The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
TypeScript 3d-modelingagent-frameworkagent-harnessai-agentscadclaude-codecodexcoding-agentsdeveloper-toolsesp32game-developmentmcp-servermulti-agentopen-hardwareopencodeopenharnesspcbroboticsterminaltmux
Route offers real Codex models, not 'default default' (#3045)
harness-for-autonomous[bot]a793554721e2
diff --git a/backend/integration/superTabs.test.ts b/backend/integration/superTabs.test.tsindex cdb4022a2..500e1f1fd 100644--- a/backend/integration/superTabs.test.ts+++ b/backend/integration/superTabs.test.ts@@ -2459,7 +2459,9 @@ describe('Super Tabs on a real Mongo replica set', () => {const data = read.json().data// An older Desktop shows the read's warnings atop its routing dialog, and reads no save's `note`: they say where routing went.expect(data).toMatchObject({ policy: DEFAULT_ROUTING_POLICY, warnings: [IGNORED_NOTE], overridden: [], override: null, account: DEFAULT_ROUTING_POLICY })- expect(data.catalog.models).toHaveLength(7)+ // Six rows since task #2972: Codex has Sol and Astra by name, and no `default default` row.+ expect(data.catalog.models).toHaveLength(6)+ expect(data.catalog.models.filter((m: { model: string; effort: string }) => m.model === 'default' || m.effort === 'default')).toEqual([])expect(data.catalog.grid).toEqual({ strength: 1, models: [{ model: 'kimi k3', strength: 2 }, { model: 'deepseek v4.1', strength: 2 }] })expect(data.catalog.prices.map((p: { model: string }) => p.model)).toContain('claude-opus-5-5')expect(data.catalog.priors.models.length).toBeGreaterThan(0)diff --git a/backend/src/superTabs/catalog.test.ts b/backend/src/superTabs/catalog.test.tsindex 06ceb5cb0..a0009fad8 100644--- a/backend/src/superTabs/catalog.test.ts+++ b/backend/src/superTabs/catalog.test.ts@@ -11,14 +11,18 @@ describe('the model catalog', () => {expect(MODEL_CATALOG.models).toEqual([{ engine: 'claude', model: 'opus', effort: 'high', strength: 3, cost: 3, offered: true },{ engine: 'claude', model: 'opus', effort: 'xhigh', strength: 3, cost: 4, offered: true },- { engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },- { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true, engineDefault: true },{ engine: 'codex', model: 'gpt-6-astra', effort: 'xhigh', strength: 3, cost: 5, offered: true },{ engine: 'claude', model: 'sonnet', effort: 'high', strength: 2, cost: 2, offered: true },{ engine: 'claude', model: 'haiku', effort: 'auto', strength: 1, cost: 1, offered: false, note: NOT_OFFERED },])// Ken, 2026-11-02: small work runs on Sonnet or Sol, nothing below high effort; Haiku stays off.- expect(MODEL_CATALOG.models.filter(m => m.offered).every(m => m.strength >= 2 && ['high', 'xhigh', 'default'].includes(m.effort))).toBe(true)+ expect(MODEL_CATALOG.models.filter(m => m.offered).every(m => m.strength >= 2 && ['high', 'xhigh'].includes(m.effort))).toBe(true)+ // Task #2972: the route offers the models the catalog rates, never an engine's own `default`, which ran whatever the account's CLI chose.+ expect(MODEL_CATALOG.models.filter(m => m.model === 'default' || m.effort === 'default')).toEqual([])+ expect(MODEL_CATALOG.models.filter(m => m.engineDefault).map(m => `${m.engine} ${m.model} ${m.effort}`)).toEqual(['codex gpt-6.1-sol high'])+ // gpt-6-luna has no rating or benchmark, so it is not a row: the route offers it only when a person names it, unrated.+ expect(MODEL_CATALOG.models.some(m => m.model.includes('luna'))).toBe(false)expect(MODEL_CATALOG.grid).toEqual({ strength: 1, models: [{ model: 'kimi k3', strength: 2 }, { model: 'deepseek v4.1', strength: 2 }] })})diff --git a/backend/src/superTabs/catalog.ts b/backend/src/superTabs/catalog.tsindex eba09f62e..8842254b0 100644--- a/backend/src/superTabs/catalog.ts+++ b/backend/src/superTabs/catalog.ts@@ -11,9 +11,10 @@ import type { PriorsTable } from './benchmarkPriors/priors.js'import { PRICES, type ModelPrice } from './costs/prices.js'/** One model at one effort. `offered`: the route offers it when nobody names a model; a row not offered is still rated, for- * a person who names it. `cost` ranks rows of equal strength (lower first); it is not a price. `default` keeps the engine's- * own configured model or effort. */-export interface CatalogModel { engine: 'claude' | 'codex'; model: string; effort: string; strength: 1 | 2 | 3; cost: number; offered: boolean; note?: string }+ * a person who names it. `cost` ranks rows of equal strength (lower first); it is not a price. `engineDefault` marks the row a+ * start runs when it asks the engine for `default`: the catalog names the model, never the account's own CLI setting (task+ * #2972: `default default` ran gpt-6-luna on one owner's Mac, which no row rates). */+export interface CatalogModel { engine: 'claude' | 'codex'; model: string; effort: string; strength: 1 | 2 | 3; cost: number; offered: boolean; engineDefault?: true; note?: string }/** How strong a model served on the Swarm's grid counts: the first named row whose every word is in its id or label, else* `strength` (the CLI's route, superTabs/route.ts gridStrength). */export interface CatalogGrid { strength: number; models: ReadonlyArray<{ model: string; strength: number }> }@@ -26,10 +27,11 @@ export const MODEL_CATALOG: { models: readonly CatalogModel[]; grid: CatalogGrid// Opus 5.5 at xhigh, as the coordinator runs (BUILT_IN_ROLE_DEFAULTS.lead): the same price per token as at high, more// thinking per task, so dearer; at equal strength the route keeps choosing high unless the instructions ask for more.{ engine: 'claude', model: 'opus', effort: 'xhigh', strength: 3, cost: 4, offered: true },- { engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },- // Codex's own default model, named: GPT-6.1 Sol scores 58.18 on Terminal-Bench 4.0 in Codex (benchmarkPriors/data.ts) and- // costs Sonnet's API rate (costs/prices.ts).- { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true },+ // Codex's default model, named: GPT-6.1 Sol scores 58.18 on Terminal-Bench 4.0 in Codex (benchmarkPriors/data.ts) and+ // costs Sonnet's API rate (costs/prices.ts). There is no `default default` row: 95% of Codex candidates were that row and+ // 67 of 71 Codex picks (Ken, 2026-11-04), and it ran whatever the account's CLI chose. A start that asks Codex for `default`+ // runs this row (commands.ts agent.start); gpt-6-luna, which an account's CLI chose, has no rating and so no row.