Document model_providers headers in configuration reference (#950)

* Document model_providers headers in configuration reference

Co-authored-by: Musa <musa@spherrrical.dev>

* ci: retrigger workflow

Co-authored-by: Musa <musa@spherrrical.dev>

* fix(llm_gateway): buffer non-streaming response body until end_of_stream

Wait for the full upstream body before JSON parsing to avoid truncated
responses on chunked replies. Retry currency_exchange demo tests on flake.

Co-authored-by: Musa <musa@spherrrical.dev>

* fix(llm_gateway): read full non-streaming body when final chunk is empty

Co-authored-by: Musa <musa@spherrrical.dev>

* fix(llm_gateway): read full non-streaming body with usize::MAX at end_of_stream

Co-authored-by: Musa <musa@spherrrical.dev>

* fix(llm_gateway): use envoy body_size for response body replacement

Co-authored-by: Musa <musa@spherrrical.dev>

* docs: explain model_providers headers in configuration reference

Revert unrelated llm_gateway and demo test runner changes.

Co-authored-by: Musa <musa@spherrrical.dev>

* chore: drop unrelated changes, keep docs-only diff

Co-authored-by: Musa <musa@spherrrical.dev>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>

docs/source/resources/includes/plano_config_full_reference.yaml

@@ -47,6 +47,14 @@ model_providers:
     http_host: api.custom-provider.com
     access_key: $CUSTOM_API_KEY
 
+  # headers: optional map of extra HTTP headers sent on upstream requests (after auth).
+  # Use for provider-specific requirements such as User-Agent, org IDs, or account headers.
+  - model: moonshotai/kimi-for-coding
+    access_key: $MOONSHOTAI_API_KEY
+    base_url: https://api.kimi.com/coding/v1
+    headers:
+      User-Agent: "KimiCLI/1.3"
+
 # Model aliases - use friendly names instead of full provider model names
 model_aliases:
   fast-llm: