feat: add P2 features — retry policy, prompt templating, usage tracking, tech debt cleanup

- Extract shared splitMessage() into channels/utils.ts (dedup 4 adapters)
- Add Slack user name resolution with caching (users.info API)
- Add withRetry() with exponential backoff + jitter, isRetryable() filter
- Wire retry config into ModelRouter.chat() (non-streaming only)
- Add assembleSystemPrompt() multi-file template system (SOUL/AGENTS/IDENTITY/USER/TOOLS.md)
- Add usage tracking accumulators in NativeAgent + AgentOrchestrator
- Add estimateCost() with per-model pricing table
- Add /usage TUI command with full usage report formatting
- Add retrySchema and promptSchema to config schema

Tests: 569 passing, typecheck clean

src/models/costs.ts

@@ -0,0 +1,21 @@
+/** Approximate cost per million tokens for known models. */
+export const MODEL_COSTS_PER_MILLION: Record<string, { input: number; output: number }> = {
+  // Anthropic
+  'claude-sonnet-4-20250514': { input: 3, output: 15 },
+  'claude-3-5-haiku-20241022': { input: 0.80, output: 4 },
+  'claude-opus-4-20250514': { input: 15, output: 75 },
+  // OpenAI
+  'gpt-4o': { input: 2.50, output: 10 },
+  'gpt-4o-mini': { input: 0.15, output: 0.60 },
+  // Local / unknown models
+  'default': { input: 0, output: 0 },
+};
+
+/**
+ * Estimate the dollar cost for a given number of input/output tokens.
+ * Falls back to zero cost for unknown or local models.
+ */
+export function estimateCost(inputTokens: number, outputTokens: number, modelName?: string): number {
+  const costs = MODEL_COSTS_PER_MILLION[modelName ?? ''] ?? MODEL_COSTS_PER_MILLION['default'];
+  return (inputTokens * costs.input + outputTokens * costs.output) / 1_000_000;
+}