llm.rb 16.0.0.pre.5 → 16.0.0.pre.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f5558a0514d6bd6b9648f743a308ce8e6dbb3802b8709edc6caf45d7c1ab3de8
-  data.tar.gz: a5d3178f0c79e152b8032cce974be69edd1e52cc629658034a750183ccb41ea8
+  metadata.gz: 0f5c0f9cb6f92099cec46e8c7a83e02498d375458a50b8b3f19a94ac2385dc8f
+  data.tar.gz: 11929258bad683f946ded02b7b2621fcfae30cf1ed11c57007e4b4cfbac05b5d
 SHA512:
-  metadata.gz: 3a0288112d140d3e0a3e34dc35e570ceb25ad62fd7f3c33a2942cb111432992b7194e18fb406bf55a25a945aff0e89ce055c292a1de50c00b66c801027b95c52
-  data.tar.gz: 454a1c74a59401689c88947714f741ada1d39f6ce95013bf8bdd6fab76690adafd3a4be8af02e9eace2a71ae26c3f4daf3a1751fdf326549f722da888cbcb309
+  metadata.gz: 5b32ee2a9301958487a808705f63895b1cd89898730e8b0bdcabcee06be62eef6a724795ccd0f6053227f0577380019436eab3b19ba3a15459560bcc78a505af
+  data.tar.gz: 7839665a301ee3ab68716737daaddc7f384308b6b24548efcb33699a3463de83efa638aa060293a27ced6145907dee6ddabb7b63d11d5cb5f1e1a0239b2e209f

data/CHANGELOG.md

@@ -196,14 +196,17 @@
   Update `data/` with current model listings, limits, and pricing. Alibaba adds
   `qwen3.5-flash`, `qwen3.7-flash`, and `qwen3.8-omni-flash`, and gives
   `qwen3.7-plus` attachments, structured output, and a lower price; OpenAI adds
-  `gpt-daybreak-blue-latest` and `gpt-daybreak-red-latest`; Bedrock adds
-  `openai.gpt-6-sol`, `openai.gpt-6-luna`, and
-  `global.anthropic.claude-sonnet-5-5`; and DeepInfra adds `tencent/Hy4-preview`
-  and the Xiaomi MiMo V2.6 Pro and V2.6 Flash models.
+  `gpt-daybreak-blue-latest`, `gpt-daybreak-red-latest`, and `gpt-6.1-sol`, and
+  gives `gpt-6-astra` an `ultrafast` mode; Bedrock adds `openai.gpt-6-sol`,
+  `openai.gpt-6-luna`, `global.anthropic.claude-sonnet-5-5`,
+  `anthropic.claude-sonnet-5-5`, and the Grok 4.7 entries in both the global
+  and US regions; DeepInfra adds `tencent/Hy4-preview` and the Xiaomi MiMo
+  V2.6 Pro and V2.6 Flash models, and marks four older entries deprecated.
   Bedrock also corrects the context and output limits of fifteen models, Google
   lowers the limits of `gemini-2.5-computer-use-preview-10-2025` and
-  `gemini-3-pro-image`, and OpenRouter adds five models, drops six, and reprices
-  many of the DeepSeek, Z.ai, and Qwen entries.
+  `gemini-3-pro-image`, and OpenRouter adds seven models, `openai/gpt-6.1-sol`
+  and `openai/gpt-6.1-sol-pro` among them, drops six, and reprices or corrects
+  the limits of many of the DeepSeek, Z.ai, Qwen, and Tencent entries.
 
 ### Schema
 
@@ -230,6 +233,42 @@
   rate limit or a timeout calls it when it lands and not once per attempt, and
   it fires even when the stream is disabled.
 
