Files, open beside the conversation

A third side panel, built the way the terminal is and filled the way the
inspector is: tabs holding open files. 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 pygments, edited in a plain
textarea, saved with a conflict check.

A bug found on the way in, and the reason this needed its own read path.
`ssh.read_file` ends in `clean_output`, which strips ANSI escapes and decodes
with errors="replace" -- right for the output of a command, and fatal for an
editor: open a file containing an escape byte, press Save, and you have
silently rewritten it with the escapes gone and every undecodable byte replaced
by U+FFFD. `read_text`/`write_text` decode strictly, report binary rather than
mangling it, carry an mtime:size token for a file that moved underneath, and
refuse an oversize write rather than truncating -- `write_file` truncates
because a model is told how many bytes it wrote, and somebody pressing Save is
not. The model-facing pair is untouched: what it returns is a contract a model
has been shown. A truncated read opens read-only for the mirror-image reason.

Six sources go through one dispatch table, for the reason tool_labels.py is a
table: six independently written permission checks is how one ends up written
slightly differently, and that failure looks like editing somebody else's note.

A save on a project file bypasses agent/policy.py, which makes it the fourth
documented exception to "the modes do not govern the keyboard" and the first
that writes. Same argument as the terminal panel -- whoever owns the credential
could write the file with scp -- but the consequence is larger and is now said
out loud rather than left to be inferred.

The model opens tabs from the file tools it was already calling, so no new
schema and no tokens. It never brings one to the front: an agent reads forty
files in a long reply, and taking the screen each time would drag somebody
through all of them and lose any edit in progress. Only the strip is streamed,
guarded on truthiness so the frame can never blank itself -- an empty one would
close every open tab, the approval card you could press twice with the sign
reversed. Both halves are settled on the server, which is why canvas.js needs
no guard against a swap at all.

No vendored editor. CodeMirror 6 needs a bundler, which is hard rule 1;
CodeMirror 5 would be a larger payload than xterm on every page, and xterm is
the one heavy dependency precisely because it loads only where it can be used.
So: server-rendered highlighting for reading, a textarea for writing, and the
panel says there is no colour while you type rather than pretending.

Also here: a scratch document per chat, with `scratch_write` at RISK_READ on
plan_update's argument, and a test pinning the three numbers that decide a
panel's width -- LAYOUT_BOUNDS drops an unknown variable silently, so a panel
missing from it has a drag handle that works and forgets.

Driven under a DOM stub and against the running application.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

src/lembas/api/chats.py

@@ -8,6 +8,7 @@ import logging
 import time
 from collections.abc import AsyncIterator
 from datetime import UTC, datetime
+from types import SimpleNamespace
 
 from fastapi import APIRouter, Depends, Form, HTTPException, Request, status
 from fastapi.responses import HTMLResponse, JSONResponse, Response, StreamingResponse
@@ -855,6 +856,25 @@ def _ask_html(chat_id: str, pending) -> str:
     )
 
 
+def _canvas_tabs(chat_id: str, state: dict) -> str:
+    """The canvas tab strip, as an out-of-band swap.
+
+    Out of band because it belongs to a panel, not to the bubble the stream is
+    writing into -- the same move the `done` frame already makes for the chat
+    title. Only the strip: pushing the file's contents on every version bump
+    would be a lot of bytes for nothing, and would overwrite a textarea somebody
+    is typing in. The active tab's body fetches itself once instead.
+    """
+    return templates.get_template("chat/_canvas_tabs.html").render(
+        {
+            "chat": SimpleNamespace(id=chat_id),
+            "tabs": state.get("tabs") or [],
+            "active": state.get("active") or "",
+            "oob": True,
+        }
+    )
+
+
 async def _follow(chat_id: str, message_id: str) -> AsyncIterator[str]:
     """Stream a generation that is running independently of this request.
 
@@ -881,6 +901,19 @@ async def _follow(chat_id: str, message_id: str) -> AsyncIterator[str]:
                     yield sse.event("tools", _tool_activity(generation.tool_events))
                 if generation.content:
                     yield sse.event("render", render_markdown(generation.text))
+                if generation.canvas.get("tabs"):
+                    # Guarded on truthiness, which puts this in the
+                    # reasoning/tools/render group and not the
+                    # metrics/status/ask one. Those three are sent even when
+                    # empty *because* each has to be able to clear itself; this
+                    # one must never be able to, since an empty canvas frame
+                    # would close every tab somebody had open. The card that
+                    # could be pressed twice, with the sign reversed.
+                    #
+                    # The whole strip each time, not a delta, so a follower
+                    # attaching mid-reply gets every tab the reply has touched
+                    # rather than the ones that happened to arrive after it.
+                    yield sse.event("canvas", _canvas_tabs(chat_id, generation.canvas))
                 yield sse.event("metrics", _metrics_html(generation))
                 yield sse.event("status", escape_text(generation.status))
                 yield sse.event("ask", _ask_html(chat_id, generation.pending))