9router/src/app/(dashboard)/dashboard/profile/page.js

632 lines
23 KiB
JavaScript
Raw Normal View History

2026-01-04 21:58:59 -05:00
"use client";
import { useState, useEffect, useRef } from "react";
import { Card, Button, Toggle, Input } from "@/shared/components";
2026-01-04 21:58:59 -05:00
import { useTheme } from "@/shared/hooks/useTheme";
2026-01-31 00:58:04 -05:00
import { cn } from "@/shared/utils/cn";
2026-01-04 21:58:59 -05:00
import { APP_CONFIG } from "@/shared/constants/config";
export default function ProfilePage() {
const { theme, setTheme, isDark } = useTheme();
const [settings, setSettings] = useState({ fallbackStrategy: "fill-first" });
const [loading, setLoading] = useState(true);
const [passwords, setPasswords] = useState({ current: "", new: "", confirm: "" });
const [passStatus, setPassStatus] = useState({ type: "", message: "" });
const [passLoading, setPassLoading] = useState(false);
const [dbLoading, setDbLoading] = useState(false);
const [dbStatus, setDbStatus] = useState({ type: "", message: "" });
const importFileRef = useRef(null);
const [proxyForm, setProxyForm] = useState({
outboundProxyEnabled: false,
outboundProxyUrl: "",
outboundNoProxy: "",
});
const [proxyStatus, setProxyStatus] = useState({ type: "", message: "" });
const [proxyLoading, setProxyLoading] = useState(false);
const [proxyTestLoading, setProxyTestLoading] = useState(false);
useEffect(() => {
fetch("/api/settings")
.then((res) => res.json())
.then((data) => {
setSettings(data);
setProxyForm({
outboundProxyEnabled: data?.outboundProxyEnabled === true,
outboundProxyUrl: data?.outboundProxyUrl || "",
outboundNoProxy: data?.outboundNoProxy || "",
});
setLoading(false);
})
.catch((err) => {
console.error("Failed to fetch settings:", err);
setLoading(false);
});
}, []);
const updateOutboundProxy = async (e) => {
e.preventDefault();
if (settings.outboundProxyEnabled !== true) return;
setProxyLoading(true);
setProxyStatus({ type: "", message: "" });
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
outboundProxyUrl: proxyForm.outboundProxyUrl,
outboundNoProxy: proxyForm.outboundNoProxy,
}),
});
const data = await res.json();
if (res.ok) {
setSettings((prev) => ({ ...prev, ...data }));
setProxyStatus({ type: "success", message: "Proxy settings applied" });
} else {
setProxyStatus({ type: "error", message: data.error || "Failed to update proxy settings" });
}
} catch (err) {
setProxyStatus({ type: "error", message: "An error occurred" });
} finally {
setProxyLoading(false);
}
};
const testOutboundProxy = async () => {
if (settings.outboundProxyEnabled !== true) return;
const proxyUrl = (proxyForm.outboundProxyUrl || "").trim();
if (!proxyUrl) {
setProxyStatus({ type: "error", message: "Please enter a Proxy URL to test" });
return;
}
setProxyTestLoading(true);
setProxyStatus({ type: "", message: "" });
try {
const res = await fetch("/api/settings/proxy-test", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ proxyUrl }),
});
const data = await res.json();
if (res.ok && data?.ok) {
setProxyStatus({
type: "success",
message: `Proxy test OK (${data.status}) in ${data.elapsedMs}ms`,
});
} else {
setProxyStatus({
type: "error",
message: data?.error || "Proxy test failed",
});
}
} catch (err) {
setProxyStatus({ type: "error", message: "An error occurred" });
} finally {
setProxyTestLoading(false);
}
};
const updateOutboundProxyEnabled = async (outboundProxyEnabled) => {
setProxyLoading(true);
setProxyStatus({ type: "", message: "" });
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ outboundProxyEnabled }),
});
const data = await res.json();
if (res.ok) {
setSettings((prev) => ({ ...prev, ...data }));
setProxyForm((prev) => ({ ...prev, outboundProxyEnabled: data?.outboundProxyEnabled === true }));
setProxyStatus({
type: "success",
message: outboundProxyEnabled ? "Proxy enabled" : "Proxy disabled",
});
} else {
setProxyStatus({ type: "error", message: data.error || "Failed to update proxy settings" });
}
} catch (err) {
setProxyStatus({ type: "error", message: "An error occurred" });
} finally {
setProxyLoading(false);
}
};
const handlePasswordChange = async (e) => {
e.preventDefault();
if (passwords.new !== passwords.confirm) {
setPassStatus({ type: "error", message: "Passwords do not match" });
return;
}
setPassLoading(true);
setPassStatus({ type: "", message: "" });
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
currentPassword: passwords.current,
newPassword: passwords.new,
}),
});
const data = await res.json();
if (res.ok) {
setPassStatus({ type: "success", message: "Password updated successfully" });
setPasswords({ current: "", new: "", confirm: "" });
} else {
setPassStatus({ type: "error", message: data.error || "Failed to update password" });
}
} catch (err) {
