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mode, the wrap-up keeps the tools and runs no call, a withdrawn tool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>
instructions.json and fs_access.json pointed at services/files/*.py,
which LLeMbas never had: the chain is services/workspace.py, the view
services/fs.py with security/access.py. context.json no longer says
"to be written". python's {{seconds}}, {{memory}}, {{output}} and
{{packages}} are implementation-defined; their descriptions record what
LLeMbas 2.0 fills (30 s, 512 MB, 20,000 characters, the standard library
only).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
context.md and loop.json `context`, spec 3.0.0-draft:
- A stub names only a result in the request being built. A chat on the
server sends no earlier reply's tool results, so a read in the next reply
is answered in full there; the CLI, which resends every result, keeps
stubbing across steps. Said for reads and for repeated listings alike.
- The compaction table is drawn from the reads the summary covers: the
full reads since the previous compaction in turns still in the history,
whether or not the request still carries them. A turn taken back takes
its reads with it. The CLI's dedupe table is exactly that set; a chat
finds it in what it stored.
- Ids are the result's number in the session, in hex, at least 4 digits
(#0001); the examples and the prompt block now use such ids.
- A bracket names the path as the call gave it; what identifies a file
is its absolute path.
Conformance `context`: a `reply` step (a request carrying none of the
results so far) and a case for both rules. The CLI's runner keeps the
history apart from the request; compactionTable takes the reads.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
conformance/context.json named results #g001…#k001, which are not the
lowercase hex context.md requires (an implementation that finds a result's id
at the head of the result by that rule cannot see them); they are #1001…#5001
now, with the same answers. Its `about` names the CLI's module,
session/results.ts.
context.md §5 says what it left open: a deleted file's bracket, and an
apply_patch over several files — the id alone, then each file in its own
bracket with its change, in the patch's order; a tool's note after the diff.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
context.md and loop.json `context`: every result has an id, a read carries its
lines and content hash, an unchanged re-read (or a range inside one) is a stub,
large output keeps head and tail with the elided line, recall shows any stored
result, edits answer with their diff, a repeated listing or search with the
same result is a stub, and compaction adds a table of reads and empties the
dedupe table. Nothing already sent is ever rewritten. Conformance area context.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
filesystem.md: paths, the node kinds dir/file/mount, the access levels
none/ro/stage/commit with grants and floors, the exact error texts, and the
rule that a granted path under one that is not is reached only by its full
path. Listings, search, indexing by tokens (480 a piece, 64 repeated),
instruction files stacked from the boundary to the start directory, skills,
and memory kept by the server for both sides. Conformance areas fs_access,
instructions and chunk_tokens, answered from a reference model of the rules.
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 CLI's facts in memory, notes_search, note_manage, skills_list,
skill_view and skill_manage are `variables` now, filled with the CLI's own
values (src/tool/spec-vars.ts): every description and parameter list the CLI
sends is word for word what 1.1.0 said, except note and document ids, which
are strings on both sides (a number is still taken). Descriptions are
filled by the prompt texts' rules, parameter descriptions too. `narrow`
says what a project offers of a shared tool's parameters. Memory's changes
are one pure function (applyOps). Conformance: fill, narrow, memory.
Co-Authored-By: Claude Opus 5.5 <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