Add parroting penalty to eval and auto-discover eval_config.json

Penalize parroted recoveries (agent echoes user's correction without
re-verifying via tool) as unhelpful in both the usefulness definition
and the unhelpful category.

Refactor quality_report.py to auto-discover eval/eval_config.json
from the repo root, removing 290 lines of hardcoded metric
definitions in favor of the config-driven approach.

Author: evekhm

scripts/eval/eval_config.json

@@ -2,15 +2,15 @@
   "metrics": [
     {
       "name": "response_usefulness",
-      "definition": "Whether the agent final response provides a genuinely useful, substantive answer to the user question. A response that apologizes, says it cannot help, returns no data, provides only generic filler, or loops without resolving the question is NOT useful.",
+      "definition": "Whether the agent final response provides a genuinely useful, substantive answer to the user question. A response that apologizes, says it cannot help, returns no data, provides only generic filler, or loops without resolving the question is NOT useful. If the conversation contains a user correction and the agent merely repeated or acknowledged the correction without independently verifying it (e.g. re-querying a tool, citing a new source), the response is NOT useful — the user did the agent's work.",
       "categories": [
         {
           "name": "meaningful",
           "definition": "The response directly and substantively addresses the user question with specific, actionable information."
         },
         {
           "name": "unhelpful",
-          "definition": "The response does NOT meaningfully answer the user question. This includes: (1) The agent said 'I don't have that information', gave generic advice, or directed the user elsewhere instead of using its tools. (2) The agent apologized without answering. (3) Empty data results or generic filler text. (4) The agent looped without resolution."
+          "definition": "The response does NOT meaningfully answer the user question. This includes: (1) The agent said 'I don't have that information', gave generic advice, or directed the user elsewhere instead of using its tools. (2) The agent apologized without answering. (3) Empty data results or generic filler text. (4) The agent looped without resolution. (5) The agent only became correct after the user provided the right answer and the agent repeated it without independent verification (e.g. re-querying a tool)."
         },
         {
           "name": "partial",