llm.rb 16.0.0.pre.1 → 16.0.0.pre.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 89404c839d44cd5a11c59fdd56d396a64f50447996a03c01216eb928aed4c28a
-  data.tar.gz: f040e94e577c068690b7bae08900468408d1dd0985bd6d40ebc239eab60ea4a8
+  metadata.gz: a8bd3b4f303036ba390981de3ec63ea0bb523cc653c4b77b221e4591e9b9a446
+  data.tar.gz: 3036ce3c4248e3ddad524657f31ea2c300f98282ad0aa68791848f56cd1b91f5
 SHA512:
-  metadata.gz: c466492b003222fd3411b2777aa982663e50330600a2b69c1bd7d2fce9180576ccfc59230140fb392d584a1dddf45307c09fc785b7c7fc06d158aa3ec11230c7
-  data.tar.gz: 2da69855287105e2926045fdef7ef346be4fc4189f5e8659eb03829e85ae136a4fc5660506dee14ef7c933775e6790bacda9acedf1e4d4c438b61fc4730a584c
+  metadata.gz: 604bafd36e8a55405e3fc487957ae97b9e4ffd67777711c071f7bfb9cfe005e0400294c089e72fbec3019538f4706c92cfe5bb15f3d0c2f994a324b9ba1a3322
+  data.tar.gz: d3bf4d7e1f9337cd7bdedb40ac4cfb4f95b6195e6df3360d428bfa6c220994edfaf8c5f053256e968c1feb9ae025b29854586dd9834dc84948729644f7a7b8ff

data/CHANGELOG.md

@@ -22,6 +22,7 @@
 | Old | New |
 |-----|-----|
 | Ruby 3.3 or later | Ruby 3.4 or later |
+| `record.messages` returns the messages the runtime holds | a `:jsonb` record returns a relation of `LLM::ActiveRecord::Message` rows |
 
 * **drop Ruby 3.3 support** <br>
   The gem now requires Ruby 3.4 or later: `required_ruby_version` is
@@ -30,6 +31,21 @@
   cancel that arrives before the tool starts is not delivered there, while
   Ruby 3.4 and 4.0 both deliver it.
 
+* **activerecord: read a `:jsonb` record's messages from the column** <br>
+  [`LLM::ActiveRecord`](https://r.uby.dev/api-docs/llm.rb/LLM/ActiveRecord.html)
+  now answers `#messages` for a record whose `format` is `:jsonb` with an
+  [`ActiveRecord::Relation`](https://api.rubyonrails.org/classes/ActiveRecord/Relation.html)
+  over the column, through
+  [`LLM::ActiveRecord::Message`](https://r.uby.dev/api-docs/llm.rb/LLM/ActiveRecord/Message.html),
+  so a conversation can be filtered, counted, and ordered in SQL, and reading it
+  needs no provider and no credentials. Before this, every record loaded the
+  runtime and returned the messages it held, whatever the format. The relation
+  is not a drop-in replacement for that buffer: it reads what is persisted
+  rather than what a runtime holds in memory, it is unordered, so order by
+  `position`, and its rows answer `unwrap!` rather than being
+  [`LLM::Message`](https://r.uby.dev/api-docs/llm.rb/LLM/Message.html) objects.
+  Every other format, and Sequel, still loads the runtime.
+
 ### Console
 
 * **console: erase with the backspace key on OpenBSD** <br>
@@ -39,18 +55,25 @@
   terminal's terminfo describes the key. All three erase. Before this only 127
   did, so the backspace key did nothing on the OpenBSD console.
 
+### Fix
+
+* **fork: require xchan.rb `~> 0.24`** <br>
+  The `:fork` concurrency strategy now requires the `xchan.rb` gem at `~> 0.24`
+  instead of `~> 0.23`, and the gemspec's development dependency follows. An
+  application that uses `:fork` needs `xchan.rb` 0.24 or later.
+
 ### Function
 
 * **function: deliver an interrupt to the tool, not to whatever is running** <br>
   [`LLM::Function::Window`](https://r.uby.dev/api-docs/llm.rb/LLM/Function/Window.html)
-  is the stretch of a call that an interrupt belongs to. The `:fork` and
-  `:ractor` strategies now raise `LLM::Interrupt` on the thread that runs
-  the tool, and only while the tool runs: a cancel that arrives before the
-  tool starts is held until it does, so the tool's own `rescue` can handle
-  it, and one that arrives after the tool has returned is a no-op, which no
-  longer throws the result away. Before this, the interrupt was raised on
-  the child process's or the ractor's main thread wherever that thread had
-  got to.
+  is the stretch of a call that an interrupt belongs to. The `:fork` and `:ractor`
+  strategies now raise
+  [`LLM::Interrupt`](https://r.uby.dev/api-docs/llm.rb/LLM/Interrupt.html) on the
+  thread that runs the tool, and only while the tool runs: a cancel that arrives
+  before the tool starts is held until it does, so the tool's own `rescue` can
+  handle it, and one that arrives after the tool has returned is a no-op, which
+  no longer throws the result away. Before this, the interrupt was raised on the
+  child process's or the ractor's main thread wherever that thread had got to.
 
 * **function: answer a ractor-backed task once its ractor has gone** <br>
   A `:ractor` tool's result is handed to a ractor the task holds it in,
@@ -68,6 +91,30 @@
   error, and a group's cancel stopped at the first task that had already
   returned, leaving the calls after it uncancelled.
 
+* **function: tell an `:async` tool it was cancelled** <br>
+  A cancel now raises `LLM::Interrupt` on the fiber the tool runs in, through the
+  reactor's scheduler, so the tool is told and can answer with its own value. A
+  cancel that arrives before the tool started stops it from running, and the
+  reactor is stopped by whoever waits. Before this, the cancel pushed an
+  interrupt sentinel to the task's result queue and left the tool running, its
+  side effects happening and its result written to a queue nobody read, and the
+  reactor thread stayed alive until a group's `wait` stopped it.
+
+* **function: run the interrupt hook on every strategy** <br>
+  A tool that implements
+  [`LLM::Tool#on_interrupt`](https://r.uby.dev/api-docs/llm.rb/LLM/Tool.html#on_interrupt-instance_method)
+  or
+  [`LLM::Tool#on_cancel`](https://r.uby.dev/api-docs/llm.rb/LLM/Tool.html#on_cancel-instance_method)
+  is now told on every concurrency strategy. `:thread`, `:fiber`, and `:async`
+  run the hook on the thread or fiber that ran the call, `:fork` and `:ractor`
+  run it inside the child or the ractor before the interrupt is delivered, and
+  a sequential group's cancel tells every task it holds. Before this, `:async`,
+  `:fork`, and `:ractor` never ran the hook, the others ran it on the thread
+  that cancelled, and a class-backed tool ran it on no strategy at all, because
+  `interrupt!` read the hook off the tool's definition and a class answers
+  `respond_to?` with false for an instance method. A hook that raises becomes
+  what the caller sees in place of the call's result.
+
 ### Provider
 
 * **deepseek: support image attachments in chat completions** <br>
@@ -88,13 +135,26 @@
   `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` and `openai.gpt-6-luna`; and DeepInfra adds
-  `tencent/Hy4-preview` and the Xiaomi MiMo V2.6 Pro and V2.6 Flash models.
+  `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.
   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 four models, drops six, and reprices
+  `gemini-3-pro-image`, and OpenRouter adds five models, drops six, and reprices
   many of the DeepSeek, Z.ai, and Qwen entries.
 
+### Schema
+
+* **schema: apply every `parameter` option to the leaf** <br>
+  [`LLM::Tool`](https://r.uby.dev/api-docs/llm.rb/LLM/Tool.html) now applies each
+  option given to `parameter` to the leaf its type resolves to, so settings such
+  as `min:`, `max:`, `multiple_of:`, and `const:` reach the schema instead of
+  being dropped. Before this only `required`, `default`, and `enum` were read, so
+  `parameter :age, Integer, "Age", min: 1, max: 9` sent a plain integer and lost
+  the range. A `default:` of `false` survives now as well, where the old code
+  discarded a false default, and `required: false` marks the parameter optional
+  rather than being ignored.
+
 ## v15.5.0
 
 Changes since `v15.4.1`.

data/README.md

@@ -18,16 +18,21 @@ llm.rb is a runtime for building agentic AI applications
 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 README covers the common cases. For everything else there is the
+[deepdive](docs/deepdive.md), a reference with a chapter for each
+topic, and for what changes between releases there is the
+[changelog](CHANGELOG.md).
 
-See llm.rb in action on the
-[the r.uby.dev website](https://r.uby.dev) where
-I am building a platform that supports users who have
-personalized agents with access to different services
-(eg GitHub, etc). Check it out if curious.
-**Still in early development.**
+[The r.uby.dev website](https://r.uby.dev) hosts
+an agentic platform that provides users with
+personalized agents who can access GitHub, and
+other services. It is built with llm.rb. Check it
+out if curious. **Still in early development.**
 
 ## Install
 
+llm.rb requires Ruby 3.4 or later.
+
 ```bash
 gem install llm.rb
 ```

data/data/alibaba.json

@@ -90,7 +90,8 @@
         "output": 0.4,
         "cache_read": 0.01,
         "cache_write": 0.125
-      }
+      },
+      "canonical_model_id": "alibaba/qwen3.5-flash"
     },
     "qwen3.7-max": {
       "id": "qwen3.7-max",
@@ -349,7 +350,8 @@
         "input": 0.2,
         "output": 0.4,
         "cache_read": 0.04
-      }
+      },
+      "canonical_model_id": "deepseek/deepseek-v4-flash-0731"
     },
     "qwen-max": {
       "id": "qwen-max",
@@ -470,7 +472,8 @@
         "output": 6,
         "cache_read": 0.25,
         "cache_write": 2.5
-      }
+      },
+      "canonical_model_id": "alibaba/qwen3.8-max"
     },
     "kimi-k3": {
       "id": "kimi-k3",
@@ -515,7 +518,8 @@
         "input": 3,
         "output": 15,
         "cache_read": 0.3
-      }
+      },
+      "canonical_model_id": "moonshotai/kimi-k3"
     },
     "qwen-plus-character-ja": {
       "id": "qwen-plus-character-ja",
@@ -799,7 +803,8 @@
             }
           }
         ]
-      }
+      },
+      "canonical_model_id": "alibaba/qwen3.7-flash"
     },
     "qwen3-max": {
       "id": "qwen3-max",
@@ -1046,7 +1051,8 @@
         "input": 0.15,
         "output": 0.47,
         "cache_read": 0.016
-      }
+      },
+      "canonical_model_id": "alibaba/qwen3.8-omni-flash"
     },
     "qvq-max": {
       "id": "qvq-max",
@@ -1685,7 +1691,8 @@
         "output": 0.47,
         "cache_read": 0.016,
         "cache_write": 0.2
-      }
+      },
+      "canonical_model_id": "alibaba/qwen3.8-flash"
     },
     "qwen2-5-vl-7b-instruct": {
       "id": "qwen2-5-vl-7b-instruct",
@@ -1956,7 +1963,8 @@
         "output": 4.4,
         "cache_read": 0.28,
         "cache_write": 0
-      }
+      },
+      "canonical_model_id": "zhipuai/glm-5.2"
     },
     "qwen-omni-turbo": {
       "id": "qwen-omni-turbo",

data/data/anthropic.json

@@ -46,7 +46,8 @@
         "output": 5,
         "cache_read": 0.1,
         "cache_write": 1.25
-      }
+      },
+      "canonical_model_id": "anthropic/claude-haiku-4-5"
     },
     "claude-opus-4-5": {
       "id": "claude-opus-4-5",
@@ -95,7 +96,8 @@
         "output": 25,
         "cache_read": 0.5,
         "cache_write": 6.25
-      }
+      },
+      "canonical_model_id": "anthropic/claude-opus-4-5"
     },
     "claude-sonnet-4-5": {
       "id": "claude-sonnet-4-5",
@@ -136,7 +138,8 @@
         "output": 15,
         "cache_read": 0.3,
         "cache_write": 3.75
-      }
+      },
+      "canonical_model_id": "anthropic/claude-sonnet-4-5"
     },
     "claude-opus-5-5": {
       "id": "claude-opus-5-5",
@@ -203,7 +206,8 @@
         "output": 20,
         "cache_read": 0.2,
         "cache_write": 5
-      }
+      },
+      "canonical_model_id": "anthropic/claude-opus-5-5"
     },
     "claude-fable-5-1": {
       "id": "claude-fable-5-1",
@@ -250,7 +254,8 @@
         "output": 50,
         "cache_read": 0.25,
         "cache_write": 12.5
-      }
+      },
+      "canonical_model_id": "anthropic/claude-fable-5-1"
     },
     "claude-opus-4-5-20251101": {
       "id": "claude-opus-4-5-20251101",
@@ -366,7 +371,8 @@
         "output": 25,
         "cache_read": 0.5,
         "cache_write": 6.25
-      }
+      },
+      "canonical_model_id": "anthropic/claude-opus-5"
     },
     "claude-fable-5": {
       "id": "claude-fable-5",
@@ -713,6 +719,54 @@
         "cache_write": 3.75
       }
     },
+    "claude-sonnet-5-5": {
+      "id": "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": true,
+      "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"
+    },
     "claude-opus-4-7": {
       "id": "claude-opus-4-7",
       "name": "Claude Opus 4.7",