bugfix

llmage/asyncinference.py

@@ -112,7 +112,7 @@ async def async_uapi_request(request, llm,
 		llmusage.accounting_status = 'created'
 		b = json.dumps(d, ensure_ascii=False)
 		yield b
-		await write_llmusage(llmusage)
+		# await write_llmusage(llmusage)
 		# if llm.callbackurl:
 		#	return
 		if d.status == 'FAILED':
@@ -128,7 +128,29 @@ async def async_uapi_request(request, llm,
 		s = ''.join(s.split('\n'))
 		exception(s)
 		yield f'{s}\n'
+		llmusage = DictObject()
+		llmusage.id = luid
+		llmusage.llmid = llm.id
+		llmusage.use_date = curDateString()
+		llmusage.use_time = timestampstr()
+		llmusage.userid = callerid
+		ioinfo = {
+			"input": params_kw,
+			'output': [ed]
+		}
+		webpath = await write_llmio(llmusage.id, ioinfo)
+		llmusage.ioinfo = webpath
+		llmusage.taskid = d.taskid
+		llmusage.transno = params_kw.transno
+		llmusage.responsed_seconds = responsed_seconds
+		llmusage.finish_seconds = finish_seconds
+		llmusage.status = 'FAILED'
+		llmusage.userorgid = callerorgid
+		llmusage.tenantid = params_kw.get('tenantid', params_kw.get('tentantid'))
+		llmusage.ownerid = llm.ownerid
 		return
+	finally:
+		await write_llmusage(llmusage)
 
 async def modify_llmusage(ns):
 	env = ServerEnv()

llmage/llmclient.py

@@ -14,6 +14,7 @@ from ahserver.filestorage import FileStorage
 from .asyncinference import async_uapi_request
 from .syncinference import sync_uapi_request
 from .accounting import llm_accounting, llm_charging
+from .balance import refund_balance
 from .utils import *
 
 async def uapi_request(request, llm, callerid, callerorgid, params_kw=None):
@@ -91,28 +92,14 @@ async def uapi_request(request, llm, callerid, callerorgid, params_kw=None):
 		llmusage.tenantid = params_kw.get('tenantid', params_kw.get('tentantid'))
 		llmusage.ownerid = llm.ownerid
 		llmusage.accounting_status = 'created'
-		await write_llmusage(llmusage)
+		# await write_llmusage(llmusage)
 	except Exception as e:
-		# Retry on duplicate key: append *1, *2, ...
-		retry = 0
-		while 'Duplicate entry' in str(e) and retry < 3:
-			retry += 1
-			llmusage.id = f'{luid}*{retry}'
-			try:
-				await write_llmusage(llmusage)
-				exception(f'write_llmusage retry {retry} succeeded with id={llmusage.id}')
-				e = None
-				break
-			except Exception as e2:
-				e = e2
 		# Refund balance reservation on failure
 		try:
-			from .balance import refund_balance
+			if luid:
-			from ahserver.serverenv import ServerEnv
+				await refund_balance(ServerEnv(), luid)
-			reserve_luid = params_kw.get('_luid') if params_kw else None
-			if reserve_luid:
-				await refund_balance(ServerEnv(), reserve_luid)
 		except:
+			debug(f'refund_balance(ServerEnv(), {luid=}) errir')
 			pass
 		exception(f'{e=},{format_exc()}')
 		estr = erase_apikey(e)
@@ -121,15 +108,27 @@ async def uapi_request(request, llm, callerid, callerorgid, params_kw=None):
 		s = ''.join(s.split('\\n'))
 		outlines.append(ed)
 		yield f'{s}\\n'
-		return
+		## except happand at call llm server
+		llmusage = DictObject()
+		llmusage.id = luid
+		llmusage.llmid = llm.id
+		llmusage.use_date = curDateString()
+		llmusage.use_time = timestampstr()
+		llmusage.userid = callerid
+		ioinfo = {
+			"input": params_kw,
+			'output': ed
+		}
+		webpath = await write_llmio(llmusage.id, ioinfo)
+		llmusage.ioinfo = webpath
+		llmusage.transno = params_kw.transno
+		llmusage.status = 'FAILED'
+		llmusage.userorgid = callerorgid
+		llmusage.tenantid = params_kw.get('tenantid', params_kw.get('tentantid'))
+		llmusage.ownerid = llm.ownerid
 	finally:
 		# GeneratorExit / client disconnect — flush partial usage
-		if llmusage and llmusage.get('id') == luid:
+		await write_llmusage(llmusage)
-			try:
-				llmusage.status = llmusage.status or 'UNKNOWN'
-				await write_llmusage(llmusage)
-			except:
-				pass
 
