p.modelDisplayName(m), m))
+        : (m: string) => sanitizeModelForDisplay(getShortModelName(m)),
     }
     providerCache.set(name, entry)
     return entry

src/models-report.ts

@@ -3,7 +3,7 @@ import stripAnsi from 'strip-ansi'
 
 import { codexCredits } from './codex-credits.js'
 import { formatCost, formatTokens } from './format.js'
-import { billableOutputTokens, sanitizeModelForDisplay } from './models.js'
+import { billableOutputTokens, fallbackRawModelDisplayName, getShortModelName, resolveCanonicalModelId, sanitizeModelForDisplay } from './models.js'
 import { getProvider } from './providers/index.js'
 import { CATEGORY_LABELS, type ProjectSummary, type TaskCategory } from './types.js'
 
@@ -28,8 +28,12 @@ export type ModelReportRow = {
   savingsBaselineModel: string
   calls: number
   /// Codex credit consumption (issues #408/#495). null for non-Codex models or
-  /// Codex models without a known credit rate.
+  /// Codex models without a known credit rate. A merged row that mixed rated
+  /// and unrated buckets stores the partial sum of the rated ones.
   credits: number | null
+  /// True when `credits` is a partial sum because some contributing buckets
+  /// had no known credit rate.
+  creditsIncomplete?: boolean
   topCategory?: TaskCategory
   topCategoryCost?: number
   topCategoryShare?: number
@@ -73,9 +77,10 @@ function bucketKey(provider: string, model: string, category: TaskCategory | nul
 }
 
 /// Walks every parsed turn, attributes each assistant call to a
-/// (provider, model, category, agent) bucket, and returns rows keyed by
-/// (provider, model) by default, (provider, model, category) under `byTask`, or
-/// (provider, model, agent) under `byAgent`.
+/// (provider, raw-model, category, agent) bucket, then merges buckets that
+/// resolve to the same provider + alias-resolved canonical id. Display names
+/// stay cosmetic. Returned rows are keyed by (provider, canonical id) by
+/// default, plus category under `byTask` or agent under `byAgent`.
 ///
 /// Default view: rows sorted by cost descending.
 /// byTask / byAgent view: rows grouped by (provider, model) so the renderer can
@@ -155,75 +160,133 @@ export async function aggregateModels(projects: ProjectSummary[], opts: Aggregat
     const entry = {
       displayName: p?.displayName ?? name,
       formatModel: p
-        ? (m: string) => sanitizeModelForDisplay(p.modelDisplayName(m))
-        : sanitizeModelForDisplay,
+        ? (m: string) => sanitizeModelForDisplay(fallbackRawModelDisplayName(p.modelDisplayName(m), m))
+        : (m: string) => sanitizeModelForDisplay(getShortModelName(m)),
     }
     providerCache.set(name, entry)
     return entry
   }
 
