feat: Phase 1 — modular backend architecture (v4.0-alpha)

Internal refactor: extract BackendAdapter, ModelRegistry, AgentRouter,
SessionManager, and StatsCollector as standalone modules. Claude CLI
logic encapsulated in ClaudeCliAdapter.

External API completely unchanged — all existing endpoints behave
identically. Legacy request path (callClaude/callClaudeStreaming)
untouched. v4 modules load in parallel for validation.

New endpoints:
  GET /backends  — backend health and status
  GET /routing   — agent routing table

Architecture:
  unified-chunk.mjs    — streaming protocol (delta/done/error)
  backends/base.mjs    — BackendAdapter interface
  backends/claude-cli.mjs — Claude CLI adapter (core)
  model-registry.mjs   — model → backend mapping (Layer 1)
  agent-router.mjs     — agent policy routing (Layer 2)
  session-manager.mjs  — conversation session management
  stats-collector.mjs  — per-model/backend/agent metrics

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

unified-chunk.mjs

@@ -0,0 +1,42 @@
+/**
+ * UnifiedChunk — the internal streaming protocol for OCP.
+ *
+ * All backend adapters MUST convert their native output into this format.
+ * server.mjs only handles UnifiedChunks → OpenAI SSE conversion.
+ */
+
+/**
+ * @typedef {Object} UnifiedChunk
+ * @property {"delta"|"done"|"error"} type
+ * @property {string} [content]       — text content (for "delta")
+ * @property {string} model           — canonical model id
+ * @property {string} backend         — backend id (e.g. "claude-cli")
+ * @property {Object} [usage]         — token usage (for "done")
+ * @property {number} [usage.promptTokens]
+ * @property {number} [usage.completionTokens]
+ * @property {Object} [cost]          — cost info (for "done")
+ * @property {number} [cost.value]
+ * @property {"actual"|"estimated"|"free"} [cost.type]
+ * @property {string} [error]         — error message (for "error")
+ */
+
+/**
+ * Create a delta chunk (streaming content)
+ */
+export function delta(content, model, backend) {
+  return { type: "delta", content, model, backend };
+}
+
+/**
+ * Create a done chunk (stream finished)
+ */
+export function done(model, backend, usage = null, cost = null) {
+  return { type: "done", model, backend, ...(usage && { usage }), ...(cost && { cost }) };
+}
+
+/**
+ * Create an error chunk
+ */
+export function error(message, model, backend) {
+  return { type: "error", error: message, model, backend };
+}