feat(calllog): 详情不截断记录(捕获/清洗/入库三处上限全部放开)
- 请求体捕获 8000 → 128KiB(_CONTENT_MAX,可用 CALLLOG_BODY_MAX 调) - 回复文本改用新增的 _content():128KiB 且保留换行/制表(_logsafe 会把换行压成 ?) - 入库上限 CALLLOG_CONTENT_MAX 默认 8000 → 256KiB(实际等于不截断) - 详情新增 prompt_full(完整提取内容,保留换行),与原始 JSON 并列展示 - BODY_BY_RID 有界 128 条,防止宽上限下内存膨胀 - 版本 2.9.1 → 2.9.2
This commit is contained in:
1 parent
6b3607c35f
commit
8e23a5ed1b
4 files changed
+74
-19
No files matched your search
+30
-9
@@ -162,6 +162,10 @@ def _setup_logging() -> None:
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(name)s] %(levelname)s: %(message)s")
|
||||
log = logging.getLogger("api-gateway")
|
||||
|
||||
# 调用日志的内容上限(2026-10-23):提示词/回复按此长度截断,默认 128KiB(≈32k tokens)。
|
||||
# 详情页要求「不截断」,实际上 128KiB 已覆盖绝大多数对话;要真的无限就把这个值调大。
|
||||
_CONTENT_MAX = int(__import__("os").environ.get("CALLLOG_BODY_MAX") or 131072)
|
||||
|
||||
|
||||
def _config_mtime() -> float:
|
||||
try:
|
||||
@@ -351,7 +355,7 @@ _docs_on = config.server.docs_enabled # 安全默认关(report: /docs、/ope
|
||||
# 2026-09-30: 2.6.1 → 2.7.0(按老板要求整个删除「火山方舟 Coding Plan」供应商:配置/模型/代码/文档/前端下拉/环境变量全清)。
|
||||
# 2026-09-30: 2.7.0 → 2.7.1(界面提示白话化:熔断器→供应商自动保护、引擎→运行环境、slug→标识;删 120 个未引用死键)。
|
||||
# ★ 版本号纪律:每次改动都要往上加,小改动加小版本号、大改动加大版本号(README 有专章)。
|
||||
VERSION = "2.9.1"
|
||||
VERSION = "2.9.2"
|
||||
|
||||
app = FastAPI(
|
||||
title="API Gateway",
|
||||
@@ -498,8 +502,9 @@ async def in_flight_tracker(request: Request, call_next):
|
||||
if rid:
|
||||
try:
|
||||
raw = await request.body()
|
||||
BODY_BY_RID[rid] = raw[:8000].decode("utf-8", "replace")
|
||||
if len(BODY_BY_RID) > 2 * _BODY_MAX:
|
||||
# 调用日志要看完整提示词:放宽到 128KiB(≈32k tokens),并只保留最近 N 条
|
||||
BODY_BY_RID[rid] = raw[:_CONTENT_MAX].decode("utf-8", "replace")
|
||||
if len(BODY_BY_RID) > 128:
|
||||
BODY_BY_RID.clear()
|
||||
except Exception:
|
||||
BODY_BY_RID.pop(rid, None)
|
||||
@@ -998,6 +1003,22 @@ def _identity_from_credentials(key: str) -> tuple[str, str, str] | None:
|
||||
return ident[0], ident[1], "apikey"
|
||||
|
||||
|
||||
def _content(v, maxlen: int = _CONTENT_MAX) -> str:
|
||||
"""调用日志用的「内容」清洗:**保留换行与制表**(详情页要看原文排版)。
|
||||
|
||||
与 `_logsafe` 的区别:后者是给**单行文本日志**用的(会把 \n 压成 `?`,
|
||||
防 `%0a` 伪造日志行)。调用日志要展示提示词/回复原文,压掉换行就没法看了,
|
||||
所以这里只去 NUL 等不可见控制字符,换行/制表原样保留。
|
||||
"""
|
||||
if v is None:
|
||||
return ""
|
||||
t = v if isinstance(v, str) else str(v)
|
||||
t = "".join(ch for ch in t if ch in "\n\t\r" or ch.isprintable())
|
||||
if maxlen and len(t) > maxlen:
|
||||
return t[:maxlen] + f"\n…(已截断,共 {len(t)} 字)"
|
||||
return t
|
||||
|
||||
|
||||
def _upstream_detail(text: str) -> str:
|
||||
"""从上游 4xx/5xx 响应体里抽出原文(可能是 {message} 或 {error:{message}})。"""
|
||||
try:
|
||||
@@ -1644,8 +1665,8 @@ async def _passthrough(request: Request, protocol: str):
|
||||
_access.add({"method": "POST", "kind": "chat", "path": f"/v1/{protocol}", "rid": rid,
|
||||
"model": model_in, "served": model_in, "provider": pkey,
|
||||
"caller": caller, "ok": ok, "stream": False,
|
||||
