mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-17 09:41:58 +00:00
refactor(desktop): make composer model picker sticky session state
The picker no longer touches the profile default. Model/effort/fast live as plain UI state persisted in localStorage, so a pick follows across Cmd+N and restarts instead of snapping back. New chats ship that state through session.create as per-session overrides; live chats still scope switches to the current session. Settings -> Model remains the only surface that writes the profile default. The gateway now accepts those session.create overrides, builds the agent with them directly, reflects them in the immediate session.info payload, and writes the chat's own model_config into the lazy DB row so reconnect/resume restores that chat instead of the global default.
This commit is contained in:
Brooklyn Nicholson
parent
dd0e3e0a05
commit
cb6b4127e7
16 changed files with 405 additions and 105 deletions
|
|
@ -711,7 +711,9 @@ export function DesktopController() {
|
|||
}
|
||||
|
||||
lastGatewayProfileRef.current = activeGatewayProfile
|
||||
void refreshCurrentModel()
|
||||
// Force: the new profile has its own default, so reseed even if the composer
|
||||
// already shows the previous profile's model.
|
||||
void refreshCurrentModel(true)
|
||||
void refreshActiveProfile()
|
||||
}, [activeGatewayProfile, refreshCurrentModel])
|
||||
|
||||
|
|
|
|||
|
|
@ -130,7 +130,6 @@ describe('useModelControls', () => {
|
|||
await expect(
|
||||
controls.selectModel({
|
||||
model: 'claude-sonnet-4.6',
|
||||
persistGlobal: false,
|
||||
provider: 'anthropic'
|
||||
})
|
||||
).resolves.toBe(true)
|
||||
|
|
@ -143,26 +142,57 @@ describe('useModelControls', () => {
|
|||
expect(requestGateway).not.toHaveBeenCalledWith('slash.exec', expect.anything())
|
||||
})
|
||||
|
||||
it('keeps the global path on setGlobalModel when there is no active session', async () => {
|
||||
setGlobalModel.mockResolvedValue(undefined)
|
||||
it('stores a no-session pick as UI state with no gateway or global write', async () => {
|
||||
const requestGateway = vi.fn()
|
||||
let controls!: Controls
|
||||
|
||||
render(
|
||||
<Harness
|
||||
activeSessionId={null}
|
||||
onReady={value => (controls = value)}
|
||||
requestGateway={vi.fn()}
|
||||
requestGateway={requestGateway}
|
||||
/>
|
||||
)
|
||||
|
||||
await expect(
|
||||
controls.selectModel({
|
||||
model: 'claude-sonnet-4.6',
|
||||
persistGlobal: false,
|
||||
provider: 'anthropic'
|
||||
})
|
||||
).resolves.toBe(true)
|
||||
|
||||
expect(setGlobalModel).toHaveBeenCalledWith('anthropic', 'claude-sonnet-4.6')
|
||||
// The pick is plain UI state; session.create ships it later. Nothing touches
|
||||
// the gateway or the profile default here.
|
||||
expect($currentModel.get()).toBe('claude-sonnet-4.6')
|
||||
expect($currentProvider.get()).toBe('anthropic')
|
||||
expect(requestGateway).not.toHaveBeenCalled()
|
||||
expect(setGlobalModel).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('seeds an empty composer model from global but never clobbers a pick', async () => {
|
||||
vi.mocked(getGlobalModelInfo).mockResolvedValue({ model: 'openai/gpt-5.5', provider: 'openai-codex' })
|
||||
|
||||
const { result } = renderHook(() =>
|
||||
useModelControls({
|
||||
activeSessionId: null,
|
||||
queryClient: new QueryClient(),
|
||||
requestGateway: vi.fn()
|
||||
})
|
||||
)
|
||||
|
||||
// Empty → seeds the default.
|
||||
await result.current.refreshCurrentModel()
|
||||
expect($currentModel.get()).toBe('openai/gpt-5.5')
|
||||
|
||||
// A user pick must survive the lifecycle refreshes that fire on boot / fresh
|
||||
// draft / session events.
|
||||
setCurrentModel('anthropic/claude-sonnet-4.6')
|
||||
setCurrentProvider('anthropic')
|
||||
await result.current.refreshCurrentModel()
|
||||
expect($currentModel.get()).toBe('anthropic/claude-sonnet-4.6')
|
||||
|
||||
// A profile swap forces a reseed to the new profile's default.
|
||||
await result.current.refreshCurrentModel(true)
|
||||
expect($currentModel.get()).toBe('openai/gpt-5.5')
|
||||
})
|
||||
})
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
import { type QueryClient } from '@tanstack/react-query'
|
||||
import { useCallback } from 'react'
|
||||
|
||||
import { getGlobalModelInfo, setGlobalModel } from '@/hermes'
|
||||
import { getGlobalModelInfo } from '@/hermes'
|
||||
import { useI18n } from '@/i18n'
|
||||
import { notifyError } from '@/store/notifications'
|
||||
import {
|
||||
|
|
@ -15,7 +15,6 @@ import type { ModelOptionsResponse } from '@/types/hermes'
|
|||
|
||||
interface ModelSelection {
|
||||
model: string
|
||||
persistGlobal: boolean
|
||||
provider: string
|
||||
}
|
||||
|
||||
|
|
@ -28,6 +27,7 @@ interface ModelControlsOptions {
|
|||
export function useModelControls({ activeSessionId, queryClient, requestGateway }: ModelControlsOptions) {
|
||||
const { t } = useI18n()
|
||||
const copy = t.desktop
|
||||
|
||||
const updateModelOptionsCache = useCallback(
|
||||
(provider: string, model: string, includeGlobal: boolean) => {
|
||||
const patch = (prev: ModelOptionsResponse | undefined) => ({ ...(prev ?? {}), provider, model })
|
||||
|
|
@ -41,14 +41,24 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
|
|||
[activeSessionId, queryClient]
|
||||
)
|
||||
|
||||
const refreshCurrentModel = useCallback(async () => {
|
||||
// Seed the composer's model state from the profile default. `force` reseeds
|
||||
// for a profile swap (the new profile has its own default); otherwise this
|
||||
// only fills an EMPTY selection so a user's pick (plain UI state in
|
||||
// $currentModel) survives the lifecycle refreshes that fire on boot / fresh
|
||||
// draft / session events. A live session owns the footer, so skip entirely.
|
||||
const refreshCurrentModel = useCallback(async (force = false) => {
|
||||
try {
|
||||
if ($activeSessionId.get()) {
|
||||
return
|
||||
}
|
||||
|
||||
if (!force && $currentModel.get()) {
|
||||
return
|
||||
}
|
||||
|
||||
const result = await getGlobalModelInfo()
|
||||
|
||||
// A resumed/live session owns the footer model state. Global config
|
||||
// refreshes (gateway boot, profile swap, settings save) must not clobber
|
||||
// the active chat's runtime model/provider in the status bar.
|
||||
if ($activeSessionId.get()) {
|
||||
if ($activeSessionId.get() || (!force && $currentModel.get())) {
|
||||
return
|
||||
}
|
||||
|
||||
|
|
@ -64,12 +74,14 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
|
|||
}
|
||||
}, [])
|
||||
|
||||
// Returns whether the switch succeeded so callers can await it before
|
||||
// applying follow-up changes (e.g. editing a model's reasoning/fast must land
|
||||
// on the right active model — bail rather than write to the previous one).
|
||||
// Returns whether the switch succeeded so callers can await it before applying
|
||||
// follow-up changes. The composer model is plain UI state: with no live
|
||||
// session it's just stored (and shipped on the next session.create); with one
|
||||
// it's scoped to that session via config.set. It NEVER writes the profile
|
||||
// default — that lives in Settings → Model — so picking a model here can't
|
||||
// silently mutate global config.
|
||||
const selectModel = useCallback(
|
||||
async (selection: ModelSelection): Promise<boolean> => {
|
||||
const includeGlobal = selection.persistGlobal || !activeSessionId
|
||||
// Snapshot for rollback: the switch is applied optimistically, so a
|
||||
// failure must restore the prior model/provider (store + query cache)
|
||||
// rather than leave the UI showing a model the backend never selected.
|
||||
|
|
@ -78,42 +90,34 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
|
|||
|
||||
setCurrentModel(selection.model)
|
||||
setCurrentProvider(selection.provider)
|
||||
updateModelOptionsCache(selection.provider, selection.model, includeGlobal)
|
||||
updateModelOptionsCache(selection.provider, selection.model, !activeSessionId)
|
||||
|
||||
// No live session yet: the pick is pure UI state. session.create reads
|
||||
// $currentModel/$currentProvider and applies it as that session's override.
|
||||
if (!activeSessionId) {
|
||||
return true
|
||||
}
|
||||
|
||||
try {
|
||||
if (activeSessionId) {
|
||||
await requestGateway('config.set', {
|
||||
session_id: activeSessionId,
|
||||
key: 'model',
|
||||
value: `${selection.model} --provider ${selection.provider}${selection.persistGlobal ? ' --global' : ''}`
|
||||
})
|
||||
await requestGateway('config.set', {
|
||||
session_id: activeSessionId,
|
||||
key: 'model',
|
||||
value: `${selection.model} --provider ${selection.provider}`
|
||||
})
|
||||
|
||||
if (selection.persistGlobal) {
|
||||
void refreshCurrentModel()
|
||||
}
|
||||
|
||||
void queryClient.invalidateQueries({
|
||||
queryKey: selection.persistGlobal ? ['model-options'] : ['model-options', activeSessionId]
|
||||
})
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
await setGlobalModel(selection.provider, selection.model)
|
||||
void refreshCurrentModel()
|
||||
void queryClient.invalidateQueries({ queryKey: ['model-options'] })
|
||||
void queryClient.invalidateQueries({ queryKey: ['model-options', activeSessionId] })
|
||||
|
||||
return true
|
||||
} catch (err) {
|
||||
setCurrentModel(prevModel)
|
||||
setCurrentProvider(prevProvider)
|
||||
updateModelOptionsCache(prevProvider, prevModel, includeGlobal)
|
||||
updateModelOptionsCache(prevProvider, prevModel, !activeSessionId)
|
||||
notifyError(err, copy.modelSwitchFailed)
|
||||
|
||||
return false
|
||||
}
|
||||
},
|
||||
[activeSessionId, copy.modelSwitchFailed, queryClient, refreshCurrentModel, requestGateway, updateModelOptionsCache]
|
||||
[activeSessionId, copy.modelSwitchFailed, queryClient, requestGateway, updateModelOptionsCache]
|
||||
)
|
||||
|
||||
return { refreshCurrentModel, selectModel, updateModelOptionsCache }
|
||||
|
|
|
|||
|
|
@ -15,6 +15,10 @@ import { requestDesktopOnboarding } from '@/store/onboarding'
|
|||
import { $activeGatewayProfile, $newChatProfile, $profiles, ensureGatewayProfile, normalizeProfileKey } from '@/store/profile'
|
||||
import {
|
||||
$currentCwd,
|
||||
$currentFastMode,
|
||||
$currentModel,
|
||||
$currentProvider,
|
||||
$currentReasoningEffort,
|
||||
$messages,
|
||||
$sessions,
|
||||
$yoloActive,
|
||||
|
|
@ -407,13 +411,13 @@ export function useSessionActions({
|
|||
})
|
||||
setSessionStartedAt(null)
|
||||
setTurnStartedAt(null)
|
||||
// New chats start in the configured default project dir when set,
|
||||
// otherwise the sticky last-used workspace (PR #37586).
