llm.rb 12.1.0 → 12.3.0

data/data/openai.json

@@ -124,6 +124,99 @@
         "output": 168
       }
     },
+    "gpt-5.6": {
+      "id": "gpt-5.6",
+      "name": "GPT-5.6",
+      "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
+      "family": "gpt",
+      "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
+      },
+      "experimental": {
+        "modes": {
+          "fast": {
+            "cost": {
+              "input": 10,
+              "output": 60,
+              "cache_read": 1,
+              "cache_write": 12.5
+            },
+            "provider": {
+              "body": {
+                "service_tier": "priority"
+              }
+            }
+          },
+          "pro": {
+            "provider": {
+              "body": {
+                "reasoning": {
+                  "mode": "pro"
+                }
+              }
+            }
+          }
+        }
+      },
+      "cost": {
+        "input": 5,
+        "output": 30,
+        "cache_read": 0.5,
+        "cache_write": 6.25,
+        "tiers": [
+          {
+            "input": 10,
+            "output": 45,
+            "cache_read": 1,
+            "cache_write": 12.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 10,
+          "output": 45,
+          "cache_read": 1,
+          "cache_write": 12.5
+        }
+      }
+    },
     "gpt-5": {
       "id": "gpt-5",
       "name": "GPT-5",
@@ -930,6 +1023,99 @@
         "output": 0
       }
     },
+    "gpt-5.6-luna": {
+      "id": "gpt-5.6-luna",
+      "name": "GPT-5.6 Luna",
+      "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
+      "family": "gpt-nano",
+      "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
+      },
+      "experimental": {
+        "modes": {
+          "fast": {
+            "cost": {
+              "input": 2,
+              "output": 12,
+              "cache_read": 0.2,
+              "cache_write": 2.5
+            },
+            "provider": {
+              "body": {
+                "service_tier": "priority"
+              }
+            }
+          },
+          "pro": {
+            "provider": {
+              "body": {
+                "reasoning": {
+                  "mode": "pro"
+                }
+              }
+            }
+          }
+        }
+      },
+      "cost": {
+        "input": 1,
+        "output": 6,
+        "cache_read": 0.1,
+        "cache_write": 1.25,
+        "tiers": [
+          {
+            "input": 2,
+            "output": 9,
+            "cache_read": 0.2,
+            "cache_write": 2.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 2,
+          "output": 9,
+          "cache_read": 0.2,
+          "cache_write": 2.5
+        }
+      }
+    },
     "gpt-5.1-codex-mini": {
       "id": "gpt-5.1-codex-mini",
       "name": "GPT-5.1 Codex mini",
@@ -974,6 +1160,149 @@
         "cache_read": 0.025
       }
     },
+    "gpt-realtime-2.1": {
+      "id": "gpt-realtime-2.1",
+      "name": "GPT-Realtime-2.1",
+      "description": "Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior",
+      "family": "gpt",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "minimal",
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": false,
+      "knowledge": "2024-09-30",
+      "release_date": "2026-07-06",
+      "last_updated": "2026-07-06",
+      "modalities": {
+        "input": [
+          "text",
+          "audio",
+          "image"
+        ],
+        "output": [
+          "text",
+          "audio"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 128000,
+        "input": 96000,
+        "output": 32000
+      },
+      "cost": {
+        "input": 4,
+        "output": 24,
+        "cache_read": 0.4,
+        "input_audio": 32,
+        "output_audio": 64
+      }
+    },
+    "gpt-5.6-terra": {
+      "id": "gpt-5.6-terra",
+      "name": "GPT-5.6 Terra",
+      "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
+      "family": "gpt-mini",
+      "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
+      },
+      "experimental": {
+        "modes": {
+          "fast": {
+            "cost": {
+              "input": 5,
+              "output": 30,
+              "cache_read": 0.5,
+              "cache_write": 6.25
+            },
+            "provider": {
+              "body": {
+                "service_tier": "priority"
+              }
+            }
+          },
+          "pro": {
+            "provider": {
+              "body": {
+                "reasoning": {
+                  "mode": "pro"
+                }
+              }
+            }
+          }
+        }
+      },
+      "cost": {
+        "input": 2.5,
+        "output": 15,
+        "cache_read": 0.25,
+        "cache_write": 3.125,
+        "tiers": [
+          {
+            "input": 5,
+            "output": 22.5,
+            "cache_read": 0.5,
+            "cache_write": 6.25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 5,
+          "output": 22.5,
+          "cache_read": 0.5,
+          "cache_write": 6.25
+        }
+      }
+    },
     "gpt-5.1-chat-latest": {
       "id": "gpt-5.1-chat-latest",
       "name": "GPT-5.1 Chat",
@@ -1851,6 +2180,99 @@
         "cache_read": 0.075
       }
     },
+    "gpt-5.6-sol": {
+      "id": "gpt-5.6-sol",
+      "name": "GPT-5.6 Sol",
+      "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
+      "family": "gpt",
+      "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
+      },
+      "experimental": {
+        "modes": {
+          "fast": {
+            "cost": {
+              "input": 10,
+              "output": 60,
+              "cache_read": 1,
+              "cache_write": 12.5
+            },
+            "provider": {
+              "body": {
+                "service_tier": "priority"
+              }
+            }
+          },
+          "pro": {
+            "provider": {
+              "body": {
+                "reasoning": {
+                  "mode": "pro"
+                }
+              }
+            }
+          }
+        }
+      },
+      "cost": {
+        "input": 5,
+        "output": 30,
+        "cache_read": 0.5,
+        "cache_write": 6.25,
+        "tiers": [
+          {
+            "input": 10,
+            "output": 45,
+            "cache_read": 1,
+            "cache_write": 12.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 10,
+          "output": 45,
+          "cache_read": 1,
+          "cache_write": 12.5
+        }
+      }
+    },
     "gpt-5-codex": {
       "id": "gpt-5-codex",
       "name": "GPT-5-Codex",

data/data/xai.json

@@ -119,7 +119,7 @@
     "grok-4.3": {
       "id": "grok-4.3",
       "name": "Grok 4.3",
-      "description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
+      "description": "xAI's Grok for chat, coding, agentic tools, and lower hallucination risk",
       "family": "grok",
       "attachment": true,
       "reasoning": true,
@@ -232,6 +232,65 @@
         "output": 0
       }
     },
+    "grok-4.5": {
+      "id": "grok-4.5",
+      "name": "Grok 4.5",
+      "description": "xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk",
+      "family": "grok",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-07-08",
+      "last_updated": "2026-07-08",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 500000,
+        "output": 500000
+      },
+      "cost": {
+        "input": 2,
+        "output": 6,
+        "cache_read": 0.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 12,
+            "cache_read": 1,
+            "tier": {
+              "type": "context",
+              "size": 200000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 12,
+          "cache_read": 1
+        }
+      }
+    },
     "grok-4.20-0309-reasoning": {
       "id": "grok-4.20-0309-reasoning",
       "name": "Grok 4.20 (Reasoning)",

data/lib/llm/active_record/acts_as_agent.rb

@@ -75,6 +75,17 @@ module LLM::ActiveRecord
         @llm
       end
 
+      ##
+      # @note
+      #  This method does not persist to the database,
+      #  but it can inspect and alter runtime state in
+      #  a way that is temporary.
+      # @param (see LLM::Agent#repl)
+      # @return (see LLM::Agent#repl)
+      def repl(**params)
+        ctx.repl(**params)
+      end
+
       private
 
       ##

data/lib/llm/agent.rb

@@ -393,10 +393,34 @@ module LLM
     # with the agent and its current state. This
     # method requires the 'curses' gem to be installed
     # and available to require.
+    #
+    # @note
+    #  By default this method disables the tracer for
+    #  the duration of the repl session, and restores
+    #  it afterwards.
+    # @param [Boolean] tracer
+    #  When true, the tracer is kept alive during the
+    #  repl session. Default is false.
+    # @param [Array<LLM::Tool>] tools
+    #  Extra tools to attach for the repl session
+    # @param [Array<String>] skills
+    #  Extra skills to attach for the repl session
     # @return [void]
-    def repl
+    def repl(tracer: false, trace: nil, tools: [], skills: [])
+      if trace != nil
+        warn "llm.rb: trace option is deprecated, use tracer instead"
+        tracer = trace
+      end
+      if !tracer
+        previous    = self.tracer
+        self.tracer = nil
+      end
       require_relative "repl" unless defined?(::LLM::Repl)
-      LLM::Repl.new(self).start
+      LLM::Repl.new(agent: self, tools:, skills:).start
+    ensure
+      if !trace
+        self.tracer = previous
+      end
     end
 
     ##
@@ -510,7 +534,7 @@ module LLM
         max = params.key?(:tool_attempts) ? params.delete(:tool_attempts) : 25
         max = Integer(max) if max
         stream = params[:stream] || @ctx.params[:stream]
-        stream.extra[:concurrency] = concurrency if LLM::Stream === stream
+        params[:stream] = LLM::Stream.try(stream, extra: {concurrency:})
         res = talk.call(apply_instructions(prompt), params)
         while @ctx.functions?
           if max

data/lib/llm/compactor.rb

@@ -71,13 +71,13 @@ class LLM::Compactor
     retention_window = [config[:retention_window], messages.size].min
     return nil unless messages.size > retention_window
     stream = ctx.params[:stream]
-    stream.on_compaction(ctx, self) if LLM::Stream === stream
+    stream.on_compaction(ctx, self)
     recent = retained_messages
     older = messages[0...(messages.size - recent.size)]
     summary = LLM::Message.new(ctx.llm.user_role, "[Previous conversation summary]\n\n#{summarize(older)}", {compaction: true})
     ctx.messages.replace([*ctx.messages.take_while(&:system?), summary, *recent])
     ctx.compacted = true
-    stream.on_compaction_finish(ctx, self) if LLM::Stream === stream
+    stream.on_compaction_finish(ctx, self)
     summary
   end