llm.rb 15.0.2 → 15.1.0

data/bin/llm.rb

@@ -49,16 +49,20 @@ def help
   warn ""
   warn "Options:"
   warn "  -p PROVIDER    Choose a provider"
+  warn "  -m MODEL       Choose a model"
   warn "  -c STRATEGY    Concurrency strategy for tool calls (eg thread, async, fork)"
   warn "  -n TRANSPORT   HTTP transports - net-http (default), net-http-persistent, and curb"
+  warn "  -x TIMEOUT     The default read timeout (in seconds)"
   warn "  -t             Temporary session that doesn't persist to disk"
   warn "  -h             Show this help"
   warn ""
   warn "Examples:"
   warn "  #{prog}                     # auto-detect provider from $PROVIDER_API_KEY"
   warn "  #{prog} -p openai           # use OpenAI"
+  warn "  #{prog} -m gpt-5.6          # use a model other than the provider default"
   warn "  #{prog} -n curb             # use libcurl"
   warn "  #{prog} -c thread           # run tool calls on a separate thread"
+  warn "  #{prog} -x 900              # read timeout of 15mins"
   warn "  #{prog} -h                  # this help"
   warn ""
 end
@@ -94,6 +98,11 @@ def fatal(ex)
     wrapped detail, "     "
   end
   warn ""
+  warn "     Backtrace:"
+  ex.backtrace.drop(1).first(3).each do |line|
+    wrapped line, "       "
+  end
+  warn ""
   warn "     This is an unexpected error. If it keeps happening,"
   warn "     consider opening an issue at"
   warn "     https://github.com/r-uby-dev/llm/issues"
@@ -153,6 +162,22 @@ def main(argv)
           help
           exit 1
         end
+      when '-m'
+        model = argv.shift
+        if model.nil?
+          warn "llm.rb: -m switch requires an argument"
+          help
+          exit 1
+        end
+      when '-x'
+        timeout = argv.shift
+        if timeout.nil?
+          warn "llm.rb: -x switch requires an argument"
+          help
+          exit 1
+        else
+          timeout = Integer(timeout)
+        end
       else
         warn "llm.rb: unknown option #{option}"
         help
@@ -164,9 +189,10 @@ def main(argv)
     # No provider has been given.
     # Try to infer one.
     transport ||= :net_http
+    options = timeout ? {timeout:, transport:} : {transport:}
     if provider.nil?
       llm = providers.filter_map do
-        LLM.method(_1).call(transport:)
+        LLM.method(_1).call(**options)
       rescue ArgumentError
       end.first
       if llm.nil?
@@ -175,7 +201,7 @@ def main(argv)
       end
     else
       begin
-        llm = LLM.method(provider).call(transport:)
+        llm = LLM.method(provider).call(**options)
       rescue ArgumentError
         warn "llm.rb: set credentials for #{provider}"
         exit 1
@@ -209,11 +235,20 @@ def main(argv)
       File.binwrite file, JSON.pretty_generate(data)
     end
 
+    if model
+      if not llm.registry.keys.include?(model)
+        warn "llm.rb: #{model} is not a valid #{llm.name} model"
+        exit 1
+      end
+    else
+      model = llm.default_model
+    end
+
     ##
     # Let's go!
     concurrency ||= :sequential
     path  = temp ? nil : data[Dir.getwd]
-    agent = LLM::Agent.new(llm, path:, concurrency:, tools: LLM::Tool.subclasses)
+    agent = LLM::Agent.new(llm, model:, path:, concurrency:, tools: LLM::Tool.subclasses)
     agent.repl
   rescue Interrupt
     warn "llm.rb: Bye!"

data/data/bedrock.json

@@ -435,6 +435,73 @@
         "cache_write": 4.125
       }
     },
+    "global.openai.gpt-5.6-sol": {
+      "id": "global.openai.gpt-5.6-sol",
+      "name": "GPT-5.6 Sol (Global)",
+      "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 5.5,
+        "output": 33,
+        "cache_read": 0.55,
+        "cache_write": 6.875,
+        "tiers": [
+          {
+            "input": 11,
+            "output": 49.5,
+            "cache_read": 1.1,
+            "cache_write": 13.75,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 11,
+          "output": 49.5,
+          "cache_read": 1.1,
+          "cache_write": 13.75
+        }
+      }
+    },
     "jp.anthropic.claude-sonnet-4-6": {
       "id": "jp.anthropic.claude-sonnet-4-6",
       "name": "Claude Sonnet 4.6 (JP)",
@@ -1907,6 +1974,55 @@
         "cache_write": 6.25
       }
     },
+    "xai.grok-4.6": {
+      "id": "xai.grok-4.6",
+      "name": "Grok 4.6",
+      "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
+      "family": "grok",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "knowledge": "2026-02-01",
+      "release_date": "2026-08-12",
+      "last_updated": "2026-08-18",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 500000,
+        "output": 500000
+      },
+      "provider": {
+        "npm": "@ai-sdk/amazon-bedrock/mantle",
+        "api": "https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1",
+        "shape": "responses"
+      },
+      "cost": {
+        "input": 2.2,
+        "output": 6.6,
+        "cache_read": 0.55
+      }
+    },
     "anthropic.claude-sonnet-4-6": {
       "id": "anthropic.claude-sonnet-4-6",
       "name": "Claude Sonnet 4.6",
@@ -3167,6 +3283,73 @@
         "cache_read": 0.2
       }
     },
+    "global.openai.gpt-5.6-luna": {
+      "id": "global.openai.gpt-5.6-luna",
+      "name": "GPT-5.6 Luna (Global)",
+      "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
+      "family": "gpt-luna",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 0.22,
+        "output": 1.32,
+        "cache_read": 0.022,
+        "cache_write": 0.275,
+        "tiers": [
+          {
+            "input": 0.44,
+            "output": 1.98,
+            "cache_read": 0.044,
+            "cache_write": 0.55,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.44,
+          "output": 1.98,
+          "cache_read": 0.044,
+          "cache_write": 0.55
+        }
+      }
+    },
     "zai.glm-4.7": {
       "id": "zai.glm-4.7",
       "name": "GLM-4.7",
@@ -3867,6 +4050,73 @@
         "cache_write": 3.75
       }
     },
+    "global.openai.gpt-5.6-terra": {
+      "id": "global.openai.gpt-5.6-terra",
+      "name": "GPT-5.6 Terra (Global)",
+      "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
+      "family": "gpt-terra",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-07-09",
+      "last_updated": "2026-07-09",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2.2,
+        "output": 13.2,
+        "cache_read": 0.22,
+        "cache_write": 2.75,
+        "tiers": [
+          {
+            "input": 4.4,
+            "output": 19.8,
+            "cache_read": 0.44,
+            "cache_write": 5.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4.4,
+          "output": 19.8,
+          "cache_read": 0.44,
+          "cache_write": 5.5
+        }
+      }
+    },
     "openai.gpt-oss-20b-1:0": {
       "id": "openai.gpt-oss-20b-1:0",
       "name": "gpt-oss-20b",

data/data/deepinfra.json

@@ -1053,6 +1053,49 @@
         "cache_read": 0.135
       }
     },
+    "deepseek-ai/DeepSeek-V4-Pro-0813": {
+      "id": "deepseek-ai/DeepSeek-V4-Pro-0813",
+      "name": "DeepSeek V4 Pro 0813",
+      "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
+      "family": "deepseek-thinking",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-08-12",
+      "last_updated": "2026-08-12",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1048576,
+        "output": 384000
+      },
+      "cost": {
+        "input": 1.3,
+        "output": 2.6,
+        "cache_read": 0.1
+      }
+    },
     "deepseek-ai/DeepSeek-V3": {
       "id": "deepseek-ai/DeepSeek-V3",
       "name": "DeepSeek-V3",
@@ -1195,6 +1238,39 @@
         "output": 0.55
       }
     },
+    "Qwen/Qwen3-VL-235B-A22B-Instruct": {
+      "id": "Qwen/Qwen3-VL-235B-A22B-Instruct",
+      "name": "Qwen3 VL 235B A22B Instruct",
+      "description": "Qwen vision-language instruct model for visual reasoning, documents, and agent tasks",
+      "family": "qwen",
+      "attachment": true,
+      "reasoning": false,
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "knowledge": "2025-03-31",
+      "release_date": "2025-09-23",
+      "last_updated": "2025-09-23",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 32768
+      },
+      "cost": {
+        "input": 0.2,
+        "output": 0.88,
+        "cache_read": 0.11
+      }
+    },
     "Qwen/Qwen3.6-27B": {
       "id": "Qwen/Qwen3.6-27B",
       "name": "Qwen3.6 27B",
@@ -1665,6 +1741,92 @@
         "output": 0.95
       }
     },
+    "Qwen/Qwen3.8-2.4T-A95B": {
+      "id": "Qwen/Qwen3.8-2.4T-A95B",
+      "name": "Qwen3.8 2.4T A95B",
+      "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows",
+      "family": "qwen",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-08-12",
+      "last_updated": "2026-08-12",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 131072
+      },
+      "cost": {
+        "input": 2,
+        "output": 6,
+        "cache_read": 0.2
+      }
+    },
+    "Qwen/Qwen3.8-27B": {
+      "id": "Qwen/Qwen3.8-27B",
+      "name": "Qwen3.8 27B",
+      "description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
+      "family": "qwen",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-08-14",
+      "last_updated": "2026-08-14",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 32768
+      },
+      "cost": {
+        "input": 0.4,
+        "output": 3,
+        "cache_read": 0.04
+      }
+    },
     "Qwen/Qwen3-Next-80B-A3B-Instruct": {
       "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
       "name": "Qwen3-Next 80B-A3B Instruct",

data/data/deepseek.json

@@ -170,6 +170,56 @@
         "reasoning": 0.28,
         "cache_read": 0.0028
       }
+    },
+    "deepseek-v4-flash-vision-exp": {
+      "id": "deepseek-v4-flash-vision-exp",
+      "name": "DeepSeek V4 Flash Vision Exp",
+      "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work",
+      "family": "deepseek-flash",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "interleaved": {
+        "field": "reasoning_content"
+      },
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-08-21",
+      "last_updated": "2026-08-21",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 384000
+      },
+      "status": "beta",
+      "cost": {
+        "input": 0.14,
+        "output": 0.28,
+        "reasoning": 0.28,
+        "cache_read": 0.0028
+      }
     }
   }
 }

data/data/google.json

@@ -149,7 +149,7 @@
     "gemini-flash-lite-latest": {
       "id": "gemini-flash-lite-latest",
       "name": "Gemini Flash-Lite Latest",
-      "description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
+      "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
       "family": "gemini-flash-lite",
       "attachment": true,
       "reasoning": true,
@@ -167,9 +167,9 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2025-01",
-      "release_date": "2026-05-07",
-      "last_updated": "2026-05-07",
+      "knowledge": "2026-03",
+      "release_date": "2026-07-21",
+      "last_updated": "2026-07-21",
       "modalities": {
         "input": [
           "text",
@@ -188,10 +188,9 @@
         "output": 65536
       },
       "cost": {
-        "input": 0.25,
-        "output": 1.5,
-        "cache_read": 0.025,
-        "input_audio": 0.5
+        "input": 0.3,
+        "output": 2.5,
+        "cache_read": 0.03
       }
     },
     "gemini-3.5-flash-lite": {
@@ -751,7 +750,7 @@
     "gemini-flash-latest": {
       "id": "gemini-flash-latest",
       "name": "Gemini Flash Latest",
-      "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
+      "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
       "family": "gemini-flash",
       "attachment": true,
       "reasoning": true,
@@ -759,7 +758,6 @@
         {
           "type": "effort",
           "values": [
-            "minimal",
             "low",
             "medium",
             "high"
@@ -769,9 +767,9 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2025-01",
-      "release_date": "2026-05-19",
-      "last_updated": "2026-05-19",
+      "knowledge": "2026-03",
+      "release_date": "2026-08-13",
+      "last_updated": "2026-08-13",
       "modalities": {
         "input": [
           "text",
@@ -790,10 +788,10 @@
         "output": 65536
       },
       "cost": {
-        "input": 1.5,
-        "output": 9,
-        "cache_read": 0.15,
-        "input_audio": 1.5
+        "input": 0.75,
+        "output": 3.75,
+        "cache_read": 0.075,
+        "input_audio": 0.75
       }
     },
     "gemini-3.5-flash": {
@@ -1164,10 +1162,10 @@
         "output": 65536
       },
       "cost": {
-        "input": 1.5,
-        "output": 7.5,
-        "cache_read": 0.15,
-        "input_audio": 1.5
+        "input": 0.75,
+        "output": 3.75,
+        "cache_read": 0.075,
+        "input_audio": 0.75
       }
     },
     "gemini-3.1-flash-image": {