rag: cap chunk size at 6KB to fit nomic-embed-text 2048-tok context

The chunker emits any single paragraph as a stand-alone chunk regardless
of size. One HVM page had a 14,858-char paragraph (a big config table) —
nomic-embed-text 400'd the entire embed batch because the model's context
is 2048 tokens. Added a hard-split fallback that splits any oversized
chunk on line boundaries to MAX_CHARS=6000 (~1500 tokens, headroom).

Also defaulted PRODUCT_NAME to "hvm" in rag/index.py to match server.py.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

rag/chunk.py

@@ -31,6 +31,27 @@ from typing import Iterator
 CHARS_PER_TOKEN = 4
 TARGET_TOKENS = 500
 TARGET_CHARS = TARGET_TOKENS * CHARS_PER_TOKEN
+# Hard cap: nomic-embed-text's context is 2048 tokens. Anything larger
+# 400s the entire embed batch. 6000 chars ≈ 1500 tokens leaves headroom.
+MAX_CHARS = 6000
+
+
+def _hard_split(text: str) -> list[str]:
+    """Split an oversized block on line boundaries into MAX_CHARS pieces."""
+    if len(text) <= MAX_CHARS:
+        return [text]
+    out: list[str] = []
+    buf: list[str] = []
+    buf_chars = 0
+    for line in text.splitlines(keepends=True):
+        if buf_chars + len(line) > MAX_CHARS and buf:
+            out.append("".join(buf).rstrip())
+            buf, buf_chars = [], 0
+        buf.append(line)
+        buf_chars += len(line)
+    if buf:
+        out.append("".join(buf).rstrip())
+    return out
 
 
 def estimate_tokens(text: str) -> int:
@@ -104,23 +125,26 @@ def chunks_from_page(
 
     # ----- Body chunks: pack paragraphs up to TARGET_CHARS -------
     ordinal = 1
+
+    def emit(buf: list[str]) -> Iterator[dict]:
+        nonlocal ordinal
+        merged = "\n\n".join(buf)
+        for piece in _hard_split(merged):
+            yield {
+                "id":       f"{metadata['bundle_id']}::{page_id}::{ordinal}",
+                "text":     piece,
+                "metadata": {**metadata, "ordinal": ordinal},
+            }
+            ordinal += 1
+
     buf: list[str] = []
     buf_chars = 0
     for p in paragraphs:
         if buf_chars + len(p) > TARGET_CHARS and buf:
-            yield {
-                "id":       f"{metadata['bundle_id']}::{page_id}::{ordinal}",
-                "text":     "\n\n".join(buf),
-                "metadata": {**metadata, "ordinal": ordinal},
-            }
-            ordinal += 1
+            yield from emit(buf)
             buf = []
             buf_chars = 0
         buf.append(p)
         buf_chars += len(p)
     if buf:
-        yield {
-            "id":       f"{metadata['bundle_id']}::{page_id}::{ordinal}",
-            "text":     "\n\n".join(buf),
-            "metadata": {**metadata, "ordinal": ordinal},
-        }
+        yield from emit(buf)