-  const rows: ModelReportRow[] = []
+  const rowsByKey = new Map<string, ModelReportRow>()
+  const foldedCategoryCost = new Map<string, Map<CategoryKey, number>>()
+  const foldedTotalCost = new Map<string, number>()
+  const foldedRawSeen = new Set<string>()
+  // Empty string on the row means both "none seen" and "conflict". Track
+  // distinct non-empty baselines separately so a later bucket cannot
+  // repopulate a conflict that was already detected.
+  const baselinesByKey = new Map<string, Set<string>>()
+
   for (const bucket of buckets.values()) {
     const meta = await resolveProvider(bucket.provider)
+    const modelDisplayName = meta.formatModel(bucket.model)
+    const canonicalId = resolveCanonicalModelId(bucket.model)
+    const resolvedKey = bucketKey(bucket.provider, canonicalId, bucket.category, bucket.agentType)
+    const foldKey = `${bucket.provider} ${canonicalId}`
     const total = bucket.inputTokens + bucket.outputTokens + bucket.cacheWriteTokens + bucket.cacheReadTokens
-    const row: ModelReportRow = {
-      provider: bucket.provider,
-      providerDisplayName: meta.displayName,
-      model: bucket.model,
-      modelDisplayName: meta.formatModel(bucket.model),
-      category: bucket.category,
-      agentType: bucket.agentType,
-      inputTokens: bucket.inputTokens,
-      outputTokens: bucket.outputTokens,
-      cacheWriteTokens: bucket.cacheWriteTokens,
-      cacheReadTokens: bucket.cacheReadTokens,
-      totalTokens: total,
-      costUSD: bucket.costUSD,
-      savingsUSD: bucket.savingsUSD,
-      savingsBaselineModel: bucket.savingsBaselineModel,
-      calls: bucket.calls,
-      // outputTokens is the billable output (for Codex that already contains
-      // reasoning, so nothing is added on top), and inputTokens is non-cached
-      // with cacheReadTokens holding cached input - exactly what the credit
-      // rates expect.
-      credits: bucket.provider === 'codex'
-        ? codexCredits(bucket.model, {
-            inputTokens: bucket.inputTokens,
-            cachedReadTokens: bucket.cacheReadTokens,
-            outputTokens: bucket.outputTokens,
-          })
-        : null,
+    // Credits are per raw id (aliases can have different rates). Sum the
+    // rated buckets and flag the row incomplete when any contributor is
+    // unrated — nulling the whole merge would zero a real menubar total.
+    // outputTokens is already the billable output (for Codex that includes
+    // reasoning, so nothing is added on top), and inputTokens is non-cached
+    // with cacheReadTokens holding cached input - exactly what the credit
+    // rates expect.
+    const bucketCredits = bucket.provider === 'codex'
+      ? codexCredits(bucket.model, {
+          inputTokens: bucket.inputTokens,
+          cachedReadTokens: bucket.cacheReadTokens,
+          outputTokens: bucket.outputTokens,
+        })
+      : null
+
+    const baselines = baselinesByKey.get(resolvedKey) ?? new Set<string>()
+    if (bucket.savingsBaselineModel) baselines.add(bucket.savingsBaselineModel)
+    baselinesByKey.set(resolvedKey, baselines)
+    const resolvedBaseline = baselines.size === 1 ? [...baselines][0]! : ''
+
+    const existing = rowsByKey.get(resolvedKey)
+    if (existing) {
+      existing.inputTokens += bucket.inputTokens
+      existing.outputTokens += bucket.outputTokens
+      existing.cacheWriteTokens += bucket.cacheWriteTokens
+      existing.cacheReadTokens += bucket.cacheReadTokens
+      existing.totalTokens += total
+      existing.costUSD += bucket.costUSD
+      existing.savingsUSD += bucket.savingsUSD
+      existing.calls += bucket.calls
+      existing.savingsBaselineModel = resolvedBaseline
+      const existingRated = existing.credits !== null
+      const incomingRated = bucketCredits !== null
+      if (incomingRated) existing.credits = (existing.credits ?? 0) + bucketCredits
+      if (existingRated !== incomingRated) existing.creditsIncomplete = true
+    } else {
+      rowsByKey.set(resolvedKey, {
+        provider: bucket.provider,
+        providerDisplayName: meta.displayName,
+        model: bucket.model,
+        modelDisplayName,
+        category: bucket.category,
+        agentType: bucket.agentType,
+        inputTokens: bucket.inputTokens,
+        outputTokens: bucket.outputTokens,
+        cacheWriteTokens: bucket.cacheWriteTokens,
+        cacheReadTokens: bucket.cacheReadTokens,
+        totalTokens: total,
+        costUSD: bucket.costUSD,
+        savingsUSD: bucket.savingsUSD,
+        savingsBaselineModel: resolvedBaseline,
+        calls: bucket.calls,
+        credits: bucketCredits,
+      })
     }
 
