feat: support web search for zhipu via web_search_options#4516
Open
feitianbubu wants to merge 1 commit intoQuantumNous:mainfrom
Open
feat: support web search for zhipu via web_search_options#4516feitianbubu wants to merge 1 commit intoQuantumNous:mainfrom
feitianbubu wants to merge 1 commit intoQuantumNous:mainfrom
Conversation
Contributor
WalkthroughThe changes add web search capability to the Zhipu API adapter by introducing a post-processing step in the OpenAI request conversion. A new helper function injects web search parameters into the Zhipu request payload when web search options are provided. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
relay/channel/zhipu_4v/relay-zhipu_v4.go (1)
71-76: Normalizesearch_context_sizebefore switching.Current matching is case-sensitive;
"Low"/"HIGH"silently miss the intended mapping. Normalizing input makes behavior more robust without changing semantics.Proposed refactor
- switch opts.SearchContextSize { + switch strings.ToLower(strings.TrimSpace(opts.SearchContextSize)) { case "low": ws["count"] = 5 case "high": ws["count"] = 15 ws["content_size"] = "high" }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@relay/channel/zhipu_4v/relay-zhipu_v4.go` around lines 71 - 76, Normalize opts.SearchContextSize before the switch so casing doesn't change behavior: convert opts.SearchContextSize to a canonical form (e.g., strings.ToLower/strings.ToLower(strings.TrimSpace(...))) and switch on that normalized value in the block that sets ws["count"] and ws["content_size"] (referencing opts.SearchContextSize, ws["count"], and ws["content_size"] to locate the code).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@relay/channel/zhipu_4v/relay-zhipu_v4.go`:
- Around line 78-80: The current code unconditionally appends a new web_search
tool to m["tools"], causing duplicates; instead, convert m["tools"] to a []any
(as done with tools), iterate its elements (expect map[string]any or
map[any]any), and if an element's "type" == "web_search" update that element's
"web_search" field with ws and set a flag; after the loop, if no existing
web_search was found append the new
map[string]any{"type":"web_search","web_search":ws}; finally assign the modified
slice back to m["tools"] (references: req.ToMap(), m, tools, "web_search").
---
Nitpick comments:
In `@relay/channel/zhipu_4v/relay-zhipu_v4.go`:
- Around line 71-76: Normalize opts.SearchContextSize before the switch so
casing doesn't change behavior: convert opts.SearchContextSize to a canonical
form (e.g., strings.ToLower/strings.ToLower(strings.TrimSpace(...))) and switch
on that normalized value in the block that sets ws["count"] and
ws["content_size"] (referencing opts.SearchContextSize, ws["count"], and
ws["content_size"] to locate the code).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 74be54c5-92e8-4b8c-baab-ea5d5e113fec
📒 Files selected for processing (2)
relay/channel/zhipu_4v/adaptor.gorelay/channel/zhipu_4v/relay-zhipu_v4.go
Comment on lines
+78
to
+80
| m := req.ToMap() | ||
| tools, _ := m["tools"].([]any) | ||
| m["tools"] = append(tools, map[string]any{"type": "web_search", "web_search": ws}) |
Contributor
There was a problem hiding this comment.
Avoid duplicating web_search tools in payload.
If tools already contains a type: "web_search" entry, this logic appends another one instead of updating it, which can produce an invalid/ambiguous upstream request.
Proposed fix
m := req.ToMap()
- tools, _ := m["tools"].([]any)
- m["tools"] = append(tools, map[string]any{"type": "web_search", "web_search": ws})
+ tools, _ := m["tools"].([]any)
+ updated := false
+ for i, t := range tools {
+ tool, ok := t.(map[string]any)
+ if !ok {
+ continue
+ }
+ if typ, _ := tool["type"].(string); typ == "web_search" {
+ tool["web_search"] = ws
+ tools[i] = tool
+ updated = true
+ break
+ }
+ }
+ if !updated {
+ tools = append(tools, map[string]any{"type": "web_search", "web_search": ws})
+ }
+ m["tools"] = tools
return m📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| m := req.ToMap() | |
| tools, _ := m["tools"].([]any) | |
| m["tools"] = append(tools, map[string]any{"type": "web_search", "web_search": ws}) | |
| m := req.ToMap() | |
| tools, _ := m["tools"].([]any) | |
| updated := false | |
| for i, t := range tools { | |
| tool, ok := t.(map[string]any) | |
| if !ok { | |
| continue | |
| } | |
| if typ, _ := tool["type"].(string); typ == "web_search" { | |
| tool["web_search"] = ws | |
| tools[i] = tool | |
| updated = true | |
| break | |
| } | |
| } | |
| if !updated { | |
| tools = append(tools, map[string]any{"type": "web_search", "web_search": ws}) | |
| } | |
| m["tools"] = tools |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@relay/channel/zhipu_4v/relay-zhipu_v4.go` around lines 78 - 80, The current
code unconditionally appends a new web_search tool to m["tools"], causing
duplicates; instead, convert m["tools"] to a []any (as done with tools), iterate
its elements (expect map[string]any or map[any]any), and if an element's "type"
== "web_search" update that element's "web_search" field with ws and set a flag;
after the loop, if no existing web_search was found append the new
map[string]any{"type":"web_search","web_search":ws}; finally assign the modified
slice back to m["tools"] (references: req.ToMap(), m, tools, "web_search").
Member
|
这个适配新版的函数计费不 |
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.
增加智谱官方支持的web search功能
📝 变更描述 / Description
智谱的web search 与 OpenAI的格式不兼容
https://docs.z.ai/api-reference/llm/chat-completion因此要进行转换
🚀 变更类型 / Type of change
将OpenAI标准的web search格式
转换为智谱的格式
📸 运行证明 / Proof of Work
请求:
返回:
Summary by CodeRabbit