feat(db+mcpd): Agent lifecycle + chat.service kind=virtual branch (v3 Stage 1)

Two pieces of v3 plumbing — schema + the latent v1 chat.service bug.

Schema (db):
- Agent gains kind/providerSessionId/lastHeartbeatAt/status/inactiveSince
  mirroring Llm's v1 lifecycle. Reuses LlmKind / LlmStatus enums; no
  new types. Existing rows backfill kind=public/status=active so v1
  CRUD is unaffected.
- @@index([kind, status]) for the GC sweep, @@index([providerSessionId])
  for disconnect-cascade lookups.
- 4 new prisma-level tests cover defaults, persisting virtual fields,
  the (kind, status) GC index, and providerSessionId lookups.
  Total agent-schema tests: 20/20.

chat.service (mcpd) — fixes the v1 latent bug:
- LlmView's kind is now plumbed through prepareContext as ctx.llmKind.
- Two new private helpers, runOneInference / streamInference, branch
  on ctx.llmKind: 'public' goes through the existing adapter
  registry, 'virtual' relays through VirtualLlmService.enqueueInferTask
  (mirrors the route-handler branch from v1 Stage 3).
- Streaming bridges VirtualLlmService's onChunk callback API to an
  async iterator via a small queue + wake pattern.
- ChatService gains an optional virtualLlms constructor parameter;
  main.ts wires it in. Older test wirings without it raise a clear
  "virtualLlms dispatcher not wired" error when the row is virtual,
  rather than silently falling through to the public path against an
  empty URL.

This unblocks any Agent (public OR future v3-virtual) pinned to a
kind=virtual Llm. Pre-this-stage, those agents 502'd against the
empty url field.

Tests: 4 new chat-service-virtual-llm.test.ts cover the relay path
non-streaming, streaming, missing-dispatcher error, and rejection
surfacing. mcpd suite: 841/841 (was 833, +8 across stages 1+v3-Stage-1).
Workspace: 2054/2054 across 153 files.

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

src/db/prisma/migrations/20260427154803_add_virtual_agent_lifecycle/migration.sql

@@ -0,0 +1,14 @@
+-- Mirror Llm's virtual-provider lifecycle on Agent. Reuses the
+-- existing LlmKind / LlmStatus enums so we don't double-define them.
+-- Existing rows backfill with kind='public' / status='active' so
+-- nothing changes for manually-created agents.
+
+ALTER TABLE "Agent"
+  ADD COLUMN "kind"               "LlmKind"   NOT NULL DEFAULT 'public',
+  ADD COLUMN "providerSessionId"  TEXT,
+  ADD COLUMN "lastHeartbeatAt"    TIMESTAMP(3),
+  ADD COLUMN "status"             "LlmStatus" NOT NULL DEFAULT 'active',
+  ADD COLUMN "inactiveSince"      TIMESTAMP(3);
+
+CREATE INDEX "Agent_kind_status_idx"          ON "Agent"("kind", "status");
+CREATE INDEX "Agent_providerSessionId_idx"    ON "Agent"("providerSessionId");

src/db/prisma/schema.prisma

@@ -469,20 +469,26 @@ model BackupPending {
 // 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
+  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?
   defaultPersonalityId String? // applied at chat time when no --personality flag
   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
+  defaultParams        Json      @default("{}") // LiteLLM-style: temperature, top_p, top_k, max_tokens, stop, ...
+  extras               Json      @default("{}") // future LoRA / tool-allowlist
+  // ── Virtual-agent lifecycle (NULL/default for kind=public, mirrors Llm) ──
+  kind                 LlmKind   @default(public)
+  providerSessionId    String? // mcplocal session that owns this row when virtual
+  lastHeartbeatAt      DateTime?
+  status               LlmStatus @default(active)
+  inactiveSince        DateTime?
   ownerId              String
-  version              Int      @default(1)
-  createdAt            DateTime @default(now())
-  updatedAt            DateTime @updatedAt
+  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)
@@ -497,6 +503,8 @@ model Agent {
   @@index([projectId])
   @@index([ownerId])
   @@index([defaultPersonalityId])
+  @@index([kind, status])
+  @@index([providerSessionId])
 }
 
 // ── Personalities (named overlay bundles of prompts on top of an Agent) ──