@turmind/halo 0.2.6 → 1.0.0

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

@@ -1,16 +1,17 @@
 id: aws-bedrock-mantle
 displayName: AWS Bedrock Mantle (OpenAI GPT-5.x)
 displayName_zh: AWS Bedrock Mantle（OpenAI GPT-5.x）
-description: OpenAI GPT-5.5 / 5.4 on Amazon Bedrock via the bedrock-mantle endpoint (OpenAI Responses API only — not Converse/InvokeModel). us-east-2 only.
-description_zh: 通过 Bedrock Mantle 端点调用 OpenAI GPT-5.5 / 5.4（仅 OpenAI Responses API，不支持 Converse/InvokeModel）。仅 us-east-2。
+description: OpenAI GPT-5.6 (Sol / Terra / Luna) on Amazon Bedrock via the bedrock-mantle endpoint (OpenAI Responses API only — not Converse/InvokeModel).
+description_zh: 通过 Bedrock Mantle 端点调用 OpenAI GPT-5.6（Sol / Terra / Luna）（仅 OpenAI Responses API，不支持 Converse/InvokeModel）。
 # Mantle is a distinct endpoint from bedrock-runtime; the OpenAI surface lives
-# under /openai/v1. GPT-5.5 is us-east-2 only (GPT-5.4 also allows us-west-2,
-# but we ship the us-east-2 endpoint that serves both).
+# under /openai/v1. Regions: us-east-2 serves ALL models below; us-west-2
+# additionally serves Terra / Luna but NOT Sol. We ship the us-east-2
+# endpoint that covers everything.
 defaultEndpoint: https://bedrock-mantle.us-east-2.api.aws/openai/v1
 endpointPresets:
   - https://bedrock-mantle.us-east-2.api.aws/openai/v1
 
-defaultModelId: openai.gpt-5.5
+defaultModelId: openai.gpt-5.6-sol
 
 # Auth: a Bedrock long-term API key passed as a Bearer token. Generate at
 # console → Bedrock → API keys → long-term. The default placeholder reads the
@@ -30,11 +31,19 @@ secrets:
 #     is sent and there's no 1h option — single 5m preset reflects reality, the
 #     runtime never writes cache control, it only reads cached_tokens back.
 #   - thinking: adaptive via reasoning.effort = low|medium|high (no budget_tokens
-#     mode; xhigh/max would be mapped down to high by the runtime).
+#     mode; xhigh/max would be mapped down to high by the runtime). Note: Mantle
+#     never surfaces reasoning summaries — output[].reasoning.summary stays empty
+#     even with reasoning.summary=detailed (verified against the live endpoint;
+#     reasoning_tokens > 0 proves thinking runs). So no thinking text is shown in
+#     the UI; that's upstream behavior, not a parsing gap.
+#   - maxOutputTokens for the 5.6 variants: not disclosed in the 5.6 model card —
+#     conservatively carried over from GPT-5.5's 64000.
 models:
-  - id: openai.gpt-5.5
-    displayName: GPT-5.5
+  # GPT-5.6 flagship.
+  - id: openai.gpt-5.6-sol
+    displayName: GPT-5.6 Sol
     maxOutputTokens: 64000
+    contextWindow: 272000
     capabilities:
       image: true
       video: false
@@ -61,9 +70,11 @@ models:
           - { value: medium, label: Medium }
           - { value: high, label: High }
 
