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

@@ -758,51 +758,83 @@ def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig
from deerflow.config.memory_config import get_effective_memory_config
from deerflow.runtime.user_context import get_effective_user_id
user_id = get_effective_user_id()
config = get_effective_memory_config(user_id)
manager = build_memory_manager(
user_id=user_id,
agent_id=agent_name or "default",
config=config,
app_config=app_config,
)
user_id = get_effective_user_id()
config = get_effective_memory_config(user_id)
manager = build_memory_manager(
user_id=user_id,
agent_id=agent_name or "default",
config=config,
app_config=app_config,
)
# 只取静态块 (builtin 的 frozen snapshot + Hindsight 的模式说明)。
# Hindsight 的动态召回需要当前 query,走 MemoryMiddleware.before_model。
context_content = manager.build_system_prompt()
if not context_content.strip():
return ""
return f"{context_content}\n"
context_content = manager.build_system_prompt()
if not context_content.strip():
return ""
return f"{context_content}\n"
except Exception:
logger.exception("Failed to load memory context")
return ""
def _render_skill_block(name: str, description: str, category: str, location: str, display_hint: str) -> str:
return f" <skill>\n <name>{name}</name>\n <description>{description} {_skill_mutability_label(category)}</description>\n <location>{location}</location>{display_hint}\n </skill>"
@lru_cache(maxsize=32)
def _get_cached_skills_prompt_section(
skill_signature: tuple[tuple[str, str, str, str], ...],
skill_signature: tuple[tuple[str, str, str, str, bool], ...],
display_signature: tuple[tuple[str, str, str], ...],
available_skills_key: tuple[str, ...] | None,
container_base_path: str,
skill_evolution_section: str,
compression_enabled: bool,
keep_index: bool,
) -> str:
display_by_skill = {name: (mode, custom_instruction) for name, mode, custom_instruction in display_signature}
filtered = [(name, description, category, location) for name, description, category, location in skill_signature if available_skills_key is None or name in available_skills_key]
filtered = [(name, description, category, location, always_on) for name, description, category, location, always_on in skill_signature if available_skills_key is None or name in available_skills_key]
def _display_hint(name: str) -> str:
display_mode, custom_instruction = display_by_skill.get(name, ("", ""))
if display_mode:
return f"\n <display mode=\"{display_mode}\">{custom_instruction}</display>"
return ""
skills_list = ""
compression_note = ""
if filtered:
items = []
for name, description, category, location in filtered:
display_mode, custom_instruction = display_by_skill.get(name, ("", ""))
display_hint = ""
if display_mode:
display_hint = f"\n <display mode=\"{display_mode}\">{custom_instruction}</display>"
items.append(
f" <skill>\n <name>{name}</name>\n <description>{description} {_skill_mutability_label(category)}</description>\n <location>{location}</location>{display_hint}\n </skill>"
)
skill_items = "\n".join(items)
skills_list = f"<available_skills>\n{skill_items}\n</available_skills>"
if compression_enabled:
# 压缩开启:常驻(always_on)技能全文注入;其余技能从提示词正文剔除,
# 仅保留可选的"名字索引",由 agent 通过 search_skills 工具按需检索。
resident = [s for s in filtered if s[4]]
compressed = [s for s in filtered if not s[4]]
blocks: list[str] = []
for name, description, category, location, _ in resident:
blocks.append(_render_skill_block(name, description, category, location, _display_hint(name)))
if blocks:
skills_list = "<available_skills>\n" + "\n".join(blocks) + "\n</available_skills>"
if compressed:
index_block = ""
if keep_index:
index_items = "\n".join(f" <skill><name>{name}</name></skill>" for name, _, _, _, _ in compressed)
index_block = f"\n<compressed_skills>\n{index_items}\n</compressed_skills>"
compression_note = (
"\n**Additional skills are available but not listed in full above to keep this prompt compact.**\n"
"When a user query might match a skill that is NOT fully described above, call the `search_skills` "
"tool with a short keyword query to discover matching skills (it returns each match's description and "
f"`location`), then `read_file` the returned `location` and follow the skill. There are {len(compressed)} "
"such compressed skill(s)."
f"{index_block}\n"
)
else:
items = [
_render_skill_block(name, description, category, location, _display_hint(name))
for name, description, category, location, _ in filtered
]
skills_list = "<available_skills>\n" + "\n".join(items) + "\n</available_skills>"
