refactor(agents): remove lsp_diagnostics from Sisyphus and Sisyphus-Junior prompts

Orchestrator Sisyphus will handle project-level code validation instead of
having each subagent run file-level lsp_diagnostics.

src/agents/sisyphus-junior.ts

@@ -1,11 +1,11 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import { isGptModel } from "./types"
 import type { AgentOverrideConfig, CategoryConfig } from "../config/schema"
 import {
   createAgentToolRestrictions,
   migrateAgentConfig,
   supportsNewPermissionSystem,
 } from "../shared/permission-compat"
+import { isGptModel } from "./types"
 
 const SISYPHUS_JUNIOR_PROMPT = `<Role>
 Sisyphus-Junior - Focused executor from OhMyOpenCode.
@@ -58,7 +58,6 @@ No todos on multi-step work = INCOMPLETE WORK.
 
 <Verification>
 Task NOT complete without:
-- lsp_diagnostics clean on changed files
 - Build passes (if applicable)
 - All todos marked completed
 </Verification>
@@ -85,7 +84,7 @@ export const SISYPHUS_JUNIOR_DEFAULTS = {
 
 export function createSisyphusJuniorAgentWithOverrides(
   override: AgentOverrideConfig | undefined,
-  systemDefaultModel?: string
+  systemDefaultModel?: string,
 ): AgentConfig {
   if (override?.disable) {
     override = undefined
@@ -121,7 +120,8 @@ export function createSisyphusJuniorAgentWithOverrides(
   }
 
   const base: AgentConfig = {
-    description: override?.description ??
+    description:
+      override?.description ??
       "Sisyphus-Junior - Focused task executor. Same discipline, no delegation.",
     mode: "subagent" as const,
     model,
@@ -148,7 +148,7 @@ export function createSisyphusJuniorAgentWithOverrides(
 
 export function createSisyphusJuniorAgent(
   categoryConfig: CategoryConfig,
-  promptAppend?: string
+  promptAppend?: string,
 ): AgentConfig {
   const prompt = buildSisyphusJuniorPrompt(promptAppend)
   const model = categoryConfig.model
@@ -158,10 +158,8 @@ export function createSisyphusJuniorAgent(
     ...(categoryConfig.tools ? { tools: categoryConfig.tools } : {}),
   })
 
-
   const base: AgentConfig = {
-    description:
+    description: "Sisyphus-Junior - Focused task executor. Same discipline, no delegation.",
-      "Sisyphus-Junior - Focused task executor. Same discipline, no delegation.",
     mode: "subagent" as const,
     model,
     maxTokens: categoryConfig.maxTokens ?? 64000,

src/agents/sisyphus.ts

@@ -1,18 +1,18 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
-import { isGptModel } from "./types"
+import type { AvailableAgent, AvailableSkill, AvailableTool } from "./sisyphus-prompt-builder"
-import type { AvailableAgent, AvailableTool, AvailableSkill } from "./sisyphus-prompt-builder"
 import {
-  buildKeyTriggersSection,
-  buildToolSelectionTable,
-  buildExploreSection,
-  buildLibrarianSection,
-  buildDelegationTable,
-  buildFrontendSection,
-  buildOracleSection,
-  buildHardBlocksSection,
   buildAntiPatternsSection,
+  buildDelegationTable,
+  buildExploreSection,
+  buildFrontendSection,
+  buildHardBlocksSection,
+  buildKeyTriggersSection,
+  buildLibrarianSection,
+  buildOracleSection,
+  buildToolSelectionTable,
   categorizeTools,
 } from "./sisyphus-prompt-builder"
+import { isGptModel } from "./types"
 
 const DEFAULT_MODEL = "anthropic/claude-opus-4-5"
 
@@ -336,7 +336,6 @@ When you're mentioned in GitHub issues or asked to "look into" something and "cr
 2. **Implement**: Make the necessary changes
    - Follow existing codebase patterns
    - Add tests if applicable
-   - Verify with lsp_diagnostics
 3. **Verify**: Ensure everything works
    - Run build if exists
    - Run tests if exists
@@ -361,18 +360,12 @@ const SISYPHUS_CODE_CHANGES = `### Code Changes:
 
 ### Verification:
 
-Run \`lsp_diagnostics\` on changed files at:
-- End of a logical task unit
-- Before marking a todo item complete
-- Before reporting completion to user
-
 If project has build/test commands, run them at task completion.
 
 ### Evidence Requirements (task NOT complete without these):
 
 | Action | Required Evidence |
 |--------|-------------------|
-| File edit | \`lsp_diagnostics\` clean on changed files |
 | Build command | Exit code 0 |
 | Test run | Pass (or explicit note of pre-existing failures) |
 | Delegation | Agent result received and verified |
@@ -401,7 +394,6 @@ const SISYPHUS_PHASE3 = `## Phase 3 - Completion
 
 A task is complete when:
 - [ ] All planned todo items marked done
-- [ ] Diagnostics clean on changed files
 - [ ] Build passes (if applicable)
 - [ ] User's original request fully addressed
 
@@ -525,7 +517,7 @@ const SISYPHUS_SOFT_GUIDELINES = `## Soft Guidelines
 function buildDynamicSisyphusPrompt(
   availableAgents: AvailableAgent[],
   availableTools: AvailableTool[] = [],
-  availableSkills: AvailableSkill[] = []
+  availableSkills: AvailableSkill[] = [],
 ): string {
   const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills)
   const toolSelection = buildToolSelectionTable(availableAgents, availableTools, availableSkills)
@@ -610,7 +602,7 @@ export function createSisyphusAgent(
   model: string = DEFAULT_MODEL,
   availableAgents?: AvailableAgent[],
   availableToolNames?: string[],
-  availableSkills?: AvailableSkill[]
+  availableSkills?: AvailableSkill[],
 ): AgentConfig {
   const tools = availableToolNames ? categorizeTools(availableToolNames) : []
   const skills = availableSkills ?? []