feat(agents): add Agent + ChatThread + ChatMessage schema (Stage 1)

Introduces the persistence layer for the upcoming Agent feature: an LLM
persona pinned to a specific Llm, optionally attached to a Project, with
persisted chat threads/messages so conversations survive REPL exits.

Constraint shape:
- Agent.llm uses ON DELETE RESTRICT — deleting an Llm in active use fails.
- Agent.project uses ON DELETE SET NULL — agents survive project deletion.
- ChatThread → ChatMessage cascade so deleting an agent purges its history.
- ChatMessage @@unique([threadId, turnIndex]) gives append ordering even
  under racing writers (services retry on collision).

LiteLLM-style per-call overrides will live in Agent.defaultParams (Json);
the loose extras Json field is reserved for future LoRA/tool-allowlist work.

Pinned vitest fileParallelism=false in @mcpctl/db: all suites share the
same Postgres, and adding a second suite exposed FK contention between a
clearAllTables in one file and a create in another. Per-test isolation
still comes from beforeEach.

Tests: 8/8 green in src/db/tests/agent-schema.test.ts (defaults, name
uniqueness, llm-in-use Restrict, project-delete SetNull, agent-delete
cascade, duplicate (threadId, turnIndex) blocked, tool-call payload
round-trip, lastTurnAt DESC ordering).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/db/prisma/schema.prisma

@@ -26,6 +26,8 @@ model User {
   ownedProjects      Project[]
   groupMemberships   GroupMember[]
   mcpTokens          McpToken[]
+  ownedAgents        Agent[]
+  chatThreads        ChatThread[]
 
   @@index([email])
 }
@@ -197,6 +199,7 @@ model Llm {
   updatedAt       DateTime @updatedAt
 
   apiKeySecret Secret? @relation(fields: [apiKeySecretId], references: [id], onDelete: SetNull)
+  agents       Agent[]
 
   @@index([name])
   @@index([tier])
@@ -268,6 +271,7 @@ model Project {
   prompts        Prompt[]
   promptRequests PromptRequest[]
   mcpTokens      McpToken[]
+  agents         Agent[]
 
   @@index([name])
   @@index([ownerId])
@@ -427,6 +431,81 @@ model BackupPending {
   @@index([createdAt])
 }
 
+// ── Agents (LLM personas pinned to a specific Llm) ──
+//
+// Agents combine a system prompt, a pinned LLM, and (optionally) a project to
+// inherit Prompts from. Each Agent is also exposed by mcplocal as a virtual
+// MCP server (`agent-<name>/chat`), so other clients can consult it as a tool.
+// Per-call LiteLLM-style overrides stack on top of `defaultParams`.
+
+model Agent {
+  id             String   @id @default(cuid())
+  name           String   @unique
+  description    String   @default("")                  // shown in MCP tools/list
+  systemPrompt   String   @default("") @db.Text          // agent persona
+  llmId          String
+  projectId      String?
+  proxyModelName String?                                 // optional informational override
+  defaultParams  Json     @default("{}")                 // LiteLLM-style: temperature, top_p, top_k, max_tokens, stop, ...
+  extras         Json     @default("{}")                 // future LoRA / tool-allowlist
+  ownerId        String
+  version        Int      @default(1)
+  createdAt      DateTime @default(now())
+  updatedAt      DateTime @updatedAt
+
+  llm     Llm          @relation(fields: [llmId], references: [id], onDelete: Restrict)
+  project Project?     @relation(fields: [projectId], references: [id], onDelete: SetNull)
+  owner   User         @relation(fields: [ownerId], references: [id], onDelete: Cascade)
+  threads ChatThread[]
+
+  @@index([name])
+  @@index([llmId])
+  @@index([projectId])
+  @@index([ownerId])
+}
+
+// ── Chat Threads (persisted conversation per Agent) ──
+
+model ChatThread {
+  id         String   @id @default(cuid())
+  agentId    String
+  ownerId    String
+  title      String   @default("")
+  lastTurnAt DateTime @default(now())
+  createdAt  DateTime @default(now())
+  updatedAt  DateTime @updatedAt
+
+  agent    Agent         @relation(fields: [agentId], references: [id], onDelete: Cascade)
+  owner    User          @relation(fields: [ownerId], references: [id], onDelete: Cascade)
+  messages ChatMessage[]
+
+  @@index([agentId, lastTurnAt(sort: Desc)])
+  @@index([ownerId])
+}
+
+// ── Chat Messages ──
+//
+// `turnIndex` is monotonic per thread; the @@unique enforces ordering even
+// under racing appends (callers retry on collision). `status` stays `pending`
+// until the orchestrator confirms the turn completed successfully.
+
+model ChatMessage {
+  id         String   @id @default(cuid())
+  threadId   String
+  turnIndex  Int
+  role       String                                      // 'system' | 'user' | 'assistant' | 'tool'
+  content    String   @db.Text
+  toolCalls  Json?                                       // assistant turn: [{id,name,arguments}]
+  toolCallId String?                                     // tool turn: which call this answers
+  status     String   @default("complete")               // 'pending' | 'complete' | 'error'
+  createdAt  DateTime @default(now())
+
+  thread ChatThread @relation(fields: [threadId], references: [id], onDelete: Cascade)
+
+  @@unique([threadId, turnIndex])
+  @@index([threadId, createdAt])
+}
+
 // ── Audit Logs ──
 
 model AuditLog {