fix(models): raise max_tokens to 98304 for reasoning models

Reasoning models share a single max_tokens budget between the <think> phase
and the answer. With 49152, a hard prompt could spend the entire budget on
reasoning and hit finish_reason=length before emitting any answer (observed
with GLM-5.2 on a complex coding task). OpenAI-compatible APIs expose no
separate reasoning budget, so the lever is a larger shared cap.

Raise every supportsReasoning model with an explicit cap below 98304 (2x the
common 49152) to 98304, giving room for both reasoning and the answer. Only
reasoning lines are touched; non-reasoning models keep their caps. These are
1M / 256K-context models, so the larger output cap fits the context window.

Note: reasoning models without an explicit cap (e.g. GLM-4.7, MiniMax-M2,
Kimi-K2-Thinking) still fall back to the provider default and are left as-is.

Author: gary149

chart/env/dev.yaml

@@ -82,26 +82,26 @@ envVars:
   MODELS: >
     [
       { "id": "omni", "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 65536 } },
-      { "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 65536 } },
-      { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
+      { "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
+      { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "Qwen/Qwen3.6-27B", "description": "Dense 27B hybrid with DeltaNet attention and 1M context.", "supportsArtifacts": true },
       { "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "description": "Native multimodal 17B MoE with 16 experts and very long context."},
       { "id": "CohereLabs/c4ai-command-r7b-12-2024", "description": "Compact 7B Command R for multilingual RAG, tool use, and agents." },
       { "id": "pearl-ai/Gemma-4-31B-it-pearl", "description": "Community Gemma-4-31B variant integrated with Pearl mining for chain-validated inference."},
       { "id": "inclusionAI/Ling-2.6-1T", "description": "1T MoE with 50B active params, hybrid MLA-Linear attention, and fast thinking.", "supportsArtifacts": true },
-      { "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "deepseek-ai/DeepSeek-V4-Flash", "description": "Compact 284B MoE with 13B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsArtifacts": true },
       { "id": "deepseek-ai/DeepSeek-V3.2", "description": "Stable 671B MoE with sparse attention for agentic reasoning and long contexts.", "supportsArtifacts": true },
       { "id": "stepfun-ai/Step-3.5-Flash", "description": "Sparse 197B MoE agent with multi-token prediction and 256K context.", "supportsArtifacts": true },
       { "id": "Qwen/Qwen3.6-35B-A3B", "description": "Hybrid 35B MoE with 3B active params, DeltaNet attention, and 1M context.", "supportsArtifacts": true },
       { "id": "zai-org/GLM-4.7-Flash", "description": "Compact 30B MoE for agentic coding with 128K context and tool use.", "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "moonshotai/Kimi-K2.6", "description": "Native multimodal 1T MoE for long-horizon coding and 300-sub-agent swarms.", "supportsArtifacts": true },
       { "id": "MiniMaxAI/MiniMax-M2.7", "description": "Self-evolving 230B MoE agent for frontier coding, reasoning, and tool use." , "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.1", "description": "Upgraded 754B MoE for agentic coding, extended reasoning, and tool use.", "parameters": { "max_tokens": 49152 } , "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.1-FP8", "description": "FP8 GLM-5.1 for efficient agentic coding and reasoning inference.", "parameters": { "max_tokens": 49152 } , "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.1", "description": "Upgraded 754B MoE for agentic coding, extended reasoning, and tool use.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.1-FP8", "description": "FP8 GLM-5.1 for efficient agentic coding and reasoning inference.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "google/gemma-4-31B-it", "description": "Dense multimodal Gemma with 256K context, reasoning, and function calling."},
       { "id": "google/gemma-4-26B-A4B-it", "description": "Efficient multimodal MoE Gemma with 4B active params and 256K context."},
       { "id": "Qwen/Qwen3.5-9B", "description": "Dense multimodal hybrid with 262K context excelling at reasoning on-device."},

