LLeMbas/PLAN.md

LLeMbas — plan and status

Where the project is, what is deliberately not built yet, and the decisions that would be expensive to revisit. Kept current as work lands; the detail of how things work lives in CLAUDE.md.

Status: usable daily. Streaming chat, attachments, reasoning, tool calling with web search, custom HTTP tools and MCP servers, agent chats that work on a machine over SSH, a knowledge library, notes, memory and skills, speech in and out, image generation over ComfyUI, users and groups, model administration, installable as an app. 1676 tests, ruff clean.

---

The shape of it

A self-hosted web UI for OpenAI-compatible endpoints, written in Python, themed after Middle-earth.

Stack	FastAPI + Jinja + htmx + a little Alpine
Build step	none — no Node, no npm, no CDN at runtime
Database	SQLite, schema synchronised additively at startup
Deployment	systemd unit + nginx vhost, one worker

These are load-bearing. Dropping the no-build rule or moving off SQLite would be a different project, not a refactor.

---

Done

Chat

• Streaming replies over server-sent events
• Markdown renders progressively — re-rendered whole every 100ms rather than appending tokens, because a list or code fence is only correct once its context exists
• Syntax highlighting (Pygments), sanitised with nh3
• Generation runs in the background — a task, not the request. Navigate away, open another chat, close the tab: the reply keeps being written and reattaching replays the whole state
• Stop — the send button becomes Stop while writing; what arrived is kept
• Rewind — edit one of your own turns and the conversation runs on from there. Truncates rather than branching
• Chat titles that fit the chat — an ordinary chat is named by a model from the first exchange, an agent chat from its opening words alone, which are already an objective. Renameable from the heading and from the sidebar row; one response updates both
• Chats created on first message, so an abandoned composer leaves nothing
• Unread indicator — a green dot and a toast when a reply lands while you were elsewhere
• A reply that started without you asking still arrives — the open chat page polls for turns it has not got, so a background job waking the model appears where you are looking instead of only after a reload. Quiet while a reply is streaming, since that reply delivers its own bubbles
• A turn nobody typed says so — a background job's completion is a user turn on the wire, because the request needs one, and a machine event in the transcript: its own icon and name, no pencil, and no claim that you sent it
• Folders that carry something — arbitrarily nested, with a name, a description, a system prompt inherited by the chats inside them, and seeds for the model, the kind and the agent target. Deleting one keeps the chats
• The sidebar splits Chat and Agent — a switch below the pinned models, stored on the account, filtering the folder tree as well as the loose chats
• A reply reads as the sequence it was — thinking, prose, a tool call, more prose, in the order they happened, rather than three stacked zones with every tool block in the middle. Marks on the row index the three stores; a reply written before them renders exactly as it always did
• Blocks open while the reply is still being written — the ids are stable across every swap and across the final one, and opening a block stops the thread chasing the bottom until you scroll back down
• Per-reply metrics — tokens, context used as a percentage, tokens/second, live while streaming and kept afterwards. Estimated with a ~ when the endpoint reports no usage. Two chips: what the reply cost and what the conversation now occupies, each labelled, both moving between one usage block and the next rather than once a round
• Compaction — a button, and automatically at a configurable percentage of the model's context. Summarised turns are kept and collapsed, not deleted
• Temporary chats — never listed, swept after a day, with a Keep button
• An admin-only request inspector beside the thread
• Canvas — a third side panel holding open files, in tabs. Project files over SFTP in an agent chat; notes, skills, knowledge documents, this chat's text attachments and its own scratch document everywhere. Read with syntax highlighting, edited in a plain textarea, saved with a conflict check. Files the model touches open themselves, without taking the screen

Tools

• Tool calling — one reply is a bounded loop of requests, not one request. Text produced before a call is kept
• Web search as the first tool: DuckDuckGo (no setup), SearXNG or Firecrawl, chosen in the admin area
• Only offered to models flagged tools, because an endpoint without support rejects the whole request rather than ignoring the array
• Sources stay in the transcript; results are not replayed as context on the next turn, for the same reasons reasoning is not
• A round's calls run together, and the reply says which tool is running — a remote tool taking seconds with nothing streaming looks like a hang
• A reply can stop and ask you something — one or more questions on one card, with answers to pick from and a box to write your own, answered together. The same mechanism carries command approvals
• Custom HTTP tools — an administrator describes one call: a JSON Schema, a URL template, headers, an encrypted secret and how to read the answer. Arguments may fill a hole but never move the target: the scheme and host are literal, values are escaped for where they land, and the origin is pinned afterwards
• MCP servers over streamable HTTP — a hand-written client, so that check_url runs on every hop rather than being bypassed by somebody else's transport. Tools are discovered and cached by a button, namespaced per server, and a server's own descriptions are bounded before they reach a model as instructions
• Both gated like the built-ins — a model capability, a permission — and restrictable to groups, with guidance of their own on /admin/prompts
• Local MCP over stdio is deliberately absent: spawning a subprocess would run on this machine, which nothing here does

Image generation

• Draws on a ComfyUI you are running, as a tool the model chooses to call and as an /image command that makes it call one. Never on this machine, the same rule agent chats follow
• Multiple workflow templates — a name, a description and a ComfyUI API export with {{prompt}} and ten other placeholders where the values go. The model picks between them by their descriptions, and by checkpoint, falling back to the chat's usual and then the instance default when it names neither
• Model may set prompt, negative, seed, steps, cfg, width, height, sampler, scheduler, denoise, checkpoint and template; only the prompt is required and everything else has a default
• The result is checked before you see it — optionally, a vision model is shown the picture and the request and says keep or retry, up to a configurable number of attempts. Only clearly wrong images are retried; the last attempt is kept whatever it says, so a request always produces something
• Preserve VRAM — opt-in, for a machine that cannot hold both at once: unload the chat's own language model, generate, free ComfyUI, and let the next request load the model back. Per connection, so a box on the network is never touched
• Instance-wide extra instructions, injected into the harness beside the tool's own guidance
• Failures say what actually happened — out of memory, cancelled, or a node that raised, read out of ComfyUI's own record within a second rather than waiting out the timeout. A memory failure tells the model to retry at a named smaller size or a lighter checkpoint; a cancelled one tells it not to start again
• Every parameter described by what it does to the picture and when to move it, because a model given "cfg: default 8" sends the prompt alone. docs/image-generation-instructions.md is a longer set to paste into the admin instructions box

Agent chats

• A chat is a Chat or an Agent, chosen when it starts and fixed thereafter — a transcript whose earlier turns ran somewhere else is not one conversation. Knowledge, memories and skills are shared across both
• Nothing runs on the LLeMbas host. Commands go to a machine reached over SSH, so containment is somebody's considered choice of host — a container built for the job — rather than a sandbox built here. A local one was designed in detail and dropped; see CLAUDE.md for why
• SSH connections are user-owned, like notes. An administrator decides only whether the feature exists at all
• Trust on first use, made explicit: adding a host does not connect to it, Check shows its fingerprint with nothing sent, and only accepting pins it. A host that later answers with a different key is refused
• Four modes as a table over what each tool does to the world — Manual asks about everything, Edit writes freely but asks before commands, Auto asks about nothing, Plan reads freely and changes nothing. Switchable at any time; read once per reply
• Enforced in the generation loop, not in the prompt: a rule a model is merely told is one a poisoned file can argue with
• A deny list beats Auto for any command it can match; an allow list cannot be matched at all by a command containing anything that joins two commands together. A deny pattern cannot either — so in Auto a compound line runs, which is the trade for Auto not asking about cd build && make. See CLAUDE.md; matching each segment would restore both and is not built
• The terminal and the canvas open before the chat exists — on the new-chat screen, against the connection and directory being chosen there, and both re-point when that changes. The shell you opened and the files you left open are adopted into the chat when you send the first prompt
• Background jobs are visible — a chip in the composer row counting what is still running, and a panel with each job's command, state, log tail, how long it took and a Stop button. The dot is coloured by outcome rather than by status, since done covers exit 0 and exit 2 alike. Survives a restart, because the job does
• shell_run, file_read, file_write, file_list — files over SFTP, never through a shell, because the SSH exec protocol has no argv form
• Plan mode ends with a plan you can carry out with one button, which switches to Edit and sends it back quoted rather than as an instruction
• Per-reply budgets on steps, wall clock and output, with time spent waiting for you subtracted
• A terminal panel beside the chat, holding a real shell on that chat's own connection. The modes govern the model; what a person types is theirs, since they hold the credential and could open the same shell with an ssh client. The model cannot see the panel — sending it output is a button
• The shell outlives the panel and the page: closing it leaves a build running, and coming back reattaches with the scrollback. An idle timeout is what eventually ends one, and so does deleting the chat, or disabling, moving or deleting the connection
• The panel is resizable, dragged from its edge or nudged with the arrow keys, and the width follows you to another browser
• It knows where one command ends and the next begins — bash and zsh are given the markers VS Code and WezTerm use, so Copy and Send mean one command and its output rather than the last forty rows of the screen. An Auto toggle collects each one into the next message. Any other shell starts exactly as it did before, the buttons fall back to the screen and say so, and Auto is disabled rather than degraded
• The project directory is listed for the model — one read-only command, git ls-files where that works so .gitignore is honoured for free, budgeted so a big directory becomes a count rather than a thousand filenames on every request
• A directory is chosen by browsing it over SFTP, not by typing a path into an unlabelled box
• The approval mode is chosen before the first message, beside the message box rather than in the header

The library

• Knowledge bases — documents, images and saved web pages, grouped into named collections and ingested through the same pipeline as chat attachments, searched with SQLite FTS5
• A chat can be pointed at particular bases, so "answer from the contracts folder" is a different question from "answer from everything I have"
• Notes — longer things the model writes down and searches later; editable by hand, because they are yours
• Memory — short facts, injected on every turn to a budget rather than searched, and managed in your settings
• Skills — saved procedures. Only the name and description are injected; the body is fetched when the model decides it applies
• A model may write and revise its own notes, memories and skills. Every skill revision is kept, attributed and revertible — the safety story is a record and a way back, not a gate
• Sharing — a knowledge base, a note or a skill can be shared with a group or with named people, read-only. One visibility rule, and administrators do not bypass it. Documents are shared through their base
• The harness — an operational prompt assembled from what a model actually has, so the tools get used rather than ignored
• Attach menu: file, image, a web page fetched on the spot, or a document from the library
• @ to name one — the library everywhere, and files in the project directory in an agent chat. The reference stays in the sentence and the contents come along, with the path and the machine, so the model knows exactly which file it was handed

Audio

• Dictation — record in the composer, transcribed by any OpenAI-shaped /v1/audio/transcriptions endpoint. The recording never touches disk
• Read aloud — any /v1/audio/speech endpoint, with the voice list discovered from the server where it offers one
• Instance defaults in Admin, per-reader overrides in Settings — voice, speed, dictation language, and whether replies play automatically

Models and reasoning

• OpenAI-compatible connections with encrypted keys and model discovery
• Reasoning display — reasoning_content and inline <think> tags, collapsed by default, labelled with how long it took, never replayed as context
• Model admin as a list plus a page per model; scales to hundreds
• Ordering, pinning (a sidebar shortcut, not a reordering), instance default, per-user default, images, capability flags
• Custom model picker showing avatars, descriptions and capabilities

Attachments

• Drag, paste or pick images, PDFs and text files
• Images downscaled and sent to vision models as content parts
• PDF and text extracted at upload and placed in the prompt
• Type decided by inspecting bytes, random names on disk, non-images served as downloads with nosniff
• No OCR: a scanned PDF says so rather than silently contributing nothing

People

• Accounts, argon2, revocable server-side sessions, self-service password change
• Users and groups with permissions that union rather than override
• Model access restricted to chosen groups
• Registration toggle, instance settings stored in the database

Prompts

• Three layers — instance, model, chat — with the most specific winning outright rather than being concatenated
• Every injected fragment editable at /admin/prompts: the tool guidance, the memory and skill sections, the seam above the authored prompt, and the request that names a chat
• {{variables}} with a legend, values shown as they currently resolve, and pass-through for anything that is not one
• A preview of the whole assembled system message, including unsaved edits
• Defaults in code and overrides in the database, so improving a default still reaches an instance that never edited it

Suggestions

• Admin-managed cards on the new-chat screen; three seeded once at startup

Interface

• / for commands — compact, usage, mode, model, title, the panels, the theme. Anything not in the table is sent as an ordinary message, and // starts one with a literal slash
• Keyboard shortcuts for the same jobs, listed beside the commands in one table so /help cannot go stale
• Mentions and recognised commands are marked as you type, and again in the transcript, so you can see what a message will do before sending it
• Reasoning effort per chat, with a per-model default. Sent as both reasoning_effort and chat_template_kwargs, and only once chosen: OpenAI and vLLM read the first, llama.cpp silently drops it and reads only the second
• Installable — manifest, generated PWA icons, a service worker for the shell and a themed offline page. The worker deliberately never touches /api/: a reply is an event stream and caching one breaks it
• Two themes (moria, shire) from one set of design tokens
• Every control sized from --control-h, so rows line up by construction
• Toasts and dialogs of our own; no window.confirm anywhere, and data-prompt for asking one line before a request goes out
• An approval card's command can be corrected before it is allowed, and the transcript says who wrote what ran
• Refusing can say why — "Give reason" opens a box beside Don't, and what you write goes back as the instruction rather than as a rejection, so the model carries on from it instead of spending a round asking what you meant
• Original SVG artwork generated from a single source

Operations

• Additive schema sync — new tables and columns applied at startup
• deploy/ — systemd unit and nginx templates, install and update scripts

---

Not built yet

In the order they are likely to be worth doing.

Smaller things

• OCR for scanned PDFs
• Conversation branching — Message.parent_id exists unused; needs a UI for choosing between versions, which is why rewind truncates for now
• Chat export (Markdown, JSON)
• Semantic search in the library — the retrieval service is one call, so an embedding backend can go behind it without touching the tools or the UI
• Archived chats — the column exists, nothing surfaces it
• Per-user quotas

---

Known limits

Worth knowing before they surprise someone.

One worker. The generation registry and the stop mechanism are in-process. Running several workers needs that state in the database or a broker, because the request following a reply would not necessarily land in the process writing it.

A restart abandons replies in flight. Shutdown cancels them and keeps what each had. There is no resume.

Schema changes are additive only. New tables and columns apply themselves; renames, drops and retypes are manual against the SQLite file. MANUAL_STEPS in db/migrations.py is where such a step gets recorded.

Attachments live on disk, unreferenced files are swept at startup. No deduplication, no size quota.

Unread is polled every 10 seconds. A push channel would be more responsive but means an always-on connection per tab for the sake of a green dot.

Installing needs HTTPS or localhost. Service workers are unavailable over plain HTTP, so a LAN install without TLS is a normal browser tab. The microphone is unavailable for the same reason.

Tool calling needs a model that supports it. The tools flag is an administrator's assertion, not something endpoints reliably advertise. Set it on a model that cannot, and its replies fail rather than degrade.

Library search is keyword, not semantic. FTS5 ranks well and needs no dependency or embedding endpoint, but "how do I get paid" will not find a document that says "invoicing".

A model can write its own skills, and they take effect at once. Marked as model-authored and fully revertible, but a model that has just read a hostile page could save a skill that outlives the conversation. The mitigation is that it is visible and undoable, not that it was prevented.

---

Deliberate decisions

Recorded because each looks like an oversight until you know the reason.

• No JavaScript build step. Browser libraries are hash-pinned and committed. A self-hosted tool should work offline and not report page views to a CDN.
• Permissions union, never deny. With denies, "why can this user not do X" cannot be answered without simulating every group.
• System prompts replace, never stack. Two layers that disagree give the model contradictory instructions and nobody can tell which is losing.
• Rewind truncates, does not branch. Branching needs a UI for choosing between versions; "go back and try again from here" is what was asked for.
• Pinning is a shortcut, not an ordering. A picker whose order silently differs from the admin screen is confusing.
• Images only reach models marked vision. Not graceful degradation: most endpoints reject the entire request rather than ignoring an image part. Tools are gated the same way, for the same reason.
• Sharing grants reading, never writing. Two people editing one note with no history and no merge is worse than the inconvenience of copying it.
• Memory is never shareable. A record about a person is not content to hand round.
• Knowledge attached to a message is copied, not referenced. History must not change under a conversation because a document was edited later.
• The harness is prepended to the authored prompt, not a fourth layer. It describes the machinery; the authored layers describe the behaviour. Only one authored layer still wins.
• Tool results are not replayed. Like reasoning: the answer already contains what the model made of them, and replaying stale results into every later request wastes the window and sends small models into search loops.
• The service worker caches the shell, never a page with a user in it. A cached conversation would be a snapshot that silently went stale, belonging to whoever was signed in last.
• Markdown rendered server-side. One code path produces the streamed and the stored view, so they cannot disagree.
• This repository is public. Deployment hostnames, ports and paths stay out of it; deploy/ is templates, and the real values live in private notes.