+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true, engineDefault: true },// Big builds run on Opus high or Astra xhigh (the owners' standing decision). Its API rate is five times Sol's and 2.5// times Opus's, so it costs 5, after Opus at xhigh: at equal strength the route keeps choosing Opus high first.{ engine: 'codex', model: 'gpt-6-astra', effort: 'xhigh', strength: 3, cost: 5, offered: true },@@ -45,6 +47,12 @@ export const MODEL_CATALOG: { models: readonly CatalogModel[]; grid: CatalogGrid/** What the tab's routing-policy read serves under `catalog`. */export interface CatalogRead { models: readonly CatalogModel[]; grid: CatalogGrid; priors: PriorsTable; prices: readonly ModelPrice[] }+/** The model and effort a start runs when it asks [engine] for `default`, or null when the catalog names none (Claude). */+export function namedDefault(engine: string): { model: string; effort: string } | null {+ const row = MODEL_CATALOG.models.find(m => m.engine === engine && m.engineDefault)+ return row ? { model: row.model, effort: row.effort } : null+}+export function catalogRead(): CatalogRead {return { models: MODEL_CATALOG.models, grid: MODEL_CATALOG.grid, priors: BENCHMARK_PRIORS, prices: PRICES }}diff --git a/backend/src/superTabs/commands.test.ts b/backend/src/superTabs/commands.test.tsindex a4971460b..c3957e1af 100644--- a/backend/src/superTabs/commands.test.ts+++ b/backend/src/superTabs/commands.test.ts@@ -849,6 +849,48 @@ it('starts only in the chosen conversation, captures authority, and never assignexpect(() => f.run({ type: 'agent.start', request, ...via }, actor, { contribution, ...decisionIn(group) })).toThrow('paused')})+// Task #2972 (Ken, 2026-11-04): 67 of 71 Codex picks were `default default`, which ran whatever the account's CLI defaulted to+// (gpt-6-luna on one Mac owner's account). A start that asks Codex for `default` runs the catalog's named default instead.+describe('a Codex start that asks for default', () => {+ const stored = (patch: Record<string, unknown>, withVia = false) => {+ const f = fixture(), lead = f.add('lead', 'owner', 'lead', true), group = f.group()+ const actor: Actor = { kind: 'agent', agentId: lead, machineOwnerId: 'host-owner' }+ const contribution = { machineOwnerId: 'target-owner', contributorId: 'owner', hostGrant: 'grant-1' }+ const request = { conversationId: group, machineId: 'host', engine: 'codex', name: 'Builder', cwd: '/repo', worktree: true,+ requirements: { memoryBytes: 100, diskBytes: 200, maxCpuPercent: 80, tools: ['git'], devices: [], quotaRequired: false }, ...patch }+ f.run({ type: 'agent.start', request, ...(withVia ? { routeDecisionId: 'd1' } : via) } as Command, actor, { contribution, ...decisionIn(group,+ { candidates: [candidate('c0', { machineId: 'host', engine: 'codex', model: 'default', effort: 'default' }), candidate('c1', { machineId: 'host', engine: 'codex', model: 'gpt-6.1-sol', effort: 'high' })] }) })+ const { model, effort } = f.state.starts![0]!.request+ return { model, effort, link: f.state.starts![0] }+ }+ it('runs the catalog\'s named default, Sol at high', () => {+ expect(stored({ model: 'default', effort: 'default' })).toMatchObject({ model: 'gpt-6.1-sol', effort: 'high' })+ expect(stored({ model: 'default' })).toMatchObject({ model: 'gpt-6.1-sol', effort: 'high' })+ })+ it('keeps an effort a person named', () => {+ expect(stored({ model: 'default', effort: 'xhigh' })).toMatchObject({ model: 'gpt-6.1-sol', effort: 'xhigh' })+ })+ it('leaves a named model, a grid model, an unnamed model and Claude as they were', () => {+ expect(stored({ model: 'gpt-6-astra', effort: 'xhigh' })).toMatchObject({ model: 'gpt-6-astra', effort: 'xhigh' })+ expect(stored({ model: 'gpt-6-luna', effort: 'high' })).toMatchObject({ model: 'gpt-6-luna', effort: 'high' })+ expect(stored({ model: 'default', effort: 'default', gridModel: 'kimi', gridName: 'grid' })).toMatchObject({ model: 'default', effort: 'default' })+ expect(stored({})).toEqual(expect.objectContaining({ model: undefined, effort: undefined }))+ expect(stored({ engine: 'claude', model: 'default', effort: 'default' })).toMatchObject({ model: 'default', effort: 'default' })+ })+ it('still links the start to the route candidate that was asked for, `default default` from an older route or Sol at high', () => {+ for (const asked of [{ model: 'default', effort: 'default' }, { model: 'gpt-6.1-sol', effort: 'high' }]) {+ const f = fixture(), lead = f.add('lead', 'owner', 'lead', true), group = f.group()+ const actor: Actor = { kind: 'agent', agentId: lead, machineOwnerId: 'host-owner' }+ const contribution = { machineOwnerId: 'target-owner', contributorId: 'owner', hostGrant: 'grant-1' }+ const request = { conversationId: group, machineId: 'host', engine: 'codex', name: 'Builder', cwd: '/repo', worktree: true, ...asked,+ requirements: { memoryBytes: 100, diskBytes: 200, maxCpuPercent: 80, tools: ['git'], devices: [], quotaRequired: false } }+ const routing = decisionIn(group, { candidates: [candidate('c0', { machineId: 'host', engine: 'codex', ...asked })], pick: undefined, via: 'instructions', p: null })+ const result = f.run({ type: 'agent.start', request, routeDecisionId: 'd1', overrideReason: 'Routing rule.' } as Command, actor, { contribution, ...routing })+ expect(result.messages.map(m => m.text).join('\n')).toMatch(/Routed to Title c0/)+ }+ })+})+it.each(['opencode', 'kilo'])('refuses to dispatch a stored legacy %s start before native launch', engine => {const f = fixture(), lead = f.add('lead', 'owner', 'lead', true), group = f.group()const actor: Actor = { kind: 'agent', agentId: lead, machineOwnerId: 'host-owner' }diff --git a/backend/src/superTabs/commands.ts b/backend/src/superTabs/commands.tsindex 91831605c..57bf82ddf 100644--- a/backend/src/superTabs/commands.ts+++ b/backend/src/superTabs/commands.ts@@ -45,6 +45,7 @@ import { assignedNotice, tellBuddies } from './buddyNews.js'import { bindPullRequestCards, bindTaskCard, pullRequestCard, recordCardMerged } from './cards.js'import { avatarChoice, setAgentAvatar, setMemberAvatar, setStatus, setTimeZone, statusSchema, type AvatarUpload } from './profile.js'import { cancelledTags, cancelReason, switchExpired, unfinishedWork } from './tidy.js'+import { namedDefault } from './catalog.js'import { BUILT_IN_ROLE_DEFAULTS, agentProjectId, audienceOf, groupRepositoryUrl, canReadAgent, canReadProject, deleteProject, markConfidential, onTeamAccount, requireSingleRegistration, groupProject, inviteLanding, ledProject, manageProject, MAX_ROLES, mutableProjects, placeRules, projectAgent, projectMembers, projectOf, projectsOf, readAgent, readConversation, readProject, requestedByLine, sameProject, sharedWithLeads, withRoleDefaults, type SwarmProject, PROJECT_STATUS_MAX } from './projects.js'import { recordClosing, sessionClosed } from './closedAgents.js'import { declinedWith, declinedWithout } from './sharing.js'@@ -2386,7 +2387,13 @@ function applyCommandOnce(original: SuperTabState, actor: Actor, input: Command,// An older client starts in a kind or a custom role, kept on the start for older readers and read by no command: the// role name it means rides on the start to the agent (instructions.ts legacyRoleName).const roleName = command.request.roleName ?? legacyRoleName(home, command.request)- const named = roleName ? { ...command.request, roleName } : command.request+ // A start that asks Codex for `default` runs the catalog's named default, never whatever the account's CLI defaults to+ // (task #2972). A named effort is kept; none, or `default`, takes the row's.+ const catalogDefault = command.request.model === 'default' && !command.request.gridModel ? namedDefault(command.request.engine) : null+ const asked = catalogDefault+ ? { ...command.request, model: catalogDefault.model, effort: !command.request.effort || command.request.effort === 'default' ? catalogDefault.effort : command.request.effort }+ : command.request+ const named = roleName ? { ...asked, roleName } : asked// The Lead's account has machines the Swarm never prepared (no clone of the project), so a Lead may start only where the// Swarm already lists a machine: a contributed one, or one an agent of the Swarm runs on. A person's start may name any// machine of theirs, because the first Lead is created before anything is listed.diff --git a/backend/src/superTabs/routingPolicy.test.ts b/backend/src/superTabs/routingPolicy.test.tsindex 36a481763..deec6d6ed 100644--- a/backend/src/superTabs/routingPolicy.test.ts+++ b/backend/src/superTabs/routingPolicy.test.ts@@ -2,6 +2,10 @@ import { describe, expect, it } from 'vitest'import { DEFAULT_ROUTING_POLICY, effectivePolicy, priorFor, routingOverrideSaveSchema, routingOverrideSchema, routingPolicySaveSchema, routingPolicySchema } from './routingPolicy.js'import type { PriorsTable } from './benchmarkPriors/priors.js'+/** The `default default` Codex row policies saved before task #2972 hold; the catalog no longer has it, and a saved policy's Codex+ * switch is still read off it (effectivePolicy). */+const SAVED_CODEX_DEFAULT = { engine: 'codex' as const, model: 'default', effort: 'default', quality: 3, cost: 2, enabled: true }+describe('routing policy', () => {it('ships a valid default that needs no setup', () => {expect(routingPolicySchema.parse(DEFAULT_ROUTING_POLICY)).toEqual(DEFAULT_ROUTING_POLICY)@@ -81,7 +85,7 @@ describe('routing policy', () => {const opusCosts = DEFAULT_ROUTING_POLICY.models.filter(m => m.model === 'opus').map(m => m.cost)expect(astra.cost).toBeGreaterThan(Math.max(...opusCosts))// A policy saved before the row reads it.- const before = { ...DEFAULT_ROUTING_POLICY, models: DEFAULT_ROUTING_POLICY.models.filter(m => m.model !== 'gpt-6-astra') }+ const before = { ...DEFAULT_ROUTING_POLICY, models: [...DEFAULT_ROUTING_POLICY.models.filter(m => m.model !== 'gpt-6-astra'), SAVED_CODEX_DEFAULT] }expect(effectivePolicy(before, null).policy.models.filter(m => m.model === 'gpt-6-astra')).toEqual([astra])// An owner's own Astra row wins over the built-in one, on or off, and is never doubled (review of #2271).const owned = { ...before, models: [...before.models, { ...astra, effort: 'high', quality: 2, cost: 9, enabled: false }] }@@ -90,7 +94,7 @@ describe('routing policy', () => {describe('a built-in row added on read (review of #2271 at 1d9499646)', () => {const sol = DEFAULT_ROUTING_POLICY.models.find(m => m.model === 'gpt-6.1-sol')!- const codexDefault = DEFAULT_ROUTING_POLICY.models.find(m => m.engine === 'codex' && m.model === 'default')!+ const codexDefault = SAVED_CODEX_DEFAULTconst claudeRows = DEFAULT_ROUTING_POLICY.models.filter(m => m.engine === 'claude')const solOf = (models: Array<{ engine: string; model: string; enabled: boolean }>) => models.find(m => m.model === 'gpt-6.1-sol')diff --git a/cli/src/superTabs/__snapshots__/route.answers.json b/cli/src/superTabs/__snapshots__/route.answers.jsonindex a50061c9f..6f11a46f7 100644--- a/cli/src/superTabs/__snapshots__/route.answers.json+++ b/cli/src/superTabs/__snapshots__/route.answers.json@@ -457,8 +457,8 @@"machineId": "b","machineName": "b","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -495,8 +495,8 @@"account": "B"},"id": "c1",- "title": "New agent · Codex default default · b",- "label": "New agent · Codex default default · strength 3, cost 2 · short: needs about 50% of the 5-hour window (5% left, resets in 4h, otherwise unused); weekly 8% of 60% · b · new · quota 5-hour 5% left (resets in 4h), weekly 60% left (resets in 3 days)"+ "title": "New agent · Codex gpt-6.1-sol high · b",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · short: needs about 50% of the 5-hour window (5% left, resets in 4h, otherwise unused); weekly 8% of 60% · b · new · quota 5-hour 5% left (resets in 4h), weekly 60% left (resets in 3 days)"},{"kind": "new",@@ -590,12 +590,12 @@"kind": "new","machineId": "b","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · b",- "label": "New agent · Codex default default · strength 3, cost 