setPassStatus({ type: "error", message: "An error occurred" });
} finally {
setPassLoading(false);
}
};
const updateFallbackStrategy = async (strategy) => {
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ fallbackStrategy: strategy }),
});
if (res.ok) {
setSettings(prev => ({ ...prev, fallbackStrategy: strategy }));
}
} catch (err) {
console.error("Failed to update settings:", err);
}
};
2026-01-04 21:58:59 -05:00
const updateStickyLimit = async (limit) => {
const numLimit = parseInt(limit);
if (isNaN(numLimit) || numLimit < 1) return;
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ stickyRoundRobinLimit: numLimit }),
});
if (res.ok) {
setSettings(prev => ({ ...prev, stickyRoundRobinLimit: numLimit }));
}
} catch (err) {
console.error("Failed to update sticky limit:", err);
}
};
const updateRequireLogin = async (requireLogin) => {
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ requireLogin }),
});
if (res.ok) {
setSettings(prev => ({ ...prev, requireLogin }));
}
} catch (err) {
console.error("Failed to update require login:", err);
}
};
const updateObservabilityEnabled = async (enabled) => {
try {
const res = await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ observabilityEnabled: enabled }),
});
if (res.ok) {
setSettings(prev => ({ ...prev, observabilityEnabled: enabled }));
}
} catch (err) {
console.error("Failed to update observabilityEnabled:", err);
}
};
const reloadSettings = async () => {
try {
const res = await fetch("/api/settings");
if (!res.ok) return;
const data = await res.json();
setSettings(data);
} catch (err) {
console.error("Failed to reload settings:", err);
}
};
const handleExportDatabase = async () => {
setDbLoading(true);
setDbStatus({ type: "", message: "" });
try {
const res = await fetch("/api/settings/database");
if (!res.ok) {
const data = await res.json().catch(() => ({}));
throw new Error(data.error || "Failed to export database");
}
const payload = await res.json();
const content = JSON.stringify(payload, null, 2);
const blob = new Blob([content], { type: "application/json" });
const url = URL.createObjectURL(blob);
const anchor = document.createElement("a");
const stamp = new Date().toISOString().replace(/[.:]/g, "-");
anchor.href = url;
anchor.download = `9router-backup-${stamp}.json`;
document.body.appendChild(anchor);
anchor.click();
document.body.removeChild(anchor);
URL.revokeObjectURL(url);
setDbStatus({ type: "success", message: "Database backup downloaded" });
} catch (err) {
setDbStatus({ type: "error", message: err.message || "Failed to export database" });
} finally {
setDbLoading(false);
}
};
const handleImportDatabase = async (event) => {
const file = event.target.files?.[0];
if (!file) return;
setDbLoading(true);
setDbStatus({ type: "", message: "" });
try {
const raw = await file.text();
const payload = JSON.parse(raw);
const res = await fetch("/api/settings/database", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify(payload),
});
const data = await res.json().catch(() => ({}));
if (!res.ok) {
throw new Error(data.error || "Failed to import database");
}
await reloadSettings();
setDbStatus({ type: "success", message: "Database imported successfully" });
} catch (err) {
setDbStatus({ type: "error", message: err.message || "Invalid backup file" });
} finally {
if (importFileRef.current) {
importFileRef.current.value = "";
}
setDbLoading(false);
}
};
const observabilityEnabled = settings.observabilityEnabled === true;
2026-01-04 21:58:59 -05:00
return (
<div className="max-w-2xl mx-auto">
<div className="flex flex-col gap-6">
{/* Local Mode Info */}
<Card>
<div className="flex items-center justify-between mb-4">
<div className="flex items-center gap-4">
<div className="size-12 rounded-lg bg-green-500/10 text-green-500 flex items-center justify-center">
<span className="material-symbols-outlined text-2xl">computer</span>
</div>
<div>
<h2 className="text-xl font-semibold">Local Mode</h2>
<p className="text-text-muted">Running on your machine</p>
</div>
2026-01-04 21:58:59 -05:00
</div>
<div className="inline-flex p-1 rounded-lg bg-black/5 dark:bg-white/5">
{["light", "dark", "system"].map((option) => (
<button
key={option}
type="button"
onClick={() => setTheme(option)}
className={cn(
"flex items-center gap-1.5 px-3 py-1.5 rounded-md font-medium transition-all",
theme === option
? "bg-white dark:bg-white/10 text-text-main shadow-sm"
: "text-text-muted hover:text-text-main"
)}
>
<span className="material-symbols-outlined text-[18px]">
{option === "light" ? "light_mode" : option === "dark" ? "dark_mode" : "contrast"}
</span>
<span className="capitalize text-sm">{option}</span>
</button>
))}
2026-01-04 21:58:59 -05:00
</div>
</div>
<div className="flex flex-col gap-3 pt-4 border-t border-border">
