2025-08-05 07:08:07 +00:00
// Code generated by protoc-gen-go. DO NOT EDIT.
// versions:
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
// protoc-gen-go v1.36.6
// protoc v6.33.4
2025-08-05 07:08:07 +00:00
// source: docreader.proto
package proto
import (
protoreflect "google.golang.org/protobuf/reflect/protoreflect"
protoimpl "google.golang.org/protobuf/runtime/protoimpl"
reflect "reflect"
sync "sync"
unsafe "unsafe"
)
const (
// Verify that this generated code is sufficiently up-to-date.
_ = protoimpl . EnforceVersion ( 20 - protoimpl . MinVersion )
// Verify that runtime/protoimpl is sufficiently up-to-date.
_ = protoimpl . EnforceVersion ( protoimpl . MaxVersion - 20 )
)
2026-02-28 05:22:07 +00:00
type ReadConfig struct {
state protoimpl . MessageState ` protogen:"open.v1" `
ParserEngine string ` protobuf:"bytes,1,opt,name=parser_engine,json=parserEngine,proto3" json:"parser_engine,omitempty" `
ParserEngineOverrides map [ string ] string ` protobuf:"bytes,2,rep,name=parser_engine_overrides,json=parserEngineOverrides,proto3" json:"parser_engine_overrides,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value" `
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
2025-08-13 13:56:20 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadConfig ) Reset ( ) {
* x = ReadConfig { }
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 0 ]
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ReadConfig ) String ( ) string {
2025-08-10 09:04:39 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ReadConfig ) ProtoMessage ( ) { }
2025-08-10 09:04:39 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ReadConfig ) ProtoReflect ( ) protoreflect . Message {
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 0 ]
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ReadConfig.ProtoReflect.Descriptor instead.
func ( * ReadConfig ) Descriptor ( ) ( [ ] byte , [ ] int ) {
2025-08-10 09:04:39 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 0 }
}
2026-02-28 05:22:07 +00:00
func ( x * ReadConfig ) GetParserEngine ( ) string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ParserEngine
2025-08-10 09:04:39 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadConfig ) GetParserEngineOverrides ( ) map [ string ] string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ParserEngineOverrides
2025-08-10 09:04:39 +00:00
}
2026-02-28 05:22:07 +00:00
return nil
2025-08-10 09:04:39 +00:00
}
2026-02-28 05:22:07 +00:00
// Unified read request: set file_content for file mode, url for URL mode.
type ReadRequest struct {
2025-08-10 09:04:39 +00:00
state protoimpl . MessageState ` protogen:"open.v1" `
2026-02-28 05:22:07 +00:00
FileContent [ ] byte ` protobuf:"bytes,1,opt,name=file_content,json=fileContent,proto3" json:"file_content,omitempty" `
FileName string ` protobuf:"bytes,2,opt,name=file_name,json=fileName,proto3" json:"file_name,omitempty" `
FileType string ` protobuf:"bytes,3,opt,name=file_type,json=fileType,proto3" json:"file_type,omitempty" `
Url string ` protobuf:"bytes,4,opt,name=url,proto3" json:"url,omitempty" `
Title string ` protobuf:"bytes,5,opt,name=title,proto3" json:"title,omitempty" `
Config * ReadConfig ` protobuf:"bytes,6,opt,name=config,proto3" json:"config,omitempty" `
RequestId string ` protobuf:"bytes,7,opt,name=request_id,json=requestId,proto3" json:"request_id,omitempty" `
2025-08-10 09:04:39 +00:00
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) Reset ( ) {
* x = ReadRequest { }
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 1 ]
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) String ( ) string {
2025-08-10 09:04:39 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ReadRequest ) ProtoMessage ( ) { }
2025-08-10 09:04:39 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) ProtoReflect ( ) protoreflect . Message {
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 1 ]
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ReadRequest.ProtoReflect.Descriptor instead.
