refactor: remove legacy tools format, use permission only

BREAKING: Requires OpenCode 1.1.1+

- Remove supportsNewPermissionSystem/usesLegacyToolsSystem checks
- Simplify permission-compat.ts to permission format only
- Unify explore/librarian deny lists: write, edit, task, sisyphus_task, call_omo_agent
- Add sisyphus_task to oracle deny list
- Update agent-tool-restrictions.ts with correct per-agent restrictions
- Clean config-handler.ts conditional version checks
- Update tests for simplified API

src/agents/librarian.ts

@@ -1,5 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
 import type { AgentPromptMetadata } from "./types"
+import { createAgentToolRestrictions } from "../shared/permission-compat"
 
 const DEFAULT_MODEL = "opencode/glm-4.7-free"
 
@@ -21,13 +22,21 @@ export const LIBRARIAN_PROMPT_METADATA: AgentPromptMetadata = {
 }
 
 export function createLibrarianAgent(model: string = DEFAULT_MODEL): AgentConfig {
+  const restrictions = createAgentToolRestrictions([
+    "write",
+    "edit",
+    "task",
+    "sisyphus_task",
+    "call_omo_agent",
+  ])
+
   return {
     description:
       "Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.",
     mode: "subagent" as const,
     model,
     temperature: 0.1,
-    tools: { write: false, edit: false, background_task: false },
+    ...restrictions,
     prompt: `# THE LIBRARIAN
 
 You are **THE LIBRARIAN**, a specialized open-source codebase understanding agent.

src/agents/oracle.ts

@@ -102,6 +102,7 @@ export function createOracleAgent(model: string = DEFAULT_MODEL): AgentConfig {
     "write",
     "edit",
     "task",
+    "sisyphus_task",
   ])
 
   const base = {

src/agents/sisyphus-junior.ts

@@ -3,8 +3,7 @@ import { isGptModel } from "./types"
 import type { AgentOverrideConfig, CategoryConfig } from "../config/schema"
 import {
   createAgentToolRestrictions,
-  migrateAgentConfig,
-  supportsNewPermissionSystem,
+  type PermissionValue,
 } from "../shared/permission-compat"
 
 const SISYPHUS_JUNIOR_PROMPT = `<Role>
@@ -99,26 +98,14 @@ export function createSisyphusJuniorAgentWithOverrides(
 
   const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
 
-  let toolsConfig: Record<string, unknown> = {}
-  if (supportsNewPermissionSystem()) {
-    const userPermission = (override?.permission ?? {}) as Record<string, string>
-    const basePermission = (baseRestrictions as { permission: Record<string, string> }).permission
-    const merged: Record<string, string> = { ...userPermission }
-    for (const tool of BLOCKED_TOOLS) {
-      merged[tool] = "deny"
-    }
-    merged.call_omo_agent = "allow"
-    toolsConfig = { permission: { ...merged, ...basePermission } }
-  } else {
-    const userTools = override?.tools ?? {}
-    const baseTools = (baseRestrictions as { tools: Record<string, boolean> }).tools
-    const merged: Record<string, boolean> = { ...userTools }
-    for (const tool of BLOCKED_TOOLS) {
-      merged[tool] = false
-    }
-    merged.call_omo_agent = true
-    toolsConfig = { tools: { ...merged, ...baseTools } }
+  const userPermission = (override?.permission ?? {}) as Record<string, PermissionValue>
+  const basePermission = baseRestrictions.permission
+  const merged: Record<string, PermissionValue> = { ...userPermission }
+  for (const tool of BLOCKED_TOOLS) {
+    merged[tool] = "deny"
   }
+  merged.call_omo_agent = "allow"
+  const toolsConfig = { permission: { ...merged, ...basePermission } }
 
   const base: AgentConfig = {
     description: override?.description ??
@@ -153,10 +140,18 @@ export function createSisyphusJuniorAgent(
   const prompt = buildSisyphusJuniorPrompt(promptAppend)
   const model = categoryConfig.model
   const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
-  const mergedConfig = migrateAgentConfig({
-    ...baseRestrictions,
-    ...(categoryConfig.tools ? { tools: categoryConfig.tools } : {}),
-  })
+  const categoryPermission = categoryConfig.tools
+    ? Object.fromEntries(
+        Object.entries(categoryConfig.tools).map(([k, v]) => [
+          k,
+          v ? ("allow" as const) : ("deny" as const),
+        ])
+      )
+    : {}
+  const mergedPermission = {
+    ...categoryPermission,
+    ...baseRestrictions.permission,
+  }
 
 
   const base: AgentConfig = {
@@ -167,7 +162,7 @@ export function createSisyphusJuniorAgent(
     maxTokens: categoryConfig.maxTokens ?? 64000,
     prompt,
     color: "#20B2AA",
-    ...mergedConfig,
+    permission: mergedPermission,
   }
 
   if (categoryConfig.temperature !== undefined) {

src/agents/sisyphus.ts

@@ -618,9 +618,7 @@ export function createSisyphusAgent(
     ? buildDynamicSisyphusPrompt(availableAgents, tools, skills)
     : buildDynamicSisyphusPrompt([], tools, skills)
 
-  // Note: question permission allows agent to ask user questions via OpenCode's QuestionTool
-  // SDK type doesn't include 'question' yet, but OpenCode runtime supports it
-  const permission = { question: "allow" } as AgentConfig["permission"]
+  const permission = { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"]
   const base = {
     description:
       "Sisyphus - Powerful AI orchestrator from OhMyOpenCode. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically to specialized agents. Uses explore for internal code (parallel-friendly), librarian only for external docs, and always delegates UI work to frontend engineer.",
@@ -630,7 +628,6 @@ export function createSisyphusAgent(
     prompt,
     color: "#00CED1",
     permission,
-    tools: { call_omo_agent: false },
   }
 
   if (isGptModel(model)) {