<div className="flex items-center justify-between p-3 rounded-lg bg-bg border border-border">
<div>
<p className="font-medium">Database Location</p>
<p className="text-sm text-text-muted font-mono">~/.9router/db.json</p>
</div>
</div>
<div className="flex flex-wrap gap-2">
<Button
variant="secondary"
icon="download"
onClick={handleExportDatabase}
loading={dbLoading}
>
Download Backup
</Button>
<Button
variant="outline"
icon="upload"
onClick={() => importFileRef.current?.click()}
disabled={dbLoading}
>
Import Backup
</Button>
<input
ref={importFileRef}
type="file"
accept="application/json,.json"
className="hidden"
onChange={handleImportDatabase}
/>
</div>
{dbStatus.message && (
<p className={`text-sm ${dbStatus.type === "error" ? "text-red-500" : "text-green-600 dark:text-green-400"}`}>
{dbStatus.message}
</p>
)}
2026-01-04 21:58:59 -05:00
</div>
</Card>
{/* Security */}
<Card>
2026-01-31 00:58:04 -05:00
<div className="flex items-center gap-3 mb-4">
<div className="p-2 rounded-lg bg-primary/10 text-primary">
<span className="material-symbols-outlined text-[20px]">shield</span>
</div>
<h3 className="text-lg font-semibold">Security</h3>
</div>
<div className="flex flex-col gap-4">
<div className="flex items-center justify-between">
<div>
<p className="font-medium">Require login</p>
<p className="text-sm text-text-muted">
When ON, dashboard requires password. When OFF, access without login.
</p>
</div>
<Toggle
checked={settings.requireLogin === true}
onChange={() => updateRequireLogin(!settings.requireLogin)}
disabled={loading}
/>
</div>
{settings.requireLogin === true && (
<form onSubmit={handlePasswordChange} className="flex flex-col gap-4 pt-4 border-t border-border/50">
{settings.hasPassword && (
<div className="flex flex-col gap-2">
<label className="text-sm font-medium">Current Password</label>
<Input
type="password"
placeholder="Enter current password"
value={passwords.current}
onChange={(e) => setPasswords({ ...passwords, current: e.target.value })}
required
/>
</div>
)}
{/* {!settings.hasPassword && (
<div className="p-3 rounded-lg bg-blue-500/10 border border-blue-500/20">
<p className="text-sm text-blue-600 dark:text-blue-400">
Setting password for the first time. Leave current password empty or use default: <code className="bg-blue-500/20 px-1 rounded">123456</code>
</p>
</div>
)} */}
<div className="grid grid-cols-1 md:grid-cols-2 gap-4">
<div className="flex flex-col gap-2">
<label className="text-sm font-medium">New Password</label>
<Input
type="password"
placeholder="Enter new password"
value={passwords.new}
onChange={(e) => setPasswords({ ...passwords, new: e.target.value })}
required
/>
</div>
<div className="flex flex-col gap-2">
<label className="text-sm font-medium">Confirm New Password</label>
<Input
type="password"
placeholder="Confirm new password"
value={passwords.confirm}
onChange={(e) => setPasswords({ ...passwords, confirm: e.target.value })}
required
/>
</div>
</div>
{passStatus.message && (
<p className={`text-sm ${passStatus.type === "error" ? "text-red-500" : "text-green-500"}`}>
{passStatus.message}
</p>
)}
<div className="pt-2">
<Button type="submit" variant="primary" loading={passLoading}>
{settings.hasPassword ? "Update Password" : "Set Password"}
</Button>
</div>
</form>
)}
</div>
</Card>
{/* Routing Preferences */}
<Card>
2026-01-31 00:58:04 -05:00
<div className="flex items-center gap-3 mb-4">
<div className="p-2 rounded-lg bg-blue-500/10 text-blue-500">
<span className="material-symbols-outlined text-[20px]">route</span>
</div>
<h3 className="text-lg font-semibold">Routing Strategy</h3>
</div>
<div className="flex flex-col gap-4">
<div className="flex items-center justify-between">
<div>
<p className="font-medium">Round Robin</p>
<p className="text-sm text-text-muted">
Cycle through accounts to distribute load
</p>
</div>
<Toggle
checked={settings.fallbackStrategy === "round-robin"}
onChange={() => updateFallbackStrategy(settings.fallbackStrategy === "round-robin" ? "fill-first" : "round-robin")}
disabled={loading}
/>
</div>
{/* Sticky Round Robin Limit */}
{settings.fallbackStrategy === "round-robin" && (
<div className="flex items-center justify-between pt-2 border-t border-border/50">
<div>
<p className="font-medium">Sticky Limit</p>
<p className="text-sm text-text-muted">
Calls per account before switching
</p>
</div>
<Input
type="number"
min="1"
max="10"
value={settings.stickyRoundRobinLimit || 3}
onChange={(e) => updateStickyLimit(e.target.value)}
disabled={loading}
className="w-20 text-center"
/>
</div>
)}
<p className="text-xs text-text-muted italic pt-2 border-t border-border/50">
{settings.fallbackStrategy === "round-robin"
? `Currently distributing requests across all available accounts with ${settings.stickyRoundRobinLimit || 3} calls per account.`
