refactor: implement three-layer agent architecture (agents / prompts / skills)

Layer 1 — src/agents/ (thin agent definitions, no prompt text)
  registry.ts   — AgentConfig, registerAgent(), getAgent(), AGENTS proxy, pick()
  orchestrator.ts, coder.ts, pm.ts, marketing.ts — one file each, just metadata + tool picks
  index.ts      — barrel: imports prompts then agents (correct registration order)

Layer 2 — src/prompts/ (prompt text separated from agent logic)
  loader.ts     — registerPrompt(), resolvePrompt() with {{variable}} substitution
  orchestrator.ts, coder.ts, pm.ts, marketing.ts — prompt templates as registered strings
  orchestrator.ts now uses resolvePrompt('orchestrator', { knowledge }) instead of
  inline SYSTEM_PROMPT const; {{knowledge}} variable injects project memory cleanly.
  agent-runner.ts uses resolvePrompt(config.promptId) per agent turn.

Layer 3 — src/tools/skills.ts (new skills capability)
  list_skills(repo)      — lists .skills/<name>/SKILL.md directories from a Gitea repo
  get_skill(repo, name)  — reads and returns the markdown body of a skill file
  Orchestrator and all agents now have get_skill in their tool sets.
  Orchestrator also has list_skills and references skills in its prompt.

Also fixed:
  - server.ts now passes history + knowledge_context from request body to orchestratorChat()
    (these were being sent by the frontend but silently dropped)
  - server.ts imports PROTECTED_GITEA_REPOS from tools/security.ts (no more duplicate)
  - Deleted src/agents.ts (replaced by src/agents/ directory)

Made-with: Cursor

src/server.ts

@@ -8,16 +8,9 @@ import { createJob, getJob, listJobs, updateJob } from './job-store';
 import { runAgent } from './agent-runner';
 import { AGENTS } from './agents';
 import { ToolContext } from './tools';
+import { PROTECTED_GITEA_REPOS } from './tools/security';
 import { orchestratorChat, listSessions, clearSession } from './orchestrator';
-
-// Protected Vibn platform repos — agents cannot clone or work in these workspaces
-const PROTECTED_GITEA_REPOS = new Set([
-    'mark/vibn-frontend',
-    'mark/theia-code-os',
-    'mark/vibn-agent-runner',
-    'mark/vibn-api',
-    'mark/master-ai',
-]);
+import { LLMMessage } from './llm';
 
 const app = express();
 app.use(cors());
@@ -186,14 +179,28 @@ app.get('/api/jobs/:id', (req: Request, res: Response) => {
 // ---------------------------------------------------------------------------
 
 app.post('/orchestrator/chat', async (req: Request, res: Response) => {
-    const { message, session_id } = req.body as { message?: string; session_id?: string };
+    const {
+        message,
+        session_id,
+        history,
+        knowledge_context
+    } = req.body as {
+        message?: string;
+        session_id?: string;
+        history?: LLMMessage[];
+        knowledge_context?: string;
+    };
+
     if (!message) { res.status(400).json({ error: '"message" is required' }); return; }
 
     const sessionId = session_id || `session_${Date.now()}`;
     const ctx = buildContext();
 
     try {
-        const result = await orchestratorChat(sessionId, message, ctx);
+        const result = await orchestratorChat(sessionId, message, ctx, {
+            preloadedHistory: history,
+            knowledgeContext: knowledge_context
+        });
         res.json(result);
     } catch (err) {
         res.status(500).json({ error: err instanceof Error ? err.message : String(err) });