+### Tracers
+
+* **tracer: report a request that failed** <br>
+  [`LLM::Tracer#on_request_error`](https://r.uby.dev/api-docs/llm.rb/LLM/Tracer.html#on_request_error-instance_method)
+  is now called wherever a request ends without a response, so a span that
+  [`LLM::Tracer#on_request_start`](https://r.uby.dev/api-docs/llm.rb/LLM/Tracer.html#on_request_start-instance_method)
+  returned is closed. Before this, a request was reported only when a provider
+  turned an error response into an exception, so a dropped connection or a
+  socket read that failed left the tracer holding a span it had opened and never
+  closed, which in a trace reads the same as a process that died. A failure that
+  surfaces as one of the transport's own error classes is reported the same way
+  unless the request was interrupted, and the exception the caller receives is
+  unchanged.
+
+* **tracer: add `on_interrupt`, called when a request is interrupted** <br>
+  [`LLM::Tracer#on_interrupt`](https://r.uby.dev/api-docs/llm.rb/LLM/Tracer.html#on_interrupt-instance_method)
+  is a new hook, called with a `scope:` of `:request` or `:tool` before
+  `LLM::Interrupt` reaches the caller, so a tracer that has to record what
+  happened to a turn does it while the work is still in flight. An interrupt is
+  the third ending a scope can have, beside `on_request_finish` and
+  `on_request_error`, and it is not reported as a failure. Unlike the other
+  request and tool hooks it does nothing by default, because an interrupt is
+  delivered to whatever tracer happens to be bound, and a hook that raised would
+  replace the interrupt every caller is written against. A request is announced
+  with the span that `on_request_start` returned and its `request_id`; a tool
+  pass has neither, so both arrive as `nil`.
+
+* **tracer: announce an interrupted tool phase once** <br>
+  [`LLM::Context#wait`](https://r.uby.dev/api-docs/llm.rb/LLM/Context.html#wait-instance_method)
+  now calls the hook once when an interrupt unwinds through it, rather than once
+  per tool, because a cancel reaches every tool that is running and the caller
+  hears a single exception, so the announcement belongs to the phase rather than
+  to a tool. The hook runs before the caller is given the interrupt. A `:ractor`
+  call that answers `cancelled: true` instead of raising is not announced,
+  because the phase was not interrupted; one call was retired.
+
 ## v15.5.0
 
 Changes since `v15.4.1`.

data/data/bedrock.json

@@ -777,6 +777,54 @@
       },
       "canonical_model_id": "anthropic/claude-opus-5-5"
     },
+    "anthropic.claude-sonnet-5-5": {
+      "id": "anthropic.claude-sonnet-5-5",
+      "name": "Claude Sonnet 5.5",
+      "description": "Fast Claude model for everyday coding, agents, and knowledge work",
+      "family": "claude-sonnet",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": false,
+      "knowledge": "2026-06",
+      "release_date": "2026-09-28",
+      "last_updated": "2026-09-28",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5
+      },
+      "canonical_model_id": "anthropic/claude-sonnet-5-5"
+    },
     "global.anthropic.claude-sonnet-5-5": {
       "id": "global.anthropic.claude-sonnet-5-5",
       "name": "Claude Sonnet 5.5 (Global)",
@@ -3717,6 +3765,52 @@
       },
       "canonical_model_id": "anthropic/claude-opus-5"
     },
+    "global.xai.grok-4.7": {
+      "id": "global.xai.grok-4.7",
+      "name": "Grok 4.7 (Global)",
+      "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": "2026-05",
+      "release_date": "2026-09-21",
+      "last_updated": "2026-09-28",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 500000,
+        "output": 500000
+      },
+      "cost": {
+        "input": 2,
+        "output": 6,
+        "cache_read": 0.5
+      },
+      "canonical_model_id": "xai/grok-4.7"
+    },
     "us.openai.gpt-5.6-sol": {
       "id": "us.openai.gpt-5.6-sol",
       "name": "GPT-5.6 Sol (US)",
@@ -4229,6 +4323,52 @@
       },
       "canonical_model_id": "mistral/ministral-3-3b-instruct-2512"
     },
+    "us.xai.grok-4.7": {
+      "id": "us.xai.grok-4.7",
+      "name": "Grok 4.7 (US)",
+      "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": "2026-05",
+      "release_date": "2026-09-21",
+      "last_updated": "2026-09-28",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 500000,
+        "output": 500000
+      },
+      "cost": {
+        "input": 2.2,
+        "output": 6.6,
+        "cache_read": 0.55
+      },
+      "canonical_model_id": "xai/grok-4.7"
+    },
     "us.openai.gpt-6-luna": {
       "id": "us.openai.gpt-6-luna",
       "name": "GPT-6 Luna (US)",

data/data/deepinfra.json

@@ -246,6 +246,7 @@
         "context": 1048576,
         "output": 16384
       },
+      "status": "deprecated",
       "cost": {
         "input": 1,
         "output": 3,
@@ -330,6 +331,7 @@
         "context": 262144,
         "output": 16384
       },
+      "status": "deprecated",
       "cost": {
         "input": 0.14,
         "output": 0.28,
@@ -1712,6 +1714,7 @@
         "context": 163840,
         "output": 163840
       },
+      "status": "deprecated",
       "cost": {
         "input": 0.24,
         "output": 0.9,
@@ -2022,6 +2025,7 @@
         "context": 262144,
         "output": 262144
       },
+      "status": "deprecated",
       "cost": {
         "input": 0.68,
         "output": 3.4,

data/data/openai.json

@@ -1121,6 +1121,99 @@
         "cache_read": 0.175
       }
     },
+    "gpt-6.1-sol": {
+      "id": "gpt-6.1-sol",
+      "name": "GPT-6.1 Sol",
+      "description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-04-30",
+      "release_date": "2026-09-29",
+      "last_updated": "2026-09-29",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "experimental": {
+        "modes": {
+          "fast": {
+            "cost": {
+              "input": 4,
+              "output": 20,
+              "cache_read": 0.2,
+              "cache_write": 5
+            },
+            "provider": {
+              "body": {
+                "service_tier": "priority"
+              }
+            }
+          },
+          "pro": {
+            "provider": {
+              "body": {
+                "reasoning": {
+                  "mode": "pro"
+                }
+              }
+            }
+          }
+        }
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.1,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.2,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.2,
+          "cache_write": 5
+        }
+      },
+      "canonical_model_id": "openai/gpt-6.1-sol"
+    },
     "text-embedding-3-large": {
       "id": "text-embedding-3-large",
       "name": "text-embedding-3-large",
@@ -1248,6 +1341,19 @@
                 }
               }
             }
+          },
+          "ultrafast": {
+            "cost": {
+              "input": 60,
+              "output": 300,
+              "cache_read": 6,
+              "cache_write": 75
+            },
+            "provider": {
+              "body": {
+                "service_tier": "ultrafast"
+              }
+            }
           }
         }
       },

data/data/openrouter.json

@@ -518,9 +518,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.4,
-        "output": 10,
-        "cache_read": 0.4
+        "input": 0.29,
+        "output": 9,
+        "cache_read": 0.28
       }
     },
     "poolside/laguna-s-2.1:free": {
@@ -1859,13 +1859,13 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 943718
       },
       "cost": {
-        "input": 0.018,
-        "output": 0.32,
-        "cache_read": 0.018
+        "input": 0.01,
+        "output": 1.28,
+        "cache_read": 0.01
       },
       "canonical_model_id": "deepseek/deepseek-v4-flash-0731"
     },
@@ -1910,9 +1910,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.3,
-        "output": 1.2,
-        "cache_read": 0.006
+        "input": 0.0198,
+        "output": 0.396,
+        "cache_read": 0.00291
       },
       "canonical_model_id": "deepseek/deepseek-v4.1-flash"
     },
@@ -2067,12 +2067,12 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 943718
+        "output": 393216
       },
       "cost": {
-        "input": 0.4,
-        "output": 4.2,
-        "cache_read": 0.32
+        "input": 0.66,
+        "output": 1.98,
+        "cache_read": 0.022
       },
       "canonical_model_id": "deepseek/deepseek-v4-pro-0813"
     },
@@ -2219,9 +2219,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 0.95526,
-        "output": 1.91052,
-        "cache_read": 0.079605
+        "input": 0.783,
+        "output": 1.566,
+        "cache_read": 0.06525
       },
       "canonical_model_id": "deepseek/deepseek-v4-pro"
     },
@@ -2335,12 +2335,12 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 131072
+        "output": 384000
       },
       "cost": {
-        "input": 0.14,
-        "output": 0.28,
-        "cache_read": 0.028
+        "input": 0.07854,
+        "output": 0.15708,
+        "cache_read": 0.015708
       },
       "canonical_model_id": "deepseek/deepseek-v4-flash"
     },
@@ -2551,9 +2551,9 @@
         "output": 128000
       },
       "cost": {
-        "input": 0.132,
-        "output": 0.528,
-        "cache_read": 0.033
+        "input": 0.0825,
+        "output": 0.33,
+        "cache_read": 0.020625
       },
       "canonical_model_id": "tencent/hy3"
     },
@@ -2623,9 +2623,9 @@
         "output": 64000
       },
       "cost": {
-        "input": 0.834,
-        "output": 2.501,
-        "cache_read": 0.042
+        "input": 0.7506,
+        "output": 2.2509,
+        "cache_read": 0.0378
       },
       "canonical_model_id": "tencent/hy4-preview"
     },
@@ -3142,7 +3142,7 @@
       "cost": {
         "input": 0.3,
         "output": 0.9,
-        "cache_read": 0.05
+        "cache_read": 0.055
       },
       "canonical_model_id": "zhipuai/glm-4.6v"
     },
@@ -3298,7 +3298,7 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 943717
       },
       "cost": {
@@ -3590,9 +3590,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.3249,
-        "output": 4.4,
-        "cache_read": 0.2599
+        "input": 0.432,
+        "output": 3.99,
+        "cache_read": 0.26
       },
       "canonical_model_id": "zhipuai/glm-5.2"
     },
@@ -3630,9 +3630,9 @@
         "output": 131072
       },
       "cost": {
-        "input": 1.4,
-        "output": 4.4,
-        "cache_read": 0.26
+        "input": 0.9646,
+        "output": 3.0316,
+        "cache_read": 0.17914
       },
       "canonical_model_id": "zhipuai/glm-5.1"
     },
@@ -3746,7 +3746,7 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 943717
       },
       "cost": {
@@ -4430,11 +4430,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 16384
+        "output": 117964
       },
       "cost": {
-        "input": 0.3,
-        "output": 1.2,
+        "input": 0.35,
+        "output": 1.5,
         "cache_read": 0.04
       },
       "canonical_model_id": "meta/muse-glimmer-30b"
@@ -4758,12 +4758,12 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 943718
       },
       "cost": {
         "input": 0.02,
-        "output": 0.3,
+        "output": 0.2475,
         "cache_read": 0.01
       }
     },
@@ -4799,13 +4799,13 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 131072
       },
       "cost": {
-        "input": 0.19,
+        "input": 0.13,
         "output": 4,
-        "cache_read": 0.19
+        "cache_read": 0.13
       }
     },
     "arcee-ai/trinity-large-thinking": {
@@ -4984,7 +4984,6 @@
         {
           "type": "effort",
           "values": [
-            "none",
             "low",
             "medium",
             "high",
@@ -5017,13 +5016,13 @@
       "cost": {
         "input": 2,
         "output": 10,
-        "cache_read": 0.2,
+        "cache_read": 0.1,
         "cache_write": 2.5,
         "tiers": [
           {
             "input": 4,
             "output": 15,
-            "cache_read": 0.4,
+            "cache_read": 0.2,
             "cache_write": 5,
             "tier": {
               "type": "context",
@@ -5034,7 +5033,7 @@
         "context_over_200k": {
           "input": 4,
           "output": 15,
-          "cache_read": 0.4,
+          "cache_read": 0.2,
           "cache_write": 5
         }
       }
@@ -6072,9 +6071,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.02,
-        "output": 0.6,
-        "cache_read": 0.02
+        "input": 0.0198,
+        "output": 0.396,
+        "cache_read": 0.00291
       }
     },
     "~deepseek/deepseek-pro-latest": {
@@ -6113,12 +6112,12 @@
       "open_weights": false,
       "limit": {
         "context": 1048576,
-        "output": 943718
+        "output": 393216
       },
       "cost": {
-        "input": 0.15808,
-        "output": 1.9584,
-        "cache_read": 0.07488
+        "input": 0.123,
+        "output": 3.5,
+        "cache_read": 0.123
       }
     },
     "~deepseek/deepseek-v4-flash-latest": {
@@ -6156,13 +6155,13 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 1310720,
+        "context": 1048576,
         "output": 943718
       },
       "cost": {
-        "input": 0.012,
-        "output": 0.7,
-        "cache_read": 0.01
+        "input": 0.0099,
+        "output": 0.13068,
+        "cache_read": 0.001386
       }
     },
     "~x-ai/grok-latest": {
@@ -6666,9 +6665,9 @@
         "output": 235929
       },
       "cost": {
-        "input": 0.0765,
-        "output": 0.255,
-        "cache_read": 0.0425
+        "input": 0.09,
+        "output": 0.3,
+        "cache_read": 0.05
       },
       "canonical_model_id": "google/gemma-4-26b-a4b-it"
     },
@@ -9041,8 +9040,8 @@
         "output": 235929
       },
       "cost": {
-        "input": 0.6562,
-        "output": 3.3,
+        "input": 0.6712,
+        "output": 3.35,
         "cache_read": 0.18
       },
       "canonical_model_id": "moonshotai/kimi-k2.7-code"
@@ -9212,7 +9211,7 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 1000000,
+        "context": 262144,
         "output": 32768
       },
       "cost": {
@@ -9717,7 +9716,7 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 1048576,
+        "context": 1050000,
         "output": 131072
       },
       "cost": {
@@ -10865,9 +10864,9 @@
         "output": 235929
       },
       "cost": {
-        "input": 0.0647,
-        "output": 4.4,
-        "cache_read": 0.0517
+        "input": 0.0249,
+        "output": 4.35,
+        "cache_read": 0.0199
       },
       "canonical_model_id": "alibaba/qwen3.8-27b"
     },
@@ -11500,7 +11499,7 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 235929
+        "output": 65536
       },
       "cost": {
         "input": 0.26,
@@ -12242,11 +12241,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 8192
+        "output": 16384
       },
       "cost": {
-        "input": 0.13,
-        "output": 0.52
+        "input": 0.12,
+        "output": 0.5
       },
       "canonical_model_id": "alibaba/qwen3-30b-a3b"
     },
@@ -14148,6 +14147,73 @@
         "output": 2
       }
     },
+    "openai/gpt-6.1-sol": {
+      "id": "openai/gpt-6.1-sol",
+      "name": "GPT-6.1 Sol",
+      "description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-04-30",
+      "release_date": "2026-09-29",
+      "last_updated": "2026-09-29",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.1,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.2,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.2,
+          "cache_write": 5
+        }
+      },
+      "canonical_model_id": "openai/gpt-6.1-sol"
+    },
     "openai/gpt-4o-2024-08-06": {
       "id": "openai/gpt-4o-2024-08-06",
       "name": "GPT-4o (2024-08-06)",
@@ -15311,6 +15377,70 @@
       },
       "canonical_model_id": "openai/gpt-6-luna"
     },
+    "openai/gpt-6.1-sol-pro": {
+      "id": "openai/gpt-6.1-sol-pro",
+      "name": "GPT-6.1 Sol Pro",
+      "description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
+      "family": "gpt",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-09-29",
+      "last_updated": "2026-09-29",
+      "modalities": {
+        "input": [
+          "pdf",
+          "image",
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.1,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.2,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.2,
+          "cache_write": 5
+        }
+      }
+    },
     "openai/o4-mini-high": {
       "id": "openai/o4-mini-high",
       "name": "o4 Mini High",
@@ -15552,12 +15682,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 65536
+        "output": 117964
       },
       "cost": {
-        "input": 0.15,
-        "output": 0.6,
-        "cache_read": 0.075
+        "input": 0.037,
+        "output": 0.17
       },
       "canonical_model_id": "openai/gpt-oss-120b"
     },

data/docs/deepdive/reference/tracer.md

@@ -156,6 +156,15 @@ Three more hooks cover a local tool call. `on_tool_start` fires before
 the tool runs and returns the span that `on_tool_finish` and
 `on_tool_error` receive.
 
+An interrupt is neither a finish nor an error, and it is reported to a
+hook of its own. `on_interrupt` is called with a `scope:` of `:request`
+or `:tool` before the caller is given the exception, so a tracer that
+records what happened to a turn records it while the work is still in
+flight. The hook receives the span that `on_request_start` returned and
+its `request_id`; a tool pass carries neither, because a tool's span
+belongs to the call. A cancel reaches every tool that is running, so the
+tool phase is announced once rather than once per tool.
+
 A tracer's own lifetime is bracketed as well. `on_exit` fires once,
 when the last scope that is open for that tracer ends. That scope can
 belong to a different thread than the one that opened the first: a tool
@@ -214,11 +223,15 @@ as hooks gain parameters.
 
 #### Notes
 
-The base class raises `NotImplementedError` for any hook it does not
-implement, so a tracer must cover every hook the runtime calls: the six
-request and tool hooks above. Accept `**` to absorb keywords you do not
-read, as the built-in tracers do, so a hook that gains a parameter does
-not break your subclass.
+The base class raises `NotImplementedError` for the six request and tool
+hooks above, so a tracer has to answer for each of them. The remaining
+hooks do nothing by default. `on_exit` does nothing because most tracers
+hold nothing that needs releasing, and `start_trace` and `stop_trace`
+are no-ops too. `on_interrupt` does nothing because an interrupt is
+delivered to whatever tracer happens to be bound, and a hook that raised
+would replace the interrupt every caller is written against. Accept `**`
+to absorb keywords you do not read, as the built-in tracers do, so a
+hook that gains a parameter does not break your subclass.
 
 ### PrettyLogger
 

data/lib/llm/context.rb

@@ -343,6 +343,14 @@ module LLM
         @queue = stream.queue
         @queue.wait
       end
+    rescue LLM::Interrupt
+      ##
+      # Once, not once per tool. A cancel reaches every tool that is
+      # running, and the caller hears one exception, so the phase is
+      # announced here - the frame every strategy's interrupt unwinds
+      # through - and before the caller is given it.
+      tracer.on_interrupt(scope: :tool)
+      raise
     ensure
       @queue = nil
       @stream = nil

data/lib/llm/tracer.rb

@@ -194,6 +194,37 @@ module LLM
       raise NotImplementedError, "#{self.class} does not implement '#{__method__}'"
     end
 
+    ##
+    # Called when a request or a tool is interrupted.
+    #
+    # An interrupt is not a failure, so this is not {#on_request_error} or
+    # {#on_tool_error} under another name: it is the third ending either
+    # scope can have, and it is called before {LLM::Interrupt} reaches the
+    # caller, so a tracer that has to record what happened to a turn does it
+    # while the work is still the work in flight.
+    #
+    # A request is announced once, by the transport. A tool is announced
+    # once for the phase rather than once per tool: a cancel reaches every
+    # tool that is running and the caller hears one exception, so there is
+    # no one tool the announcement belongs to.
+    #
+    # The default does nothing, which is the difference from the rest of the
+    # lifecycle. Every other hook raises, because a tracer that means to draw
+    # a request has to answer for it - but an interrupt is delivered to
+    # whatever tracer happens to be bound, and a hook that raised here would
+    # replace the interrupt every caller is written against.
+    # @param [Symbol] scope
+    #  :request for a request, :tool for a tool
+    # @param [Object, nil] span
+    #  The span that {#on_request_start} returned. A tool pass has none:
+    #  a tool's span belongs to the call, and the announcement is not one
+    #  tool's to make.
+    # @param [String, nil] request_id
+    #  The id, as passed to {#on_request_start}, when the scope is a request
+    # @return [void]
+    def on_interrupt(scope:, span: nil, request_id: nil)
+    end
+
     ##
     # Opens a trace group so subsequent LLM spans share the same OpenTelemetry
     # trace_id (and appear as one trace in backends like Langfuse).

data/lib/llm/transport/execution.rb

@@ -38,8 +38,37 @@ class LLM::Transport
       res = transport.request(request, owner:, stream:, &b)
       res = LLM::Transport::Response.from(res)
       [handle_response(res, tracer, span, request_id), span, tracer, request_id]
-    rescue *transport.interrupt_errors
-      raise LLM::Interrupt, "request interrupted" if transport.interrupted?(owner)
+    rescue LLM::Interrupt
+      ##
+      # Curb raises this itself, from the chunk it is reading,
+      # which is the curb shape rather than something raised
+      # ordinarily: the other transports fail, and reach the
+      # rescue below.
+      #
+      # An interrupt is not a failure, so it is not reported as
+      # one - `on_interrupt` is the hook for it - and it is called
+      # before the caller is given the exception.
+      tracer.on_interrupt(scope: :request, span:, request_id:)
+      raise
+    rescue *transport.interrupt_errors => ex
+      ##
+      # Where a Net::HTTP interrupt becomes the exception the
+      # caller gets: the socket is closed from another thread
+      # and the read fails as one of these classes. The owner
+      # is what tells the two apart.
+      if transport.interrupted?(owner)
+        tracer.on_interrupt(scope: :request, span:, request_id:)
+        raise LLM::Interrupt, "request interrupted"
+      else
+        tracer.on_request_error(ex:, span:, request_id:)
+        raise
+      end
+    rescue => ex
+      ##
+      # Everything else ends the request, so the tracer is told:
+      # a span that was opened and never closed draws a request
+      # that never ended.
+      tracer.on_request_error(ex:, span:, request_id:)
       raise
     end
 

data/lib/llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LLM
-  VERSION = "16.0.0.pre.5"
+  VERSION = "16.0.0.pre.6"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm.rb
 version: !ruby/object:Gem::Version
-  version: 16.0.0.pre.5
+  version: 16.0.0.pre.6
 platform: ruby
 authors:
 - Robert Gleeson