chart/env/prod.yaml

@@ -92,26 +92,26 @@ envVars:
   MODELS: >
     [
       { "id": "omni", "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 65536 } },
-      { "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 65536 } },
-      { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
+      { "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
+      { "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "Qwen/Qwen3.6-27B", "description": "Dense 27B hybrid with DeltaNet attention and 1M context.", "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
       { "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "description": "Native multimodal 17B MoE with 16 experts and very long context."},
       { "id": "CohereLabs/c4ai-command-r7b-12-2024", "description": "Compact 7B Command R for multilingual RAG, tool use, and agents." },
       { "id": "pearl-ai/Gemma-4-31B-it-pearl", "description": "Community Gemma-4-31B variant integrated with Pearl mining for chain-validated inference."},
       { "id": "inclusionAI/Ling-2.6-1T", "description": "1T MoE with 50B active params, hybrid MLA-Linear attention, and fast thinking.", "supportsArtifacts": true, "parameters": { "max_tokens": 32768 } },
-      { "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "deepseek-ai/DeepSeek-V4-Flash", "description": "Compact 284B MoE with 13B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsArtifacts": true },
       { "id": "deepseek-ai/DeepSeek-V3.2", "description": "Stable 671B MoE with sparse attention for agentic reasoning and long contexts.", "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
       { "id": "stepfun-ai/Step-3.5-Flash", "description": "Sparse 197B MoE agent with multi-token prediction and 256K context.", "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
       { "id": "Qwen/Qwen3.6-35B-A3B", "description": "Hybrid 35B MoE with 3B active params, DeltaNet attention, and 1M context.", "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
-      { "id": "zai-org/GLM-4.7-Flash", "description": "Compact 30B MoE for agentic coding with 128K context and tool use.", "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
+      { "id": "zai-org/GLM-4.7-Flash", "description": "Compact 30B MoE for agentic coding with 128K context and tool use.", "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
       { "id": "moonshotai/Kimi-K2.6", "description": "Native multimodal 1T MoE for long-horizon coding and 300-sub-agent swarms.", "supportsArtifacts": true, "parameters": { "max_tokens": 65536 } },
-      { "id": "MiniMaxAI/MiniMax-M2.7", "description": "Self-evolving 230B MoE agent for frontier coding, reasoning, and tool use." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
-      { "id": "zai-org/GLM-5.1", "description": "Upgraded 754B MoE for agentic coding, extended reasoning, and tool use.", "parameters": { "max_tokens": 49152 } , "supportsReasoning": true, "supportsArtifacts": true },
-      { "id": "zai-org/GLM-5.1-FP8", "description": "FP8 GLM-5.1 for efficient agentic coding and reasoning inference.", "parameters": { "max_tokens": 49152 } , "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "MiniMaxAI/MiniMax-M2.7", "description": "Self-evolving 230B MoE agent for frontier coding, reasoning, and tool use." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
+      { "id": "zai-org/GLM-5.1", "description": "Upgraded 754B MoE for agentic coding, extended reasoning, and tool use.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
+      { "id": "zai-org/GLM-5.1-FP8", "description": "FP8 GLM-5.1 for efficient agentic coding and reasoning inference.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
       { "id": "google/gemma-4-31B-it", "description": "Dense multimodal Gemma with 256K context, reasoning, and function calling."},
       { "id": "google/gemma-4-26B-A4B-it", "description": "Efficient multimodal MoE Gemma with 4B active params and 256K context."},
       { "id": "Qwen/Qwen3.5-9B", "description": "Dense multimodal hybrid with 262K context excelling at reasoning on-device."},
@@ -161,7 +161,7 @@ envVars:
       { "id": "moonshotai/Kimi-K2-Instruct-0905", "description": "Instruction MoE strong coding and multi step reasoning, long context." },
       { "id": "openai/gpt-oss-20b", "description": "Efficient open model for reasoning and tool use, runs locally." , "supportsReasoning": true },
       { "id": "swiss-ai/Apertus-8B-Instruct-2509", "description": "Open, multilingual, trained on compliant data transparent global assistant." },
-      { "id": "openai/gpt-oss-120b", "description": "High performing open model suitable for large scale applications." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 49152 } },
+      { "id": "openai/gpt-oss-120b", "description": "High performing open model suitable for large scale applications." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
       { "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "description": "Code specialized Qwen long context strong generation and function calling." },
       { "id": "meta-llama/Llama-3.1-8B-Instruct", "description": "Instruction tuned Llama efficient conversational assistant with improved alignment." },
       { "id": "deepseek-ai/DeepSeek-R1", "description": "MoE reasoning model excels at math, logic, coding with steps."},