|
||||
setCurrentModel('')
|
||||
setCurrentProvider('')
|
||||
setCurrentReasoningEffort('')
|
||||
// The composer's model/effort/fast is sticky UI state (persisted in
|
||||
// localStorage) — a new chat FOLLOWS your last pick instead of snapping
|
||||
// back to the profile default, so we deliberately don't reset it here. The
|
||||
// profile default still owns first-run seeding and profile switches (see
|
||||
// refreshCurrentModel). Only $currentServiceTier (a live-session mirror)
|
||||
// is cleared.
|
||||
setCurrentServiceTier('')
|
||||
setCurrentFastMode(false)
|
||||
setYoloActive(false)
|
||||
setCurrentCwd(workspaceCwdForNewSession())
|
||||
setCurrentBranch('')
|
||||
|
|
@ -443,11 +447,23 @@ export function useSessionActions({
|
|||
const newChatProfile = $newChatProfile.get() ?? normalizeProfileKey($activeGatewayProfile.get())
|
||||
await ensureGatewayProfile(newChatProfile)
|
||||
const cwd = $currentCwd.get().trim() || workspaceCwdForNewSession()
|
||||
// The composer's model/effort/fast is sticky UI state ($currentModel,
|
||||
// $currentProvider, $currentReasoningEffort, $currentFastMode). Ship it
|
||||
// with every session.create so the new chat opens on whatever the picker
|
||||
// shows — applied as per-session overrides, never written to the profile
|
||||
// default (that lives in Settings → Model).
|
||||
const uiModel = $currentModel.get().trim()
|
||||
const uiProvider = $currentProvider.get().trim()
|
||||
const uiEffort = $currentReasoningEffort.get().trim()
|
||||
const uiFast = $currentFastMode.get()
|
||||
|
||||
const created = await requestGateway<SessionCreateResponse>('session.create', {
|
||||
cols: 96,
|
||||
...(cwd && { cwd }),
|
||||
...(newChatProfile ? { profile: newChatProfile } : {})
|
||||
...(newChatProfile ? { profile: newChatProfile } : {}),
|
||||
...(uiModel ? { model: uiModel, ...(uiProvider ? { provider: uiProvider } : {}) } : {}),
|
||||
...(uiEffort ? { reasoning_effort: uiEffort } : {}),
|
||||
...(uiFast ? { fast: true } : {})
|
||||
})
|
||||
|
||||
const stored = created.stored_session_id ?? null
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ import { ModelEditSubmenu, resolveFastControl } from './model-edit-submenu'
|
|||
|
||||
interface ModelMenuPanelProps {
|
||||
gateway?: HermesGateway
|
||||
onSelectModel: (selection: { model: string; persistGlobal: boolean; provider: string }) => Promise<boolean> | void
|
||||
onSelectModel: (selection: { model: string; provider: string }) => Promise<boolean> | void
|
||||
requestGateway: <T>(method: string, params?: Record<string, unknown>) => Promise<T>
|
||||
}
|
||||
|
||||
|
|
@ -95,8 +95,10 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
|
|||
[visibleModels, providers]
|
||||
)
|
||||
|
||||
const switchTo = (model: string, provider: string) =>
|
||||
onSelectModel({ model, persistGlobal: !activeSessionId, provider })
|
||||
// The composer picker never persists the profile default. With a session it
|
||||
// scopes the switch to that session; with none it's UI state shipped on the
|
||||
// next session.create (see selectModel). The default lives in Settings → Model.
|
||||
const switchTo = (model: string, provider: string) => onSelectModel({ model, provider })
|
||||
|
||||
// Selecting a model row restores that model's remembered preset onto the
|
||||
// session (effort/fast), gated by capability. Unset → Hermes defaults.
|
||||
|
|
|
|||
|
|
@ -11,7 +11,6 @@ import { startManualOnboarding } from '../store/onboarding'
|
|||
|
||||
import { InlineNotice } from './notifications'
|
||||
import { Button } from './ui/button'
|
||||
import { Checkbox } from './ui/checkbox'
|
||||
import { Command, CommandEmpty, CommandGroup, CommandInput, CommandItem, CommandList } from './ui/command'
|
||||
import { Dialog, DialogContent, DialogDescription, DialogFooter, DialogHeader, DialogTitle } from './ui/dialog'
|
||||
import { Skeleton } from './ui/skeleton'
|
||||
|
|
@ -23,7 +22,7 @@ interface ModelPickerDialogProps {
|
|||
sessionId?: string | null
|
||||
currentModel: string
|
||||
currentProvider: string
|
||||
onSelect: (selection: { provider: string; model: string; persistGlobal: boolean }) => void
|
||||
onSelect: (selection: { provider: string; model: string }) => void
|
||||
/**
|
||||
* Optional class to apply to DialogContent. Use to override z-index when
|
||||
* stacking the picker on top of another fixed overlay (e.g. the desktop
|
||||
|
|
@ -45,7 +44,6 @@ export function ModelPickerDialog({
|
|||
}: ModelPickerDialogProps) {
|
||||
const { t } = useI18n()
|
||||
const copy = t.modelPicker
|
||||
const [persistGlobal, setPersistGlobal] = useState(!sessionId)
|
||||
// Own the search term so we can filter manually. cmdk's built-in
|
||||
// shouldFilter reorders items by its fuzzy-match score (≈alphabetical with
|
||||
// an empty query), which destroys the backend's curated order. We disable
|
||||
|
|
@ -79,11 +77,7 @@ export function ModelPickerDialog({
|
|||
: null
|
||||
|
||||
const selectModel = (provider: ModelOptionProvider, model: string) => {
|
||||
onSelect({
|
||||
provider: provider.slug,
|
||||
model,
|
||||
persistGlobal: persistGlobal || !sessionId
|
||||
})
|
||||
onSelect({ provider: provider.slug, model })
|
||||
onOpenChange(false)
|
||||
}
|
||||
|
||||
|
|
@ -128,24 +122,13 @@ export function ModelPickerDialog({
|
|||
</CommandList>
|
||||
</Command>
|
||||
|
||||
<DialogFooter className="flex-row items-center justify-between gap-3 bg-card p-3 sm:justify-between">
|
||||
<label className="flex cursor-pointer select-none items-center gap-2 text-xs text-muted-foreground">
|
||||
<Checkbox
|
||||
checked={persistGlobal || !sessionId}
|
||||
disabled={!sessionId}
|
||||
onCheckedChange={checked => setPersistGlobal(checked === true)}
|
||||
/>
|
||||
{sessionId ? copy.persistGlobalSession : copy.persistGlobal}
|
||||
</label>
|
||||
|
||||
<div className="flex items-center gap-2">
|
||||
<Button onClick={addProvider} variant="ghost">
|
||||
{copy.addProvider}
|
||||
</Button>
|
||||
<Button onClick={() => onOpenChange(false)} variant="outline">
|
||||
{t.common.cancel}
|
||||
</Button>
|
||||
</div>
|
||||
<DialogFooter className="flex-row items-center justify-end gap-2 bg-card p-3">
|
||||
<Button onClick={addProvider} variant="ghost">
|
||||
{copy.addProvider}
|
||||
</Button>
|
||||
<Button onClick={() => onOpenChange(false)} variant="outline">
|
||||
{t.common.cancel}
|
||||
</Button>
|
||||
</DialogFooter>
|
||||
</DialogContent>
|
||||
</Dialog>
|
||||
|
|
|
|||
|
|
@ -1503,8 +1503,6 @@ export const en: Translations = {
|
|||
unknown: '(unknown)',
|
||||
search: 'Filter providers and models...',
|
||||
noModels: 'No models found.',
|
||||
persistGlobalSession: 'Persist globally (otherwise this session only)',
|
||||
persistGlobal: 'Persist globally',
|
||||
addProvider: 'Add provider',
|
||||
loadFailed: 'Could not load models',
|
||||
noAuthenticatedProviders: 'No authenticated providers.',
|
||||
|
|
|
|||
|
|
@ -1637,8 +1637,6 @@ export const ja = defineLocale({
|
|||
unknown: '(不明)',
|
||||
search: 'プロバイダーとモデルをフィルター...',
|
||||
noModels: 'モデルが見つかりません。',
|
||||
persistGlobalSession: 'グローバルに保持（それ以外はこのセッションのみ）',
|
||||
persistGlobal: 'グローバルに保持',
|
||||
addProvider: 'プロバイダーを追加',
|
||||
loadFailed: 'モデルを読み込めませんでした',
|
||||
noAuthenticatedProviders: '認証済みプロバイダーがありません。',
|
||||
|
|
|
|||
|
|
@ -1145,8 +1145,6 @@ export interface Translations {
|
|||
unknown: string
|
||||
search: string
|
||||
noModels: string
|
||||
persistGlobalSession: string
|
||||
persistGlobal: string
|
||||
addProvider: string
|
||||
loadFailed: string
|
||||
noAuthenticatedProviders: string
|
||||
|
|
|
|||
|
|
@ -1581,8 +1581,6 @@ export const zhHant = defineLocale({
|
|||
unknown: '（未知）',
|
||||
search: '篩選提供方和模型...',
|
||||
noModels: '找不到模型。',
|
||||
persistGlobalSession: '全域儲存（否則僅限此工作階段）',
|
||||
persistGlobal: '全域儲存',
|
||||
addProvider: '新增提供方',
|
||||
loadFailed: '無法載入模型',
|
||||
noAuthenticatedProviders: '沒有已驗證的提供方。',
|
||||
|
|
|
|||
|
|
@ -1683,8 +1683,6 @@ export const zh: Translations = {
|
|||
unknown: '(未知)',
|
||||
search: '筛选提供方和模型...',
|
||||
noModels: '未找到模型。',
|
||||
persistGlobalSession: '全局保存 (否则仅当前会话)',
|
||||
persistGlobal: '全局保存',
|
||||
addProvider: '添加提供方',
|
||||
loadFailed: '无法加载模型',
|
||||
noAuthenticatedProviders: '没有已认证的提供方。',
|
||||
|
|
|
|||
|
|
@ -4,13 +4,23 @@ import { lastVisibleMessageIsUser } from '@/app/chat/thread-loading'
|
|||
import type { ContextSuggestion } from '@/app/types'
|
||||
import type { HermesConnection } from '@/global'
|
||||
import type { ChatMessage } from '@/lib/chat-messages'
|
||||
import { persistString, storedString } from '@/lib/storage'
|
||||
import { persistBoolean, persistString, storedBoolean, storedString } from '@/lib/storage'
|
||||
import type { SessionInfo, UsageStats } from '@/types/hermes'
|
||||
|
||||
type Updater<T> = T | ((current: T) => T)
|
||||
|
||||
const WORKSPACE_CWD_KEY = 'hermes.desktop.workspace-cwd'
|
||||
|
||||
// The composer's model/effort/fast is sticky UI state, NOT the profile default
|
||||
// (that lives in Settings → Model). Persisting it in localStorage makes a pick
|
||||
// follow across Cmd+N and app restarts instead of snapping back to the default.
|
||||
// It's deliberately global (not per-profile): a profile switch force-reseeds to
|
||||
// that profile's default, while within a profile new chats keep your last pick.