-  - id: openai.gpt-5.4
-    displayName: GPT-5.4
+  # GPT-5.6 balanced — official line: GPT-5.5-level performance at half the price.
+  - id: openai.gpt-5.6-terra
+    displayName: GPT-5.6 Terra
     maxOutputTokens: 64000
+    contextWindow: 272000
     capabilities:
       image: true
       video: false
@@ -80,7 +91,36 @@ models:
           - { value: low, label: Low }
           - { value: medium, label: Medium }
           - { value: high, label: High }
-      # See GPT-5.5 above — final-answer length, default low, per-agent overridable.
+      # See GPT-5.6 Sol above — final-answer length, default low, per-agent overridable.
+      verbosity:
+        default: low
+        presets:
+          - { value: low, label: Low }
+          - { value: medium, label: Medium }
+          - { value: high, label: High }
+
+  # GPT-5.6 fast / low-cost.
+  - id: openai.gpt-5.6-luna
+    displayName: GPT-5.6 Luna
+    maxOutputTokens: 64000
+    contextWindow: 272000
+    capabilities:
+      image: true
+      video: false
+      audio: false
+      promptCaching:
+        default: 5m
+        ttlPresets:
+          - { value: 5m, label: 5min }
+      thinking:
+        mode: adaptive
+        defaultEnabled: true
+        default: medium
+        effortPresets:
+          - { value: low, label: Low }
+          - { value: medium, label: Medium }
+          - { value: high, label: High }
+      # See GPT-5.6 Sol above — final-answer length, default low, per-agent overridable.
       verbosity:
         default: low
         presets:

package/templates/models/deepseek.yaml

@@ -22,6 +22,7 @@ models:
   - id: deepseek-v4-pro
     displayName: DeepSeek V4 Pro
     maxOutputTokens: 65536
+    contextWindow: 1000000
     capabilities:
       image: false
       video: false
@@ -43,6 +44,7 @@ models:
   - id: deepseek-v4-flash
     displayName: DeepSeek V4 Flash
     maxOutputTokens: 65536
+    contextWindow: 1000000
     capabilities:
       image: false
       video: false

package/templates/models/doubao.yaml

@@ -40,6 +40,7 @@ models:
   - id: doubao-seed-2-0-pro-260215
     displayName: Doubao Seed 2.0 Pro
     maxOutputTokens: 16384
+    contextWindow: 256000
     capabilities:
       image: false
       video: false
@@ -67,6 +68,7 @@ models:
   - id: doubao-seed-2-0-lite-260428
     displayName: Doubao Seed 2.0 Lite
     maxOutputTokens: 16384
+    contextWindow: 256000
     capabilities:
       image: false
       video: false
@@ -91,6 +93,7 @@ models:
   - id: doubao-seed-2-0-mini-260428
     displayName: Doubao Seed 2.0 Mini
     maxOutputTokens: 16384
+    contextWindow: 256000
     capabilities:
       image: false
       video: false
@@ -115,6 +118,7 @@ models:
   - id: doubao-seed-2-0-code-preview-260215
     displayName: Doubao Seed 2.0 Code Preview
     maxOutputTokens: 16384
+    contextWindow: 256000
     capabilities:
       image: false
       video: false

package/templates/models/hunyuan.yaml

@@ -33,6 +33,7 @@ models:
   - id: hy3-preview
     displayName: Hunyuan Hy3 Preview
     maxOutputTokens: 16384
+    contextWindow: 256000
     capabilities:
       image: false
       video: false

package/templates/models/kimi.yaml

@@ -1,8 +1,8 @@
 id: kimi
 displayName: Kimi (Moonshot AI)
 displayName_zh: Kimi（月之暗面）
-description: Kimi K2.6 via OpenAI-compatible chat completions API
-description_zh: Kimi K2.6，通过 OpenAI 兼容的 chat completions API 调用
+description: Kimi K3 / K2.6 via OpenAI-compatible chat completions API
+description_zh: Kimi K3 / K2.6，通过 OpenAI 兼容的 chat completions API 调用
 defaultEndpoint: https://api.moonshot.cn/v1
 
 secrets:
@@ -12,18 +12,53 @@ secrets:
     default: <<KIMI_API_KEY>>
     secret: true
 