# Restricted mode: agent has an explicit skill allowlist.
# We deliberately omit the "Skills are located at: <path>" hint and the
@@ -842,7 +874,7 @@ You have access to skills that provide optimized workflows for specific tasks. E
4. Load referenced resources only when needed during execution
5. Follow the skill's instructions precisely
{display_pattern}
{location_hint}{evolution_block}
{location_hint}{evolution_block}{compression_note}
{skills_list}
</skill_system>"""
@@ -877,13 +909,27 @@ def get_skills_prompt_section(
is_restricted = available_skills is not None
effective_skill_evolution_enabled = skill_evolution_enabled and not is_restricted
# 技能压缩仅作用于默认 lead agent 的全局技能集;自定义 agent 已有显式白名单
# (技能数量本就受控),不参与压缩。
compression_enabled = False
keep_index = True
if not is_restricted:
try:
from deerflow.config.system_settings import get_skill_compression_settings
compression_settings = get_skill_compression_settings()
compression_enabled = compression_settings.enabled
keep_index = compression_settings.keep_index_in_prompt
except Exception:
logger.debug("Failed to read skill compression settings for prompt injection", exc_info=True)
if not skills and not effective_skill_evolution_enabled:
return ""
if available_skills is not None and not any(skill.name in available_skills for skill in skills):
return ""
skill_signature = tuple((skill.name, skill.description, skill.category, skill.get_container_file_path(container_base_path)) for skill in skills)
skill_signature = tuple((skill.name, skill.description, skill.category, skill.get_container_file_path(container_base_path), skill.always_on) for skill in skills)
display_signature: tuple[tuple[str, str, str], ...] = ()
if display_enabled:
try:
@@ -907,7 +953,7 @@ def get_skills_prompt_section(
if not skill_signature and available_key is not None:
return ""
skill_evolution_section = _build_skill_evolution_section(effective_skill_evolution_enabled)
return _get_cached_skills_prompt_section(skill_signature, display_signature, available_key, container_base_path, skill_evolution_section)
return _get_cached_skills_prompt_section(skill_signature, display_signature, available_key, container_base_path, skill_evolution_section, compression_enabled, keep_index)
def get_agent_soul(agent_id: str | None) -> str:
@@ -37,6 +37,15 @@ logger = logging.getLogger(__name__)
# many threads can't grow it without limit. Oldest entries are evicted first.
_SUMMARY_CACHE_MAX_THREADS = 512
# After compaction the preserved window must land *comfortably* below every
# trigger threshold, otherwise the "compressed" context is still over the
# trigger and re-summarizes on the very next turn (the sticky boundary never
# sticks). We force the kept suffix down to this fraction of each trigger so a
# re-compaction only happens once meaningfully *new* content accumulates — not
# on every follow-up question. ``keep`` only sets a *target*; this is the hard
# headroom guarantee on top of it.
_KEEP_HEADROOM_FRACTION = 0.75
@dataclass(frozen=True)
class SummarizationEvent:
@@ -319,6 +328,15 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
if cutoff_index <= 0:
return None
# Force the preserved window below every trigger (with headroom) so the
# post-compaction context doesn't immediately re-trigger. Without this,
# a ``keep`` expressed in *messages* (e.g. 20) can itself blow past a
# *token* trigger (e.g. 60000) when recent messages are large (tool
# outputs, pasted docs) — and then every follow-up question re-summarizes.
cutoff_index = self._apply_stickiness_headroom(messages, cutoff_index)
if cutoff_index <= 0:
return None
messages_to_summarize, preserved = self._partition_with_skill_rescue(messages, cutoff_index)
if not messages_to_summarize:
return None
@@ -368,6 +386,62 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
while len(self._summary_cache) > _SUMMARY_CACHE_MAX_THREADS:
self._summary_cache.popitem(last=False)
def _apply_stickiness_headroom(self, messages: list[AnyMessage], cutoff_index: int) -> int:
"""Advance ``cutoff_index`` (keep fewer recent messages) so the preserved
suffix lands below every trigger threshold with headroom.
Only ever *raises* the cutoff (summarizes more / keeps less); never keeps
more than the caller's ``keep`` policy already chose. This is what makes
the sticky boundary actually stick: after compaction the kept context is
guaranteed under ~``_KEEP_HEADROOM_FRACTION`` of each trigger, so a
re-compaction waits for genuinely new content instead of firing every turn.
"""
n = len(messages)
if n <= 1:
return cutoff_index
for kind, value in getattr(self, "_trigger_conditions", []):
if kind == "messages":
keep_cap = max(1, int(int(value) * _KEEP_HEADROOM_FRACTION))
cutoff_index = max(cutoff_index, n - keep_cap)
elif kind == "tokens":
target = max(1, int(int(value) * _KEEP_HEADROOM_FRACTION))
cutoff_index = max(cutoff_index, self._suffix_token_cutoff(messages, target))
# "fraction" triggers depend on model profile limits; the message/token
# caps above (when present) already bound the window, so skip them here.
# Always keep at least the final message, and re-snap to a safe AI/Tool
# boundary so we never orphan a tool result.
cutoff_index = min(cutoff_index, n - 1)
return self._find_safe_cutoff_point(messages, cutoff_index)
def _suffix_token_cutoff(self, messages: list[AnyMessage], target_tokens: int) -> int:
"""Smallest index ``i`` such that ``token_counter(messages[i:]) <= target_tokens``.
Binary search mirroring the stock token-based cutoff; returns 0 when the
whole list already fits, and never returns the full length (keeps ≥1).
"""
n = len(messages)
if n == 0:
return 0
if self.token_counter(messages) <= target_tokens:
return 0
left, right = 0, n
cutoff = n
for _ in range(n.bit_length() + 1):
if left >= right:
break
mid = (left + right) // 2
if self.token_counter(messages[mid:]) <= target_tokens:
cutoff = mid
right = mid
else:
left = mid + 1
if cutoff == n:
cutoff = left
return min(cutoff, n - 1)
@staticmethod
def _resolve_request_thread_id(request: ModelRequest) -> str | None:
"""Best-effort thread id from the model request's runtime."""