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 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>
Fixes#18833.
When the reasoning level is enabled, `dialog_service.rag_agent()` builds a custom system prompt and passes it to `RAGTools`. `RAGTools.sys_prompt()`, however, returned only the router instructions, so the configured system prompt was dropped from the outer LLM.
This change prepends the configured system prompt to the router prompt when one is provided, and adds regression tests.
### Problem
When a chat assistant has a configured system prompt and the reasoning
level is set to anything other than `NONE`, the request goes through
`rag_agent()` / the agentic RAG harness. That path generated the final
answer with a fixed `FINAL_ANSWER_SYSTEM` prompt and never injected the
user-configured system prompt, so the assistant ignored
role/tone/language instructions (reported in #18833).
### What problem does this PR solve?
Closes#18116.
Fix cross-KB document ID collision (#18116). Older ID derivation excluded kb_id, causing two KBs to fight over one row. Unified derivation to be KB-scoped, with fallback for existing rows. Stranded rows are reclaimed, dataset deletion now cleans up state, and upgraded instances update in place. Tests added.
### Summary
Fixes#18653. Groq rejects every chat request on v0.27.0 with `property
'conversationId' is unsupported`, while the same chat works on Ollama.
Closes#18653
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### Summary
The fix is one line per helper — assign the `order_by(...)` result back
so the
ordering is actually applied to the query.
Co-authored-by: rsnetworkinginc <rsnetworkinginc@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### Summary
The fix turns a negative timeout into a finite 60 second wait inside
`MysqlDatabaseLock`, which both servers accept. Callers keep expressing
"block until available", and the equivalent PostgreSQL and GaussDB work
on the same `-1` semantics (#16346, #18506) is untouched. Non-negative
timeouts keep their current behaviour.
---------
Co-authored-by: Krim <git@krim.dev>
## Summary
- allow ISO 8601 normalization callers to provide an explicit fallback
while preserving the existing default behavior
- use the extraction conversation time when `valid_at` is missing or
invalid
- clear an invalid optional `invalid_at` instead of writing an
unparseable value
- include the rejected timestamp value in the error log
This addresses the timestamp write-through portion of #18415. It is
intentionally separate from #18462, which fixes the semantic output
prompt.
Co-authored-by: Loong <184861530+yzl0ng@users.noreply.github.com>
### Summary
- Forward each memory's stored system_prompt and user_prompt to
extract_by_llm.
- Cover both immediate save and queued extraction paths with focused
regression tests.
- Preserve the existing default-prompt fallback when stored prompts are
empty.
Fixes#18413.
### Summary
RAGFlow's "Create empty document" flow accepts names without a file
extension. The `POST /datasets/<dataset_id>/documents?type=empty` route
calls `_upload_empty_document()`, where `Path(name).suffix.lstrip(".")`
returns `""`.
In GaussDB's A/ORA compatibility mode, that empty string is persisted as
SQL `NULL`. Because `document.suffix` was defined as `NOT NULL`, the
insert failed with a constraint violation.
Follow-up to #17526 ("Refactor: merge dataset scope graph"), which introduced two code paths that touch Infinity columns the deployed schema does not declare. This PR makes the runtime robust against the old schema while also adding the new column to the new schema so freshly created tables are correct.
### Summary
#16524 reports that a manual metadata filter matching more documents
than the ES push-down cap (`filter_doc_ids_by_meta_pushdown`'s default
`limit=10000`) drops documents once the request falls back to the
in-memory path — e.g. a `canon Not in ["0"]` filter over a
39,573-document KB where ~38,500 matching documents never come back.
I traced through the current code path for this exact scenario:
- `_filter_doc_ids_by_metadata_es` correctly detects when the match
total exceeds the push-down cap and bails to the in-memory fallback
instead of returning a truncated slice.
- `get_flatted_meta_by_kbs` (fixed by #16095) now fully paginates
through every document in the KB rather than stopping after the first
page.
- `es_conn.py`'s `search()` already switches to `search_after`-based
pagination once `offset + limit` would exceed ES's `max_result_window`
(10,000), so the outer pagination loop doesn't get cut off by that
ceiling either.
- `meta_filter()` then aggregates over the complete flattened metadata
with no additional cap.
I couldn't reproduce the drop against current `main` following that
path. This PR adds a test that simulates the exact reported scenario
(12,000 synthetic documents, `canon Not in ["0"]` matching all but 30 of
them) against a fake, paginated `docStoreConn` standing in for
Elasticsearch — both assertions pass on current `main`.
To make sure this is a meaningful regression test and not a false
positive, I temporarily reverted `get_flatted_meta_by_kbs` to stop after
the first page (the pre-#16095 behavior) and confirmed the test
correctly fails (970 of the expected 11,970 documents), then restored
the original code before committing.
Given all of that, it looks like #16524 may already be fixed by the
combination of #16095 and the existing `search_after` handling in
`es_conn.py`, but I could be missing something about the reporter's
specific deployment or a scenario I haven't considered (e.g. a
downstream cap once matched doc_ids feed into the content-chunk
retrieval query). I've left a comment on the issue with this same
analysis so a maintainer familiar with the history here can confirm or
point me at what I'm missing. Either way, this test is a useful
regression guard for the pagination behavior going forward.
