### Summary
Add object as a begin-node parameter type with JSON editor UI, webhook
schema support, and backend parsing in UserFillUp.
Co-authored-by: Cursor <cursoragent@cursor.com>
### Summary
The Go backend never seeded the `canvas_template` table, so the "Create
agent from template" page was blank when the frontend proxies to the Go
API (`API_PROXY_SCHEME=go`). This PR adds `SeedCanvasTemplates()` in
`internal/dao`, invoked from `InitDB()` after migrations, which loads
`agent/templates/*.json` and mirrors Python's `add_graph_templates()`
behavior.
Changes:
- Add `internal/dao/canvas_template_seed.go` to parse and upsert
built-in templates.
- Call `SeedCanvasTemplates()` in `InitDB()`.
- Add `CanvasTypes` (`JSONSlice`) to `entity.CanvasTemplate` so the
frontend can filter/group by category.
- Skip seeding gracefully when the templates directory is absent.
This fixes the blank template catalogue in Go mode.
## Summary
Adds the missing input form metadata for the Go BGPT canvas component.
## Root Cause
The standalone BGPT component was registered in Go, but it did not
implement GetInputForm(). During component trial run, the backend asks
the component for its input_form. Since BGPT had none, the API returned:
component has no input_form: BGPT:<node_id>
Python BGPT already exposes the query input form, so the Go component
needed the same contract.
## Change
Added GetInputForm() to the Go BGPT component with a single query line
input.
Added test coverage to ensure BGPT exposes the input form.
## Validation
Backend:
bash build.sh --test -run TestBGPT ./internal/agent/component
<img width="1369" height="1184" alt="image"
src="https://github.com/user-attachments/assets/f99e4a81-2359-42e5-80bb-dcc4e6a63fea"
/>
<img width="1736" height="1152" alt="image"
src="https://github.com/user-attachments/assets/c11240a5-2c42-4d08-88e3-c6dfbf49eedb"
/>
## Summary
Fixes a page crash when opening the BGPT node configuration in the
canvas.
## Root Cause
BGPT was using the tool-form watcher call pattern in a normal canvas
component form.
Tool forms use:
useWatchFormChange(form)
Canvas component forms use:
useWatchFormChange(node?.id, form)
Tool is not equal to component. The BGPT canvas component imported the
component-level hook but called it like a tool-form hook, so the form
argument became undefined and React Hook Form tried to read control from
a null context.
## Change
Updated the BGPT canvas form to pass the node id and form instance
correctly.
## Validation
Ran ESLint for the changed file:
npx eslint src/pages/agent/form/bgpt-form/index.tsx
<img width="1369" height="1184" alt="image"
src="https://github.com/user-attachments/assets/a40c5202-7394-4f26-9da2-08329dcc7fbf"
/>
## Summary
- Add language-aware Snowball stemmer to `RagTokenizer` supporting 16
languages (Dutch, German, French, Spanish, etc.)
- Thread the KB `language` parameter through the full tokenization
pipeline (14 parser modules + task executor)
- Add Dutch to the frontend language lists and cross-language form
## Problem
RAGFlow uses the English Porter stemmer + WordNet lemmatizer for **all**
BM25 tokenization, regardless of the knowledge base language setting.
This produces incorrect stems for non-English text. For example:
| Dutch word | Dutch stemmer | English Porter |
|---|---|---|
| documenten | document | documenten (unchanged!) |
| gebruikers | gebruiker | gebruik (over-stemmed) |
| instellingen | instell | instellingen (unchanged!) |
This degrades BM25 recall for any non-English knowledge base.
## Solution
NLTK already ships Snowball stemmers for 16 languages. This PR:
1. **`rag/nlp/rag_tokenizer.py`**: Overrides `tokenize()` with
`set_language()` and `_normalize_token()` that selects the correct NLTK
Snowball stemmer. Falls back to Porter for unmapped languages (Chinese,
Japanese, Korean, etc. — these use character-based tokenization anyway).
2. **`rag/nlp/__init__.py`** + **14 `rag/app/*.py` parsers** +
**`rag/svr/task_executor.py`**: Threads the `language` parameter through
`tokenize()`, `tokenize_chunks()`, `tokenize_table()`, and all callers.
3. **Frontend**: Adds Dutch (`Nederlands`) to `LanguageList`,
`LanguageMap`, `LanguageAbbreviationMap`, `LanguageTranslationMap`,
cross-language form field, and `en.ts` locale.
## Backward Compatibility
- Default language is `"English"`, preserving existing behavior for all
current users
- Languages without a Snowball stemmer mapping fall back to Porter (no
change)
- No new dependencies — NLTK Snowball is already bundled
### Motivation
This PR evolves the harness from a pure execution runtime into an
**observable, replayable agent evaluation platform**. The current
`harness/graph` checkpoint mechanism is insufficient for true
event-sourced introspection—we need append-only event logs capturing
every tool call, state transition, memory write, and approval decision,
enabling deterministic replay, fork/diff, postmortem analysis, and
time-travel debugging.
