llm.rb 16.0.0.pre.1 → 16.0.0.pre.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 89404c839d44cd5a11c59fdd56d396a64f50447996a03c01216eb928aed4c28a
-  data.tar.gz: f040e94e577c068690b7bae08900468408d1dd0985bd6d40ebc239eab60ea4a8
+  metadata.gz: 61578ce1082ecd25f86574ef19e1ffd4cc2b68c6689b705f0544f4aa3e391ede
+  data.tar.gz: 742b8d66f49113389c5ff08772e79498334eb6d5afe9821f05c2b8d1851cf4e8
 SHA512:
-  metadata.gz: c466492b003222fd3411b2777aa982663e50330600a2b69c1bd7d2fce9180576ccfc59230140fb392d584a1dddf45307c09fc785b7c7fc06d158aa3ec11230c7
-  data.tar.gz: 2da69855287105e2926045fdef7ef346be4fc4189f5e8659eb03829e85ae136a4fc5660506dee14ef7c933775e6790bacda9acedf1e4d4c438b61fc4730a584c
+  metadata.gz: d0024edabc9ac7360a71a485362aed854644187c116777623b340e5fbd391ae257139aefe07ba29ce7fe9bf04573e66ff09c0f48024153833cbb28b385e13280
+  data.tar.gz: ec0b4f0b2ba6a66b38cd324c5c3ea6daccd4ff76cde43a1fa8c272c20da89bec735ff7b7bae3afb516d4b5a3131b4e383abe70f48365d6ba9c8a61028e233c48

data/CHANGELOG.md

@@ -43,14 +43,14 @@
 
 * **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 +68,15 @@
   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.
+
 ### Provider
 
 * **deepseek: support image attachments in chat completions** <br>

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",