-    if (!opts.byTask && !opts.byAgent) {
-      const perCat = perModelCategoryCost.get(`${bucket.provider} ${bucket.model}`)
-      if (perCat && perCat.size > 0) {
-        let topCat: TaskCategory = 'general'
-        let topCost = -1
-        let totalCost = 0
-        for (const [cat, cost] of perCat.entries()) {
-          totalCost += cost
-          if (cost > topCost) {
-            topCost = cost
-            topCat = cat
-          }
+    const rawKey = `${bucket.provider} ${bucket.model}`
+    if (!foldedRawSeen.has(rawKey)) {
+      foldedRawSeen.add(rawKey)
+      const rawCat = perModelCategoryCost.get(rawKey)
+      if (rawCat) {
+        let folded = foldedCategoryCost.get(foldKey)
+        if (!folded) {
+          folded = new Map()
+          foldedCategoryCost.set(foldKey, folded)
         }
-        row.topCategory = topCat
-        row.topCategoryCost = topCost
-        row.topCategoryShare = totalCost > 0 ? topCost / totalCost : 0
+        for (const [cat, cost] of rawCat) {
+          folded.set(cat, (folded.get(cat) ?? 0) + cost)
+        }
+      }
+      foldedTotalCost.set(
+        foldKey,
+        (foldedTotalCost.get(foldKey) ?? 0) + (perModelTotalCost.get(rawKey) ?? 0),
+      )
+    }
+  }
+
+  const rows = [...rowsByKey.values()]
+  for (const row of rows) {
+    if (opts.byTask || opts.byAgent) continue
+    const perCat = foldedCategoryCost.get(`${row.provider} ${resolveCanonicalModelId(row.model)}`)
+    if (!perCat || perCat.size === 0) continue
+    let topCat: TaskCategory = 'general'
+    let topCost = -1
+    let totalCost = 0
+    for (const [cat, cost] of perCat.entries()) {
+      totalCost += cost
+      if (cost > topCost) {
+        topCost = cost
+        topCat = cat
       }
     }
-
-    rows.push(row)
+    row.topCategory = topCat
+    row.topCategoryCost = topCost
+    row.topCategoryShare = totalCost > 0 ? topCost / totalCost : 0
   }
 
   if (opts.byTask || opts.byAgent) {
     rows.sort((a, b) => {
-      const aTotal = perModelTotalCost.get(`${a.provider} ${a.model}`) ?? 0
-      const bTotal = perModelTotalCost.get(`${b.provider} ${b.model}`) ?? 0
+      const aTotal = foldedTotalCost.get(`${a.provider} ${resolveCanonicalModelId(a.model)}`) ?? 0
+      const bTotal = foldedTotalCost.get(`${b.provider} ${resolveCanonicalModelId(b.model)}`) ?? 0
       if (aTotal !== bTotal) return bTotal - aTotal
       if (a.provider !== b.provider) return a.provider.localeCompare(b.provider)
-      if (a.model !== b.model) return a.model.localeCompare(b.model)
+      if (a.modelDisplayName !== b.modelDisplayName) return a.modelDisplayName.localeCompare(b.modelDisplayName)
       return (b.costUSD + b.savingsUSD) - (a.costUSD + a.savingsUSD)
     })
   } else {
@@ -483,7 +546,7 @@ export function renderTable(
   const rowEntries: RowCells[] = []
   let prevProviderModel = ''
   for (const row of rows) {
-    const groupKey = `${row.provider} ${row.model}`
+    const groupKey = `${row.provider} ${row.modelDisplayName}`
     const isNewGroup = !grouped || groupKey !== prevProviderModel
     prevProviderModel = groupKey
     const allCells = defaultColumns(byTask, byAgent, showSaved).map(col => {
@@ -605,6 +668,7 @@ export function renderJson(rows: ModelReportRow[]): string {
       savingsUSD: r.savingsUSD,
       savingsBaselineModel: r.savingsBaselineModel,
       credits: r.credits,
+      creditsIncomplete: r.creditsIncomplete === true,
     })),
     null,
     2,