2 · short: needs about 50% of the 5-hour window (5% left, resets in 4h, otherwise unused); weekly 8% of 60% · b · new · quota 5-hour 5% left (resets in 4h), weekly 60% left (resets in 3 days)",+ "title": "New agent · Codex gpt-6.1-sol high · b",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · short: needs about 50% of the 5-hour window (5% left, resets in 4h, otherwise unused); weekly 8% of 60% · b · new · quota 5-hour 5% left (resets in 4h), weekly 60% left (resets in 3 days)","fit": {"status": "short","coverage": 0.1,@@ -742,8 +742,8 @@"machineId": "c","machineName": "c","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -775,8 +775,8 @@"account": "C"},"id": "c2",- "title": "New agent · Codex default default · c",- "label": "New agent · Codex default default · strength 3, cost 2 · fits: 5-hour window unknown; weekly 1% of 30% · c · new · quota weekly 30% left (resets in 6 days)"+ "title": "New agent · Codex gpt-6.1-sol high · c",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · fits: 5-hour window unknown; weekly 1% of 30% · c · new · quota weekly 30% left (resets in 6 days)"}],"excluded": [],@@ -848,12 +848,12 @@"kind": "new","machineId": "c","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · c",- "label": "New agent · Codex default default · strength 3, cost 2 · fits: 5-hour window unknown; weekly 1% of 30% · c · new · quota weekly 30% left (resets in 6 days)",+ "title": "New agent · Codex gpt-6.1-sol high · c",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · fits: 5-hour window unknown; weekly 1% of 30% · c · new · quota weekly 30% left (resets in 6 days)","fit": {"status": "fits","coverage": 30,@@ -1055,8 +1055,8 @@"machineId": "a","machineName": "a","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -1081,16 +1081,16 @@"account": "a:codex"},"id": "c0",- "title": "New agent · Codex default default · a",- "label": "New agent · Codex default default · strength 3, cost 2 · fits: metered, no usage window to run out · a · new · quota metered"+ "title": "New agent · Codex gpt-6.1-sol high · a",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · fits: metered, no usage window to run out · a · new · quota metered"},{"kind": "new","machineId": "b","machineName": "b","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -1115,16 +1115,16 @@"account": "b:codex"},"id": "c1",- "title": "New agent · Codex default default · b",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · b · new · quota unknown (signed out of usage)"+ "title": "New agent · Codex gpt-6.1-sol high · b",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · b · new · quota unknown (signed out of usage)"},{"kind": "new","machineId": "c","machineName": "c","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -1148,16 +1148,16 @@"account": "c:codex"},"id": "c2",- "title": "New agent · Codex default default · c",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · c · new · quota 40% left, resets in 2h"+ "title": "New agent · Codex gpt-6.1-sol high · c",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · c · new · quota 40% left, resets in 2h"},{"kind": "new","machineId": "d","machineName": "d","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,"quota": {@@ -1182,8 +1182,8 @@"account": "d:codex"},"id": "c3",- "title": "New agent · Codex default default · d",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · d · new · quota read on Team Mac, whose subscription this account spends: 40% left"+ "title": "New agent · Codex gpt-6.1-sol high · d",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · d · new · quota read on Team Mac, whose subscription this account spends: 40% left"}],"excluded": [],@@ -1208,12 +1208,12 @@"kind": "new","machineId": "a","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · a",- "label": "New agent · Codex default default · strength 3, cost 2 · fits: metered, no usage window to run out · a · new · quota metered",+ "title": "New agent · Codex gpt-6.1-sol high · a",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · fits: metered, no usage window to run out · a · new · quota metered","fit": {"status": "fits","coverage": null,@@ -1231,12 +1231,12 @@"kind": "new","machineId": "b","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · b",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · b · new · quota unknown (signed out of usage)",+ "title": "New agent · Codex gpt-6.1-sol high · b",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · b · new · quota unknown (signed out of usage)","fit": {"status": "unknown","coverage": null,@@ -1254,12 +1254,12 @@"kind": "new","machineId": "c","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · c",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · c · new · quota 40% left, resets in 2h",+ "title": "New agent · Codex gpt-6.1-sol high · c",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · c · new · quota 40% left, resets in 2h","fit": {"status": "unknown","coverage": null,@@ -1277,12 +1277,12 @@"kind": "new","machineId": "d","engine": "codex",- "model": "default",- "effort": "default",+ "model": "gpt-6.1-sol",+ "effort": "high","quality": 3,"cost": 2,- "title": "New agent · Codex default default · d",- "label": "New agent · Codex default default · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · d · new · quota read on Team Mac, whose subscription this account spends: 40% left",+ "title": "New agent · Codex gpt-6.1-sol high · d",+ "label": "New agent · Codex gpt-6.1-sol high · strength 3, cost 2 · unknown: 5-hour window unknown; weekly unknown · d · new · quota read on Team Mac, whose subscription this account spends: 40% left","fit": {"status": "unknown","coverage": null,@@ -2938,7 +2938,7 @@"machine": "a"},{- "title": "New agent · Codex default default · b",+ "title": "New agent · Codex gpt-6.1-sol high · b","reason": "Codex is signed out.","machine": "b"}diff --git a/cli/src/superTabs/fixtures/planState.ts b/cli/src/superTabs/fixtures/planState.tsindex 2cd3f18c4..6dbe4368b 100644--- a/cli/src/superTabs/fixtures/planState.ts+++ b/cli/src/superTabs/fixtures/planState.ts@@ -5,14 +5,14 @@ export const NOW = Date.parse('2026-10-27T01:00:00Z')/** The routing read of a backend from before the catalog: a policy alone (planCommand.spec.ts reads it as the catalog below). */export const policy = { version: 1, floor: { low: 1, medium: 2, high: 3 }, quotaReserve: 10, notes: '', localModels: { quality: 1, enabled: true }, models: [{ engine: 'claude', model: 'opus', effort: 'high', quality: 3, cost: 3, enabled: true },- { engine: 'codex', model: 'default', effort: 'default', quality: 3, cost: 2, enabled: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', quality: 3, cost: 2, enabled: true },{ engine: 'claude', model: 'sonnet', effort: 'medium', quality: 2, cost: 2, enabled: true },{ engine: 'claude', model: 'haiku', effort: 'auto', quality: 1, cost: 1, enabled: false },] }/** The same rows as a catalog (route.ts catalogFrom). */export const catalog: Catalog = { grid: { strength: 1, models: [] }, models: [{ engine: 'claude', model: 'opus', effort: 'high', strength: 3, cost: 3, offered: true },- { engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true },{ engine: 'claude', model: 'sonnet', effort: 'medium', strength: 2, cost: 2, offered: true },{ engine: 'claude', model: 'haiku', effort: 'auto', strength: 1, cost: 1, offered: false },] }diff --git a/cli/src/superTabs/planCommand.spec.ts b/cli/src/superTabs/planCommand.spec.tsindex 599c72f86..732c1550b 100644--- a/cli/src/superTabs/planCommand.spec.ts+++ b/cli/src/superTabs/planCommand.spec.ts@@ -21,7 +21,7 @@ describe('planWork', () => {it('gives each open group its machine, engine, model and effort, start order and expected finish, against the route', async () => {const run = vi.fn<SolverRun>(async () => answer([- { task: 'g1', machine: 'm1', model: 'codex-default-default', start: 0, end: 60, order: 1 },+ { task: 'g1', machine: 'm1', model: 'codex-gpt-6.1-sol-high', start: 0, end: 60, order: 1 },{ task: 'g2', machine: 'm2', model: 'grid:deepseek/flash', start: 60, end: 180, order: 2 }]))const s = state({ rules, machines: [machine('m1', {}, served), machine('m2')] })const out = await planWork({ request: { groups: { g1: { difficulty: 'high', risk: 'low', size: 'medium' } } } }, scoped(s), { run, now: () => NOW, dataDir: '/unused' })@@ -29,8 +29,8 @@ describe('planWork', () => {expect(out).toEqual({ok: true, status: 'OPTIMAL', makespanMinutes: 180, cost: 540, route: { makespanMinutes: 240, cost: 600 },plan: [- // Codex default leaves the effort to the engine; an owner's minimum effort no longer lifts it (project instructions, phase 4).- { order: 1, groupId: 'g1', group: 'Group g1', machineId: 'm1', machine: 'm1.local', engine: 'codex', model: 'default', effort: 'default',+ // Codex is planned on a model the catalog names, never `default default` (task #2972).+ { order: 1, groupId: 'g1', group: 'Group g1', machineId: 'm1', machine: 'm1.local', engine: 'codex', model: 'gpt-6.1-sol', effort: 'high',startsInMinutes: 0, finishesInMinutes: 60, finishAt: at(60) },{ order: 2, groupId: 'g2', group: 'Group g2', machineId: 'm2', machine: 'm2.local', engine: 'claude', gridModel: 'deepseek/flash', gridName: 'swarm-g',startsInMinutes: 60, finishesInMinutes: 180, finishAt: at(180) },diff --git a/cli/src/superTabs/planInput.spec.ts b/cli/src/superTabs/planInput.spec.tsindex a0632e59f..f8c695b1c 100644--- a/cli/src/superTabs/planInput.spec.ts+++ b/cli/src/superTabs/planInput.spec.ts@@ -162,14 +162,14 @@ describe('planSetup', () => {expect((s.instance.tasks as Json[]).map(t => [t.id, t.floor])).toEqual([['b1', 3], ['r1', 2]])for (const task of s.instance.tasks as Json[]) {expect(task).toMatchObject({ independent_of: [], machines: ['m1', 'm2'],- models: ['claude-opus-high', 'codex-default-default', 'claude-sonnet-medium', 'grid:deepseek/flash'] })+ models: ['claude-opus-high', 'codex-gpt-6.1-sol-high', 'claude-sonnet-medium', 'grid:deepseek/flash'] })}// A review still waits for the work it reviews.expect(taskOf(s, 'r1').deps).toEqual(['b1'])expect((s.instance.machines as Json[]).find(m => m.id === 'm1')).toMatchObject({ engines: ['claude', 'codex'] })expect((s.instance.accounts as Json[]).map(a => a.reserve)).toEqual([0, 0, 0])// A row starts at its own effort: no minimum lifts it.- expect(s.rows['codex-default-default']).toMatchObject({ effort: 'default' })+ expect(s.rows['codex-gpt-6.1-sol-high']).toMatchObject({ effort: 'high' })})// Final review: every task had floor 1 and the solver minimizes finish time then cost, so the plan picked the cheapestdiff --git a/cli/src/superTabs/route.spec.ts b/cli/src/superTabs/route.spec.tsindex fcf8fb701..d6338b7fe 100644--- a/cli/src/superTabs/route.spec.ts+++ b/cli/src/superTabs/route.spec.ts@@ -1,6 +1,6 @@// cli/src/superTabs/route.spec.tsimport { afterEach, describe, expect, it, vi } from 'vitest'-import { API_BUILDERS, CHOOSE_BY_INSTRUCTIONS, NONE_COVERS, catalogFrom, quotaBrief, catalogRow, choose, decide, gridStrength, LOCAL_NONE, OTHER_REPOSITORY, parseAssessment, quotaOf2, recordOf, repoMatch, repositoryKey, strengthOf,+import { API_BUILDERS, CHOOSE_BY_INSTRUCTIONS, CODEX_DEFAULT_NOT_OFFERED, NONE_COVERS, catalogFrom, quotaBrief, catalogRow, choose, decide, gridStrength, LOCAL_NONE, OTHER_REPOSITORY, parseAssessment, quotaOf2, recordOf, repoMatch, repositoryKey, strengthOf,type Assessment, type Catalog, type Commitment, type MemberFrame, type Probe, type RoutePlugin, type TaskFolder } from './route.js'const object = (v: unknown) => v as Record<string, unknown>@@ -9,6 +9,7 @@ const object = (v: unknown) => v as Record<string, unknown>const policy: Catalog = { grid: { strength: 1, models: [] }, models: [{ engine: 'claude', model: 'opus', effort: 'high', strength: 3, cost: 3, offered: true },{ engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true },{ engine: 'claude', model: 'sonnet', effort: 'medium', strength: 2, cost: 2, offered: true },{ engine: 'claude', model: 'haiku', effort: 'auto', strength: 1, cost: 1, offered: false },] }@@ -87,6 +88,33 @@ describe('quota and rates', () => {})})+// Task #2972 (Ken, 2026-11-04): the route put `Codex default default` first 67 times of 71 Codex picks; it ran whatever the+// account's CLI defaulted to. The catalog now names Sol as the engine's default (`engineDefault`) and has no `default` row.