diff --git a/CHANGELOG.md b/CHANGELOG.md
index b753402..f6f9e14 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,48 @@ for 1.0.0 have something to be assembled from.
## Unreleased
+## 1.0.4
+
+Six things that looked like they worked. Five of them were found by reading the
+code rather than by anybody reporting them, which is what they have in common:
+none of these fails loudly, and two of them correct themselves if you reload.
+
+- Fixed: **a reply lost the model's name and picture the moment it finished.**
+ While a reply streams it is attributed correctly; at the instant it lands, the
+ frame that replaces the bubble was looking the models up as nobody, and "no
+ user" answers "no models" rather than "all models". So a finished reply swapped
+ the model's avatar for the plain leaf mark, put the instance's name where the
+ model's should be, and grew a raw model id beside it. Reloading the page put it
+ all back, which is why this survived a release: it is only ever wrong until you
+ look away.
+- Fixed: **a limit on how many replies an account may write at once could be
+ stepped over by pressing New chat.** It was enforced when sending into a chat
+ that already existed and nowhere else — not on a new chat, not on editing an
+ earlier message, not on sending a queued one, and not on regenerating. Four of
+ the six ways to start a reply ignored it, including the commonest.
+- Fixed: **a custom theme's confirmations and warnings kept the built-in
+ theme's colour behind them.** Setting `success` or `warning` moved the text and
+ left the background it sits on, because the faded companion colour was derived
+ for three of the five settable colours. Visible on every alert and badge of
+ those two kinds, on the "on" state in the permissions list, and on the added
+ lines of every diff in an agent chat.
+- Fixed: **on a phone, every page with a sidebar could be scrolled past its own
+ bottom into empty background.** The shell was sized to the part of the screen
+ you can actually see and the document around it to the part you can see with
+ the browser's toolbar retracted; the difference between those is real on a
+ phone and nil on a desktop, which is why it was never noticed on one. Reported
+ on Settings and true everywhere. A flick that ran off the end of a list now
+ stops there as well, instead of dragging the page behind it.
+- Fixed: **the conversation was rendering every assistant message twice on every
+ page load** — once into Markdown that nothing read, and once the way it is
+ actually shown. The same was true of Messages, for your own turns. Nothing
+ looked wrong; a long conversation was simply slower to open than it needed to
+ be, every time, along with every rewind and every compaction.
+- Fixed: a test file meant to skip itself on a machine without `setsid` never
+ did, because it set its marker twice and the second one replaced the first.
+- Removed: an endpoint serving a message's unrendered Markdown, which nothing
+ had ever called — the copy button reads the page it is already on.
+
## 1.0.3
Two Arch-isms in the installer, both of which only a Debian machine could find.
diff --git a/src/lembas/__init__.py b/src/lembas/__init__.py
index cb530f2..ca22f10 100644
--- a/src/lembas/__init__.py
+++ b/src/lembas/__init__.py
@@ -1,3 +1,3 @@
"""LLeMbas - a Middle-earth themed web UI for OpenAI-compatible LLM endpoints."""
-__version__ = "1.0.3"
+__version__ = "1.0.4"
diff --git a/src/lembas/api/chats.py b/src/lembas/api/chats.py
index c8a79c7..127185f 100644
--- a/src/lembas/api/chats.py
+++ b/src/lembas/api/chats.py
@@ -308,6 +308,12 @@ async def start_chat(
if not content and not file_ids:
return Response(status_code=status.HTTP_204_NO_CONTENT)
+ # Before `_new_chat`, not after: a refusal that has already written the row
+ # leaves an empty chat in the sidebar as the visible result of being told
+ # no. There is no chat yet to exclude from the count, and none is needed --
+ # nothing can be running for a chat that does not exist.