 async def inference_generator(request, *args, params_kw=None, **kw):
 	env = request._run_ns.copy()

llmage/syncinference.py

@@ -61,33 +61,13 @@ async def sync_uapi_request(request, llm, callerid, callerorgid, params_kw=None)
 		llmusage.finish_seconds = finish_seconds
 		llmusage.status = 'SUCCEEDED'
 		llmusage.amount = 0.00
-		""" 联机不记账
-		if llm.ppid:
-			try:
-				charging = await llm_charging(llm.ppid, llmusage)
-				if charging:
-					llmusage.amount = charging.amount
-					llmusage.cost = charging.cost
-				else:
-					llmusage.amount = llmusage.cost = 0.0
-			except Exception as e:
-				e = Exception(f'{llm.pid} charging error{e}')
-				exception(f'{e}')
-		else:
-			llmusage.amount = 0
-			llmusage.cost = 0
-		"""
 		llmusage.userorgid = callerorgid
 		llmusage.tenantid = params_kw.get('tenantid', params_kw.get('tentantid'))
 		llmusage.ownerid = llm.ownerid
 		llmusage.accounting_status = 'created'
 		b = json.dumps(d, ensure_ascii=False)
 		yield b
-		await write_llmusage(llmusage)
+		# await write_llmusage(llmusage)
-		"""联机不记账
-		if llmusage.amount > 0.0001:
-			await llm_accounting(llmusage)
-		"""
 	except Exception as e:
 		exception(f'{e=},{format_exc()}, {b=}')
 		estr = erase_apikey(e)
@@ -96,7 +76,29 @@ async def sync_uapi_request(request, llm, callerid, callerorgid, params_kw=None)
 		s = ''.join(s.split('\n'))
 		outlines.append(ed)
 		yield f'{s}\n'
-
+		llmusage = DictObject()
+		llmusage.id = luid
+		llmusage.llmid = llm.id
+		llmusage.use_date = curDateString()
+		llmusage.use_time = timestampstr()
+		llmusage.userid = callerid
+		llmusage.usages = None
+		ioinfo = {
+			"input": params_kw,
+			'output': [ed]
+		}
+		webpath = await write_llmio(llmusage.id, ioinfo)
+		llmusage.ioinfo = webpath
+		llmusage.transno = params_kw.transno
+		llmusage.responsed_seconds = responsed_seconds
+		llmusage.finish_seconds = finish_seconds
+		llmusage.status = 'FAILED'
+		llmusage.amount = 0.00
+		llmusage.userorgid = callerorgid
+		llmusage.tenantid = params_kw.get('tenantid', params_kw.get('tentantid'))
+		llmusage.ownerid = llm.ownerid
+	finally:
+		await write_llmusage(llmusage)
 
 async def sync_uapi_request_product(llm, api_userid, user_id, user_org_id, params_kw, luid):
 	"""Product interface version: no HTTP request dependency. Returns dict."""

llmage/utils.py

@@ -556,6 +556,14 @@ async def get_llm(llmid, catelogid=None):
 async def write_llmusage(llmusage):
 	env = ServerEnv()
 	async with get_sor_context(env, 'llmage') as sor:
+		n = 0
+		part0 = llmusage.id
+		while True:
+			recs = await sor.R('llmusage', {'id': llmusage.id})
+			if len(recs) == 0:
+				break
+			n = n + 1
+			llmusage.id = f'{part0}*{n}'
 		await sor.C('llmusage', llmusage)
 
 async def llm_query_price(llmid, config_data):