Content truncation mismatch: servers discard 60% of indexed content before LLM call

The pipeline uses `RecursiveCharacterTextSplitter` with a default `chunk_size=1000` and stores chunks as `VARCHAR(2000)`:

```python
# pipelines/kubeflow-pipeline.py
'content_text': chunk[:2000],
```

But both `server/app.py` and `server-https/app.py` truncate to 400 characters before passing results to the LLM:

```python
if isinstance(content_text, str) and len(content_text) > 400:
content_text = content_text[:400] + "..."
```

With the default chunk size of 1000 chars, the server-side truncation discards roughly 60% of each chunk before the LLM sees it. The 400-char limit is a reasonable trade-off for fitting more results into the context window, but the issue is that the MCP server in `kagent-feast-mcp/mcp-server/server.py` does **not** truncate at all. It passes full `content_text` to the agent.

This means the same query against the same index will produce different answer quality depending on whether it goes through Architecture A (main servers, 400 chars) or Architecture B (Kagent/MCP, full content). That makes it hard to evaluate retrieval quality consistently across the system.

**Suggested approach:** make the truncation limit configurable via environment variable (e.g., `CONTENT_MAX_CHARS`) and align the default across all server implementations so evaluation results are comparable regardless of code path.

PR freeze is on, so just flagging this as an issue. Happy to pick it up when PRs open back up.

Compare the truncation paths in pipelines/kubeflow-pipeline.py, server/app.py, server-https/app.py, and kagent-feast-mcp/mcp-server/server.py, starting with the existing 400-character handling. Make the limit configurable through CONTENT_MAX_CHARS and align the default across all server implementations so the same indexed content is passed consistently for evaluation.

Written by the indexing model from the issue text.