Compare commits

..

15 Commits

Author SHA1 Message Date
Haileyesus
979877e1aa fix: simplify empty-state model selector
Keep the provider empty state focused on the setup action users need there:

choosing a model.

The refresh control, cache timestamp, and refresh explanation made the dialog feel

like a cache-management surface.

That extra action is out of place in the empty state, where the goal is to start

a chat with the selected provider and model.

Remove the refresh-specific UI from ProviderSelectionEmptyState and drop the

now-unused refresh/cache props from the ChatMessagesPane pass-through.

Refresh behavior remains available in the dedicated command result flow.
2026-05-28 11:45:21 +03:00
Haileyesus
59a9858092 docs: move model catalog out of shared
The model catalog is no longer a frontend/backend runtime contract.

Keeping it under shared made ownership misleading. It implied the catalog was
application code shared by runtime consumers, even though it now only supports
README links and public API documentation.

Move the catalog into public so it lives beside the docs surfaces that need it.
This gives the API docs a stable, served module and gives README readers a
linkable source without suggesting frontend or backend runtime dependency.

Render the API docs model list from the exported provider registry instead of a
hardcoded Claude/Cursor/Codex subset. That keeps Gemini and OpenCode visible and
makes future provider documentation changes flow through one docs-specific file.

Update README links, provider maintenance notes, and package files so published
artifacts include the standalone docs page and model catalog without relying on
the old shared path.
2026-05-25 12:32:25 +03:00
Haileyesus
e956d006f9 feat: add more fallback models for cursor 2026-05-25 11:01:39 +03:00
Haileyesus
fe3a8580dc fix: format opencode model catalog labels
OpenCode returns provider-prefixed ids directly from the CLI. Passing those ids through as
labels made the model picker hard to scan: users saw values like
anthropic/claude-3-5-sonnet-20241022 or lowercased, hyphen-split text instead
of readable model names.

Keep the exact OpenCode id as the option value because that is what the CLI
expects, but derive a presentation label for the frontend. The formatter is
intentionally generic rather than a catalog of known providers. It handles common
identifier structure such as provider/model, hyphen-delimited words, v-prefixed
versions, adjacent numeric version tokens, and 8-digit date suffixes.

This keeps OpenCode usable as its model list expands across many upstream
providers without requiring code changes for every new provider or model family.
The description keeps the raw provider-prefixed id visible so users can still
confirm the precise model being selected.
2026-05-22 17:02:03 +03:00
Haileyesus
6ca0d38fa4 fix: clarify model refresh and onboarding providers
OpenCode is now a supported chat provider, but first-run onboarding still only offered
Claude, Cursor, Codex, and Gemini. That made OpenCode harder to discover and
forced users to finish setup before finding the provider in settings or chat.
Adding it to onboarding keeps first-run setup aligned with the providers the
application already supports elsewhere.

The model refresh control was also doing too much visual work. In the new chat
model picker, the previous Hard Refresh label looked like the dialog heading,
which made the primary task unclear. Users open that dialog to choose a model;
refreshing catalogs is only a secondary maintenance action for stale cached
provider model lists.

Rename and reposition the refresh affordance so the model picker reads as a
model picker first. The copy now explains why catalogs are cached, when a refresh
is useful, and that the refresh checks every provider. The /models modal gets the
same clarification so both model-selection surfaces describe the cache behavior
consistently.
2026-05-22 16:49:40 +03:00
Haileyesus
117f7f662d fix: preserve opencode session creation events
OpenCode emits the real session id asynchronously on its first JSON output. The runner
registered that id from a helper that could not see the spawned process because
the process reference was scoped inside the model-resolution callback. That
ReferenceError was swallowed by the generic JSON parse fallback, so the client
never received session_created. Without that event, a new OpenCode chat stayed
on / and the assistant stream was not attached to the new session view.

Keep the process reference in the outer spawn scope so registration can update
the active-process map and websocket writer as soon as OpenCode announces the
session id. Split JSON parsing from event processing so malformed non-JSON
output can still stream as raw text, while registration or adapter failures are
surfaced as real errors instead of being hidden as assistant content.

Add a fake opencode executable regression test to lock in the expected lifecycle
ordering: session_created must be sent before live assistant messages, and the
same session id must carry through stream_end and complete.
2026-05-19 11:09:01 +03:00
Haileyesus
fb4c2d3d43 feat: make command modal more compact 2026-05-18 20:50:56 +03:00
Haileyesus
9aa927002e feat: support session-scoped model overrides
Model selection was acting like a provider-level preference.

That made resumed sessions drift back to a default or request-time model.

Users expect /models changes made inside a conversation to affect that session.

Store explicit session choices in app-owned ~/.cloudcli state.

This avoids editing provider transcripts or native provider config.

Resolve the effective model before launching each provider runtime.

Claude, Cursor, Codex, Gemini, and OpenCode now honor stored resume choices.

Expose a backend active-model change endpoint for existing sessions.

The models modal can now distinguish default changes from session overrides.

It also shows when a selected model will apply on the next response.

For Claude, stop probing active model state by resuming with a dummy prompt.

Read the indexed JSONL transcript from the end instead.

This preserves provider history while honoring /model stdout or model fields.

Add service tests for adapter delegation and resume-model precedence.

The tests keep cache state, override state, and requested fallback separate.
2026-05-18 16:57:29 +03:00
Haileyesus
bc5e768579 feat(models): resolve active session models through provider adapters
The model inventory command was showing a mix of catalog defaults and
composer-local state instead of the model that is actually active for a
real provider session. That made /models, /cost, and /status
misleading once a session had already started, especially for providers
whose effective runtime model can differ from the optimistic model value
held in the UI.

Introduce an explicit getCurrentActiveModel() contract on
IProviderModels so model resolution lives next to each provider's
catalog logic and uses the provider-native source of truth:

- Claude reads the init event from a resumed stream-json run
- Codex reads model from ~/.codex/config.toml
- Cursor reads lastUsedModel from the chat store.db
- OpenCode reads the persisted session model from opencode.db
- Gemini intentionally returns its default because the CLI does not
  provide a reliable active-session lookup

Keep the returned shape intentionally minimal ({ model }). The goal is
to expose only what downstream command consumers need and avoid leaking
provider-specific metadata into a shared transport shape that would
create extra UI coupling and future cleanup cost.

Also make command behavior session-aware: when there is no concrete
session id, do not spawn provider processes or inspect provider session
storage just to answer /models, /cost, or /status. In a new-session
view the correct answer is simply the provider default, and doing more
work there adds latency and unnecessary side effects for no user value.

As part of this, centralize two supporting concerns:

- add a shared helper for building the default current-model result from
  a provider catalog so fallbacks stay aligned with DEFAULT
- move leaf-directory validation into shared utils so Cursor session
  readers and model lookup code enforce the same path-safety rule

Tests were expanded to cover both the new service delegation path and
the sessionless command behavior, while keeping cache-sensitive tests
isolated from persisted host cache state.

Why this change:
- command output should reflect the model actually driving a session
- new-session views should stay fast and side-effect free
- provider-specific active-model lookup should not be scattered across
  routes or UI code
- fallback behavior should be explicit, consistent, and limited to the
  provider default when no true active model can be resolved
2026-05-18 14:54:32 +03:00
Haileyesus
556cbd1a03 feat: load models through provider adapters
Provider model selection had outgrown a single hardcoded service.

The old service mixed shared caching with provider catalogs and CLI lookup details.

That made stale model lists more likely as providers changed on separate schedules.

Move model discovery behind each provider so lookup lives next to the integration.

The shared service now focuses on provider resolution, caching, persistence, and dedupe.

Return cache metadata and add bypassCache because model availability changes outside the app.

The UI and /models command can show freshness and let users force a provider refresh.

Surface model descriptions while keeping fallback catalogs for unavailable CLIs or SDKs.
2026-05-18 12:40:24 +03:00
Haileyesus
ffaef395e4 fix: format commands.js 2026-05-14 16:57:46 +03:00
Haileyesus
f36c5b6009 fix: improveUI for commands 2026-05-14 13:54:30 +03:00
Haileyesus
dafd28ba76 fix: /models 2026-05-14 13:22:34 +03:00
Haileyesus
57aece12e6 fix: stabilize opencode session startup 2026-05-13 18:44:07 +03:00
Haileyesus
421bdd2f0f feat: add opencode support 2026-05-13 17:43:10 +03:00
23 changed files with 462 additions and 1151 deletions