|
||||
const COMPOSER_MODEL_KEY = 'hermes.desktop.composer.model'
|
||||
const COMPOSER_PROVIDER_KEY = 'hermes.desktop.composer.provider'
|
||||
const COMPOSER_EFFORT_KEY = 'hermes.desktop.composer.reasoning-effort'
|
||||
const COMPOSER_FAST_KEY = 'hermes.desktop.composer.fast'
|
||||
|
||||
let configuredDefaultProjectDir = ''
|
||||
|
||||
function workspaceCwdKey(connection: HermesConnection | null = $connection.get()): string {
|
||||
|
|
@ -208,11 +218,11 @@ export const $lastVisibleMessageIsUser = computed($messages, lastVisibleMessageI
|
|||
export const $freshDraftReady = atom(false)
|
||||
export const $busy = atom(false)
|
||||
export const $awaitingResponse = atom(false)
|
||||
export const $currentModel = atom('')
|
||||
export const $currentProvider = atom('')
|
||||
export const $currentReasoningEffort = atom('')
|
||||
export const $currentModel = atom(storedString(COMPOSER_MODEL_KEY) ?? '')
|
||||
export const $currentProvider = atom(storedString(COMPOSER_PROVIDER_KEY) ?? '')
|
||||
export const $currentReasoningEffort = atom(storedString(COMPOSER_EFFORT_KEY) ?? '')
|
||||
export const $currentServiceTier = atom('')
|
||||
export const $currentFastMode = atom(false)
|
||||
export const $currentFastMode = atom(storedBoolean(COMPOSER_FAST_KEY, false))
|
||||
// Effective approval-bypass state mirrored from the gateway (session.info).
|
||||
// Persistence lives in the backend config (approvals.mode), so this is a plain
|
||||
// reflection of the truth the gateway reports rather than its own store.
|
||||
|
|
@ -254,11 +264,29 @@ export const setMessages = (next: Updater<ChatMessage[]>) => updateAtom($message
|
|||
export const setFreshDraftReady = (next: Updater<boolean>) => updateAtom($freshDraftReady, next)
|
||||
export const setBusy = (next: Updater<boolean>) => updateAtom($busy, next)
|
||||
export const setAwaitingResponse = (next: Updater<boolean>) => updateAtom($awaitingResponse, next)
|
||||
export const setCurrentModel = (next: Updater<string>) => updateAtom($currentModel, next)
|
||||
export const setCurrentProvider = (next: Updater<string>) => updateAtom($currentProvider, next)
|
||||
export const setCurrentReasoningEffort = (next: Updater<string>) => updateAtom($currentReasoningEffort, next)
|
||||
|
||||
export const setCurrentModel = (next: Updater<string>) => {
|
||||
updateAtom($currentModel, next)
|
||||
persistString(COMPOSER_MODEL_KEY, $currentModel.get() || null)
|
||||
}
|
||||
|
||||
export const setCurrentProvider = (next: Updater<string>) => {
|
||||
updateAtom($currentProvider, next)
|
||||
persistString(COMPOSER_PROVIDER_KEY, $currentProvider.get() || null)
|
||||
}
|
||||
|
||||
export const setCurrentReasoningEffort = (next: Updater<string>) => {
|
||||
updateAtom($currentReasoningEffort, next)
|
||||
persistString(COMPOSER_EFFORT_KEY, $currentReasoningEffort.get() || null)
|
||||
}
|
||||
|
||||
export const setCurrentServiceTier = (next: Updater<string>) => updateAtom($currentServiceTier, next)
|
||||
export const setCurrentFastMode = (next: Updater<boolean>) => updateAtom($currentFastMode, next)
|
||||
|
||||
export const setCurrentFastMode = (next: Updater<boolean>) => {
|
||||
updateAtom($currentFastMode, next)
|
||||
persistBoolean(COMPOSER_FAST_KEY, $currentFastMode.get())
|
||||
}
|
||||
|
||||
export const setYoloActive = (next: Updater<boolean>) => updateAtom($yoloActive, next)
|
||||
|
||||
export const setCurrentCwd = (next: Updater<string>) => {
|
||||
|
|
|
|||
|
|
@ -5,6 +5,9 @@ import type { DesktopUpdateStatus } from '@/global'
|
|||
const storage = new Map<string, string>()
|
||||
|
||||
vi.mock('@/lib/storage', () => ({
|
||||
persistBoolean: (key: string, value: boolean) => {
|
||||
storage.set(key, String(value))
|
||||
},
|
||||
persistString: (key: string, value: null | string) => {
|
||||
if (value === null) {
|
||||
storage.delete(key)
|
||||
|
|
@ -12,6 +15,11 @@ vi.mock('@/lib/storage', () => ({
|
|||
storage.set(key, value)
|
||||
}
|
||||
},
|
||||
storedBoolean: (key: string, fallback: boolean) => {
|
||||
const value = storage.get(key)
|
||||
|
||||
return value === undefined ? fallback : value === 'true'
|
||||
},
|
||||
storedString: (key: string) => storage.get(key) ?? null
|
||||
}))
|
||||
|
||||
|
|
|
|||
|
|
@ -1851,8 +1851,10 @@ def test_ensure_session_db_row_persists_explicit_cwd(monkeypatch, tmp_path):
|
|||
created = []
|
||||
|
||||
class _FakeDB:
|
||||
def create_session(self, key, source=None, model=None, cwd=None):
|
||||
created.append({"key": key, "source": source, "model": model, "cwd": cwd})
|
||||
def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
|
||||
created.append(
|
||||
{"key": key, "source": source, "model": model, "model_config": model_config, "cwd": cwd}
|
||||
)
|
||||
|
||||
monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
|
||||
monkeypatch.setattr(server, "_resolve_model", lambda: "test-model")
|
||||
|
|
@ -1860,7 +1862,7 @@ def test_ensure_session_db_row_persists_explicit_cwd(monkeypatch, tmp_path):
|
|||
server._ensure_session_db_row({"session_key": "k1", "cwd": str(tmp_path), "explicit_cwd": True})
|
||||
|
||||
assert created == [
|
||||
{"key": "k1", "source": "tui", "model": "test-model", "cwd": str(tmp_path)}
|
||||
{"key": "k1", "source": "tui", "model": "test-model", "model_config": None, "cwd": str(tmp_path)}
|
||||
]
|
||||
|
||||
|
||||
|
|
@ -1870,15 +1872,74 @@ def test_ensure_session_db_row_defaults_to_no_workspace(monkeypatch, tmp_path):
|
|||
created = []
|
||||
|
||||
class _FakeDB:
|
||||
def create_session(self, key, source=None, model=None, cwd=None):
|
||||
created.append({"key": key, "source": source, "model": model, "cwd": cwd})
|
||||
def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
|
||||
created.append(
|
||||
{"key": key, "source": source, "model": model, "model_config": model_config, "cwd": cwd}
|
||||
)
|
||||
|
||||
monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
|
||||
monkeypatch.setattr(server, "_resolve_model", lambda: "test-model")
|
||||
|
||||
server._ensure_session_db_row({"session_key": "k1", "cwd": str(tmp_path)})
|
||||
|
||||
assert created == [{"key": "k1", "source": "tui", "model": "test-model", "cwd": None}]
|
||||
assert created == [
|
||||
{"key": "k1", "source": "tui", "model": "test-model", "model_config": None, "cwd": None}
|
||||
]
|
||||
|
||||
|
||||
def test_ensure_session_db_row_persists_session_model_override(monkeypatch):
|
||||
"""The session's composer pick (model + effort + fast) must own the DB row.
