KellyvvandClaude Opus 4.6
779be78843
Major restructuring of the agent stack to support content-type skills, data-driven runtime budgets, and the new translate skill. LLM/MLX/ - Split MLXLocalLLMService.swift (1500 → 700 lines) into Core/, Gemma4/, Installation/ subdirectories - New BundledModel: LinearBudgetFormula replaces tier tables, model parameters fully data-driven via ModelRuntimeProfile - New RuntimeBudgets: pure functions for text/thinking/multimodal budgets, zero hardcoded model IDs - Drop adjustedTextOutputTokens prepared-subtraction (chunked prefill made it obsolete and triggered false-positive truncation on long prompts) Skills/ - Add SkillType (.device / .content) metadata, parsed from SKILL.md frontmatter - New translate skill (type: content, no tools) with anaphora handling - Trim translate (4563→1804), device (2357→1680), calendar (2169→1790) - contacts SKILL.md adds multi-turn disambiguation + cancel guidance, semantics owned by body not framework - SkillRegistry validates allowed-tools against ToolRegistry at load time Agent/ - ToolCallParser becomes registry-aware: drops tool_call names not in ToolRegistry or protocol set (load_skill / list_skills); ToolRegistry is now the single white list, validation moves to parser boundary - Router sticky routing uses semantic user-turn boundary instead of fixed suffix(4); correctly handles long agent loops - AgentEngine system prompt template differentiates device vs content skills with explicit invocation rules - SYSPROMPT.md auto-migration: old single-placeholder template backed up to .bak when new dual-placeholder is detected - PromptBuilder.buildLoadedSkillPrompt receives availableTools list, explicitly tells model which tools (or none) are callable Tools/ - ToolRegistry split into Helpers/Stores/AppPermissions/Handlers/* for separation of concerns - Mark Tools/Handlers/* with explicit allowed argument signatures UI/ - Add long-press copy contextMenu on user and assistant bubbles - Enable .textSelection on user bubble Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
32 lines
1.1 KiB
Swift
32 lines
1.1 KiB
Swift
import Foundation
|
|
import Darwin
|
|
|
|
// MARK: - MemoryStats
|
|
//
|
|
// task_vm_info 包装。从 MLXLocalLLMService.swift L733-745 原样迁移,
|
|
// 额外提供 headroomMB 便捷访问。
|
|
|
|
enum MemoryStats {
|
|
|
|
/// (footprint MB, jetsam limit MB) via task_info.
|
|
static func footprintMB() -> (Double, Double) {
|
|
var info = task_vm_info_data_t()
|
|
var count = mach_msg_type_number_t(MemoryLayout<task_vm_info_data_t>.size / MemoryLayout<natural_t>.size)
|
|
let kr = withUnsafeMutablePointer(to: &info) {
|
|
$0.withMemoryRebound(to: integer_t.self, capacity: Int(count)) {
|
|
task_info(mach_task_self_, task_flavor_t(TASK_VM_INFO), $0, &count)
|
|
}
|
|
}
|
|
guard kr == KERN_SUCCESS else { return (0, 0) }
|
|
let footprint = Double(info.phys_footprint) / 1_048_576
|
|
let limit = Double(info.limit_bytes_remaining) / 1_048_576 + footprint
|
|
return (footprint, limit)
|
|
}
|
|
|
|
/// 当前可用内存 headroom (MB), 用于所有 budget 计算。
|
|
static var headroomMB: Int {
|
|
let (footprint, limit) = footprintMB()
|
|
return max(0, Int(limit - footprint))
|
|
}
|
|
}
|