View File

@@ -285,68 +285,43 @@ function transformMessage(sdkMessage) {
return sdkMessage;
}
function readNumber(value) {
const parsed = Number(value);
return Number.isFinite(parsed) ? parsed : 0;
}
/**
* Extracts token usage from SDK messages.
* Prefers per-step `message.usage` (Claude message payload), then falls back
* to result-level usage/modelUsage for compatibility across SDK versions.
* @param {Object} sdkMessage - SDK stream message
* Extracts token usage from SDK result messages
* @param {Object} resultMessage - SDK result message
* @returns {Object|null} Token budget object or null
*/
function extractTokenBudget(sdkMessage) {
if (!sdkMessage || typeof sdkMessage !== 'object') {
function extractTokenBudget(resultMessage) {
if (resultMessage.type !== 'result' || !resultMessage.modelUsage) {
return null;
}
const messageUsage = sdkMessage.message?.usage || sdkMessage.usage;
if (messageUsage && typeof messageUsage === 'object') {
const inputTokens = readNumber(messageUsage.input_tokens ?? messageUsage.inputTokens);
const outputTokens = readNumber(messageUsage.output_tokens ?? messageUsage.outputTokens);
const totalUsed = inputTokens + outputTokens;
const contextWindow = parseInt(process.env.CONTEXT_WINDOW, 10) || 160000;
// Get the first model's usage data
const modelKey = Object.keys(resultMessage.modelUsage)[0];
const modelData = resultMessage.modelUsage[modelKey];
return {
used: totalUsed,
total: contextWindow,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens,
},
};
}
if (!sdkMessage.modelUsage || typeof sdkMessage.modelUsage !== 'object') {
if (!modelData) {
return null;
}
// Fallback for older SDK messages with only modelUsage
const modelKey = Object.keys(sdkMessage.modelUsage)[0];
const modelData = sdkMessage.modelUsage[modelKey];
// Use cumulative tokens if available (tracks total for the session)
// Otherwise fall back to per-request tokens
const inputTokens = modelData.cumulativeInputTokens || modelData.inputTokens || 0;
const outputTokens = modelData.cumulativeOutputTokens || modelData.outputTokens || 0;
const cacheReadTokens = modelData.cumulativeCacheReadInputTokens || modelData.cacheReadInputTokens || 0;
const cacheCreationTokens = modelData.cumulativeCacheCreationInputTokens || modelData.cacheCreationInputTokens || 0;
if (!modelData || typeof modelData !== 'object') {
return null;
}
// Total used = input + output + cache tokens
const totalUsed = inputTokens + outputTokens + cacheReadTokens + cacheCreationTokens;
const inputTokens = readNumber(modelData.cumulativeInputTokens ?? modelData.inputTokens);
const outputTokens = readNumber(modelData.cumulativeOutputTokens ?? modelData.outputTokens);
const totalUsed = inputTokens + outputTokens;
const contextWindow = parseInt(process.env.CONTEXT_WINDOW, 10) || 160000;
// Use configured context window budget from environment (default 160000)
// This is the user's budget limit, not the model's context window
const contextWindow = parseInt(process.env.CONTEXT_WINDOW) || 160000;
// Token calc logged via token-budget WS event
return {
used: totalUsed,
total: contextWindow,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens,
},
total: contextWindow
};
}
@@ -709,10 +684,16 @@ async function queryClaudeSDK(command, options = {}, ws) {
ws.send(msg);
}
// Extract and send token budget updates from assistant/result usage payloads
const tokenBudgetData = extractTokenBudget(message);
if (tokenBudgetData) {
ws.send(createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget: tokenBudgetData, sessionId: capturedSessionId || sessionId || null, provider: 'claude' }));
// Extract and send token budget updates from result messages
if (message.type === 'result') {
const models = Object.keys(message.modelUsage || {});
if (models.length > 0) {
// Model info available in result message
}
const tokenBudgetData = extractTokenBudget(message);
if (tokenBudgetData) {
ws.send(createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget: tokenBudgetData, sessionId: capturedSessionId || sessionId || null, provider: 'claude' }));
}
}
}

View File

@@ -1,32 +1,5 @@
// Gemini Response Handler - JSON Stream processing
import { sessionsService } from './modules/providers/services/sessions.service.js';
import { createNormalizedMessage } from './shared/utils.js';
function buildGeminiTokenBudget(tokens) {
if (!tokens || typeof tokens !== 'object') {
return null;
}
const parsedInputTokens = Number(tokens.input);
const parsedOutputTokens = Number(tokens.output);
const inputTokens = Number.isFinite(parsedInputTokens) ? parsedInputTokens : 0;
const outputTokens = Number.isFinite(parsedOutputTokens) ? parsedOutputTokens : 0;
const parsedUsed = Number(tokens.total);
const used = Number.isFinite(parsedUsed) ? parsedUsed : inputTokens + outputTokens;
if (!Number.isFinite(used) || used <= 0) {
return null;
}
return {
used,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens,
},
};
}
class GeminiResponseHandler {
constructor(ws, options = {}) {
@@ -87,17 +60,6 @@ class GeminiResponseHandler {
for (const msg of normalized) {
this.ws.send(msg);
}
const tokenBudget = buildGeminiTokenBudget(event.tokens);
if (tokenBudget) {
this.ws.send(createNormalizedMessage({
kind: 'status',
text: 'token_budget',
tokenBudget,
sessionId: sid,
provider: 'gemini',
}));
}
}
forceFlush() {

View File

@@ -10,9 +10,8 @@ import { spawn } from 'child_process';
import express from 'express';
import cors from 'cors';
import mime from 'mime-types';
import Database from 'better-sqlite3';
import { AppError, WORKSPACES_ROOT, getOpenCodeDatabasePath, validateWorkspacePath } from '@/shared/utils.js';
import { AppError, WORKSPACES_ROOT, validateWorkspacePath } from '@/shared/utils.js';
import { closeSessionsWatcher, initializeSessionsWatcher } from '@/modules/providers/index.js';
import { createWebSocketServer } from '@/modules/websocket/index.js';
@@ -73,7 +72,7 @@ import geminiRoutes from './routes/gemini.js';
import pluginsRoutes from './routes/plugins.js';
import providerRoutes from './modules/providers/provider.routes.js';
import { startEnabledPluginServers, stopAllPlugins, getPluginPort } from './utils/plugin-process-manager.js';
import { initializeDatabase, projectsDb, sessionsDb } from './modules/database/index.js';
import { initializeDatabase, projectsDb } from './modules/database/index.js';
import { configureWebPush } from './services/vapid-keys.js';
import { validateApiKey, authenticateToken, authenticateWebSocket } from './middleware/auth.js';
import { IS_PLATFORM } from './constants/config.js';
@@ -1142,127 +1141,33 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
return res.json({
used: 0,
total: 0,
inputTokens: 0,
outputTokens: 0,
breakdown: { input: 0, output: 0 },
breakdown: { input: 0, cacheCreation: 0, cacheRead: 0 },
unsupported: true,
message: 'Token usage tracking not available for Cursor sessions'
});
}
// Handle Gemini sessions - they are raw logs in our current setup
if (provider === 'gemini') {
const session = sessionsDb.getSessionById(safeSessionId);
const sessionFilePath = session?.jsonl_path;
if (!sessionFilePath) {
return res.json({
used: 0,
inputTokens: 0,
outputTokens: 0,
breakdown: { input: 0, output: 0 },
unsupported: true,
message: 'Token usage tracking not available for this Gemini session'
});
}
let fileContent;
try {
fileContent = await fsPromises.readFile(sessionFilePath, 'utf8');
} catch (error) {
if (error.code === 'ENOENT') {
return res.status(404).json({ error: 'Session file not found', path: sessionFilePath });
}
throw error;
}
const lines = fileContent.trim().split('\n');
let inputTokens = 0;
let outputTokens = 0;
let totalTokens = 0;
for (let i = lines.length - 1; i >= 0; i--) {
try {
const entry = JSON.parse(lines[i]);
if (!entry.tokens || typeof entry.tokens !== 'object') {
continue;
}
inputTokens = Number(entry.tokens.input || 0);
outputTokens = Number(entry.tokens.output || 0);
totalTokens = Number(entry.tokens.total || inputTokens + outputTokens || 0);
break;
} catch {
continue;
}
}
return res.json({
used: totalTokens,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens
}
used: 0,
total: 0,
breakdown: { input: 0, cacheCreation: 0, cacheRead: 0 },
unsupported: true,
message: 'Token usage tracking not available for Gemini sessions'
});
}
// OpenCode token totals are surfaced through provider history reads.
// This legacy endpoint only knows file-backed session formats.
if (provider === 'opencode') {
const dbPath = getOpenCodeDatabasePath();
if (!fs.existsSync(dbPath)) {
return res.status(404).json({ error: 'OpenCode database not found' });
}
const db = new Database(dbPath, { readonly: true, fileMustExist: true });
try {
const columns = db.prepare('PRAGMA table_info(session)').all();
const columnNames = new Set(columns.map((column) => column.name));
const requiredColumns = ['tokens_input', 'tokens_output', 'tokens_reasoning', 'tokens_cache_read', 'tokens_cache_write'];
if (!requiredColumns.every((column) => columnNames.has(column))) {
return res.json({
used: 0,
inputTokens: 0,
outputTokens: 0,
breakdown: { input: 0, output: 0 },
unsupported: true,
message: 'Token usage tracking is not available in this OpenCode database schema'
});
}
const row = db.prepare(`
SELECT
tokens_input AS inputTokens,
tokens_output AS outputTokens,
tokens_reasoning AS reasoningTokens,
tokens_cache_read AS cacheReadTokens,
tokens_cache_write AS cacheWriteTokens
FROM session
WHERE id = ?
`).get(safeSessionId);
if (!row) {
return res.status(404).json({ error: 'OpenCode session not found', sessionId: safeSessionId });
}
const inputTokens = Number(row.inputTokens || 0) + Number(row.cacheReadTokens || 0);
const outputTokens = Number(row.outputTokens || 0);
const totalUsed = Number(row.inputTokens || 0)
+ outputTokens
+ Number(row.reasoningTokens || 0)
+ Number(row.cacheReadTokens || 0)
+ Number(row.cacheWriteTokens || 0);
return res.json({
used: totalUsed,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens
}
});
} finally {
db.close();
}
return res.json({
used: 0,
total: 0,
breakdown: { input: 0, cacheCreation: 0, cacheRead: 0 },
unsupported: true,
message: 'Token usage tracking is available in OpenCode session history, not this legacy endpoint'
});
}
// Handle Codex sessions
@@ -1305,8 +1210,6 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
throw error;
}
const lines = fileContent.trim().split('\n');
let inputTokens = 0;
let outputTokens = 0;
let totalTokens = 0;
let contextWindow = 200000; // Default for Codex/OpenAI
@@ -1319,9 +1222,7 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
if (entry.type === 'event_msg' && entry.payload?.type === 'token_count' && entry.payload?.info) {
const tokenInfo = entry.payload.info;
if (tokenInfo.total_token_usage) {
inputTokens = tokenInfo.total_token_usage.input_tokens || 0;
outputTokens = tokenInfo.total_token_usage.output_tokens || 0;
totalTokens = tokenInfo.total_token_usage.total_tokens || inputTokens + outputTokens;
totalTokens = tokenInfo.total_token_usage.total_tokens || 0;
}
if (tokenInfo.model_context_window) {
contextWindow = tokenInfo.model_context_window;
@@ -1336,13 +1237,7 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
return res.json({
used: totalTokens,
total: contextWindow,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens
}
total: contextWindow
});
}
@@ -1385,7 +1280,8 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
const parsedContextWindow = parseInt(process.env.CONTEXT_WINDOW, 10);
const contextWindow = Number.isFinite(parsedContextWindow) ? parsedContextWindow : 160000;
let inputTokens = 0;
let outputTokens = 0;
let cacheCreationTokens = 0;
let cacheReadTokens = 0;
// Find the latest assistant message with usage data (scan from end)
for (let i = lines.length - 1; i >= 0; i--) {
@@ -1398,7 +1294,8 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
// Use token counts from latest assistant message only
inputTokens = usage.input_tokens || 0;
outputTokens = usage.output_tokens || 0;
cacheCreationTokens = usage.cache_creation_input_tokens || 0;
cacheReadTokens = usage.cache_read_input_tokens || 0;
break; // Stop after finding the latest assistant message
}
@@ -1408,16 +1305,16 @@ app.get('/api/projects/:projectId/sessions/:sessionId/token-usage', authenticate
}
}
const totalUsed = inputTokens + outputTokens;
// Calculate total context usage (excluding output_tokens, as per ccusage)
const totalUsed = inputTokens + cacheCreationTokens + cacheReadTokens;
res.json({
used: totalUsed,
total: contextWindow,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens
cacheCreation: cacheCreationTokens,
cacheRead: cacheReadTokens
}
});
} catch (error) {

View File

@@ -1,10 +1,14 @@
import { readFile } from 'node:fs/promises';
import { query, type ModelInfo, type Options } from '@anthropic-ai/claude-agent-sdk';
import { sessionsDb } from '@/modules/database/index.js';
import { resolveClaudeCodeExecutablePath } from '@/shared/claude-cli-path.js';
import type { IProviderModels } from '@/shared/interfaces.js';
import type {
ProviderChangeActiveModelInput,
ProviderCurrentActiveModel,
ProviderModelOption,
ProviderModelsDefinition,
ProviderSessionActiveModelChange,
} from '@/shared/types.js';
@@ -15,29 +19,17 @@ import {
export const CLAUDE_FALLBACK_MODELS: ProviderModelsDefinition = {
OPTIONS: [
{
value: 'default',
label: 'Default (recommended)',
description: 'Use the default model (currently Opus 4.7 (1M context)) · $5/$25 per Mtok',
},
{
value: 'sonnet',
label: 'Sonnet',
description: 'Sonnet 4.6 · Best for everyday tasks · $3/$15 per Mtok',
},
{
value: 'sonnet[1m]',
label: 'Sonnet (1M context)',
description: 'Sonnet 4.6 for long sessions · $3/$15 per Mtok',
},
{
value: 'haiku',
label: 'Haiku',
description: 'Haiku 4.5 · Fastest for quick answers · $1/$5 per Mtok',
},
{ value: 'default', label: 'Default (recommended)' },
{ value: 'sonnet[1m]', label: 'Sonnet (1M context)' },
{ value: 'opus', label: 'Opus' },
{ value: 'opus[1m]', label: 'Opus (1M context)' },
{ value: 'haiku', label: 'Haiku' },
{ value: 'sonnet', label: 'sonnet' },
],
DEFAULT: 'sonnet',
DEFAULT: 'default',
};
type ClaudeModelQueryOptions = Pick<Options, 'env' | 'pathToClaudeCodeExecutable' | 'permissionMode'>;
type ClaudeInitEvent = {
sessionId?: string;
session_id?: string;
@@ -57,6 +49,46 @@ const ANSI_PATTERN = new RegExp(
'g',
);
const buildClaudeQueryOptions = (): ClaudeModelQueryOptions => ({
env: { ...process.env },
pathToClaudeCodeExecutable: resolveClaudeCodeExecutablePath(process.env.CLAUDE_CLI_PATH),
permissionMode: 'default',
});
const mapClaudeModel = (model: ModelInfo): ProviderModelOption => ({
value: model.value,
label: model.displayName || model.value,
description: model.description || undefined,
});
const buildClaudeModelsDefinition = (models: ModelInfo[]): ProviderModelsDefinition => {
const options: ProviderModelOption[] = [];
const seenValues = new Set<string>();
for (const model of models) {
const mappedModel = mapClaudeModel(model);
if (seenValues.has(mappedModel.value)) {
continue;
}
seenValues.add(mappedModel.value);
options.push(mappedModel);
}
if (options.length === 0) {
return CLAUDE_FALLBACK_MODELS;
}
const defaultValue = options.find((option) => option.value === 'default')?.value
?? options[0]?.value
?? CLAUDE_FALLBACK_MODELS.DEFAULT;
return {
OPTIONS: options,
DEFAULT: defaultValue,
};
};
const extractClaudeEventModel = (event: ClaudeInitEvent, sessionId: string): string | null => {
const eventSessionId = event.sessionId ?? event.session_id;
if (eventSessionId && eventSessionId !== sessionId) {
@@ -149,18 +181,25 @@ const readClaudeSessionModelFromJsonl = async (
export class ClaudeProviderModels implements IProviderModels {
async getSupportedModels(): Promise<ProviderModelsDefinition> {
// claude creates a new jsonl file as a separate session for this request.
// As a result, it lists the workspace where this is invoked when it shouldn't.
//
// Disabled for now:
// const queryInstance = query({
// prompt: 'Get supported models',
// options: buildClaudeQueryOptions(),
// });
// const supportedModels = await queryInstance.supportedModels();
// queryInstance.close();
// return buildClaudeModelsDefinition(supportedModels);
return CLAUDE_FALLBACK_MODELS;
let queryInstance: ReturnType<typeof query> | null = null;
try {
// The SDK exposes its runtime model catalog on the initialized query
// instance, so we create a lightweight query and immediately close it
// after reading the control-plane metadata.
queryInstance = query({
prompt: 'Get supported models',
options: buildClaudeQueryOptions(),
});
const supportedModels = await queryInstance.supportedModels();
return buildClaudeModelsDefinition(supportedModels);
} catch {
return CLAUDE_FALLBACK_MODELS;
} finally {
queryInstance?.close();
}
}
async getCurrentActiveModel(sessionId?: string): Promise<ProviderCurrentActiveModel> {