"response": _logsafe(_resp_text(data) if ok else _upstream_detail(
|
||||
json.dumps(data, ensure_ascii=False) if isinstance(data, dict) else str(data)), 8000)})
|
||||
"response": _content(_resp_text(data) if ok else _upstream_detail(
|
||||
json.dumps(data, ensure_ascii=False) if isinstance(data, dict) else str(data)))})
|
||||
|
||||
if not ok:
|
||||
# 直传口径:上游的错误体**原样**回给客户端(错误文案也不翻译),只加一个
|
||||
@@ -1690,7 +1711,7 @@ async def _passthrough_stream(request, rid, caller, protocol, adapter, cb,
|
||||
_access.add({"method": "POST", "kind": "chat", "path": f"/v1/{protocol}", "rid": rid,
|
||||
"model": model_in, "served": model_in, "provider": pkey, "caller": caller,
|
||||
"ok": False, "stream": True,
|
||||
"response": _logsafe(_upstream_detail(raw.decode("utf-8", "replace")), 8000)})
|
||||
"response": _content(_upstream_detail(raw.decode("utf-8", "replace")))})
|
||||
return Response(content=raw, status_code=resp.status_code, media_type=ctype, headers=headers)
|
||||
|
||||
scanner = _UsageScanner(protocol)
|
||||
@@ -2051,7 +2072,7 @@ async def _chat_once(cfg, rid, caller, request, req, model_id, messages, tools):
|
||||
_access.add({"method": "POST", "kind": "chat", "path": "/v1/chat/completions", "rid": rid,
|
||||
"model": req.model, "served": model_id, "provider": pkey,
|
||||
"caller": caller, "ok": True, "stream": False,
|
||||
"response": _logsafe(_resp_text(result), 8000)})
|
||||
"response": _content(_resp_text(result))})
|
||||
resp = {
|
||||
"id": result.get("id", "") or f"chatcmpl-{rid}", "object": "chat.completion",
|
||||
"created": int(time.time()), "model": req.model,
|
||||
@@ -2179,7 +2200,7 @@ def _stream_response(request, req, model_id, messages, tools):
|
||||
_access.add({"method": "POST", "kind": "chat", "path": "/v1/chat/completions", "rid": rid,
|
||||
"model": req.model, "served": model_id, "provider": pkey,
|
||||
"caller": caller, "ok": True, "stream": True,
|
||||
"response": _logsafe(_stream_log_text(resp_parts, reason_parts), 8000)})
|
||||
"response": _content(_stream_log_text(resp_parts, reason_parts))})
|
||||
# 功能 8: 流式末尾发一个 usage 块(累计自上游 chunks 的 usage,若有)
|
||||
if stream_usage:
|
||||
uf = {'id': f'chatcmpl-{rid}', 'object': 'chat.completion.chunk', 'created': int(time.time()),
|
||||
@@ -2197,7 +2218,7 @@ def _stream_response(request, req, model_id, messages, tools):
|
||||
_access.add({"method": "POST", "kind": "chat", "path": "/v1/chat/completions", "rid": rid,
|
||||
"model": req.model, "served": model_id, "provider": pkey,
|
||||
"caller": caller, "ok": False, "stream": True, "error": str(e)[:200],
|
||||
"response": _logsafe(_stream_log_text(resp_parts, reason_parts), 8000)})
|
||||
"response": _content(_stream_log_text(resp_parts, reason_parts))})
|
||||
# 第六轮: 已向客户端输出过 content 时本来就无法回退(第二十七轮起更没有下一个
|
||||
# 模型可退),统一发错误帧 + [DONE] 收尾,避免破坏已输出的 SSE 流。
|
||||
yield f"data: {json.dumps({'error': str(e), 'served_model': model_id}, ensure_ascii=False)}\n\n"
|
||||
|
||||
Reference in new issue
Block a user