Converge `TokenChunker.delimiter_mode` from three values (`token_size`,
`delimiter`, `one`) to two (`delimiter`, `one`). The unified `delimiter`
mode now carries the old `token_size` semantics: when no active
(backtick) delimiter is present, text/JSON chunks are merged up to
`chunk_token_size`; when a backtick delimiter is present, the text is
split by it and not merged. `one` continues to be handled by the
separate `OneChunker`.
### What problem does this PR solve?
Feat: update templates && add resume template
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
This PR fixes an incorrect variable reference in the Advanced Ingestion
Pipeline template, which causes a runtime failure in the Auto Keywords
stage.
When creating a pipeline using the `advanced ingestion pipeline`
template, the **Auto Keywords** stage fails with the following error:
Can't find variable: 'Splitter:NineTiesSin@chunks'
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: sunsui <suisun@trip.com>
### What does this PR solve?
German translation for all agent template and optimizing line breaks in
the title for the new translation.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