-# Capabilities verified 2026-05-27 via live probes. Kimi-k2.6 returns
-# "prepare image failed" on image_url blocks despite past docs claiming
-# vision — set image:false until/unless a vision-specific model id is
-# tested here. reasoning_effort accepts { minimal, low, medium, high };
-# `max` errors with explicit message listing the four valid values.
-# Caching is automatic; cached_tokens shows up reliably from turn 2 once
-# the prompt is long enough (~2K+).
+# Capability notes (per-model specifics live on each entry):
+#   - Caching is automatic on both models; cached_tokens shows up reliably
+#     from turn 2 once the prompt is long enough (~2K+).
+#   - Thinking control is TWO separate mechanisms depending on generation:
+#     K3 uses the top-level `reasoning_effort` field (enum currently only
+#     "max" per the official OpenAPI schema); K2.x uses the
+#     `thinking:{type:'enabled'|'disabled'}` toggle and has NO
+#     reasoning_effort field at all (OpenAPI marks it unsupported for
+#     k2.6). An earlier comment here claiming K2.6 accepts
+#     reasoning_effort { minimal, low, medium, high } was wrong.
 models:
+  - id: kimi-k3
+    displayName: Kimi K3
+    # Official default output cap; the model can go up to 1M but we don't max out.
+    maxOutputTokens: 131072
+    contextWindow: 1048576
+    capabilities:
+      # K3 itself also supports video input, but Halo has no video upload
+      # path yet — keep video:false until one exists. Image input is
+      # base64-only (public URLs are not supported); kimi-agent happens to
+      # send only base64 data URLs, so it's naturally compatible.
+      image: true
+      video: false
+      audio: false
+      promptCaching:
+        # Automatic caching, hint-only (prompt_cache_key) — same as K2.6.
+        default: 5m
+        ttlPresets:
+          - { value: 5m, label: 5min }
+      thinking:
+        # K3 thinking is ALWAYS ON server-side — there is no off switch.
+        # The only knob is the top-level `reasoning_effort` field, whose
+        # enum currently contains just "max" (confirmed in the official
+        # OpenAPI schema). Do NOT send the K2.x `thinking` parameter to K3.
+        defaultEnabled: true
+        default: max
+        effortPresets:
+          - { value: max, label: Max }
+
   - id: kimi-k2.6
     displayName: Kimi K2.6
     maxOutputTokens: 32768
+    contextWindow: 262144
     capabilities:
+      # Verified 2026-05-27 via live probes: kimi-k2.6 returns "prepare
+      # image failed" on image_url blocks despite past docs claiming
+      # vision — keep image:false.
       image: false
       video: false
       audio: false
@@ -32,10 +67,11 @@ models:
         ttlPresets:
           - { value: 5m, label: 5min }
       thinking:
+        # K2.6 has NO reasoning_effort field — its only reasoning control is
+        # the top-level `thinking:{type:'enabled'|'disabled'}` on/off toggle.
+        # The effort label below is Halo-side only (doubao precedent):
+        # kimi-agent just maps enabled → omit / disabled → thinking:disabled.
         defaultEnabled: true
         default: medium
         effortPresets:
-          - { value: minimal, label: Minimal }
-          - { value: low, label: Low }
-          - { value: medium, label: Medium }
-          - { value: high, label: High }
+          - { value: medium, label: On }

package/templates/models/mimo-token-plan-china.yaml

@@ -19,6 +19,7 @@ models:
   - id: mimo-v2.5-pro
     displayName: MiMo v2.5 Pro
     maxOutputTokens: 131072
+    contextWindow: 1048576
     capabilities:
       image: false
       video: false
@@ -41,6 +42,7 @@ models:
   - id: mimo-v2.5
     displayName: MiMo v2.5
     maxOutputTokens: 131072
+    contextWindow: 1048576
     capabilities:
       image: true
       video: false

package/templates/models/minimax.yaml

@@ -1,10 +1,10 @@
 id: minimax
 displayName: MiniMax
 displayName_zh: MiniMax
-description: MiniMax M2.7 family via the Anthropic-compatible Messages API
-description_zh: MiniMax M2.7 系列，通过 Anthropic 兼容的 Messages API 调用
+description: MiniMax M3 / M2.7 family via the Anthropic-compatible Messages API
+description_zh: MiniMax M3 / M2.7 系列，通过 Anthropic 兼容的 Messages API 调用
 defaultEndpoint: https://api.minimaxi.com/anthropic
-defaultModelId: MiniMax-M2.7
+defaultModelId: MiniMax-M3
 