func ( * ReadRequest ) Descriptor ( ) ( [ ] byte , [ ] int ) {
2025-08-10 09:04:39 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 1 }
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetFileContent ( ) [ ] byte {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . FileContent
}
return nil
}
func ( x * ReadRequest ) GetFileName ( ) string {
if x != nil {
return x . FileName
2025-08-10 09:04:39 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetFileType ( ) string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . FileType
2025-08-10 09:04:39 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetUrl ( ) string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Url
2025-08-10 09:04:39 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetTitle ( ) string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Title
2025-08-10 09:04:39 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetConfig ( ) * ReadConfig {
if x != nil {
return x . Config
}
return nil
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadRequest ) GetRequestId ( ) string {
if x != nil {
return x . RequestId
}
return ""
}
type ImageRef struct {
state protoimpl . MessageState ` protogen:"open.v1" `
Filename string ` protobuf:"bytes,1,opt,name=filename,proto3" json:"filename,omitempty" `
OriginalRef string ` protobuf:"bytes,2,opt,name=original_ref,json=originalRef,proto3" json:"original_ref,omitempty" `
MimeType string ` protobuf:"bytes,3,opt,name=mime_type,json=mimeType,proto3" json:"mime_type,omitempty" `
StorageKey string ` protobuf:"bytes,4,opt,name=storage_key,json=storageKey,proto3" json:"storage_key,omitempty" ` // download URL from shared storage
ImageData [ ] byte ` protobuf:"bytes,5,opt,name=image_data,json=imageData,proto3" json:"image_data,omitempty" ` // inline bytes fallback
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
func ( x * ImageRef ) Reset ( ) {
* x = ImageRef { }
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 2 ]
2025-08-05 07:08:07 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) String ( ) string {
2025-08-05 07:08:07 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ImageRef ) ProtoMessage ( ) { }
2025-08-05 07:08:07 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) ProtoReflect ( ) protoreflect . Message {
2025-08-10 09:04:39 +00:00
mi := & file_docreader_proto_msgTypes [ 2 ]
2025-08-05 07:08:07 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ImageRef.ProtoReflect.Descriptor instead.
func ( * ImageRef ) Descriptor ( ) ( [ ] byte , [ ] int ) {
2025-08-10 09:04:39 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 2 }
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) GetFilename ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Filename
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) GetOriginalRef ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . OriginalRef
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) GetMimeType ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . MimeType
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) GetStorageKey ( ) string {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . StorageKey
2025-08-10 09:04:39 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-10 09:04:39 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ImageRef ) GetImageData ( ) [ ] byte {
2025-08-10 09:04:39 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ImageData
2025-08-10 09:04:39 +00:00
}
return nil
}
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
// SourceBlock ties a range of markdown_content to the place in the original
// file it was parsed from, so a citation can open the file there.
type SourceBlock struct {
state protoimpl . MessageState ` protogen:"open.v1" `
// Unicode code point offsets into markdown_content, end exclusive.
Start uint32 ` protobuf:"varint,1,opt,name=start,proto3" json:"start,omitempty" `
End uint32 ` protobuf:"varint,2,opt,name=end,proto3" json:"end,omitempty" `
// JSON-encoded locator: {"type":"pdf","page":3,"bbox":[x0,y0,x1,y1]}
// with ordinals 1-based and bbox as fractions of the page, origin top-left.
LocatorJson string ` protobuf:"bytes,3,opt,name=locator_json,json=locatorJson,proto3" json:"locator_json,omitempty" `
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
func ( x * SourceBlock ) Reset ( ) {
* x = SourceBlock { }
mi := & file_docreader_proto_msgTypes [ 3 ]
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
func ( x * SourceBlock ) String ( ) string {
return protoimpl . X . MessageStringOf ( x )
}
func ( * SourceBlock ) ProtoMessage ( ) { }
func ( x * SourceBlock ) ProtoReflect ( ) protoreflect . Message {
mi := & file_docreader_proto_msgTypes [ 3 ]
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
// Deprecated: Use SourceBlock.ProtoReflect.Descriptor instead.