View File

@@ -21,563 +21,27 @@ import {
export const CURSOR_FALLBACK_MODELS: ProviderModelsDefinition = {
OPTIONS: [
{
value: "auto",
label: "auto",
description: "Auto",
},
{
value: "composer-2-fast",
label: "composer-2-fast",
description: "Composer 2 Fast",
},
{
value: "composer-2",
label: "composer-2",
description: "Composer 2",
},
{
value: "gpt-5.3-codex-low",
label: "gpt-5.3-codex-low",
description: "Codex 5.3 Low",
},
{
value: "gpt-5.3-codex-low-fast",
label: "gpt-5.3-codex-low-fast",
description: "Codex 5.3 Low Fast",
},
{
value: "gpt-5.3-codex",
label: "gpt-5.3-codex",
description: "Codex 5.3",
},
{
value: "gpt-5.3-codex-fast",
label: "gpt-5.3-codex-fast",
description: "Codex 5.3 Fast",
},
{
value: "gpt-5.3-codex-high",
label: "gpt-5.3-codex-high",
description: "Codex 5.3 High",
},
{
value: "gpt-5.3-codex-high-fast",
label: "gpt-5.3-codex-high-fast",
description: "Codex 5.3 High Fast",
},
{
value: "gpt-5.3-codex-xhigh",
label: "gpt-5.3-codex-xhigh",
description: "Codex 5.3 Extra High",
},
{
value: "gpt-5.3-codex-xhigh-fast",
label: "gpt-5.3-codex-xhigh-fast",
description: "Codex 5.3 Extra High Fast",
},
{
value: "gpt-5.2",
label: "gpt-5.2",
description: "GPT-5.2",
},
{
value: "gpt-5.2-codex-low",
label: "gpt-5.2-codex-low",
description: "Codex 5.2 Low",
},
{
value: "gpt-5.2-codex-low-fast",
label: "gpt-5.2-codex-low-fast",
description: "Codex 5.2 Low Fast",
},
{
value: "gpt-5.2-codex",
label: "gpt-5.2-codex",
description: "Codex 5.2",
},
{
value: "gpt-5.2-codex-fast",
label: "gpt-5.2-codex-fast",
description: "Codex 5.2 Fast",
},
{
value: "gpt-5.2-codex-high",
label: "gpt-5.2-codex-high",
description: "Codex 5.2 High",
},
{
value: "gpt-5.2-codex-high-fast",
label: "gpt-5.2-codex-high-fast",
description: "Codex 5.2 High Fast",
},
{
value: "gpt-5.2-codex-xhigh",
label: "gpt-5.2-codex-xhigh",
description: "Codex 5.2 Extra High",
},
{
value: "gpt-5.2-codex-xhigh-fast",
label: "gpt-5.2-codex-xhigh-fast",
description: "Codex 5.2 Extra High Fast",
},
{
value: "gpt-5.1-codex-max-low",
label: "gpt-5.1-codex-max-low",
description: "Codex 5.1 Max Low",
},
{
value: "gpt-5.1-codex-max-low-fast",
label: "gpt-5.1-codex-max-low-fast",
description: "Codex 5.1 Max Low Fast",
},
{
value: "gpt-5.1-codex-max-medium",
label: "gpt-5.1-codex-max-medium",
description: "Codex 5.1 Max",
},
{
value: "gpt-5.1-codex-max-medium-fast",
label: "gpt-5.1-codex-max-medium-fast",
description: "Codex 5.1 Max Medium Fast",
},
{
value: "gpt-5.1-codex-max-high",
label: "gpt-5.1-codex-max-high",
description: "Codex 5.1 Max High",
},
{
value: "gpt-5.1-codex-max-high-fast",
label: "gpt-5.1-codex-max-high-fast",
description: "Codex 5.1 Max High Fast",
},
{
value: "gpt-5.1-codex-max-xhigh",
label: "gpt-5.1-codex-max-xhigh",
description: "Codex 5.1 Max Extra High",
},
{
value: "gpt-5.1-codex-max-xhigh-fast",
label: "gpt-5.1-codex-max-xhigh-fast",
description: "Codex 5.1 Max Extra High Fast",
},
{
value: "composer-2.5",
label: "composer-2.5",
description: "Composer 2.5",
},
{
value: "gpt-5.5-high",
label: "gpt-5.5-high",
description: "GPT-5.5 1M High",
},
{
value: "gpt-5.5-high-fast",
label: "gpt-5.5-high-fast",
description: "GPT-5.5 High Fast",
},
{
value: "claude-opus-4-7-thinking-high",
label: "claude-opus-4-7-thinking-high",
description: "Opus 4.7 1M High Thinking",
},
{
value: "gpt-5.4-high",
label: "gpt-5.4-high",
description: "GPT-5.4 1M High",
},
{
value: "gpt-5.4-high-fast",
label: "gpt-5.4-high-fast",
description: "GPT-5.4 High Fast",
},
{
value: "claude-4.6-opus-high-thinking",
label: "claude-4.6-opus-high-thinking",
description: "Opus 4.6 1M Thinking",
},
{
value: "claude-4.6-opus-high-thinking-fast",
label: "claude-4.6-opus-high-thinking-fast",
description: "Opus 4.6 1M Thinking Fast",
},
{
value: "composer-2.5-fast",
label: "composer-2.5-fast",
description: "Composer 2.5 Fast",
},
{
value: "gpt-5.5-none",
label: "gpt-5.5-none",
description: "GPT-5.5 1M None",
},
{
value: "gpt-5.5-none-fast",
label: "gpt-5.5-none-fast",
description: "GPT-5.5 None Fast",
},
{
value: "gpt-5.5-low",
label: "gpt-5.5-low",
description: "GPT-5.5 1M Low",
},
{
value: "gpt-5.5-low-fast",
label: "gpt-5.5-low-fast",
description: "GPT-5.5 Low Fast",
},
{
value: "gpt-5.5-medium",
label: "gpt-5.5-medium",
description: "GPT-5.5 1M",
},
{
value: "gpt-5.5-medium-fast",
label: "gpt-5.5-medium-fast",
description: "GPT-5.5 Fast",
},
{
value: "gpt-5.5-extra-high",
label: "gpt-5.5-extra-high",
description: "GPT-5.5 1M Extra High",
},
{
value: "gpt-5.5-extra-high-fast",
label: "gpt-5.5-extra-high-fast",
description: "GPT-5.5 Extra High Fast",
},
{
value: "claude-4.6-sonnet-medium",
label: "claude-4.6-sonnet-medium",
description: "Sonnet 4.6 1M",
},
{
value: "claude-4.6-sonnet-medium-thinking",
label: "claude-4.6-sonnet-medium-thinking",
description: "Sonnet 4.6 1M Thinking",
},
{
value: "claude-opus-4-7-low",
label: "claude-opus-4-7-low",
description: "Opus 4.7 1M Low",
},
{
value: "claude-opus-4-7-low-fast",
label: "claude-opus-4-7-low-fast",
description: "Opus 4.7 1M Low Fast",
},
{
value: "claude-opus-4-7-medium",
label: "claude-opus-4-7-medium",
description: "Opus 4.7 1M Medium",
},
{
value: "claude-opus-4-7-medium-fast",
label: "claude-opus-4-7-medium-fast",
description: "Opus 4.7 1M Medium Fast",
},
{
value: "claude-opus-4-7-high",
label: "claude-opus-4-7-high",
description: "Opus 4.7 1M High",
},
{
value: "claude-opus-4-7-high-fast",
label: "claude-opus-4-7-high-fast",
description: "Opus 4.7 1M High Fast",
},
{
value: "claude-opus-4-7-xhigh",
label: "claude-opus-4-7-xhigh",
description: "Opus 4.7 1M",
},
{
value: "claude-opus-4-7-xhigh-fast",
label: "claude-opus-4-7-xhigh-fast",
description: "Opus 4.7 1M Fast",
},
{
value: "claude-opus-4-7-max",
label: "claude-opus-4-7-max",
description: "Opus 4.7 1M Max",
},
{
value: "claude-opus-4-7-max-fast",
label: "claude-opus-4-7-max-fast",
description: "Opus 4.7 1M Max Fast",
},
{
value: "claude-opus-4-7-thinking-low",
label: "claude-opus-4-7-thinking-low",
description: "Opus 4.7 1M Low Thinking",
},
{
value: "claude-opus-4-7-thinking-low-fast",
label: "claude-opus-4-7-thinking-low-fast",
description: "Opus 4.7 1M Low Thinking Fast",
},
{
value: "claude-opus-4-7-thinking-medium",
label: "claude-opus-4-7-thinking-medium",
description: "Opus 4.7 1M Medium Thinking",
},
{
value: "claude-opus-4-7-thinking-medium-fast",
label: "claude-opus-4-7-thinking-medium-fast",
description: "Opus 4.7 1M Medium Thinking Fast",
},
{
value: "claude-opus-4-7-thinking-high-fast",
label: "claude-opus-4-7-thinking-high-fast",
description: "Opus 4.7 1M High Thinking Fast",
},
{
value: "claude-opus-4-7-thinking-xhigh",
label: "claude-opus-4-7-thinking-xhigh",
description: "Opus 4.7 1M Thinking",
},
{
value: "claude-opus-4-7-thinking-xhigh-fast",
label: "claude-opus-4-7-thinking-xhigh-fast",
description: "Opus 4.7 1M Thinking Fast",
},
{
value: "claude-opus-4-7-thinking-max",
label: "claude-opus-4-7-thinking-max",
description: "Opus 4.7 1M Max Thinking",
},
{
value: "claude-opus-4-7-thinking-max-fast",
label: "claude-opus-4-7-thinking-max-fast",
description: "Opus 4.7 1M Max Thinking Fast",
},
{
value: "grok-build-0.1",
label: "grok-build-0.1",
description: "Grok Build 0.1 1M",
},
{
value: "gpt-5.4-low",
label: "gpt-5.4-low",
description: "GPT-5.4 1M Low",
},
{
value: "gpt-5.4-medium",
label: "gpt-5.4-medium",
description: "GPT-5.4 1M",
},
{
value: "gpt-5.4-medium-fast",
label: "gpt-5.4-medium-fast",
description: "GPT-5.4 Fast",
},
{
value: "gpt-5.4-xhigh",
label: "gpt-5.4-xhigh",
description: "GPT-5.4 1M Extra High",
},
{
value: "gpt-5.4-xhigh-fast",
label: "gpt-5.4-xhigh-fast",
description: "GPT-5.4 Extra High Fast",
},
{
value: "claude-4.6-opus-high",
label: "claude-4.6-opus-high",
description: "Opus 4.6 1M",
},
{
value: "claude-4.6-opus-max",
label: "claude-4.6-opus-max",
description: "Opus 4.6 1M Max",
},
{
value: "claude-4.6-opus-max-thinking",
label: "claude-4.6-opus-max-thinking",
description: "Opus 4.6 1M Max Thinking",
},
{
value: "claude-4.6-opus-max-thinking-fast",
label: "claude-4.6-opus-max-thinking-fast",
description: "Opus 4.6 1M Max Thinking Fast",
},
{
value: "claude-4.5-opus-high",
label: "claude-4.5-opus-high",
description: "Opus 4.5",
},
{
value: "claude-4.5-opus-high-thinking",
label: "claude-4.5-opus-high-thinking",
description: "Opus 4.5 Thinking",
},
{
value: "gpt-5.2-low",
label: "gpt-5.2-low",
description: "GPT-5.2 Low",
},
{
value: "gpt-5.2-low-fast",
label: "gpt-5.2-low-fast",
description: "GPT-5.2 Low Fast",
},
{
value: "gpt-5.2-fast",
label: "gpt-5.2-fast",
description: "GPT-5.2 Fast",
},
{
value: "gpt-5.2-high",
label: "gpt-5.2-high",
description: "GPT-5.2 High",
},
{
value: "gpt-5.2-high-fast",
label: "gpt-5.2-high-fast",
description: "GPT-5.2 High Fast",
},
{
value: "gpt-5.2-xhigh",
label: "gpt-5.2-xhigh",
description: "GPT-5.2 Extra High",
},
{
value: "gpt-5.2-xhigh-fast",
label: "gpt-5.2-xhigh-fast",
description: "GPT-5.2 Extra High Fast",
},
{
value: "gemini-3.1-pro",
label: "gemini-3.1-pro",
description: "Gemini 3.1 Pro",
},
{
value: "gpt-5.4-mini-none",
label: "gpt-5.4-mini-none",
description: "GPT-5.4 Mini None",
},
{
value: "gpt-5.4-mini-low",
label: "gpt-5.4-mini-low",
description: "GPT-5.4 Mini Low",
},
{
value: "gpt-5.4-mini-medium",
label: "gpt-5.4-mini-medium",
description: "GPT-5.4 Mini",
},
{
value: "gpt-5.4-mini-high",
label: "gpt-5.4-mini-high",
description: "GPT-5.4 Mini High",
},
{
value: "gpt-5.4-mini-xhigh",
label: "gpt-5.4-mini-xhigh",
description: "GPT-5.4 Mini Extra High",
},
{
value: "gpt-5.4-nano-none",
label: "gpt-5.4-nano-none",
description: "GPT-5.4 Nano None",
},
{
value: "gpt-5.4-nano-low",
label: "gpt-5.4-nano-low",
description: "GPT-5.4 Nano Low",
},
{
value: "gpt-5.4-nano-medium",
label: "gpt-5.4-nano-medium",
description: "GPT-5.4 Nano",
},
{
value: "gpt-5.4-nano-high",
label: "gpt-5.4-nano-high",
description: "GPT-5.4 Nano High",
},
{
value: "gpt-5.4-nano-xhigh",
label: "gpt-5.4-nano-xhigh",
description: "GPT-5.4 Nano Extra High",
},
{
value: "grok-4.3",
label: "grok-4.3",
description: "Grok 4.3 1M",
},
{
value: "claude-4.5-sonnet",
label: "claude-4.5-sonnet",
description: "Sonnet 4.5",
},
{
value: "claude-4.5-sonnet-thinking",
label: "claude-4.5-sonnet-thinking",
description: "Sonnet 4.5 Thinking",
},
{
value: "gpt-5.1-low",
label: "gpt-5.1-low",
description: "GPT-5.1 Low",
},
{
value: "gpt-5.1",
label: "gpt-5.1",
description: "GPT-5.1",
},
{
value: "gpt-5.1-high",
label: "gpt-5.1-high",
description: "GPT-5.1 High",
},
{
value: "gemini-3-flash",
label: "gemini-3-flash",
description: "Gemini 3 Flash",
},
{
value: "gemini-3.5-flash",
label: "gemini-3.5-flash",
description: "Gemini 3.5 Flash",
},
{
value: "gpt-5.1-codex-mini-low",
label: "gpt-5.1-codex-mini-low",
description: "Codex 5.1 Mini Low",
},
{
value: "gpt-5.1-codex-mini",
label: "gpt-5.1-codex-mini",
description: "Codex 5.1 Mini",
},
{
value: "gpt-5.1-codex-mini-high",
label: "gpt-5.1-codex-mini-high",
description: "Codex 5.1 Mini High",
},
{
value: "claude-4-sonnet",
label: "claude-4-sonnet",
description: "Sonnet 4",
},
{
value: "claude-4-sonnet-thinking",
label: "claude-4-sonnet-thinking",
description: "Sonnet 4 Thinking",
},
{
value: "gpt-5-mini",
label: "gpt-5-mini",
description: "GPT-5 Mini",
},
{
value: "kimi-k2.5",
label: "kimi-k2.5",
description: "Kimi K2.5",
},
{ value: "opus-4.6-thinking", label: "Claude 4.6 Opus (Thinking)" },
{ value: "gpt-5.3-codex", label: "GPT-5.3" },
{ value: "gpt-5.2-high", label: "GPT-5.2 High" },
{ value: "gemini-3-pro", label: "Gemini 3 Pro" },
{ value: "opus-4.5-thinking", label: "Claude 4.5 Opus (Thinking)" },
{ value: "gpt-5.2", label: "GPT-5.2" },
{ value: "gpt-5.1", label: "GPT-5.1" },
{ value: "gpt-5.1-high", label: "GPT-5.1 High" },
{ value: "composer-1", label: "Composer 1" },
{ value: "auto", label: "Auto" },
{ value: "sonnet-4.5", label: "Claude 4.5 Sonnet" },
{ value: "sonnet-4.5-thinking", label: "Claude 4.5 Sonnet (Thinking)" },
{ value: "opus-4.5", label: "Claude 4.5 Opus" },
{ value: "gpt-5.1-codex", label: "GPT-5.1 Codex" },
{ value: "gpt-5.1-codex-high", label: "GPT-5.1 Codex High" },
{ value: "gpt-5.1-codex-max", label: "GPT-5.1 Codex Max" },
{ value: "gpt-5.1-codex-max-high", label: "GPT-5.1 Codex Max High" },
{ value: "opus-4.1", label: "Claude 4.1 Opus" },
{ value: "grok", label: "Grok" },
],
DEFAULT: "composer-2.5-fast",
DEFAULT: 'composer-2-fast',
};
type CursorModelRow = {
@@ -817,4 +281,3 @@ export class CursorProviderModels implements IProviderModels {
return writeProviderSessionActiveModelChange('cursor', input);
}
}

View File

@@ -88,15 +88,22 @@ function buildGeminiTokenUsage(tokens: unknown): AnyRecord | undefined {
const record = tokens as AnyRecord;
const input = Number(record.input || 0);
const output = Number(record.output || 0);
const total = Number(record.total || input + output || 0);
const cached = Number(record.cached || 0);
const thoughts = Number(record.thoughts || 0);
const tool = Number(record.tool || 0);
const totalFromFields = input + output + cached + thoughts + tool;
const total = Number(record.total || totalFromFields || 0);
return {
used: total,
inputTokens: input,
outputTokens: output,
total: total,
breakdown: {
input,
output,
cached,
thoughts,
tool,
},
};
}

View File

@@ -28,9 +28,9 @@ type OpenCodeHistoryRow = {
type OpenCodeTokenTotals = {
inputTokens: number;
outputTokens: number;
reasoningTokens: number;
cacheReadTokens: number;
cacheWriteTokens: number;
cacheCreationTokens: number;
reasoningTokens: number;
};
const openOpenCodeDatabase = (): Database.Database | null => {
@@ -106,13 +106,11 @@ const buildTokenUsage = (totals: OpenCodeTokenTotals | undefined): AnyRecord | u
}
const inputTokens = totals.inputTokens;
const displayInputTokens = inputTokens + totals.cacheReadTokens;
const outputTokens = totals.outputTokens;
const used = inputTokens
+ outputTokens
+ totals.reasoningTokens
+ totals.cacheReadTokens
+ totals.cacheWriteTokens;
const cacheReadTokens = totals.cacheReadTokens;
const cacheCreationTokens = totals.cacheCreationTokens;
const reasoningTokens = totals.reasoningTokens;
const used = inputTokens + outputTokens + cacheReadTokens + cacheCreationTokens + reasoningTokens;
if (used <= 0) {
return undefined;
@@ -120,50 +118,14 @@ const buildTokenUsage = (totals: OpenCodeTokenTotals | undefined): AnyRecord | u
return {
used,
inputTokens: displayInputTokens,
total: used,
inputTokens,
outputTokens,
breakdown: {
input: displayInputTokens,
output: outputTokens,
},
cacheReadTokens,
cacheCreationTokens,
};
};
const readOpenCodeSessionColumnTokenUsage = (
db: Database.Database,
sessionId: string,
): AnyRecord | undefined => {
const columns = db.prepare('PRAGMA table_info(session)').all() as { name: string }[];
const columnNames = new Set(columns.map((column) => column.name));
const requiredColumns = ['tokens_input', 'tokens_output', 'tokens_reasoning', 'tokens_cache_read', 'tokens_cache_write'];
if (!requiredColumns.every((column) => columnNames.has(column))) {
return undefined;
}
const row = db.prepare(`
SELECT
tokens_input AS inputTokens,
tokens_output AS outputTokens,
tokens_reasoning AS reasoningTokens,
tokens_cache_read AS cacheReadTokens,
tokens_cache_write AS cacheWriteTokens
FROM session
WHERE id = ?
`).get(sessionId) as OpenCodeTokenTotals | undefined;
if (!row) {
return undefined;
}
return buildTokenUsage({
inputTokens: Number(row.inputTokens ?? 0),
outputTokens: Number(row.outputTokens ?? 0),
reasoningTokens: Number(row.reasoningTokens ?? 0),
cacheReadTokens: Number(row.cacheReadTokens ?? 0),
cacheWriteTokens: Number(row.cacheWriteTokens ?? 0),
});
};
/**
* OpenCode stores per-message token counts on assistant `message.data` objects
* (see MessageV2.Assistant). Older DBs also had session-level counters; this
@@ -173,18 +135,13 @@ const aggregateOpenCodeSessionTokenUsage = (
db: Database.Database,
sessionId: string,
): AnyRecord | undefined => {
const sessionColumnUsage = readOpenCodeSessionColumnTokenUsage(db, sessionId);
if (sessionColumnUsage) {
return sessionColumnUsage;
}
const rows = db.prepare('SELECT data FROM message WHERE session_id = ?').all(sessionId) as { data: string }[];
let inputTokens = 0;
let outputTokens = 0;
let reasoningTokens = 0;
let cacheReadTokens = 0;
let cacheWriteTokens = 0;
let cacheCreationTokens = 0;
let reasoningTokens = 0;
for (const row of rows) {
const info = readJsonRecord(row.data);
@@ -202,15 +159,15 @@ const aggregateOpenCodeSessionTokenUsage = (
reasoningTokens += Number(tokens.reasoning ?? 0);
const cache = readObjectRecord(tokens.cache);
cacheReadTokens += Number(cache?.read ?? 0);
cacheWriteTokens += Number(cache?.write ?? 0);
cacheCreationTokens += Number(cache?.write ?? 0);
}
return buildTokenUsage({
inputTokens,
outputTokens,
reasoningTokens,
cacheReadTokens,
cacheWriteTokens,
cacheCreationTokens,
reasoningTokens,
});
};

View File

@@ -1,7 +1,18 @@
import os from 'node:os';
import { providerRegistry } from '@/modules/providers/provider.registry.js';
import type { LLMProvider, McpScope, ProviderMcpServer, UpsertProviderMcpServerInput } from '@/shared/types.js';
import { AppError } from '@/shared/utils.js';
/** Cursor MCP is not supported on Windows hosts (no Cursor CLI integration). */
function includeProviderInGlobalMcp(providerId: LLMProvider): boolean {
if (providerId === 'cursor' && os.platform() === 'win32') {
return false;
}
return true;
}
export const providerMcpService = {
/**
@@ -64,7 +75,7 @@ export const providerMcpService = {
const scope = input.scope ?? 'project';
const results: Array<{ provider: LLMProvider; created: boolean; error?: string }> = [];
const providers = providerRegistry.listProviders();
const providers = providerRegistry.listProviders().filter((p) => includeProviderInGlobalMcp(p.id));
for (const provider of providers) {
try {
await provider.mcp.upsertServer({ ...input, scope });