### What problem does this PR solve?
Fix:
- Pass session_id to langfuse.
- Get correct status for add model_type.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Adds a legacy mode for /chat/completions that restores v0.23.0-style
output by converting start_to_think/end_to_think back into raw
<think></think> markers and streaming cumulative answer text.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
This PR passes `session_id` into Langfuse trace observations so
multi-turn chat messages can be grouped under the same session in
Langfuse.
Changes include:
- Propagate `session_id` from chat/session APIs into
`dialog_service.async_chat`.
- Pass `session_id` into Langfuse `start_observation(...)`.
- Share Langfuse `trace_context` with chat, embedding, rerank, and TTS
model bundles where applicable.
- Add unit coverage to verify Langfuse observations receive
`session_id`.
- Update affected test stubs for the new optional Langfuse context
arguments.
## Related Issue
Closes: #15636
## Change Type
- [x] Feature
- [x] Bug fix
- [x] Test
- [ ] Refactor
- [ ] Documentation
- [ ] Breaking change
## Real Behavior Proof
Before this change:
- Langfuse observations were created without `session_id`.
- Multi-turn chat traces could not be grouped by session in Langfuse.
After this change:
- Chat/session flows pass `session_id` into `async_chat`.
- Langfuse observations include `session_id`.
- Related model bundles receive shared trace context and session
metadata.
Validation result:
```bash
uv run python -m py_compile \
api/db/services/tenant_llm_service.py \
api/db/services/llm_service.py \
api/db/services/dialog_service.py \
api/db/services/conversation_service.py \
api/apps/restful_apis/chat_api.py \
test/unit_test/api/db/services/test_dialog_service_final_answer.py \
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py
```
Passed.
```bash
uv run pytest \
test/unit_test/api/db/services/test_dialog_service_final_answer.py \
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py -q
```
Result:
```text
11 passed in 16.89s
```
```bash
git diff --check
```
Passed.
## Checklist
- [x] Analyzed the issue requirement.
- [x] Checked existing Langfuse trace integration.
- [x] Implemented only the requested session grouping behavior.
- [x] Added/updated unit tests.
- [x] Ran focused tests successfully.
- [x] Ran Python compile validation.
- [x] Ran whitespace diff validation.
Fixes#15529 .
### Problem
`async_ask()` accessed `kbs[0]` without verifying that
`KnowledgebaseService.get_by_ids()` returned any knowledge bases. Empty
or stale `kb_ids` raised `IndexError`, which surfaced as HTTP 500 on
search/bot SSE endpoints.
### Fix
- Add an early guard when `kbs` is empty, yielding a final SSE error
event (consistent with `gen_mindmap()` in the same module).
- Add regression tests for empty `kb_ids` and deleted/invalid KB IDs.
### Test plan
- [ ] `pytest
test/unit_test/api/db/services/test_dialog_service_final_answer.py -k
"async_ask_empty or async_ask_stale"`
- [ ] Manual: `POST /api/v1/searchbots/ask` with invalid `kb_ids`
returns SSE error, not HTTP 500
---------
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
Python implementation of the Go-based model_provider API suite.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: bill <yibie_jingnian@163.com>
## Summary
Implements the TODO in `evaluation_service.py`: **Track token usage** in
evaluation results.
## Changes
- **Import** `num_tokens_from_string` from `common.token_utils`
- **Prompt tokens**: Use the full prompt returned by `async_chat` when
available (includes system prompt + knowledge base + query), otherwise
fall back to the question token count
- **Completion tokens**: Count tokens in the generated answer
- **Storage**: Store `token_usage` as `{prompt_tokens,
completion_tokens, total_tokens}` in each `EvaluationResult` instead of
`None`
## Why
The evaluation pipeline previously saved `token_usage: None` for every
result. This change allows downstream consumers (e.g. evaluation
dashboards, cost tracking) to see approximate token usage per test case
using the same tokenizer (tiktoken cl100k_base) used elsewhere in
RAGFlow.
## Testing
- No new tests added; existing evaluation flow unchanged
- Token counting uses existing `num_tokens_from_string` utility
---------
Co-authored-by: kiannidev <kiannidev@users.noreply.github.com>
Liu AnandJin Hai
mkaaadandcoderabbitai[bot]
Yash Raj Pandey
MarMar Labs
Martin Civáň
euvre
georgelichenandChen Li
Yingfeng
Chakshu Dhannawat
ChendongPang
SYED ALI ABBAS RAHIL
Wang Qi
Mpider-San
Bharadwaj PendyalaandJin Hai
Sevenzuo
Jiang, Guomin
Lynn
Christian UhlandKrim
WangshuandClaude Sonnet 5
LoongandLoong
zws202606
S
buua436
Öndery
Harsh Kashyap
Zhichang Yu
Jonathan Chang
bohdansolovieandWang Qi
kpdevandkiannidev