feat(sisyphus): add Kimi K2.x prompt variant

- New src/agents/sisyphus/kimi-k2-6.ts based on gpt-5-4.ts 8-block architecture
- New src/agents/sisyphus-junior/kimi-k2-6.ts worker variant
- Preserves 4 pillars: intent gate + verbalization, parallel tools, verification
- Adds <re_entry_rule>: suppress re-verbalization for already-resolved turns
- Adds <exploration_budget>: hard stop conditions alongside aggressive parallelism
- Tiered <verification_loop> (V1/V2/V3): V3 keeps full rigor with harsh enforcement
- Adds <token_economy>: verbalization explicitly excluded from trim mandate
- isKimiK2Model in types.ts: matches kimi, k2p5/k2p6 variants (case-insensitive)
- Routing in sisyphus.ts + sisyphus-junior/agent.ts
- Tests: 3 new kimi routing cases in sisyphus-junior/index.test.ts (all pass)

Motivation: K2.x was post-trained with Toggle RL (~25-30% token reduction) and a
GRM scoring appropriate detail + intent inference. Reusing Claude-style prompts
double-taxes the model — external strictness on top of RL-learned strictness causes
over-deliberation on already-resolved requests. The re-entry rule and exploration
budget fix this without weakening verification rigor.

Refs: kimi.com/blog/kimi-k2-6, arxiv 2602.02276 §4.4.2 (Toggle, GRM)

src/agents/sisyphus.ts

@@ -6,6 +6,7 @@ import {
   isGpt5_5Model,
   isGptNativeSisyphusModel,
   isClaudeOpus47Model,
+  isKimiK2Model,
 } from "./types";
 import {
   buildGeminiToolMandate,
@@ -18,6 +19,7 @@ import {
 import { buildClaudeOpus47SisyphusPrompt } from "./sisyphus/claude-opus-4-7";
 import { buildGpt54SisyphusPrompt } from "./sisyphus/gpt-5-4";
 import { buildGpt55SisyphusPrompt } from "./sisyphus/gpt-5-5";
+import { buildKimiK26SisyphusPrompt } from "./sisyphus/kimi-k2-6";
 import { buildTaskManagementSection } from "./sisyphus/default";
 import { getGptApplyPatchPermission } from "./gpt-apply-patch-guard";
 import { getFrontierToolSchemaPermission } from "./frontier-tool-schema-guard";
@@ -489,6 +491,33 @@ export function createSisyphusAgent(
   const categories = availableCategories ?? [];
   const agents = availableAgents ?? [];
 
+  if (isKimiK2Model(model)) {
+    const prompt = buildKimiK26SisyphusPrompt(
+      model,
+      agents,
+      tools,
+      skills,
+      categories,
+      useTaskSystem,
+    );
+    return {
+      description:
+        "Powerful AI orchestrator. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs. (Sisyphus - OhMyOpenCode)",
+      mode: MODE,
+      model,
+      maxTokens: 64000,
+      prompt,
+      color: "#00CED1",
+      permission: {
+        question: "allow",
+        call_omo_agent: "deny",
+        ...getFrontierToolSchemaPermission(model),
+        ...getGptApplyPatchPermission(model),
+      } as AgentConfig["permission"],
+      reasoningEffort: "medium",
+    };
+  }
+
   if (isGpt5_5Model(model)) {
     const prompt = buildGpt55SisyphusPrompt(
       model,