+describe('Codex default in the catalog', () => {+ const sol = { engine: 'codex' as const, model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true }+ const named: Catalog = { grid: policy.grid, models: [{ engine: 'claude', model: 'opus', effort: 'high', strength: 3, cost: 3, offered: true }, { ...sol, engineDefault: true }] }+ it('rates a member launched on Codex\'s own model as the catalog\'s named default, and a small variant not at all', () => {+ expect(rate(named, 'codex', null, null)).toEqual({ quality: 3, cost: 2 })+ expect(rate(named, 'codex', 'default', 'default')).toEqual({ quality: 3, cost: 2 })+ expect(rate(named, 'codex', 'gpt-5.5', 'high', true)).toEqual({ quality: 3, cost: 2 })+ expect(rate(named, 'codex', 'gpt-5.5-mini', 'high', true)).toBeNull()+ expect(rate(named, 'codex', 'gpt-5.5', 'high')).toBeNull()+ })+ it('reads the named default from the served catalog, and never offers a `default` Codex row an older backend still serves', () => {+ const rows = [{ engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true, engineDefault: true },+ { engine: 'codex', model: 'gpt-6-astra', effort: 'xhigh', strength: 3, cost: 5, offered: true }]+ const read = catalogFrom({ catalog: { models: rows, grid: { strength: 1, models: [] } } })+ expect(read.models.filter(m => m.offered).map(m => `${m.model} ${m.effort}`)).toEqual(['gpt-6.1-sol high', 'gpt-6-astra xhigh'])+ expect(read.models.find(m => m.model === 'gpt-6.1-sol')).toMatchObject({ engineDefault: true })+ // A member launched on the engine's own model is still rated, by that row.+ expect(rate(read, 'codex', null, null, true)).toEqual({ quality: 3, cost: 2 })+ // The same from an older backend that serves only its policy.+ const old = catalogFrom({ policy: { models: rows.map(({ strength, offered, ...r }) => ({ ...r, quality: strength, enabled: offered })) } })+ expect(old.models.filter(m => m.offered).map(m => `${m.model} ${m.effort}`)).toEqual(['gpt-6.1-sol high', 'gpt-6-astra xhigh'])+ })+})+describe('choose', () => {it('returns NO_CANDIDATE with reasons when nothing can run', () => {expect(choose([probe({ refusals: ['Machine is offline.'] })], policy, a())).toEqual({ error: 'NO_CANDIDATE',@@ -796,7 +824,9 @@ describe('facts, not ranking', () => {it('reads the catalog the backend serves, or one derived from an older backend\'s policy', () => {const served = { policy: { version: 1, models: [] }, catalog: { models: catalog.models, grid: catalog.grid, priors: {}, prices: [] } }- expect(catalogFrom(served)).toEqual(catalog)+ // A Codex row at `default` is kept to rate a member launched on the engine's own model, but is never offered (task #2972).+ expect(catalogFrom(served)).toEqual({ ...catalog, models: catalog.models.map(m => m.engine === 'codex' && m.model === 'default'+ ? { ...m, offered: false, note: CODEX_DEFAULT_NOT_OFFERED } : m) })const old = { policy: { version: 1, floor: { low: 1, medium: 2, high: 3 }, quotaReserve: 10, notes: '', models: [{ engine: 'claude', model: 'opus', effort: 'high', quality: 3, cost: 3, enabled: true },{ engine: 'claude', model: 'sonnet', effort: 'medium', quality: 2, cost: 2, enabled: false },@@ -829,7 +859,8 @@ describe('facts, not ranking', () => {* record must stay byte for byte the same. */describe('route answers without plug-ins', () => {const OPUS = { model: 'opus', effort: 'high', quality: 3, cost: 3 } as const- const CODEX = { engine: 'codex', model: 'default', effort: 'default', quality: 3, cost: 2 } as const+ // Codex as the route offers it since task #2972: the catalog's named model, never `default default`.+ const CODEX = { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', quality: 3, cost: 2 } as constconst on = (machine: string, row: Partial<Probe>, quota: Probe['quota'] = windows([80, 3 * H], [90, 5 * D], machine)) =>probe({ machineId: machine, machineName: machine, ...row, quota })const frame: MemberFrame = { title: 'Fix the dial', project: 'openharness', cwd: '/r', root: '/r', remote: 'github.com/o/r', branch: 'fix/dial', updatedAt: NOW - 20 * M }diff --git a/cli/src/superTabs/route.ts b/cli/src/superTabs/route.tsindex 324de44ba..b8ae689cd 100644--- a/cli/src/superTabs/route.ts+++ b/cli/src/superTabs/route.ts@@ -25,7 +25,10 @@ export interface Needs { tools: string[]; devices: string[]; cwd?: string; heavyexport interface Assessment { difficulty: Level; risk: Level; size: Size; why: string; kind?: string; local?: boolean; model?: string; needs: Needs }/** A model of the reviewed catalog (backend superTabs/catalog.ts): how strong it is, what it costs, and whether it is offered* when nobody names it. */-export interface CatalogModel { engine: 'claude' | 'codex'; model: string; effort: string; strength: number; cost: number; offered: boolean; note?: string }+export interface CatalogModel { engine: 'claude' | 'codex'; model: string; effort: string; strength: number; cost: number; offered: boolean; engineDefault?: true; note?: string }+/** Why a Codex row at `default` model or effort is never offered. A backend from before task #2972 still serves one: it ran whatever+ * the account's CLI defaulted to (gpt-6-luna on one owner's Mac), 67 of 71 Codex picks in a day, and no one rated that. */+export const CODEX_DEFAULT_NOT_OFFERED = 'Codex at its default model or effort is not offered: it runs whatever the account\'s CLI chooses. Start the catalog\'s named models.'/** The catalog's models and how strong the models served on the Swarm's grid count: the first named row whose every word is* in a model's name, else `strength`. */export interface Catalog { models: CatalogModel[]; grid: { strength: number; models: Array<{ model: string; strength: number }> } }@@ -212,8 +215,11 @@ export function catalogFrom(effective: Json): Catalog {const models = rows.map(object).flatMap((m): CatalogModel[] => {const strength = served ? m.strength : m.quality, offered = served ? m.offered : m.enabledif (!ENGINES.includes(String(m.engine)) || typeof m.model !== 'string' || typeof m.effort !== 'string' || !finite(strength) || !finite(m.cost)) return []- return [{ engine: m.engine as CatalogModel['engine'], model: m.model, effort: m.effort, strength, cost: m.cost, offered: offered === true,- ...(served && typeof m.note === 'string' && m.note ? { note: m.note } : {}) }]+ // A Codex row at `default` model or effort stays for rating a member launched on the engine's own model, but is never offered.+ const unnamed = m.engine === 'codex' && (m.model === 'default' || m.effort === 'default')+ return [{ engine: m.engine as CatalogModel['engine'], model: m.model, effort: m.effort, strength, cost: m.cost, offered: offered === true && !unnamed,+ ...(served && m.engineDefault === true ? { engineDefault: true as const } : {}),+ ...(unnamed ? { note: CODEX_DEFAULT_NOT_OFFERED } : served && typeof m.note === 'string' && m.note ? { note: m.note } : {}) }]})const grid = served ? object(catalog.grid) : object(policy.localModels)const gridRows = (Array.isArray(grid.models) ? grid.models : []) as unknown[]@@ -303,13 +309,15 @@ export function repositoryKey(url: string): string | null {}/** A member's model is what its engine reported after work: Claude's full id (`claude-opus-4-7`, `claude-sonnet-4-5[1m]`),- * Codex's slug (`gpt-5.5`). The catalog names Claude families and a Codex `default`, so the id is reduced to its family- * first. Its row: the exact one, else the model's at another effort, else the engine's `default` row when the agent was+ * Codex's slug (`gpt-5.5`). The catalog names Claude families and Codex's default model, so the id is reduced to its family+ * first. Its row: the exact one, else the model's at another effort, else the engine's named default when the agent was* launched on the engine's own model ([engineDefault]) and is no small variant; otherwise none, so a small Codex variant is* never taken for a strong one (review of #2137). */export function catalogRow(c: Catalog, engine: string, model: string | null, effort: string | null, engineDefault = false): CatalogModel | null {const name = engine === 'claude' && model ? claudeAliasForModel(model.replace(/\[1m\]$/i, '')) ?? model : model ?? 'default'- const rowOf = (named: string) => c.models.find(m => m.engine === engine && m.model === named && m.effort === (effort ?? 'default'))+ // The engine's own model is the catalog's named default (`engineDefault`), else a `default` row of an older backend.+ const rowOf = (named: string) => named === 'default' ? c.models.find(m => m.engine === engine && m.engineDefault) ?? c.models.find(m => m.engine === engine && m.model === 'default')+ : c.models.find(m => m.engine === engine && m.model === named && m.effort === (effort ?? 'default'))?? c.models.find(m => m.engine === engine && m.model === named)// A small model it reports is never promoted by its launch (review of ee4ee6c9a).return rowOf(name) ?? (engineDefault && !SMALL.test(model ?? '') ? rowOf('default') : undefined) ?? nulldiff --git a/cli/src/superTabs/routeCommand.spec.ts b/cli/src/superTabs/routeCommand.spec.tsindex c6fa308ba..f8323de9b 100644--- a/cli/src/superTabs/routeCommand.spec.ts+++ b/cli/src/superTabs/routeCommand.spec.ts@@ -18,6 +18,7 @@ const policy = { version: 1, floor: { low: 1, medium: 2, high: 3 }, quotaReserve{ engine: 'claude', model: 'opus', effort: 'high', quality: 3, cost: 3, enabled: true },{ engine: 'claude', model: 'sonnet', effort: 'medium', quality: 3, cost: 2, enabled: true },{ engine: 'codex', model: 'default', effort: 'default', quality: 3, cost: 2, enabled: false },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', quality: 3, cost: 2, enabled: false },] }/** The table with Sonnet at its real rating, 2, for the specs of strength and floors. */const floorPolicy = { ...policy, models: policy.models.map(m => m.model === 'sonnet' ? { ...m, quality: 2 } : m) }@@ -1945,6 +1946,30 @@ describe('routing by facts', () => {expect(shown(old).map(r => r.title)).toContain('New agent · Claude sonnet medium · remote-1')})+ // Task #2972: 95% of Codex candidates were `Codex default default` (6,570 against 122 Sol and 116 Astra), and 67 of 71 Codex picks;+ // it ran whatever the account's CLI defaulted to (gpt-6-luna on one owner's account), which the catalog does not rate.+ it('offers a Codex machine only the models the catalog rates, never `default default`, and gpt-6-luna only when named', async () => {+ const catalog = { models: [{ engine: 'claude', model: 'opus', effort: 'high', strength: 3, cost: 3, offered: true },+ { engine: 'codex', model: 'default', effort: 'default', strength: 3, cost: 2, offered: true },+ { engine: 'codex', model: 'gpt-6.1-sol', effort: 'high', strength: 3, cost: 2, offered: true, engineDefault: true },+ { engine: 'codex', model: 'gpt-6-astra', effort: 'xhigh', strength: 3, cost: 5, offered: true }],+ grid: { strength: 1, models: [] }, priors: {}, prices: [] }+ const both = () => opener(id => daemon(id, { agents: id === 'm1' ? ['h1'] : [],+ engines: [{ engine: 'claude', installed: true, signedIn: true }, { engine: 'codex', installed: true, signedIn: true }] }))+ const context = (extra: Record<string, unknown> = {}) => scoped({ context: { ok: true, value: { agentId: 'lead', tab: tab(), policy: { policy, warnings: [], catalog }, machines: [{ machineId: 'm1', name: 'remote-1' }], ...extra } } })+ const served = context()+ await routeTask(input, served, where as never, both(), () => 'op')+ const codex = shown(served).filter(r => r.title.startsWith('New agent · Codex'))+ expect(codex.map(r => r.title)).toEqual(['New agent · Codex gpt-6-astra xhigh · remote-1', 'New agent · Codex gpt-6.1-sol high · remote-1'])+ expect(codex.map(r => r.label).join('\n')).toMatch(/strength 3, cost 5[\s\S]*strength 3, cost 2/)+ expect(shown(served).map(r => r.title).join('\n')).not.toMatch(/Codex default|luna/)+ // A person who names the model gets it, unrated: gpt-6-luna is no row of the catalog.