func ( * SourceBlock ) Descriptor ( ) ( [ ] byte , [ ] int ) {
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 3 }
}
func ( x * SourceBlock ) GetStart ( ) uint32 {
if x != nil {
return x . Start
}
return 0
}
func ( x * SourceBlock ) GetEnd ( ) uint32 {
if x != nil {
return x . End
}
return 0
}
func ( x * SourceBlock ) GetLocatorJson ( ) string {
if x != nil {
return x . LocatorJson
}
return ""
}
2026-02-28 05:22:07 +00:00
type ReadResponse struct {
state protoimpl . MessageState ` protogen:"open.v1" `
MarkdownContent string ` protobuf:"bytes,1,opt,name=markdown_content,json=markdownContent,proto3" json:"markdown_content,omitempty" `
ImageRefs [ ] * ImageRef ` protobuf:"bytes,2,rep,name=image_refs,json=imageRefs,proto3" json:"image_refs,omitempty" `
ImageDirPath string ` protobuf:"bytes,3,opt,name=image_dir_path,json=imageDirPath,proto3" json:"image_dir_path,omitempty" `
Metadata map [ string ] string ` protobuf:"bytes,4,rep,name=metadata,proto3" json:"metadata,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value" `
Error string ` protobuf:"bytes,5,opt,name=error,proto3" json:"error,omitempty" `
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
SourceBlocks [ ] * SourceBlock ` protobuf:"bytes,6,rep,name=source_blocks,json=sourceBlocks,proto3" json:"source_blocks,omitempty" `
2026-02-28 05:22:07 +00:00
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) Reset ( ) {
* x = ReadResponse { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 4 ]
2025-08-05 07:08:07 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) String ( ) string {
2025-08-05 07:08:07 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ReadResponse ) ProtoMessage ( ) { }
2025-08-05 07:08:07 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 4 ]
2025-08-05 07:08:07 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ReadResponse.ProtoReflect.Descriptor instead.
func ( * ReadResponse ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 4 }
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) GetMarkdownContent ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . MarkdownContent
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) GetImageRefs ( ) [ ] * ImageRef {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ImageRefs
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return nil
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) GetImageDirPath ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ImageDirPath
2025-08-05 07:08:07 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) GetMetadata ( ) map [ string ] string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Metadata
2025-08-05 07:08:07 +00:00
}
return nil
}
2026-02-28 05:22:07 +00:00
func ( x * ReadResponse ) GetError ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Error
2025-08-05 07:08:07 +00:00
}
return ""
}
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
func ( x * ReadResponse ) GetSourceBlocks ( ) [ ] * SourceBlock {
if x != nil {
return x . SourceBlocks
}
return nil
}
2026-06-02 01:50:09 +00:00
// Metadata header for a streamed read. Sent exactly once, before any image.
type ReadStreamMeta struct {
state protoimpl . MessageState ` protogen:"open.v1" `
MarkdownContent string ` protobuf:"bytes,1,opt,name=markdown_content,json=markdownContent,proto3" json:"markdown_content,omitempty" `
ImageDirPath string ` protobuf:"bytes,2,opt,name=image_dir_path,json=imageDirPath,proto3" json:"image_dir_path,omitempty" `
Metadata map [ string ] string ` protobuf:"bytes,3,rep,name=metadata,proto3" json:"metadata,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value" `
Error string ` protobuf:"bytes,4,opt,name=error,proto3" json:"error,omitempty" `
ImageCount uint32 ` protobuf:"varint,5,opt,name=image_count,json=imageCount,proto3" json:"image_count,omitempty" ` // best-effort total image count (0 if unknown)
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
SourceBlocks [ ] * SourceBlock ` protobuf:"bytes,6,rep,name=source_blocks,json=sourceBlocks,proto3" json:"source_blocks,omitempty" `
2026-06-02 01:50:09 +00:00
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
func ( x * ReadStreamMeta ) Reset ( ) {
* x = ReadStreamMeta { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 5 ]
2026-06-02 01:50:09 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
func ( x * ReadStreamMeta ) String ( ) string {
return protoimpl . X . MessageStringOf ( x )
}
func ( * ReadStreamMeta ) ProtoMessage ( ) { }
func ( x * ReadStreamMeta ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 5 ]
2026-06-02 01:50:09 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
// Deprecated: Use ReadStreamMeta.ProtoReflect.Descriptor instead.
func ( * ReadStreamMeta ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 5 }
2026-06-02 01:50:09 +00:00
}
func ( x * ReadStreamMeta ) GetMarkdownContent ( ) string {
if x != nil {
return x . MarkdownContent
}
return ""
}
func ( x * ReadStreamMeta ) GetImageDirPath ( ) string {
if x != nil {
return x . ImageDirPath
}
return ""
}
func ( x * ReadStreamMeta ) GetMetadata ( ) map [ string ] string {
if x != nil {
return x . Metadata
}
return nil
}
func ( x * ReadStreamMeta ) GetError ( ) string {
if x != nil {
return x . Error
}
return ""
}
func ( x * ReadStreamMeta ) GetImageCount ( ) uint32 {
if x != nil {
return x . ImageCount
}
return 0
}
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
func ( x * ReadStreamMeta ) GetSourceBlocks ( ) [ ] * SourceBlock {
if x != nil {
return x . SourceBlocks
}
return nil
}
2026-06-02 01:50:09 +00:00
// One frame of a ReadStream. The first frame carries `meta`; every subsequent
// frame carries a single `image`.
