Fix GET /api/v1/memories list filters — memory_type, tenant_id, owner_ids, ids now read all repeated query keys (was only first). Matches /datasets//documents pattern.
Add user attribution to embedding calls — forwards user on OpenAI-compatible providers via current_llm_user(). Excludes LocalAI/Xinference (reject unknown fields). Accepts user_id on ingest/parse/chunk endpoints; redacts from logs. Omitted = unchanged. Go/vision/TTS/ASR out of scope.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Fix MCP session cleanup — now properly awaits server task and closes transport contexts/executors before stopping event loop. Wakes queued callers on shutdown.
Fix OAuth callback URL examples in docs — now use /api/v1/auth/oauth/<channel>/callback (was stale /v1/user/oauth/callback).
Co-authored-by: 谢金城 <xiejincheng@xgd.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Fix#19019 — MCP _fetch_all_datasets() used wrong total key (total vs total_datasets), causing extra empty-page requests. Now reads total_datasets with fallback.
Fixes a family of table-retrieval truncation bugs and an action-session
infinite loop in the agentic RAG medium path, all root-caused on a
tabular-reasoning question
1. action_session turn cap enforced (action_session.py)
_route checked _pending_calls before attempts, so a model that kept
emitting tool calls never hit the 4-turn finalize — a single session
could burn the whole pass budget (219 retrievals / 600s observed). Added
_route_after_tool: after a tool batch, the turn budget is checked and
the session converges to finalize instead of looping back to run_action.
2. Table chunks kept whole through retrieval (search.py,
text_processing.py, action_session.py)
Three truncation points hid mid-table answer rows from the session
model:
- grep_search narrowed table chunks to 700 chars
(_GREP_OUT_CHARS_PER_CHUNK)
- _narrow_content only passed HTML tables (<table>/<tr/<td) whole —
markdown pipe tables were sentence-window narrowed
- _admit_evidence truncated the model-facing output to 1200 chars even
though the pool held the full chunk，non-table chunks keep the existing
truncation paths unchanged.
3. SCA sees more evidence (agentic_rag_graph.py, sufficient_context.py)
_SCA_VIEW_CAP 24 → 60; _SCA_CLAIMS_CONTEXT_MAX 9000 → 48000;
table-bearing evidence anchors rendered in full (bounded by the context
budget).
4. Supporting: runtime instrumentation for rounds/slots/retrievals, LLM
token accounting, slot-evidence preservation through SCA, dedup
checkpoints. Timeout/budget constants restored to upstream defaults.
---------
Co-authored-by: Loong <213221738@seu.edu.cn>
Co-authored-by: Hermes Agent <hermes-agent@localhost>
Fix non-streaming chat sending empty tools=[] (rejected by strict providers). Restored mdl.is_tools check and added helper to omit tools field when unbound.
Fix agentic search ignoring chat retrieval settings — now passes knn_top_k, weights, threshold, and top_n. knn_top_k critical for HNSW recall on large indices.
Fix#15962 — replace bare assert isinstance in KnowledgebaseService.dfs_update with safe conditions. Stored None values no longer crash table-parser parses. Matches DocumentService fix from #12815.
Fix reasoning + KB requests using models without tool-calling — now fall back to async_chat RAG path instead of answering from general knowledge.
Co-authored-by: Chen Li <george_lichne@163.com>
### Summary
GET /api/v1/files/{id} now sets attachment filename for both Python and
Go handlers so browsers can save downloads with the correct name.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Fix POST /api/v1/files 500 error when parent_id doesn't exist. Removed dead delete_folder_by_pf_id call (mismatched args, no tenant scope). Now returns False and documented error response.
Fix generate_nav tenant mismatch: wipe used dataset owner's tenant_id but rebuild used caller's. Team members could delete owner's navigation tree and rebuild into their own. Now both use kb.tenant_id.
MarMar Labs
Wang Qi
Manan Bansal
ÖnderyandCursor
Lem0nTea2002
Lynn
buua436
maoyifeng
euvre
Sbaaoui Idriss
mkaaadandcoderabbitai[bot]
Yingfeng
Yash Raj Pandey
xu jiaming
Martin Civáň
Josh Baptiste
georgelichenandChen Li
天海蒼灆andCursor
ChendongPang