- LEMBAS_PROTOCOL, the device protocol and the protocols the CLI logs in to
and links with are 3 alone (harness/acp.md *Versions*). A server listing
only 1 and 2 is refused at login and at every dial — before anything is
dialled — with its version and protocols and "update the server, or use
LLeMbas CLI 1.x with it"; a newer one is told to update the CLI
(ProtocolError). A 4400 stops the link with the same advice. The old
downgrade to protocol 1 is gone.
- session/new's result says `instance`: whether the session's model is the
link's instance's.
- `lembas_model` is the model, full stop: a device not logged in to the link's
instance, a link with no instance (serve --stdio), or a model the instance
does not serve to this device is -32602 with the reason, never a session on
the device's own model. `_lembas/configure` naming such a model is refused
likewise and the session keeps its model.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Harness spec 3.0.0 (acp.md *Memory*): memory records are the server's for the
device as for a chat; everything else in the library is the device's own.
- `library: lembas` (the default when the login's token has the `memory`
scope, or the older `library`) adds the server's /mcp with its `memory`
tool alone, in place of this machine's memory tool; notes_*, knowledge_*
and skill_* are always this machine's. No prompts, resources or
instructions are taken from it.
- The memory in the prompt is the server's: the resource lembas://memory,
read as a session starts (McpManager.readResource) and kept for it — put in
while nothing has been sent, so the prompt never changes under a session.
- A session the client opened (session/new, or opened from the store) sends
its id as `_meta.lembas.scope` on every memory call and on the resource
read (App.setScope); a session of the device's own sends none.
- An instance's `library` context (its knowledge bases) is no longer read:
the knowledge block names this machine's bases only.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
LLeMbas CLI 2.0 is LLeMbas-server-specific (CLI rule 2). Removed: the
anthropic, gemini, ollama and responses clients, context discovery and
llama-swap unloading (discover.ts), the Connection schema with its dialect,
auth, key_cmd, discover, unload_url and one_model_at_a_time, the model
`fallback` (it only ever moved to another server), effort_map and cache, and
the multi-connection refs. Kept: openai-chat, http, sse, think, effort,
tokens and all of src/lembas.
- connections.yaml holds the login (`type: webui`, as lembas login writes
it). A custom entry from 1.x is read past with a warning that says how to
log in, so an old file still starts; with several logins left, the latest
is used and the others named.
- A model's ref is the id the server serves it under; the older forms
(`<login>/<id>`, `<login>/<model>`) still resolve and config.yaml is
rewritten once. Without a login there is no model, and the error (and the
first-run screen, now the sign-in alone) says `lembas login <address>`.
- A login to another server signs this machine out of the previous one.
- The window is the server's word (no discovery); a capacity group comes
from the server's `capacity.group` alone; embeddings use the server's
/v1/embeddings.
- `lembas models` lists the server's models; install.sh's starter files, the
README and the JSON schemas say the same.
Tests: every fixture is a login now (the fake server lists models, answers
other GETs with 404, and can hand one model to another script, as a server
with several backends); the dialect suites and the cross-connection tests are
gone with their code.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The spec's version may be a pre-release (3.0.0-draft). Every tool file is
loaded, with the new fields `sessions`, `requires`, `unavailable` and
`confirm`; the CLI's tools are those not the server's alone and offered in an
agent session (forCli) — a chat's own tools over the server's tree (mkdir, mv,
rm, search, python, the forge verbs) are not built in. blocks/context.md is
known; blocks/workspace.md is the server's alone.
show is built in with `requires: display`: offered only in a session a client
opened over the link when that client said `show: true` (capability `show`);
the device reads the file (at most 1 MB) and sends it with `_lembas/show`.
The harness tests now say 3.0.0's split of tools instead of "the execution
tools are the CLI's alone".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The turn log answered a repeated id with what that turn had answered, which
was right for a prompt sent twice over a dropped link and wrong for a turn
the web UI had just rewound to edit: the same id came back with the old
reply. rewind now returns the ids it took out, both handlers forget them from
the log, and the turn file drops them too, or the next load would have
brought them back.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The spec: plan_write and plan_update (new, shared, offered in every mode) and
plan_submit (now shared) keep one structured plan — findings, objectives,
phases of tasks — in place of the todo list, which lives on as a former name
of plan_write. The shared system text is one text for both projects, with
variables for what differs; the mode texts, a prototypes block and a library
block are shared. acp.md: the client hands the device what only it knows
(context, library, prototypes), the plan travels as a structure (plan_state),
library calls carry the chat's scope, and a client may rewind a session.
loop.json says its numbers as numbers. Four conformance areas: plan,
prototype, library_scope, toolcall_index.
The CLI: the plan is kept per session in the store and drawn above the prompt
and on the approval card; the prompt is assembled from the spec's texts with
their variables filled; the link reads the instance's instructions,
personalization, knowledge scope and prototype offer, sends the plan as a
structure and answers rewind; library calls to the instance carry the session
as scope; a prototype written in the terminal is saved as a file and named in
the transcript; a tool-call fragment without an index continues the last call;
the default theme is Moria; dead exports and Hermes leftovers removed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The first public release of LLeMbas CLI: a terminal coding agent and project manager for any LLM
API, with permission modes, git snapshots, memory and skills, knowledge bases, MCP, voice, and a
link to a LLeMbas instance whose web UI can work its sessions too. Signed Linux binaries for x64
and arm64.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
HomerandClaude Opus 5.5