Fix schema enums

[ahuang11]

1. when limited to the first 100 rows, and the column had missing data in the first 100, the LLM was stating that columns "were placeholders" or it had no available data, which was misleading

Instead, it should mention the data was truncated:

2. I changed the limit from 100 to 1000; shouldn't seriously affect performance on modern processors(?)
3. The count was placed in the nested dict vs outer dict.

[codecov]

Codecov Report

Attention: Patch coverage is 77.77778% with 2 lines in your changes missing coverage. Please review.

Project coverage is 60.98%. Comparing base (2c83a1b) to head (6c84c1e).

Files with missing lines	Patch %	Lines
lumen/ai/agents.py	0.00%	1 Missing ⚠️
lumen/ai/utils.py	85.71%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #785      +/-   ##
==========================================
- Coverage   60.98%   60.98%   -0.01%     
==========================================
  Files         103      103              
  Lines       12544    12546       +2     
==========================================
+ Hits         7650     7651       +1     
- Misses       4894     4895       +1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

---

🚨 Try these New Features:

• Flaky Tests Detection - Detect and resolve failed and flaky tests