v2: Initial clean branch with unit tests + CI/CD pipeline

- Started from ac75faa (initial E4B-MarkBase integration) - Kept Sources/ (all engine code) + Package.swift + .gitignore - Removed all ad-hoc tests, documentation, scripts, Python files - Added Tests/00_Unit/ (MathTest, TokenizerTest, SamplerTest) - Added .gitea/workflows/ci.yaml (build + unit tests + lint) - Added Scripts/check_resources.sh (memory-aware test runner) - Added Tests/Manifest.json (resource requirements for all tests) - Focus: 4-bit quantized models only
2026-07-05 13:29:25 +08:00
commit 8a66b9086a
90 changed files with 22252 additions and 0 deletions
@@ -0,0 +1,130 @@
+import Foundation
+
+public enum Gemma4Format {
+    public static func buildChatPrompt(messages: [[String: Any]], tools: [[String: Any]]? = nil) -> String {
+        var prompt = "<bos>"
+
+        if let tools = tools, !tools.isEmpty {
+            let toolDefs = tools.compactMap { t -> String? in
+                guard let fn = t["function"] as? [String: Any],
+                      let name = fn["name"] as? String else { return nil }
+                return name
+            }
+            if !toolDefs.isEmpty {
+                prompt += "<|tool_def|>"
+                for (i, name) in toolDefs.enumerated() {
+                    if i > 0 { prompt += "|" }
+                    prompt += name
+                }
+                prompt += "<|tool_def|>"
+            }
+        }
+
+        for msg in messages {
+            guard let role = msg["role"] as? String else { continue }
+
+            switch role {
+            case "system":
+                prompt += "<|turn|>system\n"
+                if let content = msg["content"] as? String {
+                    prompt += content
+                }
+                prompt += "<turn|>"
+
+            case "user":
+                prompt += "<|turn|>user\n"
+                if let content = msg["content"] as? String {
+                    prompt += content
+                }
+                prompt += "<turn|>"
+
+            case "assistant":
+                prompt += "<|turn|>model\n"
+                if let content = msg["content"] as? String {
+                    prompt += content
+                }
+                if let toolCalls = msg["tool_calls"] as? [[String: Any]] {
+                    for tc in toolCalls {
+                        if let fn = tc["function"] as? [String: Any],
+                           let name = fn["name"] as? String,
+                           let args = fn["arguments"] {
+                            let argsStr: String
+                            if let s = args as? String { argsStr = s }
+                            else if let d = try? JSONSerialization.data(withJSONObject: args),
+                                    let s = String(data: d, encoding: .utf8) { argsStr = s }
+                            else { argsStr = "{}" }
+                            prompt += " <|tool_call|>\(name):\(argsStr)<|tool_call|>"
+                        }
+                    }
+                }
+                prompt += "<turn|>"
+
+            case "tool":
+                prompt += "<|turn|>tool\n"
+                if let content = msg["content"] as? String {
+                    prompt += content
+                }
+                if let callId = msg["tool_call_id"] as? String {
+                    prompt += " [call_id: \(callId)]"
+                }
+                prompt += "<turn|>"
+
+            default:
+                break
+            }
+        }
+
+        prompt += "<|turn|>model\n"
+        return prompt
+    }
+
+    public static func gemma4ArgsToJSON(_ rawArgs: String) -> String {
+        let trimmed = rawArgs.trimmingCharacters(in: .whitespacesAndNewlines)
+        // Try to parse as JSON first
+        if let data = trimmed.data(using: .utf8),
+           let _ = try? JSONSerialization.jsonObject(with: data) {
+            return trimmed
+        }
+        // Convert key=value or key:value pairs to JSON
+        var entries: [String: String] = [:]
+        for part in trimmed.components(separatedBy: ",") {
+            let kv = part.split(separator: "=", maxSplits: 1).map(String.init)
+            if kv.count == 2 {
+                let key = kv[0].trimmingCharacters(in: .whitespaces)
+                var val = kv[1].trimmingCharacters(in: .whitespaces)
+                // Remove any trailing punctuation
+                while val.last == "," || val.last == ")" || val.last == "]" {
+                    val = String(val.dropLast())
+                }
+                entries[key] = val
+            }
+        }
+        if !entries.isEmpty {
+            if let data = try? JSONSerialization.data(withJSONObject: entries),
+               let json = String(data: data, encoding: .utf8) {
+                return json
+            }
+        }
+        return "{\"value\":\"\(trimmed.replacingOccurrences(of: "\"", with: "\\\""))\"}"
+    }
+}
+
+public struct ToolCallResult: Codable, Sendable {
+    public let id: String
+    public let function: ToolCallFunction
+
+    public init(id: String, function: ToolCallFunction) {
+        self.id = id
+        self.function = function
+    }
+}
+
+public struct ToolCallFunction: Codable, Sendable {
+    public let name: String
+    public let arguments: String
+
+    public init(name: String, arguments: String) {
+        self.name = name
+        self.arguments = arguments
+    }
+}