Levels (models/schema.json levels): provider/effort.ts levelsOf/levelFields/
readLevel — `off` only with thinking_switch and sends enable_thinking false
and no effort, `default` for a model that takes no efforts and sends
nothing, a level not offered is read as the start level. The engine's
effort is a level; /effort shows nothing for one level, a Thinking switch
for [off, X], a list otherwise; the status bar follows. /v1/models'
thinking_switch, efforts [] and capacity.parallel are read
(lembas/webui.ts); session/capacity.ts counts parallel slots.
Reasoning (context.md §8): an assistant message of the current turn
carries reasoning_content (provider/common.ts turnReasoning,
openai-chat.ts); step-boundary deliveries, nudges and the wrap-up are
marked turn: false and do not start a turn.
Paths (context.md §11): the <env> block names the project and, started
below the root, that directory relative to it (assemble.ts envLines);
instruction files and @ attachments are named from the root or as ~/…;
file tools and bash resolve relative paths against the project root.
The team rules (team/team.ts) and conformance runners for levels,
reasoning, paths and team; the team runtime follows.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The system prompt is made once per session (start, compaction, model
switch), kept in session_meta and resent byte for byte; it holds no
date. What changes mid-session -- the date, a mode the person chose, a
plan or memory or instruction file they edited, a personality, MCP
instructions that arrived later -- is a <session-note> on the next user
message, stored with it. The tool list is fixed for the session:
plan_submit is always offered and answers unavailable outside plan
mode, the wrap-up keeps the tools and runs no call, a withdrawn tool
stays listed and answers its refusal; the first request waits up to
mcp_wait_ms for MCP servers. Compaction asks for its summary as the
next turn of the same conversation. Cached input tokens are parsed
(incl. llama.cpp timings), stored per request and shown in /context.
Spec: context.md §7/§10, loop.json context.note (+ plan_ended,
plan_own, personal, empty, mcp_wait_ms), modes.json plan.refused,
compact.md without the transcript heading. Conformance area prefix.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The login asks the server for the memory scope in place of library (the
server accepts both; library is no longer offered for new tokens).
/v1/usage is read in the server's 2.0 shape: no plan, balance, credit
costs or windows. The status bar shows what the month has cost so far and
/usage the month's tokens and cost and this device's tokens, each
currency's amount on its own (month.cost_by_currency, else cost_money in
currency). The credit wording is gone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
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>
One registry per process, every job owned by a session: bash's background commands (and a command
still running at its timeout, which now goes to the background instead of being killed) and
subagents started with task background: true. job_list, job_output, job_stop (the former
bash_list, bash_output, bash_kill) and the new job_send and report; a finished job wakes the owning
session in every front end with its marked note. The TUI counts jobs, lists them (/jobs), opens a
command's output, enters a subagent and messages it, moves a command to the background (ctrl+b)
and asks before quitting with jobs running. The link gains the jobs capability. Subagents get a
session row of their own, the spec's preamble and agent texts, and their errors reach the report.
Co-Authored-By: Claude Fable 5.1 <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>
`lembas remote list | add | remove | enable | disable | mode | terminal`, with
`--json` printing {enabled, roots, max_mode, terminal}, for LLeMbas Desktop.
Writes go through the global config writer and keep comments.
The device's limits are now live getters over the remote: block, re-read when
config.yaml's stat changes. `lembas service` links even with remote work off
or no roots: it says roots: [] and refuses every session, directory and
terminal, so the instance can tell "no folder allowed yet" from "not running".
When what the instance was told changes, the link re-dials once nothing is
working, so `lembas remote add` or `enable` takes effect without a restart.
Harness spec 1.0.1 documents both.
Co-Authored-By: Claude Opus 5.5 <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