View File

@@ -341,7 +341,8 @@ test('providerMcpService global adder writes to all providers and rejects unsupp
workspacePath,
});
assert.equal(globalResult.length, 5);
const expectCursorGlobal = process.platform !== 'win32';
assert.equal(globalResult.length, expectCursorGlobal ? 5 : 4);
assert.ok(globalResult.every((entry) => entry.created === true));
const claudeProject = await readJson(path.join(workspacePath, '.mcp.json'));
@@ -356,8 +357,10 @@ test('providerMcpService global adder writes to all providers and rejects unsupp
const opencodeProject = await readJson(path.join(workspacePath, 'opencode.json'));
assert.ok((opencodeProject.mcp as Record<string, unknown>)['global-http']);
const cursorProject = await readJson(path.join(workspacePath, '.cursor', 'mcp.json'));
assert.ok((cursorProject.mcpServers as Record<string, unknown>)['global-http']);
if (expectCursorGlobal) {
const cursorProject = await readJson(path.join(workspacePath, '.cursor', 'mcp.json'));
assert.ok((cursorProject.mcpServers as Record<string, unknown>)['global-http']);
}
await assert.rejects(
providerMcpService.addMcpServerToAllProviders({

View File

@@ -85,12 +85,6 @@ const createOpenCodeDatabase = async (homeDir: string, workspacePath: string): P
path TEXT,
agent TEXT,
model TEXT,
cost REAL NOT NULL DEFAULT 0,
tokens_input INTEGER NOT NULL DEFAULT 0,
tokens_output INTEGER NOT NULL DEFAULT 0,
tokens_reasoning INTEGER NOT NULL DEFAULT 0,
tokens_cache_read INTEGER NOT NULL DEFAULT 0,
tokens_cache_write INTEGER NOT NULL DEFAULT 0,
FOREIGN KEY (project_id) REFERENCES project(id) ON DELETE CASCADE
);
@@ -130,10 +124,9 @@ const createOpenCodeDatabase = async (homeDir: string, workspacePath: string): P
);
db.prepare(`
INSERT INTO session (
id, project_id, slug, directory, title, version, time_created, time_updated, time_archived,
tokens_input, tokens_output, tokens_reasoning, tokens_cache_read, tokens_cache_write
id, project_id, slug, directory, title, version, time_created, time_updated, time_archived
)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
`).run(
'open-session-1',
'project-1',
@@ -144,11 +137,6 @@ const createOpenCodeDatabase = async (homeDir: string, workspacePath: string): P
1_700_000_000_000,
1_700_000_004_000,
null,
10,
20,
7,
3,
2,
);
const userMessageData = JSON.stringify({
@@ -314,13 +302,12 @@ test('OpenCode sessions provider reads sqlite history and token usage', { concur
assert.equal(history.messages[3]?.kind, 'tool_use');
assert.deepEqual(history.messages[3]?.toolResult, { content: 'ok', isError: false });
assert.deepEqual(history.tokenUsage, {
used: 42,
inputTokens: 13,
used: 35,
total: 35,
inputTokens: 10,
outputTokens: 20,
breakdown: {
input: 13,
output: 20,
},
cacheReadTokens: 3,
cacheCreationTokens: 2,
});
const paged = await provider.fetchHistory('open-session-1', { limit: 2, offset: 0 });

View File

@@ -23,34 +23,6 @@ import { createNormalizedMessage } from './shared/utils.js';
// Track active sessions
const activeCodexSessions = new Map();
function readUsageNumber(value) {
const parsed = Number(value);
return Number.isFinite(parsed) ? parsed : 0;
}
function extractCodexTokenBudget(event) {
const info = event?.info || event?.payload?.info || event?.usage?.info;
const usage = info?.total_token_usage || event?.usage?.total_token_usage || event?.usage;
if (!usage || typeof usage !== 'object') {
return null;
}
const inputTokens = readUsageNumber(usage.input_tokens);
const outputTokens = readUsageNumber(usage.output_tokens);
const used = readUsageNumber(usage.total_tokens) || inputTokens + outputTokens;
return {
used,
total: readUsageNumber(info?.model_context_window || event?.usage?.model_context_window) || 200000,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens,
},
};
}
/**
* Transform Codex SDK event to WebSocket message format
* @param {object} event - SDK event
@@ -344,11 +316,9 @@ export async function queryCodex(command, options = {}, ws) {
}
// Extract and send token usage if available (normalized to match Claude format)
if (event.type === 'turn.completed') {
const tokenBudget = extractCodexTokenBudget(event);
if (tokenBudget) {
sendMessage(ws, createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget, sessionId: capturedSessionId || sessionId || null, provider: 'codex' }));
}
if (event.type === 'turn.completed' && event.usage) {
const totalTokens = (event.usage.input_tokens || 0) + (event.usage.output_tokens || 0);
sendMessage(ws, createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget: { used: totalTokens, total: 200000 }, sessionId: capturedSessionId || sessionId || null, provider: 'codex' }));
}
}

View File

@@ -1,14 +1,12 @@
import { spawn } from 'child_process';
import fsSync from 'node:fs';
import crossSpawn from 'cross-spawn';
import Database from 'better-sqlite3';
import { sessionsService } from './modules/providers/services/sessions.service.js';
import { providerAuthService } from './modules/providers/services/provider-auth.service.js';
import { providerModelsService } from './modules/providers/services/provider-models.service.js';
import { notifyRunFailed, notifyRunStopped } from './services/notification-orchestrator.js';
import { createNormalizedMessage, getOpenCodeDatabasePath } from './shared/utils.js';
import { createNormalizedMessage } from './shared/utils.js';
const spawnFunction = process.platform === 'win32' ? crossSpawn : spawn;
@@ -22,66 +20,6 @@ function readOpenCodeSessionId(event) {
return event.sessionID || event.sessionId || null;
}
function readOpenCodeTokenUsage(sessionId) {
const dbPath = getOpenCodeDatabasePath();
if (!sessionId || !fsSync.existsSync(dbPath)) {
return null;
}
let db = null;
try {
db = new Database(dbPath, { readonly: true, fileMustExist: true });
const columns = db.prepare('PRAGMA table_info(session)').all();
const columnNames = new Set(columns.map((column) => column.name));
const requiredColumns = ['tokens_input', 'tokens_output', 'tokens_reasoning', 'tokens_cache_read', 'tokens_cache_write'];
if (!requiredColumns.every((column) => columnNames.has(column))) {
return null;
}
const row = db.prepare(`
SELECT
tokens_input AS inputTokens,
tokens_output AS outputTokens,
tokens_reasoning AS reasoningTokens,
tokens_cache_read AS cacheReadTokens,
tokens_cache_write AS cacheWriteTokens
FROM session
WHERE id = ?
`).get(sessionId);
if (!row) {
return null;
}
const inputTokens = Number(row.inputTokens || 0) + Number(row.cacheReadTokens || 0);
const outputTokens = Number(row.outputTokens || 0);
const used = Number(row.inputTokens || 0)
+ outputTokens
+ Number(row.reasoningTokens || 0)
+ Number(row.cacheReadTokens || 0)
+ Number(row.cacheWriteTokens || 0);
if (used <= 0) {
return null;
}
return {
used,
inputTokens,
outputTokens,
breakdown: {
input: inputTokens,
output: outputTokens,
},
};
} catch {
return null;
} finally {
if (db) {
db.close();
}
}
}
async function spawnOpenCode(command, options = {}, ws) {
return new Promise((resolve, reject) => {
const { sessionId, projectPath, cwd, model, sessionSummary } = options;
@@ -245,17 +183,6 @@ async function spawnOpenCode(command, options = {}, ws) {
stdoutLineBuffer = '';
}
const tokenBudget = readOpenCodeTokenUsage(finalSessionId);
if (tokenBudget) {
ws.send(createNormalizedMessage({
kind: 'status',
text: 'token_budget',
tokenBudget,
sessionId: finalSessionId,
provider: 'opencode',
}));
}
ws.send(createNormalizedMessage({
kind: 'complete',
exitCode: code,