 secrets:
   - key: api_key
@@ -16,11 +16,12 @@ secrets:
 # Capability notes for MiniMax M2.7 family — verified against
 # platform.minimaxi.com/docs/api-reference/text-anthropic-api on 2026-05-26
 # plus live probes against MiniMax-M2.7:
-#   - image / video / audio: documented as not supported
+#   - image / video / audio: documented as not supported (M2.x; M3 differs —
+#     see its entry)
 #   - thinking: forced on — `thinking:{type:'disabled'}` and omitting the
 #     field both still produce thinking blocks; only budget_tokens influences
 #     output. So we don't expose an off toggle.
-#   - cache_control: both models support caching. Doc says TTL is 5min,
+#   - cache_control: both M2.7 models support caching. Doc says TTL is 5min,
 #     refreshing automatically on each hit. cache_control:{type:'ephemeral'}
 #     is the only shape — no longer-TTL knob exposed by MiniMax.
 #       - MiniMax-M2.7-highspeed: turn 1 reports cache_creation_input_tokens=N,
@@ -35,9 +36,39 @@ secrets:
 #     observed to truncate the run with stop=max_tokens before any thinking
 #     completes — leaving it out of the preset list. medium/high are safe.
 models:
+  - id: MiniMax-M3
+    displayName: MiniMax M3
+    # Official recommended value; hard cap is 524288 but we don't max out.
+    maxOutputTokens: 131072
+    contextWindow: 1000000
+    capabilities:
+      # M3 also supports video input, but Halo has no video upload path yet —
+      # keep video:false until one exists. Image rides the Anthropic-compatible
+      # API's standard image blocks; minimax-agent passes this.messages
+      # straight through, so no agent code change is needed.
+      image: true
+      video: false
+      audio: false
+      # No promptCaching key on purpose: both official caching docs agree
+      # that explicit caching (cache_control) is only supported on the
+      # M2.7/M2.5/M2.1/M2 families — NOT M3. M3 only has passive automatic
+      # caching (no parameter; usage reports cache_read, which the agent
+      # already reads). Omitting the key keeps the UI toggle away so users
+      # can't configure the unsupported M3+cache_control combination.
+      thinking:
+        # M3 thinking is off by default; enabling sends
+        # thinking:{type:'adaptive'} — no low/medium/high grading and no
+        # budget_tokens. This is the opposite of M2.x's manual+budget scheme.
+        mode: adaptive
+        defaultEnabled: true
+        default: adaptive
+        effortPresets:
+          - { value: adaptive, label: Adaptive }
+
   - id: MiniMax-M2.7
     displayName: MiniMax M2.7
     maxOutputTokens: 16384
+    contextWindow: 204800
     capabilities:
       image: false
       video: false
@@ -62,6 +93,7 @@ models:
   - id: MiniMax-M2.7-highspeed
     displayName: MiniMax M2.7 Highspeed
     maxOutputTokens: 16384
+    contextWindow: 204800
     capabilities:
       image: false
       video: false

package/templates/models/openai.yaml

@@ -30,6 +30,7 @@ models:
   - id: gpt-4o
     displayName: GPT-4o (placeholder)
     maxOutputTokens: 16384
+    contextWindow: 128000
     capabilities:
       image: true
       video: true

package/templates/models/qwen.yaml

@@ -38,6 +38,7 @@ models:
   - id: qwen3.7-max
     displayName: Qwen3.7 Max
     maxOutputTokens: 16384
+    contextWindow: 1000000
     capabilities:
       image: false
       video: false
@@ -60,6 +61,7 @@ models:
   - id: qwen3.6-plus
     displayName: Qwen3.6 Plus
     maxOutputTokens: 16384
+    contextWindow: 1000000
     capabilities:
       image: true
       video: false