type ReadStreamResponse struct {
state protoimpl . MessageState ` protogen:"open.v1" `
// Types that are valid to be assigned to Payload:
//
// *ReadStreamResponse_Meta
// *ReadStreamResponse_Image
Payload isReadStreamResponse_Payload ` protobuf_oneof:"payload" `
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
func ( x * ReadStreamResponse ) Reset ( ) {
* x = ReadStreamResponse { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 6 ]
2026-06-02 01:50:09 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
func ( x * ReadStreamResponse ) String ( ) string {
return protoimpl . X . MessageStringOf ( x )
}
func ( * ReadStreamResponse ) ProtoMessage ( ) { }
func ( x * ReadStreamResponse ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 6 ]
2026-06-02 01:50:09 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
// Deprecated: Use ReadStreamResponse.ProtoReflect.Descriptor instead.
func ( * ReadStreamResponse ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 6 }
2026-06-02 01:50:09 +00:00
}
func ( x * ReadStreamResponse ) GetPayload ( ) isReadStreamResponse_Payload {
if x != nil {
return x . Payload
}
return nil
}
func ( x * ReadStreamResponse ) GetMeta ( ) * ReadStreamMeta {
if x != nil {
if x , ok := x . Payload . ( * ReadStreamResponse_Meta ) ; ok {
return x . Meta
}
}
return nil
}
func ( x * ReadStreamResponse ) GetImage ( ) * ImageRef {
if x != nil {
if x , ok := x . Payload . ( * ReadStreamResponse_Image ) ; ok {
return x . Image
}
}
return nil
}
type isReadStreamResponse_Payload interface {
isReadStreamResponse_Payload ( )
}
type ReadStreamResponse_Meta struct {
Meta * ReadStreamMeta ` protobuf:"bytes,1,opt,name=meta,proto3,oneof" `
}
type ReadStreamResponse_Image struct {
Image * ImageRef ` protobuf:"bytes,2,opt,name=image,proto3,oneof" `
}
func ( * ReadStreamResponse_Meta ) isReadStreamResponse_Payload ( ) { }
func ( * ReadStreamResponse_Image ) isReadStreamResponse_Payload ( ) { }
2026-02-28 05:22:07 +00:00
type ListEnginesRequest struct {
state protoimpl . MessageState ` protogen:"open.v1" `
ConfigOverrides map [ string ] string ` protobuf:"bytes,1,rep,name=config_overrides,json=configOverrides,proto3" json:"config_overrides,omitempty" protobuf_key:"bytes,1,opt,name=key" protobuf_val:"bytes,2,opt,name=value" `
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesRequest ) Reset ( ) {
* x = ListEnginesRequest { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 7 ]
2025-08-05 07:08:07 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesRequest ) String ( ) string {
2025-08-05 07:08:07 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ListEnginesRequest ) ProtoMessage ( ) { }
2025-08-05 07:08:07 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesRequest ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 7 ]
2025-08-05 07:08:07 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ListEnginesRequest.ProtoReflect.Descriptor instead.
func ( * ListEnginesRequest ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 7 }
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesRequest ) GetConfigOverrides ( ) map [ string ] string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . ConfigOverrides
2025-08-05 07:08:07 +00:00
}
return nil
}
2026-02-28 05:22:07 +00:00
type ParserEngineInfo struct {
state protoimpl . MessageState ` protogen:"open.v1" `
Name string ` protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty" `
Description string ` protobuf:"bytes,2,opt,name=description,proto3" json:"description,omitempty" `
FileTypes [ ] string ` protobuf:"bytes,3,rep,name=file_types,json=fileTypes,proto3" json:"file_types,omitempty" `
Available bool ` protobuf:"varint,4,opt,name=available,proto3" json:"available,omitempty" `
UnavailableReason string ` protobuf:"bytes,5,opt,name=unavailable_reason,json=unavailableReason,proto3" json:"unavailable_reason,omitempty" `
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) Reset ( ) {
* x = ParserEngineInfo { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 8 ]
2025-08-05 07:08:07 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) String ( ) string {
2025-08-05 07:08:07 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ParserEngineInfo ) ProtoMessage ( ) { }
2025-08-05 07:08:07 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 8 ]
2025-08-05 07:08:07 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ParserEngineInfo.ProtoReflect.Descriptor instead.