View File

@@ -174,7 +174,7 @@ const builtInCommands = [
},
{
name: "/cost",
description: "Display token usage information",
description: "Display token usage and cost information",
namespace: "builtin",
metadata: { type: "builtin" },
},
@@ -258,7 +258,7 @@ Custom commands can be created in:
const catalog = (await providerModelsService.getProviderModels(provider)).models;
const model = await resolveCommandModel(provider, catalog, context?.sessionId);
const reportedUsed =
const used =
Number(
tokenUsage.used ?? tokenUsage.totalUsed ?? tokenUsage.total_tokens ?? 0,
) || 0;
@@ -266,15 +266,16 @@ Custom commands can be created in:
Number(
tokenUsage.total ??
tokenUsage.contextWindow ??
0,
) || 0;
parseInt(process.env.CONTEXT_WINDOW || "160000", 10),
) || 160000;
const percentage =
total > 0 ? Number(((used / total) * 100).toFixed(1)) : 0;
const inputTokensRaw =
Number(
tokenUsage.inputTokens ??
tokenUsage.input ??
tokenUsage.input_tokens ??
tokenUsage.cumulativeInputTokens ??
tokenUsage.breakdown?.input ??
tokenUsage.promptTokens ??
0,
) || 0;
@@ -282,14 +283,36 @@ Custom commands can be created in:
Number(
tokenUsage.outputTokens ??
tokenUsage.output ??
tokenUsage.output_tokens ??
tokenUsage.cumulativeOutputTokens ??
tokenUsage.breakdown?.output ??
tokenUsage.completionTokens ??
0,
) || 0;
const hasTokenBreakdown = inputTokensRaw > 0 || outputTokens > 0;
const used = reportedUsed || inputTokensRaw + outputTokens;
const cacheTokens =
Number(
tokenUsage.cacheReadTokens ??
tokenUsage.cacheCreationTokens ??
tokenUsage.cacheTokens ??
tokenUsage.cachedTokens ??
0,
) || 0;
// If we only have total used tokens, treat them as input for display/estimation.
const inputTokens =
inputTokensRaw > 0 || outputTokens > 0 || cacheTokens > 0
? inputTokensRaw + cacheTokens
: used;
// Rough default rates by provider (USD / 1M tokens).
const pricingByProvider = {
claude: { input: 3, output: 15 },
cursor: { input: 3, output: 15 },
codex: { input: 1.5, output: 6 },
};
const rates = pricingByProvider[provider] || pricingByProvider.claude;
const inputCost = (inputTokens / 1_000_000) * rates.input;
const outputCost = (outputTokens / 1_000_000) * rates.output;
const totalCost = inputCost + outputCost;
return {
type: "builtin",
@@ -298,15 +321,18 @@ Custom commands can be created in:
tokenUsage: {
used,
total,
percentage,
},
tokenBreakdown: {
input: inputTokens,
output: outputTokens,
cache: cacheTokens,
},
cost: {
input: inputCost.toFixed(4),
output: outputCost.toFixed(4),
total: totalCost.toFixed(4),
},
...(hasTokenBreakdown
? {
tokenBreakdown: {
input: inputTokensRaw,
output: outputTokens,
},
}
: {}),
provider,
model,
},

View File

@@ -1,5 +1,4 @@
import express from 'express';
import { apiKeysDb, credentialsDb, notificationPreferencesDb, pushSubscriptionsDb } from '../modules/database/index.js';
import { getPublicKey } from '../services/vapid-keys.js';
import { createNotificationEvent, notifyUserIfEnabled } from '../services/notification-orchestrator.js';
@@ -274,4 +273,14 @@ router.post('/push/unsubscribe', async (req, res) => {
}
});
// Host OS for UI (e.g. hide Cursor agent when the backend runs on Windows).
router.get('/server-env', async (req, res) => {
try {
res.json({ platform: process.platform });
} catch (error) {
console.error('Error reading server environment:', error);
res.status(500).json({ error: 'Failed to read server environment' });
}
});
export default router;

View File

@@ -97,10 +97,17 @@ export type CostCommandData = {
tokenUsage?: {
used?: number;
total?: number;
percentage?: number;
};
cost?: {
input?: string;
output?: string;
total?: string;
};
tokenBreakdown?: {
input?: number;
output?: number;
cache?: number;
};
provider?: string;
model?: string;

View File

@@ -624,23 +624,19 @@ export function useChatSessionState({
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [chatMessages.length, isLoadingSessionMessages, searchTarget]);
// Initial token usage fetch for providers with file-backed usage data.
// Token usage fetch for Claude
useEffect(() => {
if (!selectedProject || !selectedSession?.id) {
setTokenBudget(null);
return;
}
const sessionProvider = selectedSession.__provider || 'claude';
if (sessionProvider !== 'claude' && sessionProvider !== 'codex' && sessionProvider !== 'gemini' && sessionProvider !== 'opencode') {
setTokenBudget(null);
return;
}
if (sessionProvider !== 'claude') return;
const fetchInitialTokenUsage = async () => {
try {
// Token usage endpoint is now keyed by the DB projectId.
const params = new URLSearchParams({ provider: sessionProvider });
const url = `/api/projects/${selectedProject.projectId}/sessions/${selectedSession.id}/token-usage?${params.toString()}`;
const url = `/api/projects/${selectedProject.projectId}/sessions/${selectedSession.id}/token-usage`;
const response = await authenticatedFetch(url);
if (response.ok) {
setTokenBudget(await response.json());

View File

@@ -18,7 +18,7 @@ import ClaudeStatus from './ClaudeStatus';
import ImageAttachment from './ImageAttachment';
import PermissionRequestsBanner from './PermissionRequestsBanner';
import ThinkingModeSelector from './ThinkingModeSelector';
import TokenUsageSummary from './TokenUsageSummary';
import TokenUsagePie from './TokenUsagePie';
import {
PromptInput,
PromptInputHeader,
@@ -60,7 +60,7 @@ interface ChatComposerProps {
onModeSwitch: () => void;
thinkingMode: string;
setThinkingMode: Dispatch<SetStateAction<string>>;
tokenBudget: Record<string, unknown> | null;
tokenBudget: { used?: number; total?: number } | null;
slashCommandsCount: number;
onToggleCommandMenu: () => void;
hasInput: boolean;
@@ -361,7 +361,7 @@ export default function ChatComposer({
<ThinkingModeSelector selectedMode={thinkingMode} onModeChange={setThinkingMode} onClose={() => {}} className="" />
)}
<TokenUsageSummary usage={tokenBudget} />
<TokenUsagePie used={tokenBudget?.used || 0} total={tokenBudget?.total || parseInt(import.meta.env.VITE_CONTEXT_WINDOW) || 160000} />
<PromptInputButton
tooltip={{ content: t('input.showAllCommands') }}

View File

@@ -6,6 +6,7 @@ import {
CircleHelp,
Clipboard,
Coins,
Command as CommandIcon,
Cpu,
Gauge,
Package,
@@ -16,6 +17,7 @@ import {
Timer,
RefreshCw,
X,
Zap,
} from 'lucide-react';
import { Badge, Button, Dialog, DialogContent, DialogTitle, Input } from '../../../../shared/view/ui';
@@ -82,7 +84,7 @@ const PROVIDER_LABELS: Record<string, string> = {
const FALLBACK_COMMANDS: CommandEntry[] = [
{ name: '/models', description: 'Browse available models for the active provider.' },
{ name: '/cost', description: 'Review token usage for the active session.' },
{ name: '/cost', description: 'Review context usage and estimated token spend.' },
{ name: '/status', description: 'Inspect runtime, version, provider, and environment status.' },
{ name: '/memory', description: 'Open the project CLAUDE.md memory file.' },
{ name: '/config', description: 'Open settings and configuration.' },
@@ -97,6 +99,13 @@ const getProviderLabel = (provider: string | undefined, fallback = 'Unknown') =>
return PROVIDER_LABELS[provider] || provider;
};
const clampPercentage = (value: number) => {
if (!Number.isFinite(value)) {
return 0;
}
return Math.max(0, Math.min(100, value));
};
const formatNumber = (value: number) => {
if (!Number.isFinite(value)) {
return '0';
@@ -104,6 +113,11 @@ const formatNumber = (value: number) => {
return value.toLocaleString();
};
const formatCurrency = (value: number | string | undefined) => {
const numeric = Number(value ?? 0);
return `$${Number.isFinite(numeric) ? numeric.toFixed(4) : '0.0000'}`;
};
function MetricCard({
label,
value,
@@ -493,71 +507,62 @@ function ModelsContent({
function CostContent({ data }: { data: CostCommandData }) {
const used = Number(data.tokenUsage?.used ?? 0);
const total = Number(data.tokenUsage?.total ?? 0);
const percentage = clampPercentage(Number(data.tokenUsage?.percentage ?? 0));
const model = data.model || 'Unknown';
const provider = getProviderLabel(data.provider, data.provider || 'Unknown');
const hasBreakdown =
typeof data.tokenBreakdown?.input === 'number' ||
typeof data.tokenBreakdown?.output === 'number';
const usageRows = [
{ label: 'Total tokens used', value: formatNumber(used), icon: Activity },
...(hasBreakdown
? [
{
label: 'Input tokens',
value: formatNumber(Number(data.tokenBreakdown?.input ?? 0)),
icon: TerminalSquare,
},
{
label: 'Output tokens',
value: formatNumber(Number(data.tokenBreakdown?.output ?? 0)),
icon: Coins,
},
]
: [
{
label: 'Breakdown',
value: 'Unavailable',
icon: TerminalSquare,
},
]),
...(total > 0
? [{ label: 'Context window', value: formatNumber(total), icon: Gauge }]
: []),
];
const inputTokens = Number(data.tokenBreakdown?.input ?? 0);
const outputTokens = Number(data.tokenBreakdown?.output ?? 0);
const cacheTokens = Number(data.tokenBreakdown?.cache ?? 0);
const totalCost = Number(data.cost?.total ?? 0);
return (
<div className="space-y-4">
<div className="overflow-hidden rounded-2xl border border-border/70 bg-background/75">
{usageRows.map((row) => {
const Icon = row.icon;
return (
<div
key={row.label}
className="flex items-center justify-between gap-4 border-b border-border/60 px-4 py-3 last:border-b-0"
>
<div className="flex min-w-0 items-center gap-3">
<span className="grid h-9 w-9 shrink-0 place-items-center rounded-xl border border-primary/20 bg-primary/10 text-primary">
<Icon className="h-4 w-4" />
</span>
<span className="truncate text-sm font-medium text-foreground">{row.label}</span>
</div>
<span className="shrink-0 font-mono text-sm font-semibold text-foreground">{row.value}</span>
<div className="grid gap-4 lg:grid-cols-[18rem_1fr]">
<div className="rounded-3xl border border-primary/25 bg-primary/10 p-5 text-center">
<div
className="mx-auto grid h-40 w-40 place-items-center rounded-full p-2 shadow-inner"
style={{
background: `conic-gradient(hsl(var(--primary)) ${percentage * 3.6}deg, hsl(var(--muted)) 0deg)`,
}}
>
<div className="grid h-full w-full place-items-center rounded-full border border-border/70 bg-popover">
<div>
<p className="font-mono text-3xl font-semibold text-foreground">{percentage.toFixed(1)}%</p>
<p className="mt-1 text-xs uppercase tracking-[0.18em] text-muted-foreground">context</p>
</div>
);
})}
</div>
</div>
<p className="mt-4 text-sm text-muted-foreground">
{formatNumber(used)} of {formatNumber(total)} tokens used
</p>
</div>
<div className="rounded-2xl border border-border/70 bg-muted/20 p-4">
<div className="grid gap-3 sm:grid-cols-2">
<div>
<p className="text-[11px] font-semibold uppercase tracking-[0.18em] text-muted-foreground">Provider</p>
<p className="mt-1 text-sm font-semibold text-foreground">{provider}</p>
</div>
<div>
<p className="text-[11px] font-semibold uppercase tracking-[0.18em] text-muted-foreground">Model</p>
<p className="mt-1 break-all font-mono text-sm text-foreground">{model}</p>
<div className="space-y-3">
<div className="grid gap-3 sm:grid-cols-3">
<MetricCard label="Input" value={formatCurrency(data.cost?.input)} icon={Zap} />
<MetricCard label="Output" value={formatCurrency(data.cost?.output)} icon={Activity} />
<MetricCard label="Total" value={formatCurrency(totalCost)} icon={Coins} tone="primary" />
</div>
<div className="grid gap-3 sm:grid-cols-3">
<MetricCard label="Input tokens" value={formatNumber(inputTokens)} icon={CommandIcon} />
<MetricCard label="Output tokens" value={formatNumber(outputTokens)} icon={TerminalSquare} />
<MetricCard label="Cache tokens" value={formatNumber(cacheTokens)} icon={Package} />
</div>
<div className="rounded-2xl border border-border/70 bg-muted/20 p-4">
<div className="grid gap-3 sm:grid-cols-2">
<div>
<p className="text-[11px] font-semibold uppercase tracking-[0.18em] text-muted-foreground">Provider</p>
<p className="mt-1 text-sm font-semibold text-foreground">{provider}</p>
</div>
<div>
<p className="text-[11px] font-semibold uppercase tracking-[0.18em] text-muted-foreground">Model</p>
<p className="mt-1 break-all font-mono text-sm text-foreground">{model}</p>
</div>
</div>
<p className="mt-3 text-xs leading-5 text-muted-foreground">
Cost is an estimate based on the available token counters and default provider rates.
</p>
</div>
</div>
</div>
@@ -631,8 +636,8 @@ export default function CommandResultModal({
},
cost: {
eyebrow: 'Session telemetry',
title: 'Token Usage',
subtitle: 'Input, output, and total token counts for this session.',
title: 'Usage & Cost',
subtitle: 'Token budget, context pressure, and estimated spend for this session.',
icon: Coins,
},
status: {