+ _refuse_extra_reply(db, None, user)
+
chat = _new_chat(
db,
user,
@@ -981,7 +987,7 @@ def _note_rewind(chat: Chat) -> None:
chat.rewound_at = datetime.now(UTC)
-def _too_many_replies(db: DBSession, chat: Chat, user: User) -> str:
+def _too_many_replies(db: DBSession, chat: Chat | None, user: User) -> str:
"""Why this account may not start another reply right now, or "".
In-process, and that is exact rather than approximate only because this
@@ -998,10 +1004,13 @@ def _too_many_replies(db: DBSession, chat: Chat, user: User) -> str:
row[0]
for row in db.execute(select(Chat.id).where(Chat.user_id == user.id)).all()
}
+ # `chat` is None on the new-chat path, where there is no row yet and so
+ # nothing to exclude -- every running reply of theirs counts.
+ here = chat.id if chat is not None else None
running = sum(
1
for chat_id in mine
- if chat_id != chat.id and generation_service.running_for(chat_id) is not None
+ if chat_id != here and generation_service.running_for(chat_id) is not None
)
if running < ceiling:
return ""
@@ -1011,6 +1020,22 @@ def _too_many_replies(db: DBSession, chat: Chat, user: User) -> str:
)
+def _refuse_extra_reply(db: DBSession, chat: Chat | None, user: User) -> None:
+ """Raise if this account is already writing as many replies as it may.
+
+ A function rather than two lines repeated, because it is repeated five
+ times now. It used to be called once -- from `_send`, which serves
+ `post_message` and `execute_plan` -- while four other routes start a
+ generation: `start_chat`, `edit_message`, `send_queued_now` and
+ `regenerate`. So a group's `concurrent_replies` was reached by sending into
+ a chat that already existed and walked straight past by pressing New chat,
+ which is the commonest way to start a reply there is. A quota you can step
+ over by using the obvious button is not a quota.
+ """
+ if busy := _too_many_replies(db, chat, user):
+ raise HTTPException(status.HTTP_429_TOO_MANY_REQUESTS, busy)
+
+
def _send(
request: Request,
db: Db,
@@ -1042,8 +1067,7 @@ def _send(
# This chat's own reply does not count against it -- a second message here
# is queued rather than sent, a few lines down, and that path is what the
# queue is for.
- if busy := _too_many_replies(db, chat, user):
- raise HTTPException(status.HTTP_429_TOO_MANY_REQUESTS, busy)
+ _refuse_extra_reply(db, chat, user)
if queued := _reply_in_flight(db, chat):
waiting = db.scalar(
@@ -1328,8 +1352,16 @@ async def _follow(chat_id: str, message_id: str) -> AsyncIterator[str]:
# template shares both roles, and a missing `user` would only
# blow up on whichever branch is not being exercised here.
"user": owner,
+ # `owner`, never None. `models_visible_to` answers an absent
+ # user with [], so a None here is not "every model" but *no*
+ # model -- and this frame replaces the whole bubble at the
+ # moment a reply finishes. The template then finds no
+ # `speaking_model` and the finished reply swaps its avatar for
+ # the LLeMbas mark, its author for the instance name, and grows
+ # a raw model_id chip, all of which a reload silently corrects.
+ # That is why it went unreported for so long.
"models_by_id": {
- m.model_id: m for m in chat_service.available_models(db, None)
+ m.model_id: m for m in chat_service.available_models(db, owner)
},
# This frame replaces the whole bubble, so it has to carry the
# speaker button's conditions too -- and the owner's, not the
@@ -1360,7 +1392,7 @@ def _render_bubble(db: DBSession, chat: Chat, owner: User | None, message: Messa
"message": message,
"chat": chat,
"user": owner,
- "models_by_id": {m.model_id: m for m in chat_service.available_models(db, None)},
+ "models_by_id": {m.model_id: m for m in chat_service.available_models(db, owner)},
**audio_service.template_flags(db, owner),
}
)
@@ -1447,11 +1479,6 @@ def _thread_context(db: DBSession, chat: Chat, user: User) -> dict:
"user": user,
"messages": messages,
"compacted": compacted,
- "bodies": {
- m.id: render_markdown(m.content)
- for m in everything
- if m.role == ROLE_ASSISTANT and m.content
- },
"models_by_id": {m.model_id: m for m in chat_service.available_models(db, user)},
**audio_service.template_flags(db, user),
}
@@ -1560,6 +1587,8 @@ async def edit_message(
raise HTTPException(
status.HTTP_409_CONFLICT, "Wait for the current reply to finish, or stop it."
