[GNU ELPA] Ellama version 1.31.0
ELPA update <[email protected]> Mon, 20 Jul 2026 17:06:52 -0400
| Newsgroups | gmane.emacs.sources |
|---|---|
| Message-ID | <[email protected]> |
Version 1.31.0 of package Ellama has just been released in GNU ELPA.
You can now find it in M-x list-packages RET.
Ellama describes itself as:
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D
Tool for interacting with LLMs
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D
More at https://elpa.gnu.org/packages/ellama.html
## Summary:
=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=
=81
ELLAMA
=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=81=E2=94=
=81
[file:https://img.shields.io/badge/license-GPL_3-green.svg]
[file:https://melpa.org/packages/ellama-badge.svg]
[file:https://stable.melpa.org/packages/ellama-badge.svg]
[file:https://elpa.gnu.org/packages/ellama.svg]
Ellama brings large language models into Emacs without turning Emacs
into a web app. You can use it for ordinary chat, one-shot commands
over the current buffer or region, and longer sessions that keep their
history. It also has agent loops for work that needs several steps:
make a plan, call tools, read project context, and continue from the
previous turn.
## Recent NEWS:
1 Version 1.31.0
=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=
=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90
=E2=80=A2 Show irreversible action confirmation details. Named tool argum=
ents
are now included in security confirmation prompts, and a full-detail
view flow has been added for DLP and irreversible actions. The flow
preserves context even when audit logging fails, and regression
tests cover prompt contents as well as the view interaction.
2 Version 1.30.0
=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=
=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90
=E2=80=A2 Split the subagent task tool into two separate contracts. The `=
task'
tool handles free-form delegation, while `task_from_template'
handles template-based delegation. Both now have proper required
schemas and validation checks instead of accepting anything
silently. The direct Lisp template interface still works as
before. Updated the docs and added regression tests.
=E2=80=A2 Added a plan-and-act action to the blueprint-mode transient
menu. Starting it kicks off the plan-and-act agent loop from the
current blueprint buffer and then closes the buffer. Included
regression tests to verify the buffer contents get forwarded to
`ellama-plan-and-act' and that the source buffer is killed once the
loop starts.
3 Version 1.29.0
=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=
=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90
=E2=80=A2 Added `ellama-setup-agentic-coding' to configure long-running
coding-agent defaults. This profile enables DLP enforcement,
fail-closed DLP behavior, session compaction, visible sub-agent
sessions, and longer agent loop limits. In non-SRT mode, ordinary
DLP findings ask first while normal confirmations stay active; in
SRT mode, ordinary input findings are allowed and ordinary output
findings are redacted, with irreversible findings still
blocked. Tests cover non-SRT, SRT, and secure modes.
=E2=80=A2 Removed obsolete problem solver commands
`ellama-solve-reasoning-problem' and
`ellama-solve-domain-specific-problem' from the codebase and the
main transient menu, along with the `ellama-chain' function they
relied upon.
=E2=80=A2 Updated the README onboarding section to refresh Installation
references around GNU ELPA, Ollama, and added an explicit
`qwen3.6:35b' agentic setup example.
=E2=80=A2 Documented the new `ellama-setup-agentic-coding' profile and sp=
lit
Commands and Configuration sections into smaller groups for easier
navigation. Regenerated `ellama.info'.
4 Version 1.28.0
=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=
=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90=E2=95=90
=E2=80=A2 Audio input support: audio files can now be attached alongside
images in prompts, with provider capability validation. Includes
transient entries, key bindings, a recording lighter in the mode
line, and microphone recording commands. `ellama-read-file' can
queue audio files for the next model turn, exposing audio mode in
customization and tool metadata.
=E2=80=A2 Audio recording backends: on startup, auto-selects the available
recorder by platform =E2=80=94 FFmpeg or SoX on macOS, arecord/FFmpeg/S=
oX on
GNU/Linux. Fallback failures include the recorder's output and a
macOS microphone-permission hint.
=E2=80=A2 Recording normalization: default FFmpeg recordings are processed
through a configurable dynamic audio normalization filter so quiet
speech reaches audio models at a usable level.
=E2=80=A2 Provider type selection: `ellama-transient' now supports select=
ing
LLM provider types (Ollama, Claude, Gemini, etc.) via
`ellama-transient-provider-types' and
`ellama-transient-set-provider-type', with improved error handling
during streamed responses.
=E2=80=A2 Self-check step in plan-and-act: the workflow now appends an
unstepped "Check yourself" entry to the checklist, allowing manual
review before the acting phase.
=E2=80=A2 Silent buffer revert after editing file: calls `revert-buffer' =
after
`save-buffer' to stop Emacs from asking whether to revert a file
that was just written.
=E2=80=A2 File buffer refresh after shell commands: file-visiting buffers
under the shell command working directory are refreshed silently
after command completion, without prompting.
=E2=80=A2 Non-interactive shell environment: `shell_command' sets `TERM=
=3Ddumb'
and `NO_COLOR=3Dtrue' for subprocesses, preserving pager
normalization.
=E2=80=A2 Improved truncated output hints: line-range reporting now shows
accurate output and source line counts, includes the configured line
budget in
=E2=80=A6 =E2=80=A6