src/models.ts

@@ -655,6 +655,19 @@ function getCanonicalName(model: string): string {
   )
 }
 
+/// Alias-resolved identity for report merge. Display names stay cosmetic —
+/// prefix matches in SHORT_NAMES must not fold distinct SKUs into one row.
+/// Path-form ids (`accounts/fireworks/models/<slug>`, `cline-pass/<slug>`)
+/// peel to the leaf so they share a bucket with the bare slug.
+export function resolveCanonicalModelId(model: string): string {
+  const viaUser = Object.hasOwn(userAliases, model) ? userAliases[model]! : model
+  const aliased = resolveAlias(getCanonicalName(viaUser))
+  if (!aliased.includes('/')) return aliased
+  const leaf = aliased.slice(aliased.lastIndexOf('/') + 1)
+  if (!leaf) return aliased
+  return resolveAlias(getCanonicalName(leaf))
+}
+
 // Namespaces the pricing catalog itself uses, plus the ones below. An unknown
 // `provider/model` must stay unpriced — do not treat `/` as authority. Derived
 // rather than hand-listed so a vendor LiteLLM already knows (`x-ai/`, `qwen/`,
@@ -1144,6 +1157,14 @@ export function getShortModelName(model: string): string {
   return shortModelName(model, new Set())
 }
 
+/// Provider-first display name. Local labels win (Cursor estimated suffixes,
+/// provider tables that intentionally override the global map). If the provider
+/// echoed the raw id, it missed — fall back to the global resolver instead of
+/// showing `gpt-5.6-sol` / `accounts/fireworks/models/kimi-k2p6`.
+export function fallbackRawModelDisplayName(localLabel: string, rawModel: string): string {
+  return localLabel === rawModel ? getShortModelName(rawModel) : localLabel
+}
+
 function shortModelName(model: string, seen: Set<string>): string {
   if (autoModelNames[model]) return autoModelNames[model]
   if (seen.has(model)) {

src/providers/cursor-agent.ts

@@ -4,7 +4,7 @@ import { readdir, readFile, stat } from 'fs/promises'
 import { join, basename } from 'path'
 import { homedir } from 'os'
 
-import { calculateCost } from '../models.js'
+import { calculateCost, getShortModelName } from '../models.js'
 import { openDatabase, type SqliteDatabase } from '../sqlite.js'
 import { normalizeContentBlocks } from '../content-utils.js'
 import { estimateTokensFromChars } from '../token-estimate.js'
@@ -506,7 +506,7 @@ export function createCursorAgentProvider(baseDirOverride?: string): Provider {
 
     modelDisplayName(model: string): string {
       if (model === 'cursor-agent-auto') return 'Cursor (auto)'
-      const label = modelDisplayNames[model] ?? model
+      const label = modelDisplayNames[model] ?? getShortModelName(model)
       return `${label} (est.)`
     },
 

src/providers/vercel-gateway.ts

@@ -1,3 +1,4 @@
+import { getShortModelName } from '../models.js'
 import type { DateRange } from '../types.js'
 import type { Provider, SessionSource, SessionParser, ParsedProviderCall } from './types.js'
 import { fetchWithTimeout } from '../fetch-utils.js'
@@ -124,7 +125,7 @@ export const vercelGateway: Provider = {
 
   modelDisplayName(model: string): string {
     const slash = model.indexOf('/')
-    return slash >= 0 ? model.slice(slash + 1) : model
+    return getShortModelName(slash >= 0 ? model.slice(slash + 1) : model)
   },
 
   toolDisplayName(rawTool: string): string {

tests/models-report.test.ts

@@ -8,6 +8,7 @@ import chalk from 'chalk'
 import stripAnsi from 'strip-ansi'
 