)
+ # `_reply_in_flight` is about *this* chat; the quota is about the account.
+ _refuse_extra_reply(db, chat, user)
message.content = content
@@ -1703,6 +1732,7 @@ async def send_queued_now(
raise HTTPException(
status.HTTP_409_CONFLICT, "Wait for the current reply to finish, or stop it."
)
+ _refuse_extra_reply(db, chat, user)
message.queued = False
db.commit()
@@ -2123,16 +2153,6 @@ async def delete_chat(db: Db, user: RequiredUser, chat_id: str) -> Response:
return response
-@router.get("/{chat_id}/messages/{message_id}/raw")
-async def raw_message(db: Db, user: RequiredUser, chat_id: str, message_id: str) -> HTMLResponse:
- """The unrendered Markdown of a message, for the copy button."""
- _owned_chat(db, chat_id, user.id)
- message = db.get(Message, message_id)
- if message is None or message.chat_id != chat_id:
- raise HTTPException(status.HTTP_404_NOT_FOUND, "That message no longer exists.")
- return HTMLResponse(escape_text(message.content))
-
-
@router.post("/{chat_id}/messages/{message_id}/regenerate")
async def regenerate(
request: Request,
@@ -2147,6 +2167,8 @@ async def regenerate(
if message is None or message.chat_id != chat.id or message.role != ROLE_ASSISTANT:
raise HTTPException(status.HTTP_404_NOT_FOUND, "That reply no longer exists.")
+ _refuse_extra_reply(db, chat, user)
+
message.content = ""
message.error = ""
message.complete = False
diff --git a/src/lembas/api/messages.py b/src/lembas/api/messages.py
index 990e2b1..01da782 100644
--- a/src/lembas/api/messages.py
+++ b/src/lembas/api/messages.py
@@ -21,7 +21,6 @@ from lembas.api.pages import _chat_context, sidebar_context
from lembas.db.models import Message, Schedule
from lembas.services import messages as messages_service
from lembas.services import schedules as schedules_service
-from lembas.services.markdown import render_markdown
from lembas.services.schedule import clock
from lembas.services.schedule import rule as rule_service
from lembas.web.templating import render
@@ -31,11 +30,6 @@ log = logging.getLogger(__name__)
router = APIRouter(tags=["messages"])
-def _bodies(messages: list[Message]) -> dict[str, str]:
- """Markdown rendered server-side, keyed by id, as `chat_detail` does."""
- return {m.id: render_markdown(m.content) for m in messages if m.role == "user"}
-
-
@router.get("/messages")
async def messages_page(request: Request, db: Db, user: RequiredUser):
conversation = messages_service.for_user(db, user)
@@ -61,7 +55,6 @@ async def messages_page(request: Request, db: Db, user: RequiredUser):
"chat": conversation,
"messages": live,
"compacted": [],
- "bodies": _bodies(live),
"inherited_prompt": "",
"inherited_from": "",
"more_before": bool(live) and messages_service.has_more_before(
@@ -109,7 +102,6 @@ async def messages_history(
"messages/_history.html",
{
"messages": page,
- "bodies": _bodies(page),
"more_before": messages_service.has_more_before(db, conversation, page[0]),
"oldest_id": page[0].id,
# `render()` injects `user` and friends; `TemplateResponse` does
diff --git a/src/lembas/services/branding.py b/src/lembas/services/branding.py
index 470557a..b0d8cdf 100644
--- a/src/lembas/services/branding.py
+++ b/src/lembas/services/branding.py
@@ -462,7 +462,20 @@ def theme_css(theme: Theme) -> str:
if not theme.tokens:
return ""
lines = [f" --{name}: {value};" for name, value in theme.tokens.items()]
- for name, alpha in (("accent", "0.14"), ("leaf", "0.14"), ("danger", "0.14")):
+ # Every settable colour that has a `-soft` companion in tokens.css, not the
+ # three somebody stopped at. `success` and `warning` were settable and their
+ # softs were not derived, so a custom theme moved the text and left the
+ # background behind it in the base theme's hue -- an alert, a badge, a
+ # permission's "on" state and the `+` lines of every agent diff, each in two
+ # colours that were never meant to meet. Precisely the half-working failure
+ # this function's own docstring says it exists to prevent.
+ for name, alpha in (
+ ("accent", "0.14"),
+ ("leaf", "0.14"),
+ ("danger", "0.14"),
+ ("success", "0.14"),
+ ("warning", "0.14"),
+ ):
soft = _soft(theme.tokens.get(name, ""), alpha)
if soft:
lines.append(f" --{name}-soft: {soft};")
diff --git a/src/lembas/web/static/css/admin.css b/src/lembas/web/static/css/admin.css
index cd84fad..1e31391 100644
--- a/src/lembas/web/static/css/admin.css
+++ b/src/lembas/web/static/css/admin.css
@@ -15,14 +15,10 @@
that one, silently, while the reader was lost in the other. Under
`.admin-scroll` the body is now an ordinary block and the page scrolls as one.
*/
-.admin-scroll,
-.main > .tabs > .tabs__body {
- flex: 1;
- min-height: 0;
- overflow-y: auto;
- scrollbar-width: thin;
- scrollbar-color: var(--border-strong) transparent;
-}
+/* What makes one of these scroll is `.scroll-region` in app.css, which both of
+ these selectors are listed in. Named there so the four declarations exist
+ once; named *here* is the reasoning above, which is about which element is
+ the scroller on which screen rather than about how a scroller behaves. */
.page,
.admin-page {
diff --git a/src/lembas/web/static/css/app.css b/src/lembas/web/static/css/app.css
index d1f2e21..afbbc43 100644
--- a/src/lembas/web/static/css/app.css
+++ b/src/lembas/web/static/css/app.css
@@ -18,6 +18,33 @@ body {
height: 100%;
}
+/*
+ A page built around the shell never scrolls its own document.
+
+ `.shell` is `100dvh` -- the *dynamic* viewport, which is what you can actually
+ see -- while `html` and `body` above are `100%`, which resolves against the
+ initial containing block and is the *large* viewport, the one you get with the
+ browser's toolbar retracted. On a desktop those are the same number and this
+ rule does nothing. On a phone they differ by the height of the toolbar, and
+ the difference is a document taller than its own window: you scroll past the
+ bottom of the sidebar and the main column into bare background, and because
+ every gesture retracts or extends the toolbar the shell resizes underneath you
+ and it never settles.
+
+ Reported on /settings, true of every page with a shell. `:has()` rather than a
+ class because the shell is what decides this, not the route -- the auth, error
+ and offline pages have no shell and genuinely do scroll their document, and
+ they must keep doing so.
+*/
+html:has(body > .shell),
+body:has(> .shell) {
+ height: 100dvh;
+ overflow: hidden;
+ /* A flick that reaches the end of an inner scroller stops there rather than
+ pulling the page around behind it. */
+ overscroll-behavior: none;
+}
+
/*
The `hidden` attribute has to win.
@@ -367,6 +394,39 @@ button, input, textarea, select {
.badge--danger { background: var(--danger-soft); color: var(--danger); }
.badge--warning { background: var(--warning-soft); color: var(--warning); }
+/* --- Scroll regions --------------------------------------------------------
+ The four declarations that make an element *the* scroller, written once.
+
+ They were spelled out five times -- the sidebar's list, the thread, the
+ inspector, the canvas and (in admin.css) the tabs and admin pages -- and
+ agreed on three of them. The fourth, `overscroll-behavior`, was on the
+ sidebar alone, with a good comment explaining why it was needed there. It is
+ needed everywhere for the same reason: a flick that reaches the end of a
+ scroller chains to whatever is behind it, and behind these is the shell,
+ which does not scroll -- so what the gesture produces is not a scrolled page
+ but a rubber-band into blank background, which reads as the layout having
+ come loose.
+
+ `min-height: 0` is the half that is load-bearing rather than cosmetic: a flex
+ child will not shrink below its content without it, so a scroller missing it
+ grows its parent instead of scrolling inside it. `.thread-scroll` relied on a
+ scroll container's automatic minimum size to get away with omitting it, which
+ is true and is not something the next person should have to know. */
+.scroll-region,
+.sidebar__scroll,
+.inspector__body,
+.canvas__body,
+.thread-scroll,
+.admin-scroll,
+.main > .tabs > .tabs__body {
+ flex: 1;
+ min-height: 0;
+ overflow-y: auto;
+ overscroll-behavior: contain;
+ scrollbar-width: thin;
+ scrollbar-color: var(--border-strong) transparent;
+}
+
/* --- Application shell ----------------------------------------------------- */
.shell { display: flex; height: 100dvh; overflow: hidden; }
@@ -412,18 +472,9 @@ button, input, textarea, select {
flex: none;
}
+/* A `.scroll-region`; only the padding is its own. */
.sidebar__scroll {
- flex: 1;
- min-height: 0;
- overflow-y: auto;
- /* A flick past the end of the list stops there rather than chaining to
- whatever is behind it. The shell is `overflow: hidden`, so what chaining
- produced was not a scrolled page but a rubber-band into blank background --
- which reads as the sidebar having come loose from the layout. */
- overscroll-behavior: contain;
padding: 0 var(--sp-2) var(--sp-3);
- scrollbar-width: thin;
- scrollbar-color: var(--border-strong) transparent;
}
.sidebar__footer {
@@ -491,12 +542,7 @@ button, input, textarea, select {
}
.inspector__body {
- flex: 1;
- min-height: 0;
- overflow-y: auto;
padding: var(--sp-4);
- scrollbar-width: thin;
- scrollbar-color: var(--border-strong) transparent;
}
.inspector__heading {
@@ -789,8 +835,8 @@ body.is-resizing .canvas__body { pointer-events: none; }
}
.canvas__body {
- flex: 1;
- min-height: 0;
+ /* Both axes, unlike every other scroll region: nothing re-wraps a source
+ line, so it has to be reachable sideways. */
overflow: auto;
padding: var(--sp-3);
}
diff --git a/src/lembas/web/static/css/chat.css b/src/lembas/web/static/css/chat.css
index 56a15a0..745931d 100644
--- a/src/lembas/web/static/css/chat.css
+++ b/src/lembas/web/static/css/chat.css
@@ -6,12 +6,11 @@
*/
/* --- Thread --------------------------------------------------------------- */
+/* A `.scroll-region` (app.css); the smooth behaviour is this one's own, because
+ this is the scroller something is repeatedly scrolled *to* -- the newest
+ message, a jump back to the bottom -- and the others are not. */
.thread-scroll {
- flex: 1;
- overflow-y: auto;
scroll-behavior: smooth;
- scrollbar-width: thin;
- scrollbar-color: var(--border-strong) transparent;
}
.thread {
diff --git a/src/lembas/web/templates/chat/_thread.html b/src/lembas/web/templates/chat/_thread.html
index afcad66..1fe70cf 100644
--- a/src/lembas/web/templates/chat/_thread.html
+++ b/src/lembas/web/templates/chat/_thread.html
@@ -25,16 +25,12 @@
{% for message in compacted %}
- {% with body_html = bodies.get(message.id, "") %}
- {% include "chat/_message.html" %}
- {% endwith %}
+ {% include "chat/_message.html" %}
{% endfor %}
{% endif %}
{% for message in messages %}
- {% with body_html = bodies.get(message.id, "") %}
- {% include "chat/_message.html" %}
- {% endwith %}
+ {% include "chat/_message.html" %}
{% endfor %}
diff --git a/src/lembas/web/templates/messages/_history.html b/src/lembas/web/templates/messages/_history.html
index 3c1af21..caf7b3d 100644
--- a/src/lembas/web/templates/messages/_history.html
+++ b/src/lembas/web/templates/messages/_history.html
@@ -29,7 +29,5 @@
{% endif %}
{% for message in messages %}
- {% with body_html = bodies.get(message.id, "") %}
- {% include "chat/_message.html" %}
- {% endwith %}
+ {% include "chat/_message.html" %}
{% endfor %}
diff --git a/src/lembas/web/templates/messages/index.html b/src/lembas/web/templates/messages/index.html
index c91439e..8da96d1 100644
--- a/src/lembas/web/templates/messages/index.html
+++ b/src/lembas/web/templates/messages/index.html
@@ -83,9 +83,7 @@
{% endif %}
{% for message in messages %}
- {% with body_html = bodies.get(message.id, "") %}
- {% include "chat/_message.html" %}
- {% endwith %}
+ {% include "chat/_message.html" %}
{% endfor %}
diff --git a/tests/test_agent_jobs.py b/tests/test_agent_jobs.py
index 1297622..0ddae21 100644
--- a/tests/test_agent_jobs.py
+++ b/tests/test_agent_jobs.py
@@ -22,14 +22,19 @@ from lembas.services.agent.base import ExecRequest, ExecResult, clean_output
from lembas.services.agent.session import AgentContext
from lembas.services.agent.tools import _run_shell
-pytestmark = pytest.mark.skipif(
- shutil.which("setsid") is None or shutil.which("base64") is None,
- reason="needs setsid and base64 (Linux)",
-)
-
-
-# Stands up something real -- see the `slow` marker in pyproject.toml.
-pytestmark = pytest.mark.slow
+# A list, because there are two of them and `pytestmark = ...` twice is not two
+# marks -- the second binding replaces the first, silently. It did, for the
+# whole life of this file: the guard below was written, read as present, and
+# never once applied, so a host without `setsid` got a module that errored
+# instead of the skip somebody had taken the trouble to write.
+pytestmark = [
+ pytest.mark.skipif(
+ shutil.which("setsid") is None or shutil.which("base64") is None,
+ reason="needs setsid and base64 (Linux)",
+ ),
+ # Stands up something real -- see the `slow` marker in pyproject.toml.
+ pytest.mark.slow,
+]
class LocalExecutor:
"""`SshExecutor.run`'s contract, run against the local shell.
diff --git a/tests/test_chat.py b/tests/test_chat.py
index 0310951..285ac36 100644
--- a/tests/test_chat.py
+++ b/tests/test_chat.py
@@ -1167,3 +1167,68 @@ def test_the_think_frame_lands_beside_the_reasoning_body_not_around_it():
# Neither element may open a tag that the other closes: siblings, not nested.
assert "" in between or "" in between
assert between.count(" .tabs > .tabs__body" in admin
+ # The scroller rule names where the tabs must be, not just the class. Which
+ # stylesheet it is written in is not the point and is not asserted -- the
+ # four declarations that make something a scroller now live once, in
+ # app.css, and this selector is listed there with the rest.
+ assert ".main > .tabs > .tabs__body" in admin + app
assert "\n.tabs__body {" not in admin
+ assert "\n.tabs__body {" not in app
assert "overflowY" in SOURCE
assert "scrollHeight > " in SOURCE