func ( * ParserEngineInfo ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 8 }
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) GetName ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Name
2025-08-05 07:08:07 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) GetDescription ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Description
2025-08-05 07:08:07 +00:00
}
return ""
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) GetFileTypes ( ) [ ] string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . FileTypes
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return nil
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) GetAvailable ( ) bool {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Available
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return false
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ParserEngineInfo ) GetUnavailableReason ( ) string {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . UnavailableReason
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return ""
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
type ListEnginesResponse struct {
2025-08-05 07:08:07 +00:00
state protoimpl . MessageState ` protogen:"open.v1" `
2026-02-28 05:22:07 +00:00
Engines [ ] * ParserEngineInfo ` protobuf:"bytes,1,rep,name=engines,proto3" json:"engines,omitempty" `
2025-08-05 07:08:07 +00:00
unknownFields protoimpl . UnknownFields
sizeCache protoimpl . SizeCache
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesResponse ) Reset ( ) {
* x = ListEnginesResponse { }
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 9 ]
2025-08-05 07:08:07 +00:00
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
ms . StoreMessageInfo ( mi )
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesResponse ) String ( ) string {
2025-08-05 07:08:07 +00:00
return protoimpl . X . MessageStringOf ( x )
}
2026-02-28 05:22:07 +00:00
func ( * ListEnginesResponse ) ProtoMessage ( ) { }
2025-08-05 07:08:07 +00:00
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesResponse ) ProtoReflect ( ) protoreflect . Message {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
mi := & file_docreader_proto_msgTypes [ 9 ]
2025-08-05 07:08:07 +00:00
if x != nil {
ms := protoimpl . X . MessageStateOf ( protoimpl . Pointer ( x ) )
if ms . LoadMessageInfo ( ) == nil {
ms . StoreMessageInfo ( mi )
}
return ms
}
return mi . MessageOf ( x )
}
2026-02-28 05:22:07 +00:00
// Deprecated: Use ListEnginesResponse.ProtoReflect.Descriptor instead.
func ( * ListEnginesResponse ) Descriptor ( ) ( [ ] byte , [ ] int ) {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
return file_docreader_proto_rawDescGZIP ( ) , [ ] int { 9 }
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
func ( x * ListEnginesResponse ) GetEngines ( ) [ ] * ParserEngineInfo {
2025-08-05 07:08:07 +00:00
if x != nil {
2026-02-28 05:22:07 +00:00
return x . Engines
2025-08-05 07:08:07 +00:00
}
2026-02-28 05:22:07 +00:00
return nil
}
2025-08-05 07:08:07 +00:00
var File_docreader_proto protoreflect . FileDescriptor
const file_docreader_proto_rawDesc = "" +
"\n" +
2026-03-03 13:30:27 +00:00
"\x0fdocreader.proto\x12\tdocreader\"\xeb\x01\n" +
2025-08-10 09:04:39 +00:00
"\n" +
2026-02-28 05:22:07 +00:00
"ReadConfig\x12#\n" +
"\rparser_engine\x18\x01 \x01(\tR\fparserEngine\x12h\n" +
2026-03-03 13:30:27 +00:00
"\x17parser_engine_overrides\x18\x02 \x03(\v20.docreader.ReadConfig.ParserEngineOverridesEntryR\x15parserEngineOverrides\x1aH\n" +
2026-02-28 05:22:07 +00:00
"\x1aParserEngineOverridesEntry\x12\x10\n" +
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
