luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(qoder): report usage to all clients and stop inlining large attachments

Browse Source 
- Coalesce Qoder's empty finish-in-delta frame with the later choices:[] usage
  frame so OpenAI and Claude clients receive prompt_tokens, completion_tokens
  and cache-hit tokens (the dashboard already saw them)
- Upload inlined images through /api/v2/image/upload like qodercli, and stub
  oversized non-image files instead of stuffing 30MB+ data URIs into
  agent_chat_generation
- Emit response.completed -> response.usage for chat-native upstreams so
  /v1/responses clients (Codex CLI, sub2api) no longer log 0/0/0
- Keep Claude message_delta.usage working when usage arrives without choices[0]
- Escalate to the smallest advertised Qoder context tier (200K/400K/1M) when
  the estimated prompt no longer fits max_input_tokens
- Pass apiKey for PAT connections and list hidden enable:false catalog keys
  from /v1/models
This commit is contained in:
LLL
2026-09-10 22:06:49 +07:00
committed by decolua
parent 832a34659e
commit 1f10f9e5c4
19 changed files with 1615 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
open-sse/handlers/chatCore/nonStreamingHandler.js
View File

@@ -10,6 +10,7 @@ import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, sav
import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
import { decloakToolNames } from "../../utils/claudeCloaking.js";
import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
import { toResponsesUsage } from "../../translator/concerns/usage.js";
function parseToolArguments(value) {
if (!value) return {};
@@ -130,11 +131,8 @@ function openAICompletionToResponses(responseBody, customToolNames = null) {
background: false,
error: null,
output,
usage: {
input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
output_tokens: usage.completion_tokens || usage.output_tokens || 0,
total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
},
// Keep cached/reasoning details (input_tokens_details) — proxies bill cache hits from them
usage: toResponsesUsage(usage) || { input_tokens: 0, output_tokens: 0, total_tokens: 0 },
};
}

8
open-sse/handlers/chatCore/sseToJsonHandler.js
View File

@@ -5,6 +5,7 @@ import { FORMATS } from "../../translator/formats.js";
import { PROVIDERS } from "../../config/providers.js";
import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
import { toResponsesUsage } from "../../translator/concerns/usage.js";
// Responses-API providers (e.g. codex) may emit SSE without content-type + use Responses output shape
const isResponsesProvider = (p) => PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
@@ -97,11 +98,8 @@ function chatCompletionToResponses(responseBody, customToolNames = null) {
background: false,
error: null,
output,
usage: {
input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
output_tokens: usage.completion_tokens || usage.output_tokens || 0,
total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
},
// Keep cached/reasoning details (input_tokens_details) — proxies bill cache hits from them
usage: toResponsesUsage(usage) || { input_tokens: 0, output_tokens: 0, total_tokens: 0 },
};
}