 import { aggregateModels, renderTable, renderMarkdown, renderJson, renderCsv, type ModelReportRow } from '../src/models-report.js'
+import { setModelAliases } from '../src/models.js'
 import type {
   ProjectSummary,
   SessionSummary,
@@ -37,6 +38,8 @@ function makeCall(opts: {
   output?: number
   cacheWrite?: number
   cacheRead?: number
+  savingsUSD?: number
+  savingsBaselineModel?: string
 }): ParsedApiCall {
   return {
     provider: opts.provider,
@@ -58,6 +61,8 @@ function makeCall(opts: {
     timestamp: '2026-05-09T00:00:00.000Z',
     bashCommands: [],
     deduplicationKey: `${opts.provider}-${opts.model}-${opts.costUSD}`,
+    savingsUSD: opts.savingsUSD,
+    savingsBaselineModel: opts.savingsBaselineModel,
   }
 }
 
@@ -165,6 +170,32 @@ describe('aggregateModels', () => {
     expect(byKey['codex:gpt-5.5']!.credits).toBeCloseTo(887.5, 6)
     expect(byKey['codex:gpt-5']!.credits).toBeNull()
     expect(byKey['claude:claude-sonnet-4-6']!.credits).toBeNull()
+    expect(byKey['codex:gpt-5.5']!.creditsIncomplete).toBeFalsy()
+  })
+
+  it('partial-sums Codex credits when a merge mixes rated and unrated ids', async () => {
+    setModelAliases({ 'codex-house-sku': 'gpt-5.5' })
+    try {
+      const rows = await aggregateModels([makeProject([
+        makeTurn('feature', [
+          makeCall({ provider: 'codex', model: 'gpt-5.5', input: 0, output: 1_000_000, costUSD: 9 }),
+        ]),
+        makeTurn('feature', [
+          makeCall({ provider: 'codex', model: 'codex-house-sku', input: 0, output: 1_000_000, costUSD: 9 }),
+        ]),
+      ])])
+      expect(rows).toHaveLength(1)
+      expect(rows[0]!.model).toBe('gpt-5.5')
+      // gpt-5.5 output is 750 credits/M; the aliased house SKU has no rate.
+      expect(rows[0]!.credits).toBeCloseTo(750, 6)
+      expect(rows[0]!.creditsIncomplete).toBe(true)
+      expect(rows[0]!.calls).toBe(2)
+      const parsed = JSON.parse(renderJson(rows))
+      expect(parsed[0].credits).toBeCloseTo(750, 6)
+      expect(parsed[0].creditsIncomplete).toBe(true)
+    } finally {
+      setModelAliases({})
+    }
   })
 
   it('includes credits in the JSON output', async () => {
@@ -188,6 +219,110 @@ describe('aggregateModels', () => {
     expect(rows[0]!.cacheReadTokens).toBe(4000) // not 8000
   })
 