2026-03-03 13:30:27 +00:00
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01J\x04\b\x03\x10\x04\"\xe0\x01\n" +
2026-02-28 05:22:07 +00:00
"\vReadRequest\x12!\n" +
"\ffile_content\x18\x01 \x01(\fR\vfileContent\x12\x1b\n" +
"\tfile_name\x18\x02 \x01(\tR\bfileName\x12\x1b\n" +
"\tfile_type\x18\x03 \x01(\tR\bfileType\x12\x10\n" +
"\x03url\x18\x04 \x01(\tR\x03url\x12\x14\n" +
"\x05title\x18\x05 \x01(\tR\x05title\x12-\n" +
"\x06config\x18\x06 \x01(\v2\x15.docreader.ReadConfigR\x06config\x12\x1d\n" +
2025-08-05 07:08:07 +00:00
"\n" +
2026-02-28 05:22:07 +00:00
"request_id\x18\a \x01(\tR\trequestId\"\xa6\x01\n" +
"\bImageRef\x12\x1a\n" +
"\bfilename\x18\x01 \x01(\tR\bfilename\x12!\n" +
"\foriginal_ref\x18\x02 \x01(\tR\voriginalRef\x12\x1b\n" +
"\tmime_type\x18\x03 \x01(\tR\bmimeType\x12\x1f\n" +
"\vstorage_key\x18\x04 \x01(\tR\n" +
"storageKey\x12\x1d\n" +
2025-08-05 07:08:07 +00:00
"\n" +
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
"image_data\x18\x05 \x01(\fR\timageData\"X\n" +
"\vSourceBlock\x12\x14\n" +
"\x05start\x18\x01 \x01(\rR\x05start\x12\x10\n" +
"\x03end\x18\x02 \x01(\rR\x03end\x12!\n" +
"\flocator_json\x18\x03 \x01(\tR\vlocatorJson\"\xe6\x02\n" +
2026-02-28 05:22:07 +00:00
"\fReadResponse\x12)\n" +
"\x10markdown_content\x18\x01 \x01(\tR\x0fmarkdownContent\x122\n" +
2025-08-05 07:08:07 +00:00
"\n" +
2026-02-28 05:22:07 +00:00
"image_refs\x18\x02 \x03(\v2\x13.docreader.ImageRefR\timageRefs\x12$\n" +
"\x0eimage_dir_path\x18\x03 \x01(\tR\fimageDirPath\x12A\n" +
"\bmetadata\x18\x04 \x03(\v2%.docreader.ReadResponse.MetadataEntryR\bmetadata\x12\x14\n" +
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
"\x05error\x18\x05 \x01(\tR\x05error\x12;\n" +
"\rsource_blocks\x18\x06 \x03(\v2\x16.docreader.SourceBlockR\fsourceBlocks\x1a;\n" +
2026-02-28 05:22:07 +00:00
"\rMetadataEntry\x12\x10\n" +
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\"\xd7\x02\n" +
2026-06-02 01:50:09 +00:00
"\x0eReadStreamMeta\x12)\n" +
"\x10markdown_content\x18\x01 \x01(\tR\x0fmarkdownContent\x12$\n" +
"\x0eimage_dir_path\x18\x02 \x01(\tR\fimageDirPath\x12C\n" +
"\bmetadata\x18\x03 \x03(\v2'.docreader.ReadStreamMeta.MetadataEntryR\bmetadata\x12\x14\n" +
"\x05error\x18\x04 \x01(\tR\x05error\x12\x1f\n" +
"\vimage_count\x18\x05 \x01(\rR\n" +
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
"imageCount\x12;\n" +
"\rsource_blocks\x18\x06 \x03(\v2\x16.docreader.SourceBlockR\fsourceBlocks\x1a;\n" +
2026-06-02 01:50:09 +00:00
"\rMetadataEntry\x12\x10\n" +
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\"}\n" +
"\x12ReadStreamResponse\x12/\n" +
"\x04meta\x18\x01 \x01(\v2\x19.docreader.ReadStreamMetaH\x00R\x04meta\x12+\n" +
"\x05image\x18\x02 \x01(\v2\x13.docreader.ImageRefH\x00R\x05imageB\t\n" +
"\apayload\"\xb7\x01\n" +
2026-02-28 05:22:07 +00:00
"\x12ListEnginesRequest\x12]\n" +
"\x10config_overrides\x18\x01 \x03(\v22.docreader.ListEnginesRequest.ConfigOverridesEntryR\x0fconfigOverrides\x1aB\n" +
"\x14ConfigOverridesEntry\x12\x10\n" +
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\"\xb4\x01\n" +
"\x10ParserEngineInfo\x12\x12\n" +
"\x04name\x18\x01 \x01(\tR\x04name\x12 \n" +
"\vdescription\x18\x02 \x01(\tR\vdescription\x12\x1d\n" +
2025-08-10 09:04:39 +00:00
"\n" +
2026-02-28 05:22:07 +00:00
"file_types\x18\x03 \x03(\tR\tfileTypes\x12\x1c\n" +
"\tavailable\x18\x04 \x01(\bR\tavailable\x12-\n" +
"\x12unavailable_reason\x18\x05 \x01(\tR\x11unavailableReason\"L\n" +
"\x13ListEnginesResponse\x125\n" +
2026-06-02 01:50:09 +00:00
"\aengines\x18\x01 \x03(\v2\x1b.docreader.ParserEngineInfoR\aengines2\xdf\x01\n" +
2026-02-28 05:22:07 +00:00
"\tDocReader\x129\n" +
