1c8ff7b569
增加模型；增加上下文窗口信息
2026-07-08 00:06:07 +08:00
kim
ceedbe8a71
Merge branch 'main' of ssh://gitea.228778.xyz:23022/kim/litellm-config
...
merge
2026-07-04 15:26:16 +08:00
kim
f5f9171d9b
添加glm5.2
2026-07-04 15:24:47 +08:00
58db397bbf
更新到最新的镜像
2026-06-15 17:13:33 +08:00
kim
28c76a1052
注释豆包2.0pro和lite模型，因为没额度了
2026-06-15 14:03:00 +08:00
kim
b1973a1def
添加doubao-seed-2-0-code-nothink
2026-06-11 14:58:02 +08:00
kim
27324f459c
fix: add doubao-seed-2-0-code alias to monitored models
2026-06-11 14:52:02 +08:00
kim
ed14ee26f3
添加doubao-seed-2-0-code-nothink
2026-06-11 14:45:58 +08:00
kim
e291a51c56
添加doubao-seed-2-0-code
2026-06-11 14:35:19 +08:00
kim
671ef1087f
fix: resolve falsy effective_limit bug preventing model block on negative quota
2026-06-11 14:09:42 +08:00
kim
28c81c4816
fix: resolve volcengine package quota parsing and status filtering
2026-06-11 13:27:06 +08:00
fff6397c42
未知修改
2026-06-11 13:16:26 +08:00
kim
255e197150
docs: add drop_params note to config
2026-04-01 14:12:48 +08:00
kim
f36c560bb0
fix: clarify effective limit debug output
2026-04-01 14:10:59 +08:00
kim
730e444a76
增加 drop_params: true 参数
2026-04-01 13:49:36 +08:00
kim
2f1c2642e5
fix: streamline monitored model maintenance
2026-04-01 13:29:10 +08:00
63658dadd2
修改config，添加模型；指定litellm主版本规避风险
2026-04-01 12:12:34 +08:00
kim
1e27201675
增加内存限制2g
2026-03-22 18:19:20 +08:00
kim
d34c7c11c0
删除过时的模型
2026-03-22 18:17:37 +08:00
kim
b3d798ef15
删除失效的gemini
2026-03-19 12:19:45 +08:00
kim
96691af3eb
修改数据库密码
2026-03-18 17:34:35 +08:00
kim
ede69fe8b4
测试切换数据库到专用lxc容器
2026-03-18 17:27:54 +08:00
kim
8d62816f72
config取消储存详细提示词到数据库
2026-03-18 15:17:52 +08:00
kim
afbd39db4d
删除doubao-code模型
2026-03-04 14:51:01 +08:00
kim
84d561e81a
添加doubao-seed-code用于排查token异常消耗事件
2026-02-07 11:25:46 +08:00
kim
995e0b6ecb
修改gemini-2.5-flash为默认回退
2026-02-06 09:43:07 +08:00
kim
a620473fff
增加时区环境变量
2026-02-04 10:05:33 +08:00
kim
cb2cf90966
config增加多级fallback
2026-02-03 11:52:28 +08:00
kim
3ba7e03cce
1.添加env的追踪2.修复config中的gemini模型配置
2026-02-03 11:03:36 +08:00
kim
55a09a62a1
添加反重力 gemini2.5flash
2026-02-03 00:05:32 +08:00
kim
e47f335bbf
添加反重力 gemini2.5flash
2026-02-03 00:00:25 +08:00
kim
afc5a77b53
添加反重力 gemini2.5pro作为fallback
2026-02-02 23:08:26 +08:00
kim
f48c72e93b
1.修改部分火山模型前缀为volcengine，2.火山模型添加额外请求头，避免复用导致长连接僵化
2026-02-02 15:07:00 +08:00
kim
bdd51e8f9c
feat: implement startup audit to block over-limit models on restart
...
- Add startup_audit() to check Redis usage against limits at startup
- Call startup_audit() in active_monitor_loop
- Add AGENTS.md for agent guidelines
2026-02-02 13:39:34 +08:00
kim
6430c2e828
修改config
2026-02-01 12:41:36 +08:00
kim
90c6b1c444
修改config
2026-02-01 12:34:29 +08:00
kim
c596b7e11b
修改config
2026-01-31 17:18:01 +08:00
kim
ef7b53d8aa
config中的code添加超时参数
2026-01-30 17:18:02 +08:00
kim
03df1d553e
fix: strip volcengine prefix in limit sync to match config
2026-01-30 12:35:19 +08:00
kim
e1c5d3ae72
修改上游标识 volcengine
2026-01-30 10:53:18 +08:00
kim
bc9f4e4680
Add README.md for volc_limit_sync
2026-01-30 09:01:03 +08:00
kim
f16af28dfe
feat: 优化火山引擎配额同步策略
...
- 添加硬限制: doubao-seed-code 480w/日, 其他模型 180w/日
- 强制北京时间(UTC+8)计算日期，确保 Docker 容器时区无关
- 移除'忽略小跌'逻辑，Pool 下跌时立即接受（更保守的风控）
- 优化轮询间隔适配小时级 API 延迟（减少无效请求）
2026-01-30 00:39:06 +08:00
kim
dd8cbe5f63
revert: remove hardcoded daily limits, restoring dynamic calculation only
2026-01-30 00:05:40 +08:00
kim
d5b8829265
feat: add specific hard limits and log format
2026-01-29 23:54:32 +08:00
kim
cd35a193b6
feat: finalize smart pool tracking with hysteresis (handle jumps, drops, and expiry)
2026-01-29 23:17:39 +08:00
kim
2d849dc62d
fix: upgrade quota logic to track Total Pool (Usage + Rem) to prevent mid-day blocking
2026-01-29 22:30:42 +08:00
kim
73fe82de3b
feat: enhance volcengine quota sync with hard limits and smart buffering
2026-01-29 22:21:29 +08:00
kim
0988b1fc1d
optimize: increase burst traffic threshold to 300,000 tokens to handle long-context models
2026-01-29 20:54:18 +08:00
kim
be6d2ed1bd
chore: update config.yaml with new model mappings
2026-01-29 20:28:48 +08:00
kim
e6110cd9c1
optimize: adjust restore window to 07:00-13:00 Beijing time and optimize sleep logic for dead models
2026-01-29 20:27:32 +08:00
root
kim