llm.rb 15.4.0 → 15.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: de1f4eeee4762548e75eac2b5d4112de49cf446944b30c545b76e62750aad6c3
-  data.tar.gz: 4abc1d2d707717fde266b48bfa626f06d553514761653db8c3cd190cfcffb864
+  metadata.gz: df1a9b7fbf194f568b95f3f1b2d0314bb703027bc89e4432109d118f238ea2ba
+  data.tar.gz: 679938a2f6538f9c1999d31870462498393e1b3a7c7203630c5e8706c893e9ce
 SHA512:
-  metadata.gz: c28cadd2a412e2623b472d3be7814aa51a462076782fc847bc73cdc57a601a630d909bb9b40c29d31dd7107b487bf169bdeb245e9803581df0d90d642694bc16
-  data.tar.gz: 2fd3c1905d2db4212958e98e537db76d37f0f30f5cee4dda3cbf351c7f0fffe1ce6eaa5b38553e80b9441b029e2edf78c4e9ea75c200b731638dbbe49bd947df
+  metadata.gz: 49151bad60a22a06b119e08062e58c6d35727d59d10e07d9921166a23b5817083ea11fe942a090bc0e64b68a06340b9cf175a87ecfa81775dffcc7d88a8abb0c
+  data.tar.gz: 92ddc3cd73f7af70f25e735fd8ac63dcbca6ed48fd78ba3510be0171ea180d006f399ff60e215bdf1b9159e52b721916c59fcb7278c322fb0ffe789db5900602

data/CHANGELOG.md

@@ -17,6 +17,86 @@
 
 *No unreleased changes yet. Check back after the next release.*
 
+## v15.5.0
+
+Changes since `v15.4.1`.
+
+This release makes the exec-backed tools report how long a command ran, calls a
+tracer's `on_exit` hook once when the last scope ends, and resolves a `Proc`
+parameter type when a schema is serialized. It also fixes `LLM::Schema.to_s`
+for a schema with a deferred type.
+
+### Tools
+
+* **tools: report how long a command ran** <br>
+  [`LLM::Tool::Exec#call`](https://r.uby.dev/api-docs/llm.rb/LLM/Tool/Exec.html#call-instance_method)
+  now includes a `duration` field in its result, a string such as `"0.4 seconds"`
+  that reports how long the command took. The tools that route through `exec`
+  (`git`, `rg`, `mkdir`, `ruby`, and `bundle`) return it as well. A command that
+  was not found still returns the error hash, which has no `duration`.
+
+### Tracers
+
+* **tracer: call `on_exit` once, when the last scope ends** <br>
+  [`LLM::Tracer#on_exit`](https://r.uby.dev/api-docs/llm.rb/LLM/Tracer.html#on_exit-instance_method)
+  is a new hook, called once when the last scope that is open for a tracer
+  ends. A tracer that holds a connection, a file, or a span releases it here.
+  The count of open scopes belongs to the tracer rather than to the thread that
+  opened one, because a tool runs on a thread of its own and scopes the turn's
+  tracer while it does. Before this, a tool's scope looked like the outermost
+  one: a tracer that released its resource in `on_exit` lost it in the middle
+  of the turn, and the rest of the trace was written without it.
+
+### Schema
+
+* **schema: resolve a parameter type when the schema is serialized** <br>
+  [`LLM::Schema`](https://r.uby.dev/api-docs/llm.rb/LLM/Schema.html) and
+  [`LLM::Tool`](https://r.uby.dev/api-docs/llm.rb/LLM/Tool.html) accept a `Proc`
+  as the type of a parameter or a property, and the proc is called when the
+  schema is serialized rather than when the class that declares it is defined.
+  A type that is only known at runtime no longer has to be known at load time:
+  `parameter :kind, proc { Enum[*Article.kinds] }, "The article kind"` asks the
+  model for the values a store holds right now, and the proc runs again on the
+  next request, so it sees the values that are current then. Whatever the proc
+  returns is resolved in turn, so it may be a leaf, a class, or an array of
+  either, and the description, `required`, `default`, and `enum` given with the
+  parameter are applied to it.
+
+* **schema: keep `to_s` working for a deferred type** <br>
+  Fix a bug where a schema with a proc-typed property raised from
+  [`LLM::Schema.to_s`](https://r.uby.dev/api-docs/llm.rb/LLM/Schema.html#to_s-class_method)
+  (and so from `inspect` and `p`) because the placeholder resolved its leaf
+  through a private method that shadowed the one `LLM::Schema::Leaf#default`
+  uses. Serialization, and therefore the request sent to a provider, was
+  unaffected.
+
+## v15.4.1
+
+Changes since `v15.4.0`.
+
+This release removes the gemspec's post-install message, so installing the gem
+no longer prints the r.uby.dev notice. It also refreshes the model registry
+with current model listings, limits, and pricing.
+
+### Core
+
+* **remove the gemspec post install message** <br>
+  The gemspec no longer sets `post_install_message`, so installing the
+  gem no longer prints the r.uby.dev website notice.
+
+### Registry
+
+* **refresh model metadata** <br>
+  Update `data/` with current model listings, limits, and pricing for the
+  Alibaba, Bedrock, DeepSeek, Google, Moonshot, and OpenRouter registries.
+  Bedrock adds the Kimi K3 and GPT-6 Sol and GPT-6 Luna families in both
+  the global and US regions and raises the context limit to 1M tokens for
+  two models, while Moonshot raises the Kimi K3 output limit to 1M tokens.
+  OpenRouter adds `qwen/qwen3.8-max-prime`, `z-ai/glm-5.3-prime`,
+  `upstage/solar-mini4`, the Aion 3.5 models, and `stealth/space-bunny-alpha`,
+  drops `mistralai/devstral-2512` and a free Ling 3.0 Flash VL entry, and
+  reprices several DeepSeek and Mistral models.
+
 ## v15.4.0
 
 Changes since `v15.3.0`.

data/README.md

@@ -19,10 +19,13 @@ on CRuby. It has zero runtime dependencies by default, supports
 concurrent and parallel tool execution and has a single coherent API
 that spans 14+ providers.
 
-The most effective way to learn about llm.rb is to ask [the r.uby.dev chatbot](https://r.uby.dev)
-a question. It is connected to the llm.rb GitHub repository, backed by
-ActiveRecord and uses the builtin MCP feature to connect to GitHub. The chatbot
-is an llm.rb agent that is deployed with [roda-llm](https://github.com/r-uby-dev/roda-llm#readme).
+It is possible to see llm.rb in action on the
+[the r.uby.dev website](https://r.uby.dev) where
+I am working on building an agentic platform that
+users can use to manage multiple agents that are
+specialized in different areas, and have access to
+different services (eg GitHub, etc). Check it out if
+curious. Still in early development.
 
 ## Install
 
@@ -362,9 +365,6 @@ for both Rack-based / Rails-based applications. On databases
 where it is supported, such as PostgreSQL, the column can be optimized by using
 the `jsonb` type.
 
-The following example is based on the agent used to power the
-[r.uby.dev chatbot](https://r.uby.dev).
-
 ```ruby
 require "active_record"
 require "llm"
@@ -1030,10 +1030,8 @@ IO.copy_stream res.images[0], "rocket-with-dog.svg"
 <summary>Where can I see llm.rb in action?</summary>
 <br>
 
-The [r.uby.dev](https://r.uby.dev) website deploys
-multiple llm.rb agents that guests can interact with
-and there is even an agent that is connected to this
-GitHub repository.
+The [r.uby.dev](https://r.uby.dev) website.
+
 </details>
 <details>
 <summary>What about local LLM support?</summary>
@@ -1094,9 +1092,9 @@ web</a>.
 
 The llm.rb project was started more than three
 years ago by
-[@0x1eef](https://github.com/0x1eef) and
-[@antaz](https://github.com/0x1eef). The primary
-maintainer is [@0x1eef](https://github.com/0x1eef).
+[@altruby](https://github.com/altruby) and
+[@antaz](https://github.com/altruby). The primary
+maintainer is [@altruby](https://github.com/altruby).
 Over those three years multiple other contributors have
 contributed to llm.rb as well, and new contributors are
 always welcome.

data/data/alibaba.json

@@ -38,7 +38,7 @@
       "open_weights": false,
       "limit": {
         "context": 1000000,
-        "output": 65536
+        "output": 131072
       },
       "cost": {
         "input": 2.5,
@@ -1848,7 +1848,7 @@
       "open_weights": false,
       "limit": {
         "context": 1000000,
-        "output": 65536
+        "output": 131072
       },
       "cost": {
         "input": 0.5,

data/data/bedrock.json

@@ -566,7 +566,7 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 272000,
+        "context": 1000000,
         "output": 128000
       },
       "provider": {
@@ -886,7 +886,7 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 272000,
+        "context": 1000000,
         "output": 128000
       },
       "provider": {
@@ -1587,6 +1587,41 @@
         "cache_write": 6.875
       }
     },
+    "global.moonshotai.kimi-k3": {
+      "id": "global.moonshotai.kimi-k3",
+      "name": "Kimi K3 (Global)",
+      "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
+      "family": "kimi-k3",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [],
+      "tool_call": true,
+      "interleaved": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-07-16",
+      "last_updated": "2026-07-16",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 3,
+        "output": 15,
+        "cache_read": 0.3,
+        "cache_write": 3.75
+      }
+    },
     "apac.amazon.nova-pro-v1:0": {
       "id": "apac.amazon.nova-pro-v1:0",
       "name": "Nova Pro (APAC)",
@@ -1675,6 +1710,41 @@
         "cache_write": 4.125
       }
     },
+    "us.moonshotai.kimi-k3": {
+      "id": "us.moonshotai.kimi-k3",
+      "name": "Kimi K3 (US)",
+      "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
+      "family": "kimi-k3",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [],
+      "tool_call": true,
+      "interleaved": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-07-16",
+      "last_updated": "2026-07-16",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 3.3,
+        "output": 16.5,
+        "cache_read": 0.33,
+        "cache_write": 4.125
+      }
+    },
     "apac.amazon.nova-lite-v1:0": {
       "id": "apac.amazon.nova-lite-v1:0",
       "name": "Nova Lite (APAC)",
@@ -1933,6 +2003,72 @@
         "output": 1.2
       }
     },
+    "us.openai.gpt-6-luna": {
+      "id": "us.openai.gpt-6-luna",
+      "name": "GPT-6 Luna (US)",
+      "description": "OpenAI's most efficient model for focused, high-volume tasks",
+      "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": "2026-05-18",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 0.11,
+        "output": 0.55,
+        "cache_read": 0.011,
+        "cache_write": 0.1375,
+        "tiers": [
+          {
+            "input": 0.22,
+            "output": 0.825,
+            "cache_read": 0.022,
+            "cache_write": 0.275,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.22,
+          "output": 0.825,
+          "cache_read": 0.022,
+          "cache_write": 0.275
+        }
+      }
+    },
     "meta.llama3-3-70b-instruct-v1:0": {
       "id": "meta.llama3-3-70b-instruct-v1:0",
       "name": "Llama 3.3 70B Instruct",
@@ -3258,6 +3394,72 @@
         "cache_write": 0.33
       }
     },
+    "global.openai.gpt-6-sol": {
+      "id": "global.openai.gpt-6-sol",
+      "name": "GPT-6 Sol (Global)",
+      "description": "OpenAI model for complex 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": "2026-04-20",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.4,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.4,
+          "cache_write": 5
+        }
+      }
+    },
     "global.xai.grok-4.6": {
       "id": "global.xai.grok-4.6",
       "name": "Grok 4.6 (Global)",
@@ -4572,6 +4774,72 @@
         }
       }
     },
+    "global.openai.gpt-6-luna": {
+      "id": "global.openai.gpt-6-luna",
+      "name": "GPT-6 Luna (Global)",
+      "description": "OpenAI's most efficient model for focused, high-volume tasks",
+      "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": "2026-05-18",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 0.1,
+        "output": 0.5,
+        "cache_read": 0.01,
+        "cache_write": 0.125,
+        "tiers": [
+          {
+            "input": 0.2,
+            "output": 0.75,
+            "cache_read": 0.02,
+            "cache_write": 0.25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.2,
+          "output": 0.75,
+          "cache_read": 0.02,
+          "cache_write": 0.25
+        }
+      }
+    },
     "us.anthropic.claude-fable-5-1": {
       "id": "us.anthropic.claude-fable-5-1",
       "name": "Claude Fable 5.1 (US)",
@@ -5349,6 +5617,72 @@
         "cache_write": 0.06
       }
     },
+    "us.openai.gpt-6-sol": {
+      "id": "us.openai.gpt-6-sol",
+      "name": "GPT-6 Sol (US)",
+      "description": "OpenAI model for complex 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": "2026-04-20",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2.2,
+        "output": 11,
+        "cache_read": 0.22,
+        "cache_write": 2.75,
+        "tiers": [
+          {
+            "input": 4.4,
+            "output": 16.5,
+            "cache_read": 0.44,
+            "cache_write": 5.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4.4,
+          "output": 16.5,
+          "cache_read": 0.44,
+          "cache_write": 5.5
+        }
+      }
+    },
     "global.anthropic.claude-opus-4-7": {
       "id": "global.anthropic.claude-opus-4-7",
       "name": "Claude Opus 4.7 (Global)",

data/data/deepseek.json

@@ -49,7 +49,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "status": "deprecated",
       "cost": {
@@ -100,7 +100,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "status": "deprecated",
       "cost": {
@@ -149,7 +149,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
         "input": 0.435,
@@ -199,7 +199,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
         "input": 0.15,

data/data/google.json

@@ -138,7 +138,7 @@
       "open_weights": false,
       "limit": {
         "context": 65536,
-        "output": 65536
+        "output": 4096
       },
       "cost": {
         "input": 0.25,
@@ -933,8 +933,8 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 65536,
-        "output": 65536
+        "context": 131072,
+        "output": 32768
       },
       "cost": {
         "input": 0.5,

data/data/moonshot.json

@@ -167,7 +167,7 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 131072
+        "output": 1048576
       },
       "cost": {
         "input": 3,