: "Currently using accounts in priority order (Fill First)."}
</p>
</div>
</Card>
{/* Network */}
<Card>
<div className="flex items-center gap-3 mb-4">
<div className="p-2 rounded-lg bg-purple-500/10 text-purple-500">
<span className="material-symbols-outlined text-[20px]">wifi</span>
</div>
<h3 className="text-lg font-semibold">Network</h3>
</div>
<div className="flex flex-col gap-4">
<div className="flex items-center justify-between">
<div>
<p className="font-medium">Outbound Proxy</p>
<p className="text-sm text-text-muted">Enable proxy for OAuth + provider outbound requests.</p>
</div>
<Toggle
checked={settings.outboundProxyEnabled === true}
onChange={() => updateOutboundProxyEnabled(!(settings.outboundProxyEnabled === true))}
disabled={loading || proxyLoading}
/>
</div>
{settings.outboundProxyEnabled === true && (
<form onSubmit={updateOutboundProxy} className="flex flex-col gap-4 pt-2 border-t border-border/50">
<div className="flex flex-col gap-2">
<label className="font-medium">Proxy URL</label>
<Input
placeholder="http://127.0.0.1:7897"
value={proxyForm.outboundProxyUrl}
onChange={(e) => setProxyForm((prev) => ({ ...prev, outboundProxyUrl: e.target.value }))}
disabled={loading || proxyLoading}
/>
<p className="text-sm text-text-muted">Leave empty to inherit existing env proxy (if any).</p>
</div>
<div className="flex flex-col gap-2 pt-2 border-t border-border/50">
<label className="font-medium">No Proxy</label>
<Input
placeholder="localhost,127.0.0.1"
value={proxyForm.outboundNoProxy}
onChange={(e) => setProxyForm((prev) => ({ ...prev, outboundNoProxy: e.target.value }))}
disabled={loading || proxyLoading}
/>
<p className="text-sm text-text-muted">Comma-separated hostnames/domains to bypass the proxy.</p>
</div>
<div className="pt-2 border-t border-border/50 flex items-center gap-2">
<Button
type="button"
variant="secondary"
loading={proxyTestLoading}
disabled={loading || proxyLoading}
onClick={testOutboundProxy}
>
Test proxy URL
</Button>
<Button type="submit" variant="primary" loading={proxyLoading}>
Apply
</Button>
</div>
</form>
)}
{proxyStatus.message && (
<p className={`text-sm ${proxyStatus.type === "error" ? "text-red-500" : "text-green-500"} pt-2 border-t border-border/50`}>
{proxyStatus.message}
</p>
)}
</div>
</Card>
Feature/ai observability dashboard (#79) * feat: add AI request details feature with latency tracking Add comprehensive request history and debugging capability to the Usage dashboard: **Storage Layer** (usageDb.js): - Add saveRequestDetail() for storing full request/response details - Implement FIFO queue with 1000-record limit in request-details.json - Auto-sanitize sensitive headers (authorization, api-key, cookie, token) - Add getRequestDetails() with pagination and filtering support - Add getRequestDetailById() for single record lookup **Pipeline Integration** (chatCore.js): - Track request start time and calculate total latency - Record TTFT (Time To First Token) and total latency for all requests - Capture full request details (messages, model, parameters) - Save response content for non-streaming, mark streaming responses - Handle error cases with detailed error information - Async non-blocking saves to avoid impacting request performance **API Layer** (/api/usage/request-details): - GET endpoint with pagination (page, pageSize: 1-100) - Filter by provider, model, connectionId, status, date range - Returns { details: [...], pagination: {...} } format **UI Components**: - Drawer.js: Right slide-out panel with backdrop blur and ESC close - Pagination.js: Full pagination with page size selector (10/20/50) - RequestDetailsTab.js: Complete table view with filters and detail drawer **Dashboard Integration**: - Add "Details" tab to Usage page (4th tab after Overview/Logger/Limits) - Table columns: Timestamp, Model, Provider, Input Tokens, Output Tokens, Latency (TTFT/Total), Action - Provider filter dropdown (9 providers supported) - Date range filters (start/end datetime) - Click "Detail" button to view full request/response JSON in slide-out drawer **Features**: - Real-time latency monitoring (TTFT & Total) - Complete request/response inspection for debugging - Filterable and searchable request history - Responsive design with mobile-friendly filters - Data security with automatic header sanitization - Performance: async saves don't block request pipeline **Files Created/Modified**: - src/lib/usageDb.js (modified) - open-sse/handlers/chatCore.js (modified) - src/app/api/usage/request-details/route.js (new) - src/shared/components/Drawer.js (new) - src/shared/components/Pagination.js (new) - src/app/(dashboard)/dashboard/usage/components/RequestDetailsTab.js (new) - src/app/(dashboard)/dashboard/usage/page.js (modified) Closes: AI Observability Dashboard feature * feat: enhance request details with full config and streaming content capture Improve Request Details feature to capture comprehensive request parameters and actual streaming response content: **Request Configuration Enhancement** (chatCore.js): - Add extractRequestConfig() helper function to capture all request parameters - Include temperature controls: temperature, top_p, top_k - Include token limits: max_tokens, max_completion_tokens - Include thinking/reasoning modes: thinking, reasoning, enable_thinking - Include OpenAI parameters: presence_penalty, frequency_penalty, seed, stop, tools, tool_choice, response_format, n, logprobs, top_logprobs, logit_bias, user, parallel_tool_calls, prediction, store, metadata - Apply to all request types: non-streaming, streaming, and error cases **Streaming Content Capture** (chatCore.js & stream.js): - Add onStreamComplete callback mechanism to stream processors - Accumulate content from all formats: OpenAI, Claude, Gemini - Track content from delta.content, delta.reasoning_content, delta.text, delta.thinking, and Gemini content.parts - Save initial record with "[Streaming in progress...]" marker - Update record with actual content when stream completes - Include usage tokens when available from stream **Files Modified**: - open-sse/handlers/chatCore.js - extractRequestConfig() + streaming capture - open-sse/utils/stream.js - onStreamComplete callback + content accumulation **Benefits**: - View complete request configuration in Request Details (thinking mode, etc.) - See actual streaming response content instead of placeholder - Better debugging and observability for AI requests Refs: #request-details-enhancement * feat: separate thinking/reasoning content from response content Improve Request Details to display thinking process separately from final response: **Backend Changes**: - stream.js: Capture content and thinking separately in streaming mode - Add accumulatedThinking variable alongside accumulatedContent - Route delta.content to content, delta.reasoning_content to thinking - Support OpenAI (reasoning_content), Claude (thinking), Gemini (part.thought) - Update onStreamComplete callback to return { content, thinking } object - chatCore.js: Update response structure to include thinking field - Non-streaming: Extract thinking from reasoning_content field - Streaming: Receive { content, thinking } from stream callback - Error responses: Include thinking: null - Initial streaming save: Include thinking: null **Frontend Changes**: - RequestDetailsTab.js: Display thinking and content in separate sections - Add amber/yellow themed "Thinking Process" section with psychology icon - Show "Final Response" label when thinking is present - Use distinct visual styling for thinking (amber bg) vs content (gray bg) - Only show thinking section when thinking content exists **Benefits**: - Users can clearly see model's reasoning process vs final answer - Better debugging for models with thinking capabilities (Claude, o1, etc.) - Visual distinction makes it easy to identify thinking vs response Refs: #thinking-content-separation * fix: map Claude thinking to reasoning_content field Fix Claude thinking content to be properly captured as reasoning_content instead of regular content, enabling separate display in Request Details: **Changes**: - claude-to-openai.js: Use reasoning_content field for thinking blocks - thinking start: send { reasoning_content: "" } instead of { content: "```\n```" } - thinking delta: map to reasoning_content instead of content - thinking stop: send { reasoning_content: "" } instead of { content: "```\n```" } **Why This Matters**: - Previously Claude thinking was sent as `content` field, mixed with actual response - Now thinking uses `reasoning_content` field, matching OpenAI's o1 format - stream.js can now properly route thinking to accumulatedThinking variable - Request Details UI will show Claude thinking in separate "Thinking Process" section **Supported Thinking Formats**: - OpenAI: delta.reasoning_content → thinking - Claude: delta.thinking → reasoning_content (now fixed) - Gemini: part.thought === true → thinking Refs: #claude-thinking-fix * feat(observability): capture and display full 4-layer request chain Capture complete request/response chain in AI Request Details: - Add providerRequest field (translated request sent to provider) - Add providerResponse field (raw provider response, streaming indicator) - Update chatCore.js at all 5 saveRequestDetail() call sites - Reorganize UI into 4 collapsible sections with Material icons - Preserve backward compatibility for old records - Add distinct styling for streaming indicator * fix(observability): resolve React duplicate key warning in request details table - Use composite key (detail.id + index) to ensure unique keys - Prevents React warnings when database contains duplicate IDs from old ID generation * fix(observability): display actual content in streaming request details Change providerResponse field for streaming requests from placeholder "[Streaming - raw response not captured]" to actual final content. This improves debugging experience by showing the real AI response in the "Provider Response (Raw)" section instead of a confusing placeholder message. Files changed: - open-sse/handlers/chatCore.js: Save contentObj.content to providerResponse - src/app/.../RequestDetailsTab.js: Remove special handling for placeholder * refactor(observability): migrate request details to SQLite for improved concurrency - Replace LowDB JSON storage with better-sqlite3 - Enable WAL mode for true concurrent read/write support - Add 5 indexes to accelerate queries (timestamp, provider, model, connection_id, status) - Perform pagination at the database level to reduce memory footprint - Maintain 1000 record limit with automatic cleanup of old data - Ensure API compatibility via re-exports, requiring no caller changes Performance improvements: - Concurrent Writes: Lock-free WAL mode prevents data contention - Query Efficiency: Index-based searches replace full dataset loading - Data Integrity: Atomic operations prevent file corruption * fix(observability): resolve pagination statistics display issues - Fix issue where totalItems=0 showed 'Showing 1 to 0 of 0 results' - Hide pagination controls when totalItems=0 or totalPages<=1 - Standardize API response fields: pagination.total -> pagination.totalItems Before: Incorrect stats shown for empty data, and pager visible even for single-page results After: Stats hidden for empty data, pager hidden when navigation is unnecessary * feat(observability): display friendly provider names in request details - Add /api/usage/providers endpoint to dynamically fetch provider list with names - Replace hardcoded provider options with dynamic loading from database - Display friendly provider names instead of IDs in both table and detail drawer - Support custom provider nodes (e.g., OpenAI-compatible) with user-defined names - Add provider name caching to optimize performance * fix(observability): use INSERT OR REPLACE for request details to handle streaming updates * fix(observability): resolve zero-token display issue by ensuring streaming usage capture and fixing key mismatch * fix(observability): separate TTFT and total latency calculation for streaming requests * feat(observability): implement SQLite write queue and JSON size limits - Added in-memory buffer and batch writing for SQLite to prevent lock contention - Implemented with configurable 1MB limit to prevent DB bloat - Added dashboard UI for observability performance and data management settings - Integrated graceful shutdown handlers to prevent data loss * fix(observability): resolve ReferenceError by declaring dbInstance
2026-02-08 22:30:42 -05:00
{/* Observability Settings */}
<Card>
<div className="flex items-center gap-3 mb-4">
<div className="p-2 rounded-lg bg-orange-500/10 text-orange-500">
<span className="material-symbols-outlined text-[20px]">monitoring</span>
</div>
<h3 className="text-lg font-semibold">Observability</h3>
</div>
<div className="flex items-center justify-between">
<div>
<p className="font-medium">Enable Observability</p>
<p className="text-sm text-text-muted">
Record request details for inspection in the logs view
</p>
</div>
<Toggle
checked={observabilityEnabled}
onChange={updateObservabilityEnabled}
disabled={loading}
/>
Feature/ai observability dashboard (#79) * feat: add AI request details feature with latency tracking Add comprehensive request history and debugging capability to the Usage dashboard: **Storage Layer** (usageDb.js): - Add saveRequestDetail() for storing full request/response details - Implement FIFO queue with 1000-record limit in request-details.json - Auto-sanitize sensitive headers (authorization, api-key, cookie, token) - Add getRequestDetails() with pagination and filtering support - Add getRequestDetailById() for single record lookup **Pipeline Integration** (chatCore.js): - Track request start time and calculate total latency - Record TTFT (Time To First Token) and total latency for all requests - Capture full request details (messages, model, parameters) - Save response content for non-streaming, mark streaming responses - Handle error cases with detailed error information - Async non-blocking saves to avoid impacting request performance **API Layer** (/api/usage/request-details): - GET endpoint with pagination (page, pageSize: 1-100) - Filter by provider, model, connectionId, status, date range - Returns { details: [...], pagination: {...