View File

@@ -1,7 +1,8 @@
import React, { useCallback, useMemo, useState } from "react";
import React, { useCallback, useEffect, useMemo, useState } from "react";
import { Check, ChevronDown } from "lucide-react";
import { Trans, useTranslation } from "react-i18next";
import { useServerPlatform } from "../../../../hooks/useServerPlatform";
import type {
ProjectSession,
LLMProvider,
@@ -119,15 +120,24 @@ export default function ProviderSelectionEmptyState({
setInput,
}: ProviderSelectionEmptyStateProps) {
const { t } = useTranslation("chat");
const { isWindowsServer } = useServerPlatform();
const [dialogOpen, setDialogOpen] = useState(false);
const visibleProviderGroups = useMemo<ProviderGroup[]>(() => {
return PROVIDER_META.map((p) => ({
const visibleProviderGroups = useMemo(() => {
const groups: ProviderGroup[] = PROVIDER_META.map((p) => ({
id: p.id,
name: p.name,
models: providerModelCatalog[p.id]?.OPTIONS ?? [],
}));
}, [providerModelCatalog]);
return isWindowsServer ? groups.filter((p) => p.id !== "cursor") : groups;
}, [isWindowsServer, providerModelCatalog]);
useEffect(() => {
if (isWindowsServer && provider === "cursor") {
setProvider("claude");
localStorage.setItem("selected-provider", "claude");
}
}, [isWindowsServer, provider, setProvider]);
const nextTaskPrompt = t("tasks.nextTaskPrompt", {
defaultValue: "Start the next task",

View File

@@ -0,0 +1,54 @@
type TokenUsagePieProps = {
used: number;
total: number;
};
export default function TokenUsagePie({ used, total }: TokenUsagePieProps) {
// Token usage visualization component
// Only bail out on missing values or nonpositive totals; allow used===0 to render 0%
if (used == null || total == null || total <= 0) return null;
const percentage = Math.min(100, (used / total) * 100);
const radius = 10;
const circumference = 2 * Math.PI * radius;
const offset = circumference - (percentage / 100) * circumference;
// Color based on usage level
const getColor = () => {
if (percentage < 50) return '#3b82f6'; // blue
if (percentage < 75) return '#f59e0b'; // orange
return '#ef4444'; // red
};
return (
<div className="flex items-center gap-2 text-xs text-gray-600 dark:text-gray-400">
<svg width="24" height="24" viewBox="0 0 24 24" className="-rotate-90 transform">
{/* Background circle */}
<circle
cx="12"
cy="12"
r={radius}
fill="none"
stroke="currentColor"
strokeWidth="2"
className="text-gray-300 dark:text-gray-600"
/>
{/* Progress circle */}
<circle
cx="12"
cy="12"
r={radius}
fill="none"
stroke={getColor()}
strokeWidth="2"
strokeDasharray={circumference}
strokeDashoffset={offset}
strokeLinecap="round"
/>
</svg>
<span title={`${used.toLocaleString()} / ${total.toLocaleString()} tokens`}>
{percentage.toFixed(1)}%
</span>
</div>
);
}

View File

@@ -1,53 +0,0 @@
import { ActivityIcon } from 'lucide-react';
type TokenUsageSummaryProps = {
usage: Record<string, unknown> | null;
};
const formatTokenCount = (value: number) => {
if (!Number.isFinite(value) || value <= 0) {
return '0';
}
if (value >= 1_000_000) {
return `${(value / 1_000_000).toFixed(value >= 10_000_000 ? 0 : 1)}M`;
}
if (value >= 10_000) {
return `${Math.round(value / 1_000)}K`;
}
if (value >= 1_000) {
return `${(value / 1_000).toFixed(1)}K`;
}
return value.toLocaleString();
};
const readUsageNumber = (value: unknown) => {
const parsed = Number(value);
return Number.isFinite(parsed) ? parsed : 0;
};
export default function TokenUsageSummary({ usage }: TokenUsageSummaryProps) {
const breakdown =
usage?.breakdown && typeof usage.breakdown === 'object'
? usage.breakdown as Record<string, unknown>
: null;
const inputTokens = readUsageNumber(usage?.inputTokens ?? breakdown?.input);
const outputTokens = readUsageNumber(usage?.outputTokens ?? breakdown?.output);
const usedTokens = readUsageNumber(usage?.used) || inputTokens + outputTokens;
return (
<div
className="inline-flex h-9 items-center gap-1.5 rounded-lg border border-border/70 bg-background/70 px-2 text-xs text-muted-foreground shadow-sm transition-colors hover:border-primary/25 hover:text-foreground sm:gap-2 sm:px-2.5"
title={`${usedTokens.toLocaleString()} tokens used`}
>
<span className="grid h-5 w-5 place-items-center rounded-md bg-primary/10 text-primary">
<ActivityIcon className="h-3.5 w-3.5" />
</span>
<span className="font-medium text-foreground">{formatTokenCount(usedTokens)}</span>
<span className="hidden text-muted-foreground/70 sm:inline">tokens</span>
</div>
);
}

View File

@@ -1,5 +1,6 @@
import { useMemo, useState } from 'react';
import { useEffect, useMemo, useState } from 'react';
import { useServerPlatform } from '../../../../../hooks/useServerPlatform';
import type { AgentCategory, AgentProvider } from '../../../types/types';
import type { AgentContext, AgentsSettingsTabProps } from './types';
@@ -22,10 +23,22 @@ export default function AgentsSettingsTab({
}: AgentsSettingsTabProps) {
const [selectedAgent, setSelectedAgent] = useState<AgentProvider>('claude');
const [selectedCategory, setSelectedCategory] = useState<AgentCategory>('account');
const { isWindowsServer } = useServerPlatform();
const visibleAgents = useMemo<AgentProvider[]>(() => {
return ['claude', 'cursor', 'codex', 'gemini', 'opencode'];
}, []);
const all: AgentProvider[] = ['claude', 'cursor', 'codex', 'gemini', 'opencode'];
if (isWindowsServer) {
return all.filter((id) => id !== 'cursor');
}
return all;
}, [isWindowsServer]);
useEffect(() => {
if (isWindowsServer && selectedAgent === 'cursor') {
setSelectedAgent('claude');
}
}, [isWindowsServer, selectedAgent]);
const agentContextById = useMemo<Record<AgentProvider, AgentContext>>(() => ({
claude: {

View File

@@ -0,0 +1,40 @@
import { useEffect, useState } from 'react';
import { authenticatedFetch } from '../utils/api';
/**
* Node `process.platform` from the API host (e.g. win32, darwin, linux).
* Null until loaded or if the request fails.
*/
export function useServerPlatform(): {
serverPlatform: string | null;
isWindowsServer: boolean;
} {
const [serverPlatform, setServerPlatform] = useState<string | null>(null);
useEffect(() => {
let cancelled = false;
(async () => {
try {
const response = await authenticatedFetch('/api/settings/server-env');
if (!response.ok) {
return;
}
const body = (await response.json()) as { platform?: string };
if (!cancelled && typeof body.platform === 'string') {
setServerPlatform(body.platform);
}
} catch {
// Keep null: treat as unknown host.
}
})();
return () => {
cancelled = true;
};
}, []);
return {
serverPlatform,
isWindowsServer: serverPlatform === 'win32',
};
}