+  it('falls back from a provider local table miss to the global short name', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({ provider: 'cursor-agent', model: 'gpt-5.6-sol', costUSD: 2.5 })]),
+    ])])
+    expect(rows).toHaveLength(1)
+    expect(rows[0]!.modelDisplayName).toBe('GPT-5.6 Sol (est.)')
+    expect(rows[0]!.model).toBe('gpt-5.6-sol')
+  })
+
+  it('resolves Fireworks path-form ids through the global table', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({ provider: 'cline', model: 'accounts/fireworks/models/kimi-k2p6', costUSD: 1 })]),
+    ])])
+    expect(rows).toHaveLength(1)
+    expect(rows[0]!.modelDisplayName).toBe('Kimi K2.6')
+    expect(rows[0]!.model).toBe('accounts/fireworks/models/kimi-k2p6')
+  })
+
+  it('merges two raw ids that resolve to the same alias-resolved canonical id', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('testing', [makeCall({
+        provider: 'cline-cli', model: 'accounts/fireworks/models/glm-5p2',
+        input: 800, output: 67, costUSD: 0.246,
+      })]),
+      makeTurn('conversation', [makeCall({
+        provider: 'cline-cli', model: 'glm-5p2',
+        input: 15, output: 1, costUSD: 0.019,
+      })]),
+    ])])
+    expect(rows).toHaveLength(1)
+    expect(rows[0]!.provider).toBe('cline-cli')
+    expect(rows[0]!.modelDisplayName).toBe('GLM-5.2')
+    // First-seen raw id, not the lexicographically-smallest of the merge.
+    expect(rows[0]!.model).toBe('accounts/fireworks/models/glm-5p2')
+    expect(rows[0]!.inputTokens).toBe(815)
+    expect(rows[0]!.outputTokens).toBe(68)
+    expect(rows[0]!.costUSD).toBeCloseTo(0.265, 6)
+    expect(rows[0]!.calls).toBe(2)
+    expect(rows[0]!.topCategory).toBe('testing')
+    expect(rows[0]!.topCategoryShare).toBeCloseTo(0.246 / 0.265, 3)
+  })
+
+  it('does not pick the lexicographically-smallest raw id after a merge', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({ provider: 'codex', model: 'kimi-k3', costUSD: 2 })]),
+      makeTurn('feature', [makeCall({ provider: 'codex', model: 'k3', costUSD: 1 })]),
+    ])])
+    expect(rows).toHaveLength(1)
+    expect(rows[0]!.model).toBe('kimi-k3')
+    expect(rows[0]!.modelDisplayName).toBe('Kimi K3')
+    expect(rows[0]!.calls).toBe(2)
+  })
+
+  it('does not merge same-provider ids that only share a display name', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({ provider: 'codex', model: 'gpt-5', costUSD: 3 })]),
+      makeTurn('feature', [makeCall({ provider: 'codex', model: 'gpt-5-untracked-xyz', costUSD: 1 })]),
+      makeTurn('feature', [makeCall({ provider: 'cline-cli', model: 'glm-5p2', costUSD: 1 })]),
+      makeTurn('feature', [makeCall({ provider: 'cline-cli', model: 'GLM-5.2', costUSD: 2 })]),
+    ])])
+    const codex = rows.filter(r => r.provider === 'codex')
+    expect(codex).toHaveLength(2)
+    expect(codex.every(r => r.modelDisplayName === 'GPT-5')).toBe(true)
+    expect(new Set(codex.map(r => r.model))).toEqual(new Set(['gpt-5', 'gpt-5-untracked-xyz']))
+
+    const cline = rows.filter(r => r.provider === 'cline-cli')
+    expect(cline).toHaveLength(2)
+    expect(cline.every(r => r.modelDisplayName === 'GLM-5.2')).toBe(true)
+    expect(new Set(cline.map(r => r.model))).toEqual(new Set(['glm-5p2', 'GLM-5.2']))
+  })
+
+  it('clears a merged savings baseline when three raw ids disagree', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({
+        provider: 'codex', model: 'k3',
+        costUSD: 1, savingsUSD: 2, savingsBaselineModel: 'gpt-4o',
+      })]),
+      makeTurn('feature', [makeCall({
+        provider: 'codex', model: 'kimi-k3',
+        costUSD: 1, savingsUSD: 2, savingsBaselineModel: 'claude-sonnet-4-6',
+      })]),
+      makeTurn('feature', [makeCall({
+        provider: 'codex', model: 'k3-agent',
+        costUSD: 1, savingsUSD: 2, savingsBaselineModel: 'gpt-5',
+      })]),
+    ])])
+    expect(rows).toHaveLength(1)
+    expect(rows[0]!.provider).toBe('codex')
+    expect(rows[0]!.modelDisplayName).toBe('Kimi K3')
+    expect(rows[0]!.savingsUSD).toBe(6)
+    expect(rows[0]!.savingsBaselineModel).toBe('')
+    expect(rows[0]!.calls).toBe(3)
+  })
+
+  it('does not merge the same display name across providers', async () => {
+    const rows = await aggregateModels([makeProject([
+      makeTurn('feature', [makeCall({ provider: 'cline-cli', model: 'glm-5p2', costUSD: 1 })]),
+      makeTurn('feature', [makeCall({ provider: 'hermes', model: 'glm-5p2', costUSD: 2 })]),
+    ])])
+    expect(rows).toHaveLength(2)
+    expect(new Set(rows.map(r => r.provider))).toEqual(new Set(['cline-cli', 'hermes']))
+    expect(rows.every(r => r.modelDisplayName === 'GLM-5.2')).toBe(true)
+  })
+
   it('reports the dominant task type with its cost share in default mode', async () => {
     const project = makeProject([
       makeTurn('feature', [makeCall({ provider: 'claude', model: 'claude-sonnet-4-6', costUSD: 6.0, input: 100, output: 20 })]),

