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

@@ -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."""