2026-06-02 01:50:09 +00:00
"\x04Read\x12\x16.docreader.ReadRequest\x1a\x17.docreader.ReadResponse\"\x00\x12G\n" +
"\n" +
"ReadStream\x12\x16.docreader.ReadRequest\x1a\x1d.docreader.ReadStreamResponse\"\x000\x01\x12N\n" +
2026-03-03 13:30:27 +00:00
"\vListEngines\x12\x1d.docreader.ListEnginesRequest\x1a\x1e.docreader.ListEnginesResponse\"\x00B5Z3github.com/Tencent/WeKnora/internal/docreader/protob\x06proto3"
2025-08-05 07:08:07 +00:00
var (
file_docreader_proto_rawDescOnce sync . Once
file_docreader_proto_rawDescData [ ] byte
)
func file_docreader_proto_rawDescGZIP ( ) [ ] byte {
file_docreader_proto_rawDescOnce . Do ( func ( ) {
file_docreader_proto_rawDescData = protoimpl . X . CompressGZIP ( unsafe . Slice ( unsafe . StringData ( file_docreader_proto_rawDesc ) , len ( file_docreader_proto_rawDesc ) ) )
} )
return file_docreader_proto_rawDescData
}
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
var file_docreader_proto_msgTypes = make ( [ ] protoimpl . MessageInfo , 14 )
2025-08-05 07:08:07 +00:00
var file_docreader_proto_goTypes = [ ] any {
2026-03-03 13:30:27 +00:00
( * ReadConfig ) ( nil ) , // 0: docreader.ReadConfig
( * ReadRequest ) ( nil ) , // 1: docreader.ReadRequest
( * ImageRef ) ( nil ) , // 2: docreader.ImageRef
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
( * SourceBlock ) ( nil ) , // 3: docreader.SourceBlock
( * ReadResponse ) ( nil ) , // 4: docreader.ReadResponse
( * ReadStreamMeta ) ( nil ) , // 5: docreader.ReadStreamMeta
( * ReadStreamResponse ) ( nil ) , // 6: docreader.ReadStreamResponse
( * ListEnginesRequest ) ( nil ) , // 7: docreader.ListEnginesRequest
( * ParserEngineInfo ) ( nil ) , // 8: docreader.ParserEngineInfo
( * ListEnginesResponse ) ( nil ) , // 9: docreader.ListEnginesResponse
nil , // 10: docreader.ReadConfig.ParserEngineOverridesEntry
nil , // 11: docreader.ReadResponse.MetadataEntry
nil , // 12: docreader.ReadStreamMeta.MetadataEntry
nil , // 13: docreader.ListEnginesRequest.ConfigOverridesEntry
2025-08-05 07:08:07 +00:00
}
var file_docreader_proto_depIdxs = [ ] int32 {
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
10 , // 0: docreader.ReadConfig.parser_engine_overrides:type_name -> docreader.ReadConfig.ParserEngineOverridesEntry
2026-06-02 01:50:09 +00:00
0 , // 1: docreader.ReadRequest.config:type_name -> docreader.ReadConfig
2 , // 2: docreader.ReadResponse.image_refs:type_name -> docreader.ImageRef
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
11 , // 3: docreader.ReadResponse.metadata:type_name -> docreader.ReadResponse.MetadataEntry
3 , // 4: docreader.ReadResponse.source_blocks:type_name -> docreader.SourceBlock
12 , // 5: docreader.ReadStreamMeta.metadata:type_name -> docreader.ReadStreamMeta.MetadataEntry
3 , // 6: docreader.ReadStreamMeta.source_blocks:type_name -> docreader.SourceBlock
5 , // 7: docreader.ReadStreamResponse.meta:type_name -> docreader.ReadStreamMeta
2 , // 8: docreader.ReadStreamResponse.image:type_name -> docreader.ImageRef
13 , // 9: docreader.ListEnginesRequest.config_overrides:type_name -> docreader.ListEnginesRequest.ConfigOverridesEntry
8 , // 10: docreader.ListEnginesResponse.engines:type_name -> docreader.ParserEngineInfo
1 , // 11: docreader.DocReader.Read:input_type -> docreader.ReadRequest
1 , // 12: docreader.DocReader.ReadStream:input_type -> docreader.ReadRequest
7 , // 13: docreader.DocReader.ListEngines:input_type -> docreader.ListEnginesRequest
4 , // 14: docreader.DocReader.Read:output_type -> docreader.ReadResponse
6 , // 15: docreader.DocReader.ReadStream:output_type -> docreader.ReadStreamResponse
