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:
吉鑫升andClaude Opus 4.8 committed 2026-06-16 15:23:54 +08:00
1 parent e6662cf673
commit 5ebbb82d66
54 files changed
+2658 -100

No files matched your search

@@ -145,6 +145,7 @@ class KnowledgeService:
source_id=draft.source_id,
status=draft.status,
confidence=draft.confidence,
folder=draft.folder,
tags=draft.tags,
created_by=created_by,
)
@@ -223,15 +224,21 @@ class KnowledgeService:
created_by: str | None = None,
skip_existing: bool = False,
model_name: str | None = None,
template_id: str | None = None,
folder: str | None = None,
) -> dict[str, Any]:
"""Sediment a thread into a knowledge note.
``model_name`` optionally overrides the configured extraction model for
this one capture (falls back to ``config.extract_model_name``).
``template_id`` selects an operator-edited extraction prompt template
(falls back to the ``thread`` default, then the built-in prompt).
``folder`` files the resulting note(s) under a user directory.
Returns ``{"note": <note>, "created": bool}``. Raises
:class:`EmptyThreadError` when there is nothing worth keeping.
"""
extract_prompt = await self._resolve_extract_prompt(template_id, "thread")
# Always-on entry log: proves a capture was triggered for this thread,
# regardless of how it ends (success / skip / fallback). Lets you tell
# "capture never ran" apart from "logs not visible" via one grep.
@@ -276,6 +283,7 @@ class KnowledgeService:
model_name=model_name or self.config.extract_model_name,
max_input_chars=self.config.extract_max_input_chars,
allow_multi=self.config.multi_note_enabled,
system_prompt=extract_prompt,
)
except llm_extractor.LLMRejectedIngest as exc:
# The model judged this conversation worthless (greeting / meta
@@ -324,6 +332,8 @@ class KnowledgeService:
normalized = normalize_status(effective_status)
for draft in drafts:
draft.status = normalized
if folder:
draft.folder = folder
# Cross-link sibling notes from the same conversation by title, so the
# split pages reference each other (resolved once all are persisted).
if len(drafts) > 1:
@@ -370,6 +380,7 @@ class KnowledgeService:
tags: list[str] | None = None,
status: str = "approved",
summary: str | None = None,
folder: str | None = None,
created_by: str | None = None,
) -> dict[str, Any]:
"""Create a note directly from product-edited Markdown."""
@@ -388,6 +399,7 @@ class KnowledgeService:
source_type="manual",
source_id=None,
status=normalize_status(status),
folder=(folder or None),
tags=base_tags,
confidence=0.5,
related=extractor.related_links(self.project_name),
@@ -431,6 +443,8 @@ class KnowledgeService:
created_by: str | None = None,
model_name: str | None = None,
skip_existing: bool = False,
template_id: str | None = None,
folder: str | None = None,
) -> dict[str, Any]:
"""Import a file (already converted to Markdown/text) into knowledge notes.
@@ -468,6 +482,7 @@ class KnowledgeService:
logger.info("[knowledge] file '%s' already imported (note %s); skipping", filename, existing.get("id"))
return {"note": existing, "created": False, "notes": [existing], "llm_fallback": False}
extract_prompt = await self._resolve_extract_prompt(template_id, "document")
drafts: list[NoteDraft] = []
llm_fallback = False
if self.config.llm_extract_enabled:
@@ -482,6 +497,7 @@ class KnowledgeService:
model_name=model_name or self.config.extract_model_name,
max_input_chars=self.config.extract_max_input_chars,
allow_multi=self.config.multi_note_enabled,
system_prompt=extract_prompt,
)
except llm_extractor.LLMRejectedIngest as exc:
raise EmptyThreadError(f"File {filename} judged not worth ingesting: {exc}") from exc
@@ -496,6 +512,8 @@ class KnowledgeService:
normalized = normalize_status(effective_status)
for draft in drafts:
draft.status = normalized
if folder:
draft.folder = folder
# Cross-link sibling notes split from the same document (resolved by title
# once all are persisted), mirroring multi-note thread capture.
@@ -526,6 +544,7 @@ class KnowledgeService:
entity: str | None = None,
source_type: str | None = None,
status: str | None = None,
folder: str | None = None,
limit: int = 20,
offset: int = 0,
) -> dict[str, Any]:
@@ -535,6 +554,7 @@ class KnowledgeService:
entity=entity,
source_type=normalize_source_type(source_type) if source_type else None,
status=status,
folder=folder,
limit=limit,
offset=offset,
)
@@ -555,6 +575,8 @@ class KnowledgeService:
tags: list[str] | None = None,
status: str | None = None,
summary: str | None = None,
folder: str | None = None,
set_folder: bool = False,
updated_by: str | None = None,
) -> dict[str, Any] | None:
current = await self.repo.get_note(note_id, with_sources=False)
@@ -576,6 +598,8 @@ class KnowledgeService:
content_md=body,
status=normalize_status(status) if status else None,
tags=tags,
folder=folder,
set_folder=set_folder,
updated_by=updated_by,
)
if note is None:
@@ -604,6 +628,84 @@ class KnowledgeService:
async def list_versions(self, note_id: str) -> list[dict[str, Any]]:
return await self.repo.list_versions(note_id)
# -- folders ----------------------------------------------------------
async def list_folders(self) -> list[dict[str, Any]]:
return await self.repo.list_folders()
async def create_folder(self, path: str, *, created_by: str | None = None) -> dict[str, Any]:
return await self.repo.create_folder(path, created_by=created_by)
async def rename_folder(self, folder_id: str, new_path: str) -> dict[str, Any] | None:
return await self.repo.rename_folder(folder_id, new_path)
async def delete_folder(self, folder_id: str, *, reassign_to: str | None = None) -> bool:
return await self.repo.delete_folder(folder_id, reassign_to=reassign_to)
# -- extraction templates ---------------------------------------------
async def _resolve_extract_prompt(self, template_id: str | None, scope: str) -> str | None:
"""Return the system prompt for a capture, or ``None`` for the built-in default.
Resolution: explicit ``template_id`` → the scope's default template →
``None`` (the extractor then uses its hard-coded prompt). Best-effort: any
lookup failure degrades to the built-in prompt so capture never breaks.
"""
try:
if template_id:
tpl = await self.repo.get_template(template_id)
if tpl and tpl.get("enabled") and (tpl.get("system_prompt") or "").strip():
return tpl["system_prompt"]
default = await self.repo.get_default_template(scope)
if default and (default.get("system_prompt") or "").strip():
return default["system_prompt"]
except Exception:
logger.exception("Failed to resolve knowledge extraction template (id=%s, scope=%s)", template_id, scope)
return None
async def list_extract_templates(self, *, scope: str | None = None, enabled_only: bool = False) -> list[dict[str, Any]]:
return await self.repo.list_templates(scope=scope, enabled_only=enabled_only)
async def get_extract_template(self, template_id: str) -> dict[str, Any] | None:
return await self.repo.get_template(template_id)
async def create_extract_template(self, **kwargs: Any) -> dict[str, Any]:
return await self.repo.create_template(**kwargs)
async def update_extract_template(self, template_id: str, **kwargs: Any) -> dict[str, Any] | None:
return await self.repo.update_template(template_id, **kwargs)
async def delete_extract_template(self, template_id: str) -> bool:
return await self.repo.delete_template(template_id)
async def template_name_taken(self, name: str, *, exclude_id: str | None = None) -> bool:
return await self.repo.template_name_taken(name, exclude_id=exclude_id)
async def seed_default_templates(self, *, created_by: str | None = None) -> int:
"""Seed the two built-in distillation prompts as editable templates (idempotent).
Runs once on startup so an operator immediately sees — and can edit — the
prompts that drive 对话 / 文档 extraction. Existing templates with the same
name are left untouched. Returns the number of templates created.
"""
from deerflow.knowledge import llm_extractor
guidance = llm_extractor.WIKI_CAPTURE_GUIDANCE
seeds = [
("默认 · 对话提炼", "thread", llm_extractor._SYSTEM_PROMPT + "\n\n" + guidance, "对话沉淀的默认提炼提示词(wiki-capture 规范)。"),
("默认 · 文档提炼", "document", llm_extractor._DOC_SYSTEM_PROMPT + "\n\n" + guidance, "文档导入的默认提炼提示词(wiki-capture 规范)。"),
]
created = 0
for name, scope, prompt, desc in seeds:
try:
if await self.repo.template_name_taken(name):
continue
await self.repo.create_template(name=name, system_prompt=prompt, scope=scope, description=desc, is_default=True, enabled=True, created_by=created_by)
created += 1
except Exception:
logger.exception("Failed to seed knowledge extraction template '%s'", name)
if created:
logger.info("[knowledge] seeded %d default extraction template(s)", created)
return created
async def delete_note(self, note_id: str, *, updated_by: str | None = None, hard: bool = False) -> bool:
"""Soft delete (archive) by default; hard delete removes the vault file."""
current = await self.repo.get_note(note_id, with_sources=False)