Version 1.17.0 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: ============================== Tool for interacting with LLMs ============================== More at https://elpa.gnu.org/packages/ellama.html ## Summary: ━━━━━━━━ ELLAMA ━━━━━━━━ [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 is a tool for interacting with large language models from Emacs. It allows you to ask questions and receive responses from the LLMs. Ellama can perform various tasks such as translation, code review, summarization, enhancing grammar/spelling or wording and more through the Emacs interface. Ellama natively supports streaming output, making it effortless to use with your preferred text editor. ## Recent NEWS: 1 Version 1.17.0 ════════════════ • Add maximum output token support. Ellama now exposes `ellama-max-tokens' and passes per-request `:max-tokens' values through `llm-make-chat-prompt', so providers can cap generated responses using their standard token limit support. The model transient menu can set or reset the max-token override, and documentation and tests cover the new behavior. 2 Version 1.16.3 ════════════════ • Sort saved session candidates newest first in `ellama-load-session'. Ellama now orders session files by modification time and exposes standard completion metadata so completion UIs can preserve that order. 3 Version 1.16.2 ════════════════ • Fix GNU ELPA tarball manual generation from `README.org'. Add Org export metadata so ELPA writes `ellama.texi' with a valid title, and keep the local manual exporter from inheriting those README-only export keywords. 4 Version 1.16.1 ════════════════ • Remove false statement from documentation. 5 Version 1.16.0 ════════════════ • Add image input support for prompts and context. Ellama can now attach image files to chat requests, queue image context ephemerally, and build multipart prompts for providers that support image media. • Add image-aware tool handling. The `read_file' tool can run in auto, text, or image mode, and image files read by tools are bridged into the next model request without persisting binary media in saved sessions or compaction summaries. • Add transient commands and documentation for image workflows, including direct image chat, image context, supported formats, read-file modes, tool-call image bridging, and persistence behavior. • Fix chat buffer rendering for ephemeral context, including image context added before sending a manually typed chat message. • Change image ask commands to use ephemeral image context, matching `ellama-ask-about' and keeping the chat transcript aligned with request context. 6 Version 1.15.0 ════════════════ • Add task prompt templates for subagents. The task tool can now render relative template paths with object-based argument substitution, strict path checks, validation hints, and callback-based error reporting. • Improve task subagent sessions. Ellama can display session buffers when session-backed generation starts, insert delegated task prompts into worker session buffers, preserve worker session metadata, and keep subagent continuations bound to the correct worker session after tool calls. • Document task subagent templates, template path resolution, argument validation hints, continuation behavior, and session buffer display. The Info manual has been regenerated from `README.org'. • Improve OpenAI-compatible tool-call history handling by normalizing stored tool-use arguments and decoding unibyte strings before provider request serialization. This keeps retried tool-call history JSON serializable across older or mixed `llm' versions. • Fix OpenAI-compatible streaming tool-call collection for multi-call batches. Streaming tool calls are collected using the maximum emitted tool-call index, avoiding out-of-range errors when a single chunk contains multiple tool calls. • Fix CI compatibility issues around the task template directory default and provider request sanitization tests. 7 Version 1.14.2 ════════════════ • Add project-local skill pointers for changelog and commit-message workflows. This makes repository-specific Codex skills discoverable from `.codex/skills'. • Add a `commit-message' skill for concise commit message generation from diffs. • Update agent instructions to document the project commit workflow. The workflow now covers pre-commit checks, branch creation from `main', iterative check/fix/commit/push cycles, documentation updates, changelog generation, version bumps, and when to ask for clarification. 8 Version 1.14.1 ════════════════ • Refactor transient model handling and provider construction. Generalize transient model handling to support multiple provider types beyond Ollama, including OpenAI-compatible providers. • Implement `ellama-transient-set-model' and `ellama-transient-set-url' for … …