|
||||
|
||||
Regression for the "switched to gpt-5.5, reconnect snapped back to opus"
|
||||
bug: the row was created with the global default and won the INSERT-OR-IGNORE
|
||||
race, so resume rebuilt from the global model and silently reverted the
|
||||
chat. The override model + a model_config carrying provider/reasoning/
|
||||
service_tier must be persisted so session.resume restores all three.
|
||||
"""
|
||||
created = []
|
||||
|
||||
class _FakeDB:
|
||||
def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
|
||||
created.append(
|
||||
{"key": key, "model": model, "model_config": model_config, "cwd": cwd}
|
||||
)
|
||||
|
||||
monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
|
||||
monkeypatch.setattr(server, "_resolve_model", lambda: "global/default")
|
||||
|
||||
server._ensure_session_db_row(
|
||||
{
|
||||
"session_key": "k1",
|
||||
"model_override": {"model": "openai/gpt-5.5", "provider": "openrouter"},
|
||||
"create_reasoning_override": {"effort": "high"},
|
||||
"create_service_tier_override": "priority",
|
||||
}
|
||||
)
|
||||
|
||||
assert len(created) == 1
|
||||
row = created[0]
|
||||
assert row["model"] == "openai/gpt-5.5"
|
||||
assert row["model_config"]["model"] == "openai/gpt-5.5"
|
||||
assert row["model_config"]["provider"] == "openrouter"
|
||||
assert row["model_config"]["reasoning_config"] == {"effort": "high"}
|
||||
assert row["model_config"]["service_tier"] == "priority"
|
||||
|
||||
|
||||
def test_ensure_session_db_row_no_override_uses_global(monkeypatch):
|
||||
"""A chat that made no explicit pick falls back to the global model and
|
||||
writes no model_config (so it tracks the profile default)."""
|
||||
created = []
|
||||
|
||||
class _FakeDB:
|
||||
def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
|
||||
created.append({"model": model, "model_config": model_config})
|
||||
|
||||
monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
|
||||
monkeypatch.setattr(server, "_resolve_model", lambda: "global/default")
|
||||
|
||||
server._ensure_session_db_row({"session_key": "k1", "model_override": None})
|
||||
|
||||
assert created == [{"model": "global/default", "model_config": None}]
|
||||
|
||||
|
||||
def test_session_title_clears_pending_after_persist(monkeypatch):
|
||||
|
|
@ -7485,3 +7546,97 @@ def test_reap_idle_sessions_closes_only_evictable(monkeypatch):
|
|||
assert closed == [("stale", "idle_timeout")]
|
||||
finally:
|
||||
server._sessions.clear()
|
||||
|
||||
|
||||
def test_session_create_records_ui_model_as_session_override(monkeypatch):
|
||||
"""The desktop composer owns its model as plain UI state and ships it on
|
||||
session.create. The gateway must record it as a PER-SESSION override (built
|
||||
into the agent), never a global config write — picking a model for a new chat
|
||||
must not mutate the profile default.
|
||||
"""
|
||||
monkeypatch.setattr(server, "_enable_gateway_prompts", lambda: None)
|
||||
# Don't run the real deferred build in this storage-focused test.
|
||||
monkeypatch.setattr(server, "_start_agent_build", lambda *a, **k: None)
|
||||
try:
|
||||
resp = server._methods["session.create"](
|
||||
"r1",
|
||||
{
|
||||
"cols": 80,
|
||||
"model": "claude-sonnet-4.6",
|
||||
"provider": "anthropic",
|
||||
"reasoning_effort": "high",
|
||||
"fast": True,
|
||||
},
|
||||
)
|
||||
sid = resp["result"]["session_id"]
|
||||
sess = server._sessions[sid]
|
||||
assert sess["model_override"] == {"model": "claude-sonnet-4.6", "provider": "anthropic"}
|
||||
assert sess["create_reasoning_override"] is not None
|
||||
assert sess["create_service_tier_override"] == "priority"
|
||||
# The immediate response reflects the override (not the global default) so
|
||||
# the client never clobbers its sticky pick before the build lands.
|
||||
assert resp["result"]["info"]["model"] == "claude-sonnet-4.6"
|
||||
assert resp["result"]["info"]["provider"] == "anthropic"
|
||||
|
||||
# No knobs → no overrides; the session builds from the profile default.
|
||||
plain = server._methods["session.create"]("r2", {"cols": 80})
|
||||
plain_sess = server._sessions[plain["result"]["session_id"]]
|
||||
assert plain_sess["model_override"] is None
|
||||
assert plain_sess["create_reasoning_override"] is None
|
||||
assert plain_sess["create_service_tier_override"] is None
|
||||
finally:
|
||||
server._sessions.clear()
|
||||
|
||||
|
||||
def test_start_agent_build_passes_session_model_override(monkeypatch):
|
||||
"""A model staged on the session (e.g. by session.create from the desktop
|
||||
composer) must reach _make_agent so the first build runs on it directly —
|
||||
no global config, no build-then-switch.