} } format **UI Components**: - Drawer.js: Right slide-out panel with backdrop blur and ESC close - Pagination.js: Full pagination with page size selector (10/20/50) - RequestDetailsTab.js: Complete table view with filters and detail drawer **Dashboard Integration**: - Add "Details" tab to Usage page (4th tab after Overview/Logger/Limits) - Table columns: Timestamp, Model, Provider, Input Tokens, Output Tokens, Latency (TTFT/Total), Action - Provider filter dropdown (9 providers supported) - Date range filters (start/end datetime) - Click "Detail" button to view full request/response JSON in slide-out drawer **Features**: - Real-time latency monitoring (TTFT & Total) - Complete request/response inspection for debugging - Filterable and searchable request history - Responsive design with mobile-friendly filters - Data security with automatic header sanitization - Performance: async saves don't block request pipeline **Files Created/Modified**: - src/lib/usageDb.js (modified) - open-sse/handlers/chatCore.js (modified) - src/app/api/usage/request-details/route.js (new) - src/shared/components/Drawer.js (new) - src/shared/components/Pagination.js (new) - src/app/(dashboard)/dashboard/usage/components/RequestDetailsTab.js (new) - src/app/(dashboard)/dashboard/usage/page.js (modified) Closes: AI Observability Dashboard feature * feat: enhance request details with full config and streaming content capture Improve Request Details feature to capture comprehensive request parameters and actual streaming response content: **Request Configuration Enhancement** (chatCore.js): - Add extractRequestConfig() helper function to capture all request parameters - Include temperature controls: temperature, top_p, top_k - Include token limits: max_tokens, max_completion_tokens - Include thinking/reasoning modes: thinking, reasoning, enable_thinking - Include OpenAI parameters: presence_penalty, frequency_penalty, seed, stop, tools, tool_choice, response_format, n, logprobs, top_logprobs, logit_bias, user, parallel_tool_calls, prediction, store, metadata - Apply to all request types: non-streaming, streaming, and error cases **Streaming Content Capture** (chatCore.js & stream.js): - Add onStreamComplete callback mechanism to stream processors - Accumulate content from all formats: OpenAI, Claude, Gemini - Track content from delta.content, delta.reasoning_content, delta.text, delta.thinking, and Gemini content.parts - Save initial record with "[Streaming in progress...]" marker - Update record with actual content when stream completes - Include usage tokens when available from stream **Files Modified**: - open-sse/handlers/chatCore.js - extractRequestConfig() + streaming capture - open-sse/utils/stream.js - onStreamComplete callback + content accumulation **Benefits**: - View complete request configuration in Request Details (thinking mode, etc.) - See actual streaming response content instead of placeholder - Better debugging and observability for AI requests Refs: #request-details-enhancement * feat: separate thinking/reasoning content from response content Improve Request Details to display thinking process separately from final response: **Backend Changes**: - stream.js: Capture content and thinking separately in streaming mode - Add accumulatedThinking variable alongside accumulatedContent - Route delta.content to content, delta.reasoning_content to thinking - Support OpenAI (reasoning_content), Claude (thinking), Gemini (part.thought) - Update onStreamComplete callback to return { content, thinking } object - chatCore.js: Update response structure to include thinking field - Non-streaming: Extract thinking from reasoning_content field - Streaming: Receive { content, thinking } from stream callback - Error responses: Include thinking: null - Initial streaming save: Include thinking: null **Frontend Changes**: - RequestDetailsTab.js: Display thinking and content in separate sections - Add amber/yellow themed "Thinking Process" section with psychology icon - Show "Final Response" label when thinking is present - Use distinct visual styling for thinking (amber bg) vs content (gray bg) - Only show thinking section when thinking content exists **Benefits**: - Users can clearly see model's reasoning process vs final answer - Better debugging for models with thinking capabilities (Claude, o1, etc.) - Visual distinction makes it easy to identify thinking vs response Refs: #thinking-content-separation * fix: map Claude thinking to reasoning_content field Fix Claude thinking content to be properly captured as reasoning_content instead of regular content, enabling separate