tests/models.test.ts

@@ -7,6 +7,7 @@ import {
   findUnpricedModels,
   getModelCosts,
   getShortModelName,
+  resolveCanonicalModelId,
   calculateCost,
   loadPricing,
   setModelAliases,
@@ -150,6 +151,22 @@ describe('getModelCosts', () => {
   })
 })
 
+describe('resolveCanonicalModelId', () => {
+  it('aliases, peels path-form ids, and leaves display-only collisions distinct', () => {
+    expect(resolveCanonicalModelId('k3')).toBe('kimi-k3')
+    expect(resolveCanonicalModelId('k3-agent')).toBe('kimi-k3')
+    expect(resolveCanonicalModelId('kimi-k3')).toBe('kimi-k3')
+    expect(resolveCanonicalModelId('accounts/fireworks/models/glm-5p2')).toBe('glm-5p2')
+    expect(resolveCanonicalModelId('glm-5p2')).toBe('glm-5p2')
+    expect(resolveCanonicalModelId('GLM-5.2')).toBe('glm-5p1')
+    expect(resolveCanonicalModelId('gpt-5-fast')).toBe('gpt-5')
+    expect(resolveCanonicalModelId('gpt-5-untracked-xyz')).toBe('gpt-5-untracked-xyz')
+    expect(resolveCanonicalModelId('claude-opus-4.6')).toBe('claude-opus-4-6')
+    expect(resolveCanonicalModelId('kimi-code')).toBe('kimi-k2-thinking')
+    expect(resolveCanonicalModelId('cline-pass/kimi-k3')).toBe('kimi-k3')
+  })
+})
+
 describe('getShortModelName', () => {
   it('maps gpt-4o-mini correctly (not gpt-4o)', () => {
     expect(getShortModelName('gpt-4o-mini-2024-07-18')).toBe('GPT-4o Mini')

tests/providers/cursor-agent.test.ts

@@ -79,6 +79,7 @@ describe('cursor-agent provider', () => {
 
     expect(provider.modelDisplayName('claude-5-future-model')).toBe('claude-5-future-model (est.)')
     expect(provider.modelDisplayName('gpt-9')).toBe('gpt-9 (est.)')
+    expect(provider.modelDisplayName('gpt-5.6-sol')).toBe('GPT-5.6 Sol (est.)')
   })
 
   it('returns identity for tool display name', () => {

tests/providers/vercel-gateway.test.ts

@@ -66,6 +66,11 @@ describe('vercel-gateway provider', () => {
     expect(calls[0]?.costUSD).toBe(1.25)
     expect(calls[0]?.model).toBe('anthropic/claude-sonnet-4.6')
   })
+
+  it('resolves vendor/slug ids through the global short-name table', () => {
+    expect(vercelGateway.modelDisplayName('openai/gpt-5.6-terra')).toBe('GPT-5.6 Terra')
+    expect(vercelGateway.modelDisplayName('accounts/fireworks/models/kimi-k2p6')).toBe('Kimi K2.6')
+  })
 })
 
 describe('vercel-gateway end-to-end (parseAllSessions network path)', () => {