### Key Design Goals
1. **Event-Sourced Execution Model**
Replace coarse checkpoints with granular, append-only event logs. Every
operation becomes a durable event: tool invocation, state mutation,
memory update, human approval. This unlocks deterministic replay,
branching execution histories, and regression datasets derived directly
from production failures.
2. **First-Class Replay & Evaluation Loop**
Replay is not an afterthought—it is a core primitive. A single live run
seeds an offline corpus that supports: repeated playback, model
substitution, tool result mocking, and strategy comparison. The harness
graduates from "executor" to "continuous evaluation platform" where
failed production traces convert directly into offline regression
suites.
3. **Operational Observability**
Beyond raw traces, expose metrics that prove stability over time:
- Tool success / failure rates
- Approval latency distributions
- Retry frequencies
- Checkpoint restore reliability
- Memory retrieval quality
- Cost per completed task
- Fork replay pass rates
The underlying thesis: the bottleneck for most agent systems is not
execution capability, but the inability to **demonstrate continuous,
measurable improvement**.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
Closes#15483.
Default workflow/session agent completions to non-streaming when
`stream` is omitted.
## Changes
- `api/apps/restful_apis/agent_api.py`: `req.get("stream", False)` on
workflow paths.
## Test plan
- [ ] POST workflow completion without `stream`; assert JSON response.
Ports remaining Go parser wiring and PDF backends, adds tenant-aware VLM
dispatch, aligns post-processing with Python, and adds end-to-end
pipeline coverage with a generated six-page PDF.
### Summary
Keep `data` as the uploaded document array when dataset document upload
partially succeeds.
This matches the Python API behavior and allows parse-on-creation to run
for successfully uploaded files when other files in the same folder are
unsupported.
## Summary
- Add Go dynamic input form support for ExeSQL and Browser components.
- Align their input form metadata with the Python implementation.
- Add regression tests for `/components/:component_id/input-form`.
## Summary
Debugging YahooFinance component in agent canvas returns "unknown
component" and "no input_form".
YahooFinance was only registered as an eino tool, not as a runtime
component. The component factory only searches the runtime registry.
- `universe_a_wrappers.go`: add `yahooFinanceComponent` wrapper
delegating to `agenttool.YahooFinanceTool` with `GetInputForm()`
- `fixture_stubs.go`: register `"YahooFinance"` component
## TEST
`go build` and `go test ./internal/agent/component/...` all pass.
## What this fixes
Closes#16400.
`get_data_openai()` currently returns `created: null` when callers do
not pass a timestamp, and it replaces explicit timestamp values with the
current time. This makes non-streaming OpenAI-compatible responses
inconsistent with the expected integer `created` timestamp field.
## Change
- Preserve explicit `created` values when provided.
- Default non-streaming responses to `int(time.time())` when `created`
is not provided.
- Add focused unit coverage for default timestamps, explicit timestamps,
and unchanged streaming chunk shape.
## Verification
- `./.venv/bin/python -m pytest
test/unit_test/api/utils/test_api_utils.py -q`
- `python3 -m py_compile api/utils/api_utils.py
test/unit_test/api/utils/test_api_utils.py`
- `uvx ruff check api/utils/api_utils.py
test/unit_test/api/utils/test_api_utils.py`
---------
Co-authored-by: Harsh Kashyap <harshkashyap@Harshs-MacBook-Pro.local>
### What problem does this PR solve?
The Go chunk pipeline's `PostprocessOperator` `filter` stage
(`internal/ingestion/chunk/postprocess.go`) only filtered by length
(`min_length`/`max_length`). It could not drop empty/whitespace-only
chunks or duplicate chunks — both standard RAG post-processing steps
(blank chunks shouldn't be indexed; identical chunks waste embedding
compute and add redundant retrieval results).
This adds two optional, default-off booleans to the `filter` config:
- `drop_empty` — drop chunks whose content is empty or whitespace-only.
- `drop_duplicates` — drop chunks whose exact content already appeared
(order-preserving; the first occurrence is kept).
They compose with the existing length bounds and are reflected in
`String()` for plan explainability. Also adds the first unit tests for
the postprocess filter (length bounds, drop_empty, drop_duplicates,
combined, exact-content matching, and config parsing).
Validation: `gofmt` clean, `go vet ./internal/ingestion/chunk/` clean,
`go build` ok, `go test ./internal/ingestion/chunk/` — all tests pass.
Closes#16048
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Ling Qin <qinling0210@163.com>
