## Summary
Remediates CVE-2026-26209 (HIGH) in `cbor2` by adding `cbor2>=5.9.0` to
`constraint-dependencies` in `pyproject.toml`.
| CVE | Severity | Package | Installed | Fixed in |
|---|---|---|---|---|
| CVE-2026-26209 | HIGH | cbor2 | 5.8.0 | 5.9.0 |
`cbor2` is a transitive dependency pulled in by `ranx` with no version
constraint, stuck at 5.8.0 because lockfile hadn't been re-resolved.
Net effect: inline prose stays on one line (`Hello World`), real `<br>` boundaries survive (including before tags and repeated breaks), and source formatting whitespace no longer over-splits.
## Summary
- `api/apps/services/provider_api_service.py` hardcoded the DashScope
international base URL for Tongyi-Qianwen as `.../compatible-model/v1`
instead of `.../compatible-mode/v1`, in two places (`list_providers`,
lines ~93 and ~116).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Ports the dataset knowledge compilation (wiki/graph/tree/mindmap) to the
Go scheduler with a status contract, aligns wiki storage/retrieval with
Python, and sizes prompts by content_length.
## Summary
The generic `buildRequestBody` in `internal/entity/models/base_model.go`
unconditionally forwarded `ChatConfig.MaxTokens` as `"max_tokens"` for
every OpenAI-compatible provider.
Providers that need a different token field already delete or override
it after the call (e.g. Xiaomi uses `max_completion_tokens`, Replicate
uses `max_new_tokens`). This change stops setting `max_tokens` in the
shared builder so it only forwards the parameters common across
providers, and each provider remains free to set its own token limit
field.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Go `TokenChunker` text/markdown path (`mergeByTokenSize`)
unconditionally
called `splitOversizedUnit` on any unit that exceeded
`chunk_token_size`,
emitting Go-only sub-chunks. Python's `naive_merge`
(`_merge_paragraph_groups`,
`rag/nlp/__init__.py`) never atom-splits an oversize unit under either
`OVER_CAP` or `UNDER_CAP`: a paragraph larger than the budget becomes
its own
standalone chunk and the model layer truncates it later.
This aligns the text/markdown path with the **structured JSON path**
(`invokeJSONPayload` → `mergeByTokenSizeFromJSON(...,
subSplitOversize=false)`,
#17739). It completes the OVER_CAP alignment started in #17835.
## Summary
- Pin `werkzeug>=3.1.7,<4` and refresh `uv.lock` to **3.1.8**.
- Fixes intermittent corruption of uploaded file bodies: when TCP
segments split right after multipart part headers, Werkzeug **3.1.5**
can include a leading `\r\n` in the file content
([pallets/werkzeug#3088](https://github.com/pallets/werkzeug/issues/3088);
fixed in 3.1.7).
- In RAGFlow this commonly breaks `.xlsx` parsing: ZIP/OOXML magic
(`PK\x03\x04`) no longer matches, the Excel parser falls back to CSV,
then fails with UTF-8 decode errors such as `invalid start/continuation
byte`.
Made with [Cursor](https://cursor.com)
Co-authored-by: zhangjiangshan1 <zhangjiangshan1@kingsoft.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Go's `TokenChunker` kept the captured delimiter glued to the preceding
segment on **both** the primary (`chunkFromItem`) and secondary
(`children_delimiters`) split paths, while Python's reference
`token_chunker` drops it via `_split_text_by_pattern`
(`token_chunker.py:79-93`, used by both `_build_json_chunks` and
`_split_chunk_docs_by_children`). The divergence leaked the delimiter
into every emitted chunk's `text`.
- Prefer canonical `dataset_ids` over legacy `kb_ids` in Canvas
retrieval components.
- Cover selected and explicitly cleared dataset IDs with regression
tests.
- Add cross-language retrieval with dataset-specific embedding and
rerank models.
- Support vector and keyword similarity controls, metadata filtering,
TOC enhancement, and child-chunk expansion.
- Route Canvas retrieval across datasets and memories with compatible
embedding validation.
## Summary
Update `conf/all_models.json`: replace legacy `max_tokens` with
`content_length` + `max_output` for all 2,178 chat/vision models, with
values verified against official vendor documentation.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
## Summary
- Verify and populate `content_length` (context window) and `max_output`
(max generation tokens) for all **478 chat/vision models** across **47
provider configs**
- Data sourced from **official API documentation** via 12 parallel
agents + targeted web verification
- Update Go test assertions to match verified values
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
