feat(adk): add EnhancedRead with custom FileContentPart types#973
Open
feat(adk): add EnhancedRead with custom FileContentPart types#973
Conversation
Contributor
JonXSnow
commented
Apr 16, 2026
JonXSnow
commented
- Define FileContentPartType, FileContentPart in filesystem package to replace direct schema.ToolOutputPart dependency, supporting only Image (bytes) and File (bytes) types
- Add EnhancedReader interface and Pages field to ReadRequest
- Add enhancedReadFileArgs extending readFileArgs with PDF pages param
- Convert FileContentPart to schema.ToolOutputPart with base64 encoding in middleware layer
- Add EnhancedInvokable support to large tool result offloading
- Add textOnlyContent helper for multimodal result detection
- Add enhanced read file tool description suffix (EN/CN)
- Add tests for image, file, unsupported type, pages passthrough
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## alpha/09 #973 +/- ##
===========================================
Coverage ? 82.38%
===========================================
Files ? 162
Lines ? 20698
Branches ? 0
===========================================
Hits ? 17052
Misses ? 2444
Partials ? 1202 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
JonXSnow
force-pushed
the
feat/enhancedread
branch
2 times, most recently
from
4f972fe to
1e81be8
Compare
- Define FileContentPartType, FileContentPart in filesystem package to replace direct schema.ToolOutputPart dependency, supporting only Image (bytes) and File (bytes) types - Add EnhancedReader interface and Pages field to ReadRequest - Add enhancedReadFileArgs extending readFileArgs with PDF pages param - Convert FileContentPart to schema.ToolOutputPart with base64 encoding in middleware layer - Add EnhancedInvokable support to large tool result offloading - Add textOnlyContent helper for multimodal result detection - Add enhanced read file tool description suffix (EN/CN) - Add tests for image, file, unsupported type, pages passthrough
JonXSnow
force-pushed
the
feat/enhancedread
branch
from
1e81be8 to
471bc2a
Compare
| // EnhancedReader is an optional extension interface for Backend. | ||
| // Backends that implement this interface support multimodal file reading | ||
| // (e.g. returning images as base64 image parts). | ||
| type EnhancedReader interface { |
Contributor
There was a problem hiding this comment.
MultiModalReader 会更好吗？EnhancedTool 的定位是最终会替换掉第一版的 Tool。这个 EnhancedReader 的定位也是最终会替换掉之前的 Reader 吗？
| } | ||
| } | ||
|
|
||
| func (t *toolResultOffloading) enhancedInvoke(endpoint compose.EnhancedInvokableToolEndpoint) compose.EnhancedInvokableToolEndpoint { |
Contributor
There was a problem hiding this comment.
enhancedStream 怎么处理
| default: | ||
| // FileContentPartType is defined by Backend implementations. | ||
| // Unrecognized types are unlikely but should fail explicitly rather than silently. | ||
| return nil, fmt.Errorf("unsupported FileContentPartType: %s", p.Type) |
Contributor
There was a problem hiding this comment.
需要支持 'Backend Implementation' 自定义 FileContentPartType 吗
| merged = make(map[string]any, len(p.Extra)) | ||
| } | ||
| for k, v := range p.Extra { | ||
| merged[k] = v |
Contributor
There was a problem hiding this comment.
mergeExtra 这个要复用那个 RegisterCustomMergeFunc 之类的吗？这里是 key 冲突直接覆盖，可能打破用户预期
| } | ||
|
|
||
| // Multimodal result: convert FileContentPart to ToolOutputPart | ||
| if len(fileCt.Parts) > 0 { |
Contributor
There was a problem hiding this comment.
fileCt 可能是 nil，需要防御
| if p.MIMEType == "" { | ||
| return nil, fmt.Errorf("FileContentPart.MIMEType is empty for type %s", p.Type) | ||
| } | ||
| b64 := base64.StdEncoding.EncodeToString(p.Data) |
Contributor
There was a problem hiding this comment.
var sb strings.Builder
sb.Grow(base64.StdEncoding.EncodedLen(len(p.Data)))
enc := base64.NewEncoder(base64.StdEncoding, &sb)
enc.Write(p.Data)
enc.Close()
b64 := sb.String()
考虑换成这个
| // EnhancedReader is an optional extension interface for Backend. | ||
| // Backends that implement this interface support multimodal file reading | ||
| // (e.g. returning images as base64 image parts). | ||
| type EnhancedReader interface { |
Contributor
There was a problem hiding this comment.
注释加一下：EnhancedReader implementation 需要实现自己的文件最大 size 限制
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.