9router/open-sse/translator/response/claude-to-openai.js

207 lines
7.2 KiB
JavaScript
Raw Normal View History

import { register } from "../index.js";
import { FORMATS } from "../formats.js";
// Create OpenAI chunk helper
function createChunk(state, delta, finishReason = null) {
return {
id: `chatcmpl-${state.messageId}`,
object: "chat.completion.chunk",
created: Math.floor(Date.now() / 1000),
model: state.model,
choices: [{
index: 0,
delta,
finish_reason: finishReason
}]
};
}
// Convert Claude stream chunk to OpenAI format
2026-01-29 06:07:28 -05:00
export function claudeToOpenAIResponse(chunk, state) {
if (!chunk) return null;
const results = [];
const event = chunk.type;
switch (event) {
case "message_start": {
state.messageId = chunk.message?.id || `msg_${Date.now()}`;
state.model = chunk.message?.model;
state.toolCallIndex = 0;
results.push(createChunk(state, { role: "assistant" }));
break;
}
case "content_block_start": {
const block = chunk.content_block;
if (block?.type === "server_tool_use") {
// Built-in tool (web search) - Claude handles internally, skip
state.serverToolBlockIndex = chunk.index;
break;
}
if (block?.type === "text") {
state.textBlockStarted = true;
} else if (block?.type === "thinking") {
state.inThinkingBlock = true;
state.currentBlockIndex = chunk.index;
results.push(createChunk(state, { content: "<think>" }));
} else if (block?.type === "tool_use") {
const toolCallIndex = state.toolCallIndex++;
// Restore original tool name from mapping (Claude OAuth)
const toolName = state.toolNameMap?.get(block.name) || block.name;
const toolCall = {
index: toolCallIndex,
id: block.id,
type: "function",
function: {
name: toolName,
arguments: ""
}
};
state.toolCalls.set(chunk.index, toolCall);
results.push(createChunk(state, { tool_calls: [toolCall] }));
}
break;
}
case "content_block_delta": {
// Skip deltas for built-in server tool blocks (web search)
if (chunk.index === state.serverToolBlockIndex) break;
const delta = chunk.delta;
if (delta?.type === "text_delta" && delta.text) {
results.push(createChunk(state, { content: delta.text }));
} else if (delta?.type === "thinking_delta" && delta.thinking) {
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
results.push(createChunk(state, { reasoning_content: delta.thinking }));
} else if (delta?.type === "input_json_delta" && delta.partial_json) {
const toolCall = state.toolCalls.get(chunk.index);
if (toolCall) {
toolCall.function.arguments += delta.partial_json;
results.push(createChunk(state, {
tool_calls: [{
index: toolCall.index,
id: toolCall.id,
function: { arguments: delta.partial_json }
}]
}));
}
}
break;
}
case "content_block_stop": {
// Skip stop for built-in server tool blocks (web search)
if (chunk.index === state.serverToolBlockIndex) {
state.serverToolBlockIndex = -1;
break;
}
if (state.inThinkingBlock && chunk.index === state.currentBlockIndex) {
results.push(createChunk(state, { content: "</think>" }));
state.inThinkingBlock = false;
}
state.textBlockStarted = false;
state.thinkingBlockStarted = false;
break;
}
case "message_delta": {
// Extract usage from message_delta event (Claude native format)
// Normalize to OpenAI format (prompt_tokens/completion_tokens) for consistent logging
if (chunk.usage && typeof chunk.usage === "object") {
const inputTokens = typeof chunk.usage.input_tokens === "number" ? chunk.usage.input_tokens : 0;
const outputTokens = typeof chunk.usage.output_tokens === "number" ? chunk.usage.output_tokens : 0;
const cacheReadTokens = typeof chunk.usage.cache_read_input_tokens === "number" ? chunk.usage.cache_read_input_tokens : 0;
const cacheCreationTokens = typeof chunk.usage.cache_creation_input_tokens === "number" ? chunk.usage.cache_creation_input_tokens : 0;
// prompt_tokens = input_tokens + cache_read + cache_creation (all prompt-side tokens)
const promptTokens = inputTokens + cacheReadTokens + cacheCreationTokens;
state.usage = {
prompt_tokens: promptTokens,
completion_tokens: outputTokens,
total_tokens: promptTokens + outputTokens,
input_tokens: inputTokens,
output_tokens: outputTokens
};
if (cacheReadTokens > 0) state.usage.cache_read_input_tokens = cacheReadTokens;
if (cacheCreationTokens > 0) state.usage.cache_creation_input_tokens = cacheCreationTokens;
}
if (chunk.delta?.stop_reason) {
state.finishReason = convertStopReason(chunk.delta.stop_reason);
const finalChunk = {
id: `chatcmpl-${state.messageId}`,
object: "chat.completion.chunk",
created: Math.floor(Date.now() / 1000),
model: state.model,
choices: [{ index: 0, delta: {}, finish_reason: state.finishReason }]
};
if (state.usage) {
finalChunk.usage = {
prompt_tokens: state.usage.prompt_tokens,
completion_tokens: state.usage.completion_tokens,
total_tokens: state.usage.total_tokens
};
const cacheRead = state.usage.cache_read_input_tokens;
const cacheCreate = state.usage.cache_creation_input_tokens;
if (cacheRead > 0 || cacheCreate > 0) {
finalChunk.usage.prompt_tokens_details = {};
if (cacheRead > 0) finalChunk.usage.prompt_tokens_details.cached_tokens = cacheRead;
if (cacheCreate > 0) finalChunk.usage.prompt_tokens_details.cache_creation_tokens = cacheCreate;
}
}
results.push(finalChunk);
state.finishReasonSent = true;
}
break;
}
case "message_stop": {
if (!state.finishReasonSent) {
const finishReason = state.finishReason || (state.toolCalls?.size > 0 ? "tool_calls" : "stop");
const usageObj = (state.usage && typeof state.usage === 'object') ? {
usage: {
prompt_tokens: state.usage.input_tokens || 0,
completion_tokens: state.usage.output_tokens || 0,
total_tokens: (state.usage.input_tokens || 0) + (state.usage.output_tokens || 0)
}
} : {};
results.push({
id: `chatcmpl-${state.messageId}`,
object: "chat.completion.chunk",
created: Math.floor(Date.now() / 1000),
model: state.model,
choices: [{
index: 0,
delta: {},
finish_reason: finishReason
}],
...usageObj
});
state.finishReasonSent = true;
}
break;
}
}
return results.length > 0 ? results : null;
}
// Convert Claude stop_reason to OpenAI finish_reason
function convertStopReason(reason) {
switch (reason) {
case "end_turn": return "stop";
case "max_tokens": return "length";
case "tool_use": return "tool_calls";
case "stop_sequence": return "stop";
default: return "stop";
}
}
// Register
register(FORMATS.CLAUDE, FORMATS.OPENAI, null, claudeToOpenAIResponse);