feat: add execution metrics support to Pi Coding Agent provider

[christso]

Summary

The Pi Coding Agent provider should return execution metrics (tokenUsage, costUsd, durationMs) in its ProviderResponse so they can be used by evaluators and included in evaluation results.

Current State

The provider already captures some of this data but doesn't surface it:

• usage data is extracted from Pi's agent_end event and stored in metadata.usage on output messages
• Execution duration is tracked for logging but not returned
• Cost is not calculated

Proposed Changes

In packages/core/src/evaluation/providers/pi-coding-agent.ts:

1. Parse token usage from agent_end event

   // In extractOutputMessages or new function
   const usage = agentEndEvent.usage; // { input_tokens, output_tokens, ... }
   const tokenUsage = {
     input: usage.input_tokens,
     output: usage.output_tokens,
     cached: usage.cached_tokens, // if available
   };

2. Calculate duration

   const startTime = Date.now();
   // ... execute Pi ...
   const durationMs = Date.now() - startTime;

3. Return metrics in ProviderResponse

   return {
     raw: { ... },
     outputMessages,
     tokenUsage,
     durationMs,
     // costUsd: optional, requires pricing info
   };

Files to Update

• packages/core/src/evaluation/providers/pi-coding-agent.ts

Acceptance Criteria

• tokenUsage extracted from Pi's usage data and returned in response
• durationMs calculated from wall-clock execution time
• Metrics appear in evaluation results when using Pi provider
• Unit tests for metric extraction

Labels

enhancement, good-first-issue