{
  "@context": "https://schema.org",
  "@id": "https://aggr.aymericbeaumet.com/items/simonwillison-net/2026-09-22-llm-0-36/#webpage",
  "@type": [
    "WebPage",
    "ArchiveComponent"
  ],
  "articleBody": "**Release:** [llm 0.36](https://github.com/simonw/llm/releases/tag/0.36)\n\n> - New OpenAI models: `gpt-6-sol` for [GPT-6 Sol](https://developers.openai.com/api/docs/models/gpt-6-sol) and `gpt-6-luna` for [GPT-6 Luna](https://developers.openai.com/api/docs/models/gpt-6-luna). [#1702](https://github.com/simonw/llm/issues/1702)\n> - Model plugins can now declare `supports_conversation = False` for models that only accept single-turn prompts. LLM raises `llm.ConversationNotSupported` when these models receive assistant or tool history, and `llm chat` rejects them before starting a session. See [Models that do not support conversations](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#advanced-model-plugins-conversations). The first plugin to use this is [llm-typesafe](https://github.com/simonw/llm-typesafe). [#1692](https://github.com/simonw/llm/issues/1692)\n> - Reasoning traces in the Markdown output of `llm logs` are now wrapped in `<details><summary>` tags. [#1701](https://github.com/simonw/llm/issues/1701)\n\nPlus [bug fixes from five new contributors](https://llm.datasette.io/en/stable/changelog.html#v0-36).\n\nTags: [openai](https://simonwillison.net/tags/openai), [llm](https://simonwillison.net/tags/llm)\n",
  "authors": [],
  "captured_at": "2026-09-23T00:20:14.260676283+00:00",
  "category": "programming",
  "content_html": "<p><strong>Release:</strong> <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/simonw/llm/releases/tag/0.36\">llm 0.36</a></p>\n<blockquote>\n<ul>\n<li>New OpenAI models: <code>gpt-6-sol</code> for <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://developers.openai.com/api/docs/models/gpt-6-sol\">GPT-6 Sol</a> and <code>gpt-6-luna</code> for <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://developers.openai.com/api/docs/models/gpt-6-luna\">GPT-6 Luna</a>. <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/simonw/llm/issues/1702\">#1702</a></li>\n<li>Model plugins can now declare <code>supports_conversation = False</code> for models that only accept single-turn prompts. LLM raises <code>llm.ConversationNotSupported</code> when these models receive assistant or tool history, and <code>llm chat</code> rejects them before starting a session. See <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#advanced-model-plugins-conversations\">Models that do not support conversations</a>. The first plugin to use this is <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/simonw/llm-typesafe\">llm-typesafe</a>. <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/simonw/llm/issues/1692\">#1692</a></li>\n<li>Reasoning traces in the Markdown output of <code>llm logs</code> are now wrapped in <code>&lt;details&gt;&lt;summary&gt;</code> tags. <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/simonw/llm/issues/1701\">#1701</a></li>\n</ul>\n</blockquote>\n<p>Plus <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://llm.datasette.io/en/stable/changelog.html#v0-36\">bug fixes from five new contributors</a>.</p>\n<p>Tags: <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://simonwillison.net/tags/openai\">openai</a>, <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://simonwillison.net/tags/llm\">llm</a></p>\n",
  "content_markdown": "**Release:** [llm 0.36](https://github.com/simonw/llm/releases/tag/0.36)\n\n> - New OpenAI models: `gpt-6-sol` for [GPT-6 Sol](https://developers.openai.com/api/docs/models/gpt-6-sol) and `gpt-6-luna` for [GPT-6 Luna](https://developers.openai.com/api/docs/models/gpt-6-luna). [#1702](https://github.com/simonw/llm/issues/1702)\n> - Model plugins can now declare `supports_conversation = False` for models that only accept single-turn prompts. LLM raises `llm.ConversationNotSupported` when these models receive assistant or tool history, and `llm chat` rejects them before starting a session. See [Models that do not support conversations](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#advanced-model-plugins-conversations). The first plugin to use this is [llm-typesafe](https://github.com/simonw/llm-typesafe). [#1692](https://github.com/simonw/llm/issues/1692)\n> - Reasoning traces in the Markdown output of `llm logs` are now wrapped in `<details><summary>` tags. [#1701](https://github.com/simonw/llm/issues/1701)\n\nPlus [bug fixes from five new contributors](https://llm.datasette.io/en/stable/changelog.html#v0-36).\n\nTags: [openai](https://simonwillison.net/tags/openai), [llm](https://simonwillison.net/tags/llm)\n",
  "dateCreated": "2026-09-23T00:20:14.260676283+00:00",
  "date_created": "2026-09-22T18:48:37+00:00",
  "date_modified": "2026-09-22T18:48:37+00:00",
  "date_published": "2026-09-22T18:48:37+00:00",
  "description": "Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn prompts. LLM raises…",
  "external_url": "https://simonwillison.net/2026/Sep/22/llm/",
  "git": {
    "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e",
    "path": "items/simonwillison-net/2026/09/2026-09-22-llm-0-36.md",
    "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/simonwillison-net/2026/09/2026-09-22-llm-0-36.md"
  },
  "id": "urn:aggr:item:bd1a0bb13d8a0ca5a0450055579d07e2210e9d9b",
  "isBasedOn": {
    "@id": "https://simonwillison.net/2026/Sep/22/llm/"
  },
  "mainEntity": {
    "@id": "https://simonwillison.net/2026/Sep/22/llm/",
    "@type": "CreativeWork",
    "archivedAt": {
      "@id": "https://aggr.aymericbeaumet.com/items/simonwillison-net/2026-09-22-llm-0-36/#webpage"
    },
    "dateModified": "2026-09-22T18:48:37+00:00",
    "datePublished": "2026-09-22T18:48:37+00:00",
    "headline": "llm 0.36",
    "timeRequired": "PT1M",
    "url": "https://simonwillison.net/2026/Sep/22/llm/",
    "wordCount": 101
  },
  "name": "Archived snapshot: llm 0.36",
  "preview": null,
  "reading_minutes": 1,
  "replicated_at": null,
  "source": "simonwillison-net",
  "source_name": "Simon Willison's Weblog",
  "summary": "Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn prompts. LLM raises llm.ConversationNotSupported when these models receive assistant or tool history, and llm chat rejects them before starting a session. See Models that do not support conversations. The first plugin to use this is llm-typesafe. #1692 Reasoning traces in the Markdown output of llm logs are now wrapped in <details><summary> tags. #1701 Plus bug fixes from five new contributors. Tags: openai, llm",
  "tags": [
    "llm",
    "openai"
  ],
  "temporalCoverage": "2026-09-23T00:20:14.260676283+00:00",
  "title": "llm 0.36",
  "url": "https://aggr.aymericbeaumet.com/items/simonwillison-net/2026-09-22-llm-0-36/",
  "word_count": 101
}