feat: cap telemetry bodies at a configurable length

Chat rows stored full message and response text with no upper bound, so
downstream contracts and tenders lived in llm_calls indefinitely. Add
_cap_text/_cap_messages in the single telemetry exit (_record), applied
after digest_messages and before json.dumps, plus to response/thinking.

Capping is per text, not over the serialized JSON: cutting the whole
string would emit invalid JSON into an unvalidated TEXT column. The cap
builds new dicts and never mutates in place — digest_messages passes
non-list content straight through as the same object, so an in-place cut
would silently poison the caller's messages and the cache key.

text_cap is required on TelemetryEmitter (internal class, three known
construction sites) and defaults to None on the three public clients, so
the default behaviour stays byte-for-byte identical. Settings wiring
lands separately.

src/polygateway/embedding.py

@@ -104,6 +104,7 @@ class EmbeddingClient:
         quota_full: str = "wait",
         telemetry: TelemetryRecorder | None = None,
         pricing: PricingTable | None = None,
+        text_cap: int | None = None,
         batch_size: int,
         normalize: bool = False,
         expected_dim: int | None = None,
@@ -128,7 +129,9 @@ class EmbeddingClient:
         self._retry = retry
         self._bp = backpressure
         self._quota_full = quota_full
-        self._emitter = TelemetryEmitter(telemetry, pricing=pricing) if telemetry else None
+        self._emitter = (
+            TelemetryEmitter(telemetry, pricing=pricing, text_cap=text_cap) if telemetry else None
+        )
         self._telemetry = telemetry
         self._pricing = pricing
         self._batch_size = batch_size