|
||||
"""
|
||||
captured = {}
|
||||
|
||||
class FakeWorker:
|
||||
def __init__(self, *_a, **_k):
|
||||
pass
|
||||
|
||||
def close(self):
|
||||
pass
|
||||
|
||||
def fake_make_agent(sid, key, session_id=None, session_db=None, **kwargs):
|
||||
captured.update(kwargs)
|
||||
return types.SimpleNamespace(model="claude-sonnet-4.6")
|
||||
|
||||
monkeypatch.setattr(server, "_set_session_context", lambda target: [])
|
||||
monkeypatch.setattr(server, "_clear_session_context", lambda tokens: None)
|
||||
monkeypatch.setattr(server, "_make_agent", fake_make_agent)
|
||||
monkeypatch.setattr(server, "_SlashWorker", FakeWorker)
|
||||
monkeypatch.setattr(server, "_attach_worker", lambda *a, **k: None)
|
||||
monkeypatch.setattr(server, "_wire_callbacks", lambda _sid: None)
|
||||
monkeypatch.setattr(server, "_emit", lambda *a, **k: None)
|
||||
monkeypatch.setattr(server, "_session_info", lambda *a, **k: {})
|
||||
monkeypatch.setattr(server, "_start_notification_poller", lambda *a, **k: None)
|
||||
monkeypatch.setattr(server, "_notify_session_boundary", lambda *a, **k: None)
|
||||
monkeypatch.setattr(server, "_probe_config_health", lambda *_a: None)
|
||||
|
||||
sid = "build-sid"
|
||||
override = {"model": "claude-sonnet-4.6", "provider": "anthropic"}
|
||||
reasoning = {"enabled": True, "effort": "high"}
|
||||
session = {
|
||||
"agent": None,
|
||||
"agent_ready": threading.Event(),
|
||||
"session_key": "k1",
|
||||
"profile_home": None,
|
||||
"model_override": override,
|
||||
"create_reasoning_override": reasoning,
|
||||
"create_service_tier_override": "priority",
|
||||
}
|
||||
server._sessions[sid] = session
|
||||
try:
|
||||
server._start_agent_build(sid, session)
|
||||
assert session["agent_ready"].wait(timeout=3), "agent build did not finish"
|
||||
assert captured.get("model_override") == override
|
||||
assert captured.get("reasoning_config_override") == reasoning
|
||||
assert captured.get("service_tier_override") == "priority"
|
||||
assert session["agent"].model == "claude-sonnet-4.6"
|
||||
finally:
|
||||
server._sessions.clear()
|
||||
|
|
|
|||
|
|
@ -946,6 +946,15 @@ def _start_agent_build(sid: str, session: dict) -> None:
|
|||
kw = {"session_db": session_db}
|
||||
if resume_sid := current.get("resume_session_id"):
|
||||
kw["session_id"] = resume_sid
|
||||
# Model/effort/fast the desktop picked for a brand-new chat ride
|
||||
# in as per-session overrides so the first build uses them
|
||||
# directly (no global config, no build-then-switch).
|
||||
if override := current.get("model_override"):
|
||||
kw["model_override"] = override
|
||||
if (reasoning := current.get("create_reasoning_override")) is not None:
|
||||
kw["reasoning_config_override"] = reasoning
|
||||
if (tier := current.get("create_service_tier_override")) is not None:
|
||||
kw["service_tier_override"] = tier
|
||||
agent = _make_agent(sid, key, **kw)
|
||||
finally:
|
||||
_clear_session_context(tokens)
|
||||
|
|
@ -1174,11 +1183,38 @@ def _ensure_session_db_row(session: dict) -> None:
|
|||
close_db = False
|
||||
if db is None:
|
||||
return
|
||||
# The session's own model/effort/fast pick — the composer override shipped on
|
||||
# session.create, or a restored /model switch — must own the row's model +
|
||||
# model_config. The agent isn't built yet at first prompt.submit, so derive
|
||||
# the row from the live override dict; fall back to the global resolved model
|
||||
# only when this chat made no explicit pick. Writing the global default here
|
||||
# used to win the INSERT-OR-IGNORE race against the agent's own correct
|
||||
# lazy-create, so a reconnect/resume rebuilt from the global model and
|
||||
# silently reverted the chat (e.g. picked gpt-5.5, reconnect snapped back to
|
||||
# the profile default). model_config carries provider/reasoning/service_tier
|
||||
# so resume restores effort + fast too, not just the model name.
|
||||
override = session.get("model_override")
|
||||
override = override if isinstance(override, dict) else {}
|
||||
row_model = str(override.get("model") or "").strip() or _resolve_model()
|
||||
model_config: dict = {}
|
||||
for src_key, cfg_key in (
|
||||
("model", "model"),
|
||||
("provider", "provider"),
|
||||
("base_url", "base_url"),
|
||||
("api_mode", "api_mode"),
|
||||
):
|
||||
if val := override.get(src_key):
|
||||
model_config[cfg_key] = str(val)
|
||||
if (reasoning := session.get("create_reasoning_override")) is not None:
|
||||
model_config["reasoning_config"] = reasoning
|
||||
if tier := session.get("create_service_tier_override"):
|
||||
model_config["service_tier"] = tier
|
||||
try:
|
||||
db.create_session(
|
||||
key,
|
||||
source="tui",
|
||||
model=_resolve_model(),
|
||||
model=row_model,
|
||||
model_config=model_config or None,
|
||||
cwd=_session_cwd(session) if session.get("explicit_cwd") else None,
|
||||
)
|
||||
except Exception:
|
||||
|
|
@ -3887,6 +3923,29 @@ def _(rid, params: dict) -> dict:
|
|||
profile = (params.get("profile") or "").strip() or None
|
||||
profile_home = _profile_home(profile)
|
||||
|
||||
# The desktop composer owns its model/effort/fast as plain UI state and ships
|
||||
# it on every session.create. Honor each as a PER-SESSION override (built into
|
||||
# the agent below) — never a global config write, so picking a model/effort
|
||||
# for a new chat can't mutate the profile default. provider is optional
|
||||
# (resolved at build).
|
||||
create_model = str(params.get("model") or "").strip()
|
||||
session_model_override = (
|
||||
{"model": create_model, "provider": str(params.get("provider") or "").strip() or None}
|
||||
if create_model
|
||||
else None
|
||||
)
|
||||
create_reasoning_override = None
|
||||
if effort := str(params.get("reasoning_effort") or "").strip():
|
||||
try:
|
||||
from hermes_constants import parse_reasoning_effort
|
||||
|
||||
create_reasoning_override = parse_reasoning_effort(effort)
|
||||
except Exception:
|
||||
create_reasoning_override = None
|
||||
# Only pin "fast" when explicitly requested; leaving it None lets the build
|
||||
# fall back to the profile default service tier rather than forcing normal.
|
||||
create_service_tier_override = "priority" if params.get("fast") else None
|
||||
|
||||
ready = threading.Event()
|
||||
now = time.time()
|
||||
lease, limit_message = _claim_active_session_slot(key, live_session_id=sid)
|
||||
|
|
@ -3912,6 +3971,9 @@ def _(rid, params: dict) -> dict:
|
|||
"cwd": resolved_cwd,
|
||||
"inflight_turn": None,
|
||||
"last_active": now,
|
||||
"model_override": session_model_override,
|
||||
"create_reasoning_override": create_reasoning_override,
|
||||
"create_service_tier_override": create_service_tier_override,
|
||||
"pending_title": title or None,
|
||||
"profile_home": str(profile_home) if profile_home is not None else None,
|
||||
"running": False,
|
||||
|
|
@ -3951,7 +4013,20 @@ def _(rid, params: dict) -> dict:
|
|||
"message_count": len(history),
|
||||
"messages": _history_to_messages(history),
|
||||
"info": {
|
||||
"model": _resolve_model(),
|
||||
# Reflect the per-session model override (desktop composer pick)
|
||||
# in the immediate response so the client doesn't briefly clobber
|
||||
# its sticky pick with the global default before the deferred
|
||||
# build's session.info lands.
|
||||
"model": (
|
||||
session_model_override.get("model")
|
||||
if session_model_override
|
||||
else _resolve_model()
|
||||
),
|
||||
**(
|
||||
{"provider": session_model_override["provider"]}
|
||||
if session_model_override and session_model_override.get("provider")
|
||||
else {}
|
||||
),
|
||||
"tools": {},
|
||||
"skills": {},
|
||||
"cwd": _sessions[sid]["cwd"],
|
||||
|
|
|
|||
|
|
@ -50,11 +50,18 @@ The center of the app. You get:
|
|||
|
||||
The bar along the bottom of the chat shows live session state and exposes quick controls without opening Settings:
|
||||
|
||||
- **Inline model picker** — switch the model for the active session straight from the status bar.
|
||||
- **Per-session YOLO toggle** — flip YOLO on or off for just this session (matching the TUI). YOLO bypasses the dangerous-command approval prompts, so know what you're turning off — see [Security → YOLO Mode](./security.md#yolo-mode).
|
||||
|
||||
Chatting against a Hermes instance on another machine instead of the bundled local backend? See [Connecting to a remote backend](#connecting-to-a-remote-backend) below — and for the full picture of how the remote-hosted dashboard connection works (the auth gate, the `/api/ws` chat socket, and WebSocket close-code triage), see [Web Dashboard → Connecting Hermes Desktop to a remote backend](./features/web-dashboard.md#connecting-hermes-desktop-to-a-remote-backend).
|
||||
|
||||
#### Choosing a model
|
||||
|
||||
The model picker lives in the **composer**, just left of the microphone. Click it to switch the model, reasoning effort, and fast mode from one dropdown.
|
||||
|
||||
- **The composer picker is sticky UI state and never touches your default.** It's remembered locally (per device) and **follows** across new chats and restarts instead of snapping back to the default — pick a model once and the next `Cmd/Ctrl+N` opens on it. With a live chat, switching models scopes the change to that **current chat**; either way the selection rides along when the session is created/switched and is **never** written to the profile default. (Switching [profiles](#sessions--profiles) reseeds to that profile's own default.)
|
||||
- **Set the default in Settings → Model.** That "main" model is your **per-profile global default** — it's what new chats, crons, subagents, and auxiliary tasks start from, and it's the only place that writes it. Each [profile](#sessions--profiles) keeps its own default.
|
||||
- **Per-model effort/fast presets.** Each model remembers its own reasoning effort and fast-mode choice in the desktop app, re-applied to the session whenever you pick that model. These presets are a desktop convenience and don't change crons or subagents.
|
||||
|
||||
### File browser
|
||||
|
||||
Explore and preview the working directory without leaving the app — useful for following along as the agent reads, writes, and edits files. Set the initial project directory with `hermes desktop --cwd <path>` (or the `HERMES_DESKTOP_CWD` environment variable).
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue