Tool support is finally here! This release adds support exposing tools to LLMs, previously described in the release notes for 0.26a0 and 0.26a1.

Read Large Language Models can run tools in your terminal with LLM 0.26 for a detailed overview of the new features.

Also in this release:

• Two new default tools: llm_version() and llm_time(). #1096, #1103
• Documentation on how to add tool supports to a model plugin. #1000
• Added a prominent warning about the risk of prompt injection when using tools. #1097
• Switched to using monotonic ULIDs for the response IDs in the logs, fixing some intermittent test failures. #1099
• New tool_instances table records details of Toolbox instances created while executing a prompt. #1089
• llm.get_key() is now a documented utility function. #1094

Hopefully the last alpha before a stable release that includes tool support.

Features

• Plugin-provided tools can now be grouped into "Toolboxes".
  • Toolboxes (llm.Toolbox classes) allow plugins to expose multiple related tools that share state or configuration, enhancing modularity and reusability (e.g., a Memory tool or Filesystem tool). (#1059, #1086)
• Tool support for llm chat.
  • The llm chat command now accepts --tool and --functions arguments, allowing interactive chat sessions to use tools. (#1004, #1062)
• Tools can now execute asynchronously.
  • Models that implement AsyncModel can now run tools, including tool functions defined as async def. This enables non-blocking tool calls for potentially long-running operations. (#1063)
• llm chat now supports adding fragments during a session.
  • Use the new !fragment <id> command while chatting to insert content from a fragment. Initial fragments can also be passed to llm chat using -f or --sf. Thanks, Dan Turkel. (#1044, #1048)
• Filter llm logs by tools.
  • New --tool <name> option to filter logs to show only responses that involved a specific tool (e.g., --tool simple_eval).
  • The --tools flag shows all responses that used any tool. (#1013, #1072)
• llm schemas list can output JSON.
  • Added --json and --nl (newline-delimited JSON) options to llm schemas list for programmatic access to saved schema definitions. (#1070)
• Filter llm similar results by ID prefix.
  • The new --prefix option for llm similar allows searching for similar items only within IDs that start with a specified string (e.g., llm similar my-collection --prefix 'docs/'). Thanks, Dan Turkel. (#1052)
• Control chained tool execution limit.
  • New --chain-limit <N> (or --cl) option for llm prompt and llm chat to specify the maximum number of consecutive tool calls allowed for a single prompt. Defaults to 5; set to 0 for unlimited. (#1025)
• llm plugins --hook <NAME> option.
  • Filter the list of installed plugins to only show those that implement a specific plugin hook. (#1047)
• llm tools list now shows toolboxes and their methods. (#1013)
• llm prompt and llm chat now automatically re-enable plugin-provided tools when continuing a conversation (-c or --cid). (#1020)
• The --tools-debug option now pretty-prints JSON tool results for improved readability. (#1083)
• New LLM_TOOLS_DEBUG environment variable to permanently enable --tools-debug. (#1045)
• llm chat sessions now correctly respect default model options configured with llm models set-options. Thanks, André Arko. (#985)
• New --pre option for llm install to allow installing pre-release packages. (#1060)
• OpenAI models (gpt-4o, gpt-4o-mini) now explicitly declare support for tools and vision. (#1037)
• The supports_tools parameter is now supported in extra-openai-models.yaml. Thanks, Mahesh Hegde . (#1068)

This is the first alpha to introduce support for tools! Models with tool capability (which includes the default OpenAI model family) can now be granted access to execute Python functions as part of responding to a prompt.

Tools are supported by the command-line interface:

llm  --functions '
def multiply(x: int, y: int) -> int:
 """Multiply two numbers."""
 return x * y
' 'what is 34234 * 213345'

And in the Python API, using a new model.chain() method for executing multiple prompts in a sequence:

import llm

def multiply(x: int, y: int) -> int:
  """Multiply two numbers."""
    return x * y

model = llm.get_model("gpt-4.1-mini")
response = model.chain(
    "What is 34234 * 213345?",
    tools=[multiply]
)
print(response.text())

New tools can also be defined using the register_tools() plugin hook. They can then be called by name from the command-line like this:

llm  -T  multiply  'What is 34234 * 213345?'

Tool support is currently under active development. Consult this milestone for the latest status.

• New trigger design, using sqlite-chronicle 0.4. #4
• Existing chronicle tables are automatically upgraded to the new design, maintaining version and timestamp data.
• Now uses the text "Enable row version tracking for this table" in the UI. #5

• Upsert operations now use SQLite's INSERT ... ON CONFLICT SET syntax on all SQLite versions later than 3.23.1. This is a very slight breaking change for apps that depend on the previous INSERT OR IGNORE followed by UPDATE behavior. (#652)
• Python library users can opt-in to the previous implementation by passing use_old_upsert=True to the Database() constructor, see Alternative upserts using INSERT OR IGNORE.
• Dropped support for Python 3.8, added support for Python 3.13. (#646)
• sqlite-utils tui is now provided by the sqlite-utils-tui plugin. (#648)
• Test suite now also runs against SQLite 3.23.1, the last version (from 2018-04-10) before the new INSERT ... ON CONFLICT SET syntax was added. (#654)

• Fixed error about a missing table on server startup for some environments. #58

• New feature: --all --exclude name_of_table lets you import all tables but exclude one or more by name. Thanks, giuli007. #11
• Migrated from setup.py to pyproject.toml.

• New plugin feature: register_fragment_loaders(register) plugins can now return a mixture of fragments and attachments. The llm-video-frames plugin is the first to take advantage of this mechanism. #972
• New OpenAI models: gpt-4.1, gpt-4.1-mini, gpt-41-nano, o3, o4-mini. #945, #965, #976.
• New environment variables: LLM_MODEL and LLM_EMBEDDING_MODEL for setting the model to use without needing to specify -m model_id every time. #932
• New command: llm fragments loaders, to list all currently available fragment loader prefixes provided by plugins. #941
• llm fragments command now shows fragments ordered by the date they were first used. #973
• llm chat now includes a !edit command for editing a prompt using your default terminal text editor. Thanks, Benedikt Willi. #969
• Allow -t and --system to be used at the same time. #916
• Fixed a bug where accessing a model via its alias would fail to respect any default options set for that model. #968
• Improved documentation for extra-openai-models.yaml. Thanks, Rahim Nathwani and Dan Guido. #950, #957
• llm -c/--continue now works correctly with the -d/--database option. llm chat now accepts that -d/--database option. Thanks, Sukhbinder Singh. #933

• Now depends on LLM to support multiple models, not just Anthropic. #13

• Tiny cosmetic bug fix for mobile display of table rows. #2479

• Update plugin to work with latest Datasette 1.0 alpha
• Various UI improvements for comment icon on table view, bug fixes

• Fixed bugs with floating point columns. #34
• Now strips unicode null characters entirely (GPT-4.1-mini returned these for an image). #35

• Fix for incorrect foreign key references in the internal database schema. #2466
• The prepare_connection() hook no longer runs for the internal database. #2468
• Fixed bug where link: HTTP headers used invalid syntax. #2470
• No longer tested against Python 3.8. Now tests against Python 3.13.
• FTS tables are now hidden by default if they correspond to a content table. #2477
• Fixed bug with foreign key links to rows in databases with filenames containing a special character. Thanks, Jack Stratton. #2476

• Now depends on LLM and supports any model that has both async and schema support. You can also limit it to a subset of models using the new plugins.datasette-extract.models configuration list. #27

• llm models --options now shows keys and environment variables for models that use API keys. Thanks, Steve Morin. #903
• Added py.typed marker file so LLM can now be used as a dependency in projects that use mypy without a warning. #887
• $ characters can now be used in templates by escaping them as $$. Thanks, @guspix. #904
• LLM now uses pyproject.toml instead of setup.py. #908