display in Request Details: **Changes**: - claude-to-openai.js: Use reasoning_content field for thinking blocks - thinking start: send { reasoning_content: "" } instead of { content: "```\n```" } - thinking delta: map to reasoning_content instead of content - thinking stop: send { reasoning_content: "" } instead of { content: "```\n```" } **Why This Matters**: - Previously Claude thinking was sent as `content` field, mixed with actual response - Now thinking uses `reasoning_content` field, matching OpenAI's o1 format - stream.js can now properly route thinking to accumulatedThinking variable - Request Details UI will show Claude thinking in separate "Thinking Process" section **Supported Thinking Formats**: - OpenAI: delta.reasoning_content → thinking - Claude: delta.thinking → reasoning_content (now fixed) - Gemini: part.thought === true → thinking Refs: #claude-thinking-fix * feat(observability): capture and display full 4-layer request chain Capture complete request/response chain in AI Request Details: - Add providerRequest field (translated request sent to provider) - Add providerResponse field (raw provider response, streaming indicator) - Update chatCore.js at all 5 saveRequestDetail() call sites - Reorganize UI into 4 collapsible sections with Material icons - Preserve backward compatibility for old records - Add distinct styling for streaming indicator * fix(observability): resolve React duplicate key warning in request details table - Use composite key (detail.id + index) to ensure unique keys - Prevents React warnings when database contains duplicate IDs from old ID generation * fix(observability): display actual content in streaming request details Change providerResponse field for streaming requests from placeholder "[Streaming - raw response not captured]" to actual final content. This improves debugging experience by showing the real AI response in the "Provider Response (Raw)" section instead of a confusing placeholder message. Files changed: - open-sse/handlers/chatCore.js: Save contentObj.content to providerResponse - src/app/.../RequestDetailsTab.js: Remove special handling for placeholder * refactor(observability): migrate request details to SQLite for improved concurrency - Replace LowDB JSON storage with better-sqlite3 - Enable WAL mode for true concurrent read/write support - Add 5 indexes to accelerate queries (timestamp, provider, model, connection_id, status) - Perform pagination at the database level to reduce memory footprint - Maintain 1000 record limit with automatic cleanup of old data - Ensure API compatibility via re-exports, requiring no caller changes Performance improvements: - Concurrent Writes: Lock-free WAL mode prevents data contention - Query Efficiency: Index-based searches replace full dataset loading - Data Integrity: Atomic operations prevent file corruption * fix(observability): resolve pagination statistics display issues - Fix issue where totalItems=0 showed 'Showing 1 to 0 of 0 results' - Hide pagination controls when totalItems=0 or totalPages<=1 - Standardize API response fields: pagination.total -> pagination.totalItems Before: Incorrect stats shown for empty data, and pager visible even for single-page results After: Stats hidden for empty data, pager hidden when navigation is unnecessary * feat(observability): display friendly provider names in request details - Add /api/usage/providers endpoint to dynamically fetch provider list with names - Replace hardcoded provider options with dynamic loading from database - Display friendly provider names instead of IDs in both table and detail drawer - Support custom provider nodes (e.g., OpenAI-compatible) with user-defined names - Add provider name caching to optimize performance * fix(observability): use INSERT OR REPLACE for request details to handle streaming updates * fix(observability): resolve zero-token display issue by ensuring streaming usage capture and fixing key mismatch * fix(observability): separate TTFT and total latency calculation for streaming requests * feat(observability): implement SQLite write queue and JSON size limits - Added in-memory buffer and batch writing for SQLite to prevent lock contention - Implemented with configurable 1MB limit to prevent DB bloat - Added dashboard UI for observability performance and data management settings - Integrated graceful shutdown handlers to prevent data loss * fix(observability): resolve ReferenceError by declaring dbInstance
2026-02-08 22:30:42 -05:00
</div>
</Card>
2026-01-04 21:58:59 -05:00
{/* App Info */}
<div className="text-center text-sm text-text-muted py-4">
<p>{APP_CONFIG.name} v{APP_CONFIG.version}</p>
<p className="mt-1">Local Mode - All data stored on your machine</p>
</div>
</div>
</div>
);
}