## Summary
Fixes#15487 — lone markdown headers are no longer isolated as empty
chunks when a custom `delimiter` is set.
- Merge consecutive lone headers before attaching to the following prose
body
- Skip code fences, tables, lists, and blockquotes via
`_is_attachable_body()`
- Unit tests include the `# Title / ## Intro / Body` regression from
CodeRabbit review
## Validation
- `pytest test/unit_test/deepdoc/parser/test_markdown_parser.py` (11
passed locally)
Closes#15487
### What problem does this PR solve?
- Migrated MCP server detail and export (download) API from Python to
Go.
- Registered route: `GET /api/v1/mcp/servers/:mcp_id` (supporting
`?mode=download` query parameter).
### What problem does this PR solve?
This PR implements the Go backend counterpart for the document partial
update API:
`PATCH /api/v1/datasets/:dataset_id/documents/:document_id`
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
This PR improves code readability in the CLI parser by renaming the loop
index `i` to `modelIndex`. It also renames the loop label `A` to
`optionsLoop` to align with standard Go naming conventions.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.26.0 to v0.26.1
- Modify Docker image references and documentation to reflect new
version
- Update version badges and image descriptions
- Maintain consistency across all language variants of README files
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
Fixes two bugs in the OpenRouter streaming chat request builder
(`internal/entity/models/openrouter.go`, `ChatStreamlyWithSender`):
1. **qwen/glm models streamed to a broken URL.** The code routed any
`qwen`/`glm` model to
`URLSuffix.AsyncChat`, but `conf/models/openrouter.json` defines no
`async_chat` suffix
(empty), so the request was POSTed to `<base>/` instead of
`<base>/chat/completions` —
breaking streaming for every qwen/glm model. The non-stream path has no
such branch.
Fix: all models use the standard `Chat` suffix, consistent with the
non-stream path.
2. **Streaming reasoning was never enabled.** The request set reasoning
via a non-standard
`thinking` key, which OpenRouter ignores. OpenRouter's API — and this
provider's own
non-stream request (line ~110) and its streamed `delta.reasoning` parser
(line ~311) —
use the `reasoning` object. Fix: send `reasoning: {"enabled":
<thinking>}` (and
`{"effort": ...}` when set, taking precedence as in the non-stream
path).
Closes#16110
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add chat model factory for Xiaomi model.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Adds qqbot as a built-in chat channel so it can be discovered and
started by the channel bootstrapper and shown in the chat channel
settings UI.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Part of #15853 (provider model-list refactor).
Refactors **Ollama** `ListModels` onto the shared `ParseListModel`
pattern and fixes two correctness issues:
- **Endpoint:** switch the models suffix from `api/ps` (only
currently-running models) to `api/tags` (all installed models) — the
latter is what a model picker should show.
- **Parsing:** Ollama returns `{"models":[{"name","model"}]}`, a
non-OpenAI shape. Decode it into a typed struct, map the names into
`ModelList`, then enrich through `ParseListModel`. This removes the
previous unchecked type assertions (`result["models"].([]interface{})` /
`.(map[string]interface{})` / `.(string)`) that **panicked** when the
body was missing the `models` array or any field, and adds a fallback to
the `model` field when `name` is blank.
- Drops the no-op GET request body and a dead base-URL reassignment.
#### Drive-by fix
Shared gitee_test.go `DSModelList` -> `ModelList` compile fix (renamed
in #15900) so the models test package builds; auto-resolves against the
sibling #15853 PRs.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
Fix: The pipeline created from the template fails immediately upon
execution.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix: misc frontend fixes for agent log, login, search settings
- agent-log: restore server-side pagination on export and search;
replace hardcoded labels with i18n keys; switch container to
text-text-primary
- login: validate register nickname against NICKNAME_PATTERN with
reusable setting i18n
- next-search: align llm_setting schema with chat (LlmSettingFieldSchema
+ LLMIdFormField nested, LlmSettingEnabledSchema at form
root) so the slider Switch reads the correct path; strip *Enabled flags
before submit to avoid backend "Unrecognized field name"
errors
- locales: add common.reset (zh/en)
- skills/go-naming: fix relative link to rules/named.md
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: The .docx file is not displaying fully; the hierarchy of the
pipeline created from the template is missing.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix chat channel message routing to use the connected `chat_id`, and
make the Feishu websocket client bind to the thread-local event loop.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Show Telegram in the chat channel picker alongside the existing Discord
and Feishu entries.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Use a 95% max_length threshold before truncating embedding inputs, which
reduces the chance of provider-side invalid-parameter errors on
near-limit chunks.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Replaces the Python agent canvas runtime with a Go implementation that
runs inside `cmd/server_main`.
The canvas compiles into an eino Workflow that pauses on wait-for-user
via native Interrupt/Resume (no sentinel flag) and resumes from a
Redis-backed CheckPointStore.
All 21 Python agent components and ~35 tools are ported with functional
parity.
Sandbox providers now read their JSON config from the admin-panel
system_settings table with env fallback.
234 files / +35,413 / -6,111. All Go files are gofmt-clean (CI gate
added); drops the v2 DSL E2E step and the gap-analysis plan (both
redundant after the port ships).
## Type of change
- [x] Refactoring
- [x] New feature
- [x] Bug fix
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
### What problem does this PR solve?
The `get_ingestion_log` endpoint (both Python
`dataset_api_service.get_ingestion_log` and Go
`DatasetService.GetIngestionLog`) was returning only the
**dataset-level** field set, which omits critical fields such as `dsl`,
`document_id`, `parser_id`, `document_name`, `pipeline_id`, etc.
This caused the front-end **dataflow-result page** to be unable to
render the pipeline timeline and chunks when viewing a single ingestion
log, regardless of whether the log was a dataset-level operation
(graph/raptor/mindmap) or a per-file parse.
### Background
`PipelineOperationLogService` provides two field sets:
| Method | Fields |
|---|---|
| `get_dataset_logs_fields` | Minimal set (progress, status, timestamps,
etc.) |
| `get_file_logs_fields` | Superset — includes `document_id`, `dsl`,
`parser_id`, `document_name`, `pipeline_id`, … |
When listing logs, the API correctly distinguishes dataset-level vs
file-level logs and uses the appropriate converter. However, when
**fetching a single log by ID**, both the Python and Go implementations
were hardcoded to the dataset-level set, dropping the extra fields that
the front-end needs.
### What problem does this PR solve?
Part of #15853 (provider model-list refactor). Final two providers.
- **voyage:** Voyage AI exposes no live model-list endpoint — its public
API only has `/v1/embeddings` and `/v1/rerank` — so the previous
`ListModels` was a `no such method` stub. Replace it with a
static-catalog listing sourced from the loaded provider definition,
carrying each model's `max_tokens`, `model_types`, and embedding
`dimensions`. `list models from voyage` now returns the 13-model catalog
instead of erroring.
- **fishaudio:** route the existing `/model` voice listing through the
shared `ParseListModel` helper for consistency; keep the human-readable
`title` as the model name and fall back to `_id` when a title is blank.
#### Drive-by fix
Shared gitee_test.go `DSModelList` -> `ModelList` compile fix (renamed
in #15900); auto-resolves against the sibling #15853 PRs.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
Co-authored-by: Haruko386 <tryeverypossible@163.com>
# Summary
- The culprit is commit b4c8711d5 / PR #15415 (fix: upgrade crawl4ai to
0.8.0).
- That upgrade brought in unclecode-litellm, which installs the same
top-level litellm namespace as upstream litellm.
- The crash happens when files from one LiteLLM distribution are mixed
with files from the other: custom_guardrail.py expects
GuardrailTracingDetail, but types/utils.py can come from the older
conflicting package.
## Changes
1. **Entity (`internal/entity/chat_channel.go`)**:
- Implemented `ChatChannel` struct mapping the `chat_channel` database
table.
- Declared `ChatChannelListResponse` as a DTO to filter out sensitive
credentials (`config` field) and fetch the associated `dialog_name` via
left join.
2. **GORM Migration (`internal/dao/database.go`)**:
- Registered `&entity.ChatChannel{}` in the `dataModels` array inside
`InitDB()` to enable safe GORM schema synchronization.
3. **DAO (`internal/dao/chat_channel.go`)**:
- Implemented `ChatChannelDAO` wrapping GORM CRUD methods (`Create`,
`GetByID`, `UpdateByID`, `DeleteByID`).
- Implemented `ListByTenantID` performing a `LEFT JOIN` on the `dialog`
table to retrieve `dialog_name` while excluding `config` values to avoid
credential leaks.
4. **Test (`internal/dao/chat_channel_test.go`)**:
- Added integration unit tests testing the full CRUD lifecycle and GORM
left-join mapping list querying.
### What problem does this PR solve?
Fix: Importing the MCP dialog causes duplicate submissions.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
The parser pods suffer from OOM kills when processing large PDF
documents. The root cause is in api/db/services/task_service.py: when
layout_recognize is not DeepDOC (e.g. Plain Text), page_size was set to
MAXIMUM_TASK_PAGE_NUMBER (100 million), causing the entire PDF to be
processed as a single task with all pages loaded into memory
simultaneously.
This PR fixes the issue by paginating non-DeepDOC PDF parsing tasks the
same way DeepDOC already does.
### What problem does this PR solve?
Syncs the /api/v1/chat/completions docs with the current behavior,
including the new legacy streaming mode.
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
The parser pods suffer from OOM kills when processing large PDF
documents. The root cause is in api/db/services/task_service.py: when
layout_recognize is not DeepDOC (e.g. Plain Text), page_size was set to
MAXIMUM_TASK_PAGE_NUMBER (100 million), causing the entire PDF to be
processed as a single task with all pages loaded into memory
simultaneously.
This PR fixes the issue by paginating non-DeepDOC PDF parsing tasks the
same way DeepDOC already does.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
## Summary
Add image parsing capability to PaddleOCR integration, building on top
of #15967 (async Job API migration).
## Changes
### `deepdoc/parser/paddleocr_parser.py`
- Add `parse_image()` method that uses the same async Job API flow as
`parse_pdf()`
- Extracts text from `layoutParsingResults` → `prunedResult` →
`parsing_res_list`
- Returns concatenated block content as a single string
### `rag/llm/ocr_model.py`
- Add `parse_image()` wrapper to `PaddleOCROcrModel` with availability
check and logging
## Relationship to other PRs
- **Depends on**: #15967 (async Job API migration) — this PR is based on
that branch
- **Replaces**: #14826 (original image processing PR based on old sync
API)
## Notes
This PR uses `base_url` and the async Job API (submit → poll → fetch)
consistent with #15967, rather than the old `api_url` + sync POST
pattern from #14826.
## Summary
Migrate PaddleOCR integration from the deprecated synchronous HTTP API
to the new asynchronous Job API (`submit → poll → fetch`), aligning with
PaddleOCR 3.6.0+ architecture.
## Changes
### Python (`deepdoc/parser/paddleocr_parser.py`)
- Replace synchronous `requests.post()` with async Job API flow (submit
→ poll → fetch)
- Authentication: `token {token}` → `Bearer {token}`
- File transfer: base64 JSON body → multipart file upload
- Polling: exponential backoff (initial 3s, ×1.5, max 15s, timeout
controlled by `request_timeout`)
- Result: fetch full JSONL from result URL, preserving `prunedResult`
with bbox info for crop functionality
- Rename `api_url` → `base_url` (backward compatible: `api_url` still
accepted as fallback)
### Python (`rag/llm/ocr_model.py`)
- Prefer `paddleocr_base_url` / `PADDLEOCR_BASE_URL`, fallback to
`paddleocr_api_url` / `PADDLEOCR_API_URL`
### Go (`internal/entity/models/paddleocr.go`)
- Add `Client-Platform: ragflow` header to submit and poll requests
- Change polling from fixed 3s to exponential backoff (initial 3s, ×1.5,
max 15s)
### Python (`common/constants.py`)
- Add `PADDLEOCR_BASE_URL` to env keys and default config
## Backward Compatibility
- Old env var `PADDLEOCR_API_URL` still works (used as fallback)
- Frontend field `paddleocr_api_url` still works (backend reads it as
fallback)
- No user-facing configuration changes required for existing setups
## Why not use the `paddleocr` SDK package directly?
RAGFlow's `_transfer_to_sections()` relies on `prunedResult` (containing
`block_bbox`, `block_label`, `parsing_res_list`) from the raw API
response for PDF crop functionality. The SDK's public `parse_document()`
API only returns `DocParsingResult` with `markdown_text`, discarding the
bbox data. Therefore we implement the async Job API flow directly via
HTTP, following the same logic as the SDK internally.
### What problem does this PR solve?
Merge password related functions
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