+ const luna = context()+ await routeTask({ ...input, assessment: { ...input.assessment, model: 'gpt-6-luna' } }, luna, where as never, both(), () => 'op')+ expect(shown(luna).filter(r => r.title.startsWith('New agent')).map(r => r.title)).toEqual(['New agent · Codex gpt-6-luna default · remote-1'])+ expect(shown(luna)[0]!.label).toContain('unrated')+ })+// Final review: a named grid model whose host is down became an unrated Codex candidate; nothing serves it, and the route says// why. An unreadable catalog became an empty one without a word: no new agent was offered and nobody heard why.it('names no stand-in for a named model whose host is offline, and says why', async () => {diff --git a/docs/plans/2026-11-04-route-real-codex-models-plan.md b/docs/plans/2026-11-04-route-real-codex-models-plan.mdnew file mode 100644index 000000000..1680b3d4f--- /dev/null+++ b/docs/plans/2026-11-04-route-real-codex-models-plan.md@@ -0,0 +1,86 @@+# Route offers real Codex models Implementation Plan++> Implemented by the task's Engineer task by task, each failing test committed before its code (project instructions,+> Engineer). One independent review on the pull request.++**Goal:** The route never offers Codex "default default". It offers the models the catalog rates (GPT-6.1 Sol at high,+GPT-6 Astra at xhigh), and a start that asks Codex for `default` runs the catalog's named default, Sol at high, not+whatever the account's CLI defaults to (task #2972, Ken, 2026-11-04).++**Architecture:** Measured in the 24 hours before #3010's release: 95% of Codex candidates were `codex default default`+and 67 of 71 Codex picks were that row, so a PM that started it as offered got a model nobody rated; the two Codex runs+were `gpt-6-luna`, the default of one Mac owner's account, which the catalog does not list.++- Backend `catalog.ts`: drop the `codex/default/default` row. Mark the Sol row `engineDefault`, the catalog's own word for+ "the model Codex runs when nobody names one", so the backend and the CLI read it from one place.+- Backend `commands.ts` `agent.start`: a Codex start with `model: 'default'` (not a grid model) is stored as the+ catalog's default model, and an effort of `default` or none as that row's effort. A named effort is kept. The route+ decision link still matches on what the caller sent, so a start of an old `default default` candidate stays linked.+- Backend `routingPolicy.ts`: an owner's saved policy gets the Sol and Astra rows when Codex is on; that was read off the+ `default` row, which no longer exists, so it reads any enabled Codex row.+- CLI `route.ts`: `catalogFrom` keeps `engineDefault`. A `codex` row at `default` model or effort read from an older+ backend is not offered. `catalogRow` takes the `engineDefault` row for a member launched on the engine's own model, so+ it keeps its Sol rating.+- A Codex start that names no model at all is left as it is: Desktop's import sends none to keep an existing session's model, and+ the route always names one. Only `model: 'default'` is resolved.+- `gpt-6-luna` is not rated: there is no benchmark for it, so it is never offered unless a person names it, when it is+ offered unrated as before.++**Tech Stack:** TypeScript; vitest in `backend/` and `cli/`.++**Spec:** task #2972's brief.++## Global Constraints++- Red first for each risk the task names; red/green evidence in a PR comment.+- Order stays the instructions' (#2901): nothing here ranks.+- Swarm code stays out of `cli/src/core`.+- No new setting; no migration: the catalog is served on read and old CLIs read the same rows as a policy.++## Design++- growth: N/A because the catalog is a fixed list of rows in code; one row fewer.+- concurrency: N/A because nothing is stored beyond the start's request, written under the existing command lock.+- read cost: N/A because the catalog read is unchanged in size (one row fewer).+- scale: N/A because nothing scales with the change.+- compatibility: an older CLI reading the catalog or the policy sees no `default` row, so it offers the named models;+ a newer CLI on an older backend does not offer a `default` row it still serves; a start that sends `default` from an+ older client is resolved by the backend.+- migration + rollback: none; reverting the commit restores the row, and a start made meanwhile keeps the explicit model+ it was stored with.+- audience: N/A because the catalog is public to members already.+- identity: N/A because no login is read or written.+- failure: a Team account whose owner's ChatGPT plan does not offer Sol is refused before launch with what it offers+ (the existing `codexModelNotOffered` check), instead of launching on whatever the CLI defaults to.+- platforms: all; no platform code.++## Review Focus++- A start with `model: 'default'` on Codex, with and without an effort, a named effort, a grid model, and Claude.+- Saved routing policies keep their Sol and Astra rows with the `default` row gone.+- Members launched on the engine's own model keep their rating.++## Tasks++### Task 1: The route offers only named Codex models++**Files:** `backend/src/superTabs/catalog.ts`, `backend/src/superTabs/catalog.test.ts`,+`backend/src/superTabs/routingPolicy.ts`, `cli/src/superTabs/route.ts`, `cli/src/superTabs/routeCommand.spec.ts`,+`cli/src/superTabs/__snapshots__/route.answers.json`++- [ ] Failing test: the catalog has no Codex `default` row, and Sol is its `engineDefault`.+- [ ] Failing test: a route over a catalog served with a `default` row (older backend) offers Sol high and Astra xhigh+ and never `default default`, on a Codex machine; `gpt-6-luna` is never offered, and is offered unrated when named.+- [ ] Failing test: a member launched on the engine's own model is rated as the catalog's `engineDefault`.+- [ ] Failing test: a saved policy still gains its Sol and Astra rows.+- [ ] Code for the above; update the route snapshot.++### Task 2: A Codex start for `default` runs the catalog's default++**Files:** `backend/src/superTabs/commands.ts`, `backend/src/superTabs/commands.test.ts`++- [ ] Failing test: `agent.start` Codex `default`/`default` is stored as Sol at high; `default` with a named effort+ keeps the effort; `default` with no effort gets high; a named model, a grid model and Claude are untouched.+- [ ] Failing test: starting a candidate by the route decision still links to it, for an old `default default` candidate+ and for Sol high.+- [ ] Code.