9 , // 16: docreader.DocReader.ListEngines:output_type -> docreader.ListEnginesResponse
14 , // [14:17] is the sub-list for method output_type
11 , // [11:14] is the sub-list for method input_type
11 , // [11:11] is the sub-list for extension type_name
11 , // [11:11] is the sub-list for extension extendee
0 , // [0:11] is the sub-list for field type_name
2025-08-05 07:08:07 +00:00
}
func init ( ) { file_docreader_proto_init ( ) }
func file_docreader_proto_init ( ) {
if File_docreader_proto != nil {
return
}
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
file_docreader_proto_msgTypes [ 6 ] . OneofWrappers = [ ] any {
2026-06-02 01:50:09 +00:00
( * ReadStreamResponse_Meta ) ( nil ) ,
( * ReadStreamResponse_Image ) ( nil ) ,
}
2025-08-05 07:08:07 +00:00
type x struct { }
out := protoimpl . TypeBuilder {
File : protoimpl . DescBuilder {
GoPackagePath : reflect . TypeOf ( x { } ) . PkgPath ( ) ,
RawDescriptor : unsafe . Slice ( unsafe . StringData ( file_docreader_proto_rawDesc ) , len ( file_docreader_proto_rawDesc ) ) ,
2026-02-28 05:22:07 +00:00
NumEnums : 0 ,
feat(chat): open cited documents at the cited passage (#3700)
* feat(chat): open cited documents at the cited passage
Clicking a citation used to show only the parsed chunk. It now opens the
original file in the references panel, jumps to the cited place and
highlights it, narrowed to the sentence the citation supports.
Parsing records where each chunk sits in the original file
(chunks.source_locators): PDF page and paragraph boxes from the docreader,
MinerU and PaddleOCR-VL layouts; Word paragraphs, slides, sheet rows and
EPUB chapters aligned in Go against any parser engine's Markdown; text
offsets for Markdown/TXT; segment times for audio. Pipeline text rewrites
are followed with a line-diff remapper. Scanned PDF pages get their OCR
text as quotes at search time so a sentence can pick its page.
The frontend renders PDFs with pdf.js and every other previewable type
with the existing preview, then highlights with the CSS Custom Highlight
API in a highlighter yellow that stays visible against the brand green.
* fix(docreader): serialize source blocks outside main so tests import it
test_docx_tables stubs docreader.parser in sys.modules, so importing
docreader.main from a later test failed in the full unittest discover run.
The wire conversion now lives in docreader.source_wire, which needs only
the proto.
* fix(chat): tighten source locators from review
- Remap rewritten-line-for-line stretches by line so scanned PDF pages
no longer drift onto the wrong page.
- Keep the source preview mounted for citations in the file already open.
- Wait for in-flight PDF page renders before looking for the text layer.
- Count image rune offsets in one pass; stream xlsx rows up to maxUnits.
- Start text locators after a UTF-8 BOM, as viewers decode without it.
- Only re-query image children for scanned-page results.
- Seek audio citations without autoplay and drop stale seek listeners.
- Fix the SQLite migration's cross-reference to versioned/000113.
* fix(migrations): renumber chunk source locators after main's chunk_images
main took versioned 000113 and sqlite 000032 for chunk_images, so the
source_locators column moves to versioned 000114 and sqlite 000033.
2026-09-25 05:26:16 +00:00
NumMessages : 14 ,
2025-08-05 07:08:07 +00:00
NumExtensions : 0 ,
NumServices : 1 ,
} ,
GoTypes : file_docreader_proto_goTypes ,
DependencyIndexes : file_docreader_proto_depIdxs ,
MessageInfos : file_docreader_proto_msgTypes ,
} . Build ( )
File_docreader_proto = out . File
file_docreader_proto_goTypes = nil
file_docreader_proto_depIdxs = nil
}