feat: 知识库文件夹/模板、技能压缩设置与摘要窗口调优
- 知识库新增文件夹与模板支持(模型/仓储/服务/迁移),前端知识管理组件 - 岗位管理模型与接口完善 - 技能新增压缩设置页与相关存储/工具能力 - 系统设置扩展配置项 - 摘要中间件 keep 窗口改用 token 预算(16000),减少重复压缩 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
e6662cf673
commit
5ebbb82d66
54 files changed
+2658
-100
No files matched your search
@@ -310,7 +310,14 @@ summarization:
|
||||
value: 60000
|
||||
- type: messages
|
||||
value: 80
|
||||
# Keep a small *token* budget of recent context (same unit as the token
|
||||
# trigger, well below it). This is what the model receives after compaction:
|
||||
# [summary, ~16000 tokens of recent turns]. Small keep = small model context
|
||||
# (fast, no overflow) AND infrequent re-compaction — the preserved window
|
||||
# grows from ~16000 up to the 60000 trigger before folding into a new summary,
|
||||
# which spans many turns. The full conversation still stays in state for the
|
||||
# page; only what is sent to the model is compressed.
|
||||
keep:
|
||||
type: messages
|
||||
value: 20
|
||||
type: tokens
|
||||
value: 16000
|
||||
trim_tokens_to_summarize: 4000
|
||||
Reference in new issue
Block a user