@turmind/halo 2.1.1 → 2.1.3

package/templates/models/aws-bedrock-openai.yaml

@@ -1,6 +1,6 @@
 id: aws-bedrock-openai
 runtime: bedrock-mantle
-revision: 2026102701
+revision: 2026110402
 displayName: AWS Bedrock OpenAI-compatible (GPT-6.1 / 6 / 5.6 · Grok 4.7 / 4.6 · Kimi K3 · GLM 5.3)
 displayName_zh: AWS Bedrock OpenAI 兼容接口（GPT-6.1 / 6 / 5.6 · Grok 4.7 / 4.6 · Kimi K3 · GLM 5.3）
 description: Frontier models on Amazon Bedrock via the bedrock-runtime endpoint's OpenAI Responses API (/openai/v1) — OpenAI GPT-6.1 (Sol / Terra), GPT-6 (Astra / Sol / Luna) and GPT-5.6 (Sol / Terra / Luna), xAI Grok 4.7 / 4.6, Moonshot Kimi K3, Z.AI GLM 5.3. Cross-Region inference profiles (global.*) only — every region serves every model, no region split. No server-side web_search (that is Mantle-only).
@@ -56,8 +56,12 @@ secrets:
 #     field (model default) — it does not send `none`. Good thing too: on this
 #     host GPT-6 Astra and GPT-6.1 Sol 400 on `none` while every other GPT
 #     accepts it.
-#   - Reasoning summaries are never surfaced (output[].reasoning.summary
-#     empty) — same as GPT on Mantle; reasoning_tokens > 0 proves it ran.
+#   - reasoning summaries: returned when requested — with reasoning.summary=
+#     detailed, output[].reasoning.summary carries summary_text (live-probed
+#     2026-10-22 on us.openai.gpt-6-astra, same as GPT on Mantle; the GPT-6.x /
+#     5.6 Bedrock model cards list Reasoning Summaries for bedrock-runtime
+#     Responses). MantleAgent sends only reasoning.effort, never
+#     reasoning.summary, so no thinking text shows in the UI.
 models:
   # OpenAI GPT-6.1 / GPT-6 / GPT-5.6 — the same eight models as
   # aws-bedrock-mantle.yaml (see that file for the per-model background: