An owner's tab layout holds at most MAX_TAB_REFS (512) refs, counting saved web
tabs (up to MAX_WEBVIEWS, 50 by default) as well as sessions. With a ceiling of
500, session creation could still fail with HTTP 500 on the layout limit before
the capacity message. 512 - 50 = 462; a test pins the ceiling plus MAX_WEBVIEWS
inside MAX_TAB_REFS so the two limits cannot drift apart again.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
The proxy hands undici the request body as a stream and dropped the browser's
content-length, assuming undici recomputes it. For a stream it cannot: undici
frames it as Transfer-Encoding: chunked. A dashboard that reads only
Content-Length (Python's http.server, many small Go/C servers) then saw an
empty body on every POST through a web tab. Found on a WoL dashboard whose
Shut down posted {"confirm":true} and was refused for a missing flag on every
click through Codeman, while curl straight at it worked.
buildUpstreamRequestHeaders now puts the browser's content-length back when a
body goes upstream (relayBodyLength), it is a plain number, and no
transfer-encoding contradicts it. GET/HEAD never carry it. undici 6.28 frames
the stream with that length and fails cleanly on a mismatch. Side effect:
a DELETE/OPTIONS with content-length 0 now goes upstream with neither header
nor body instead of an empty chunked body.
test/webview-proxy-body-framing.test.ts pins it end to end against a
Content-Length-only upstream; it fails on the old code with
"expected 'chunked' to be null".
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The input ended on a whitespace run, so the old regex returned a different
string and the test failed on the result before it reached the time bound.
Keep the run inside a line ('a<run>b\nc'): the old regex and the split now
return the same 'a<run>b c', and only the elapsed time tells them apart
(about 1.8 s against well under a millisecond).
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
"\nfix it\r" pasted an empty first line. Leading line breaks are now
dropped like trailing ones. Document what useMux does with a line feed,
and that a pane without bracketed paste receives each pasted line break
as CR, so a multi-line write without \r runs every line but the last
there, where the old line-stripping typed the joined text and ran nothing.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
/\s*[\r\n]+\s*/g backtracks over every start position of a long
whitespace run, so 50,000 spaces took over a second. Split on line breaks,
trim each line, drop blank ones and join with a space: linear, and a
leading or trailing blank line no longer leaves a space behind. A prompt
without a line break is still returned unchanged. session-auto-ops now
imports toSingleLine from the utils barrel like respawn-controller.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
Every pane starts in TMUX_LAUNCH_CWD (/tmp) and reaches its workspace with a
cd inside the pane command, but a remote or docker pane never does that cd,
so tmux reports /tmp for it. A rediscovered record carries no remote/docker
metadata and looks local, so adopting that directory would root the session
at /tmp: hooks written into /tmp/.claude, the Files panel at /tmp, and a
respawn running claude in a directory any local account can write to.
reconcileSessions() now skips a pane whose directory is the launch directory,
in both spellings a pane can report it: the literal one and its realpath
(/private/tmp on macOS, where a process cwd comes back resolved). The set is
computed once at module load. Such a session falls back to process.cwd(),
as before this series.
Also stop trimming the list-panes output: the directory is the last field,
so a trim cut a trailing space off the last row's path; parsePaneRows()
already skips empty lines. And the comments that list what a discovered
record knows for certain now include the directory, when tmux reported a
usable one.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
Review follow-up. Other bounds assume a small session count: an owner's
tab layout holds at most MAX_TAB_REFS (512) refs and PUT
/api/session-order accepts at most 500 ids, so with
CODEMAN_MAX_SESSIONS=600 the 513th session creation answered HTTP 500
instead of the capacity message. The value is now clamped to a named
MAX_CONCURRENT_SESSIONS_CEILING of 500; any digit string above it
(including one past the safe-integer range) resolves to 500 instead of
falling back to 50. The resolver reads process.env directly, the unused
env parameter is gone.
Docs: a CODEMAN_MAX_SESSIONS row in the Settings Reference environment
table, the env name next to the cap in the cron guide and the
architecture invariants, and both copies of the skill's endpoints
reference now give the per-user cap as half the global cap (25 by
default). The changeset says "1 to 500". The test drops the
`as unknown as string` casts and adds '1000', '501' and an
out-of-range value, each refusing at 500.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
- cron resolvePrompt(): give the reason the rest of the cron docs give (the
submit check cannot recognise a multi-line paste; in paste mode the newlines
reach the CLI as keys) instead of the old one about writeViaMux fusing lines.
- sendInputToPane(): it types with send-keys -l and strips line breaks, so it
no longer uses "the same approach as sendInput()".
- TUI client: newlines become spaces (the docstring said stripped), and the
test name no longer cites "multi-line breaks Ink".
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Auto-compact writes `/compact <prompt>\r` through writeViaMux when the token
count crosses the threshold, unattended. AutoCompactSchema.prompt accepts line
breaks, so a prompt set through the API can hold several lines. The mux used to
strip them and run the lines together; it now pastes multi-line text as one
block, and the check that re-presses a stranded Enter cannot recognise that
paste in the composer. That is the case respawn's update and kickstart prompts
were already joined for.
The join moves out of respawn-controller into a shared toSingleLine()
(src/utils/single-line.ts), used by both respawn steps and by auto-compact.
Behaviour for respawn is unchanged. The respawn test file becomes
test/unattended-single-line-prompt.test.ts and gains an auto-compact block that
feeds a real Session a token count over its threshold and reads what reaches
writeViaMux.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The update and kickstart prompts are textareas in the respawn settings and
the schema accepts line breaks, so a saved config can hold several lines.
Both steps went out through writeViaMux, which used to strip every `\n` and
run the lines together. Since the mux now pastes multi-line text as one
block, a multi-line respawn prompt would have gone out as a multi-line paste,
and the check that re-presses a stranded Enter cannot recognise that paste in
the composer. Respawn runs unattended, the same situation for which cron
keeps rejecting multi-line prompts.
singleLineRespawnPrompt() joins the lines with a space before the write; a
single-line prompt is passed through unchanged. Respawn joins rather than
rejects, so a multi-line config that was accepted before is still sent.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
TmuxManager.sendInput() removed every `\n` before the text reached tmux, so a
multi-line prompt sent with `useMux` (or a multi-line respawn prompt) arrived as
one line with its lines run together: `"echo A\necho B\r"` ran `echo Aecho B`.
The text half of a submit has gone in as one bracketed paste
(buildPasteTextCommands) since the Codex paste-burst fix, and inside the paste
markers Claude Code and Codex insert a pasted line break into the composer
instead of submitting. So the `\n` is now kept (`\r\n` loses only its `\r`) and
the existing paste carries the lines; the Enter stays a separate tmux call.
Multi-line text without an Enter is pasted too rather than typed with
`send-keys -l`, where every line break would reach the pane as a key.
Single-line input is unchanged.
The test-mode gate moves from the top of sendInput() into inputRunner(), as
readPaneRows() does, so a test subclass can record the commands sendInput()
would run instead of pinning the branch shapes on the source.
SubmitVerifier still compares the composer's last glyph line with the prompt
minus its newlines, so it does not reliably recognise a multi-line paste and
may not re-press an Enter that Claude Code ignored. `agent send` and the TUI
therefore keep refusing or joining multi-line input; the docs that described
the stripping now describe the paste and that limit.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
reconcileSessions() adopts codeman-* sessions it finds on the socket but has
no record of (a lost or stale mux-sessions.json) as "Restored: ..." entries,
and set their workingDir to process.cwd(). Every such session then looked like
it lived wherever the server was started, and a later respawn of it cd'd
there instead of into its project.
tmux already knows the answer as #{pane_current_path}. It is appended as the
last field of PANE_LIST_FORMAT, so a directory containing the separator stays
whole, and parsePaneRows() reads it as PaneRow.currentPath. No extra tmux call:
the same list-panes read that yields the pid now yields the directory.
The path is set by whoever owns the pane, so it is admitted only if it passes
isValidPath(), the check createSession() and respawnPane() already apply to a
workingDir; otherwise, and when tmux reported none, process.cwd() stays the
fallback. A hand-split session takes the first pane tmux lists.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The cap of 50 concurrent sessions was a hard-coded constant, so a machine
with the memory for more (or a small box that wants fewer) had to patch the
source. CODEMAN_MAX_SESSIONS now sets it at startup. The default stays 50,
and anything that is not a positive integer (empty, 0, negative, fractional,
1e3, out of safe-integer range) falls back to it, so a typo never locks
session creation.
Every site keeps reading MAX_CONCURRENT_SESSIONS, so the session routes,
cron launches, the scheduled-run loop and the multi-user per-user cap (half
the global cap unless CODEMAN_MAX_SESSIONS_PER_USER is set) all follow the
variable. The test goes through sessionCapacityState and
sessionCapacityMessage, the check every session-creating route uses.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Review round 3 on #661: retention aged each snapshot by its own createdAt, so the first change after a quiet month deleted the last good copy; it now ages from when the next snapshot was made. users.json lastLoginAt, settings.json lastUsedCase and intents.json recentPrompts/updatedAt are volatile keys for the change check. The keep count has a minimum of 2. Wiki restore paragraph aligned with RESTART_REQUIRED.
Review round 2 on #661: the hostname in the origin orphaned every snapshot when a Docker container was recreated, so the origin is a random id kept in <data dir>/config-backup-id; after restoring settings.json the Settings form is re-read from /api/settings so Save cannot write the old values back; the restore confirm names the files and the credential ones; clis.json is reloaded (reloadCliRegistry) and users.json needs no restart; API reference and route docs corrected.
Review round on #661: webhook.json and intents.json are redacted in compare and URL values lose userinfo/query; a custom folder is probed (bounded, pastCap) before each pass and in each route and only created when its parent exists; manifests record an origin and change check, prune, list, restore and diff are scoped to it; a restore reloads IntentStore, lists untouched files and treats settings.json as restart-required; remote-cases.json is tracked; stale .tmp-cfg-* folders are swept and a failed restore unlinks its temp; the group is hidden from non-admins; an empty days field saves 30.
Settings -> System -> Config backups gains a Compare view: a backup against the
running config, a backup against the one before it, or any two backups. Each
differing file lists its changed keys as before/after, plus files that appeared
or vanished. GET /api/config-backups/diff?from=&to= serves it (`to` defaults to
`current`; admin only in multi-user mode).
Credential values are never returned: .env, users.json and push-keys.json report
names only, and any other key that looks like a token, secret, password,
credential or key is reported as changed without its value. A non-JSON file
reports only that it differs, a file is cut at 200 changes, and a self-refreshed
discovery timestamp does not count as a difference.
custom-model-hosts.json carries a lastDiscoveredAt per host that the 5-minute model
discovery poll rewrites, so the content hash never matched the latest snapshot and a
snapshot was written every tick. At the default keep count of 20 that left about 100
minutes of history and evicted every useful older copy.
The change check now looks through volatile keys per tracked file. The snapshot still
stores the file as written and restore still verifies against its own digest.
The files that hold a user's customization (settings.json, clis.json, custom-model-hosts.json,
webhook.json, intents.json, linked-cases.json, push-keys.json, users.json, .env) are plain JSON
in the data dir, rewritten by the server, the Settings UI and the CLI, with no copy to go back to.
A snapshot is taken at startup and whenever the tracked files' content changes (checked every
five minutes, and only written when a digest of the file set differs from the latest snapshot's),
into `<data dir>/backups/config` by default or any absolute folder. Retention keeps the newest
configBackupKeepCount (1-500) and, when configBackupKeepDays > 0, drops older ones; it only ever
deletes folders it made (name pattern and a parseable manifest) and never the newest.
GET/POST /api/config-backups list and back up now; POST .../:id/restore verifies every file against
the manifest's SHA-256, takes a pre-restore snapshot, then replaces files atomically with mode
0600, writing only allowlisted names. Snapshots are 0700 folders of 0600 files and all routes are
admin only in multi-user mode. Settings -> System gets the controls and a Restore list.
The nightly browser suite failed in run-mode-menu-scroll: the short-menu case
opened the stock menu and asserted it needs no scrollbar on a 390x640 phone.
The GitHub Copilot entry made the stock CLI list eleven rows, 562px of content
against a 538px cap, so the menu now scrolls there, which is the cap-and-scroll
behaviour the CSS is written for (and what the other two cases verify). Every
further CLI would have broken the same assumption again.
The case now hides the whole CLI block (the container, since its buttons are
rebuilt from the registry) and also checks the "not stretched" half of its name:
the border-box height must stay under max-height. clientHeight would not do,
since it leaves out the border and a menu stretched to its cap reads just under it.
Visible side effect worth knowing: on a phone about 640px tall the stock Run
dropdown now scrolls by roughly one row. At 900px it fits (564px) unscrolled.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude Code draws its prompt suggestion in an empty composer, the first letter in the reverse-video cursor cell and the rest faint, so a plain capture read it as typed text and keep-warm never nudged those sessions. The keep-warm pane read now uses capture-pane -e and drops the suggestion before checking the composer.
Also from review: an off status carries no window, automation and an unreadable composer retry instead of stopping, a failed evaluation re-arms a retry, a trigger during an evaluation queues one follow-up that remove() cancels, and the cap's clock is seeded from lastSubmitAt for pre-upgrade state.
Story Mode's prompt bar and the phone's Compose sheet send a prompt as two
writes: one bracketed paste, then a bare Enter about 120 ms later. Neither is
a `text\r` pair, so SubmitVerifier was never armed for them, and a send while
Claude Code was still ignoring Enter (2.1.277+, the first 30 to 50 s after the
composer paints) sat unsent.
PastedPromptWatch pairs the two writes back up, in Session.write() (the
WebSocket path) and writeViaMux() (the POST fallback's Enter), and arms the
verifier with the pasted text. Nothing may come between the two, and a newer
paste cancels a pending check, so Enter never sends the user's own paste.
The composer match learns what a pasted prompt looks like (measured on
2.1.303): continuation lines count for a short first line, and Claude's
`[Pasted text #1 +3 lines]` stand-in counts only when its line count is the
prompt's own. A prompt under 24 characters must now match whole, so a short
answer cannot read a dialog's highlighted `1. Yes` row as itself.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Only a human spends an idle alert, but the keep-alive turn resolved an unseen one three ways: its working transition, its stop hook, and its own idle prompt replacing the item with a pre-acknowledged one. While the turn runs, a pending idle item is now left exactly as found, the page's stop handler returns on the keep-alive reason before clearing hooks or raising Response Complete, and session:working/session:idle carry keepAlive so the stuck-detection timer neither restarts nor re-arms.
The window that marks the turn closes on its own idle prompt or any other submit instead of a fixed three minutes, which a slow turn's idle prompt (sent a minute after the turn ends) could outlast. The service keeps the default and cap in memory, read through a strict reader so a mid-write read is retried rather than kept, and the cap is clamped before the strict settings save.
A panel ignores a growth of 2 px or less, but the clamp measured against
the exact room, so a balloon that fell 0.6 px short of two lines showed
one. The clamp now lets a balloon use those 2 px of the 4 px gap it keeps
from the art and Claude's head, which is what the ignored growth would
have bought, and rounds away float error.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The owner asked to merge the turn picker with the new input field. The prompts you already sent
(the picker and its arrows) now sit on the left of the bottom bar, the next message beside them,
the hint under the field; on a narrow screen the turns get their own row above it. The top bar
keeps the title, the reading levels, Save image and close, so a phone's bar is two rows. On a
touch screen the ready hint (Enter and Shift+Enter) is hidden: it means nothing on a touch
keyboard, and the hints that matter still show.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The Director's cut is now the default level, so a test that turns it on right after opening
changed nothing and the wire was never placed. Start from Advanced, as a reader would.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The comic sheet was capped at 1240px with empty margins beside it, the
Director's cut wire was a 320px box, and a short page ended half way down
the window. Now the stage takes the full width (16px gutters kept), the
wire is clamp(320px, 25vw, 460px) wide and runs the main area's whole
visible height, sticky, its list scrolling inside, and the rows grow to
fill the visible height.
Row heights come from a pure function next to storyLayoutSpans
(storyRowHeights): the visible height is shared evenly between the page's
rows for the active column count (6 over a 1000px sheet, 2 over 600px; one
column keeps its natural heights), never under 270px (a longer page keeps
270px rows and scrolls as before) and never over a cap: 540px (twice the
drawn size: past it a one-row page is mostly background and the text, which
stops growing at 1.45x, looks lost), and the height at which a row's
narrowest panel would get a scene stage under 280 units wide (the mission's
exclamation mark ran off the panel below that, which is where a span-2 panel
turns into a portrait). What a capped row cannot take goes to the rows that
can, mostly the final panel's full-width row; its scene keeps a stage wide
enough (440 units) to stand beside its words. When the final panel's
in-flow words make its row taller, the other rows give that height up, so
the page still ends at the bottom. A capped page leaves blank paper, never a
band of background: the sheet reaches the visible bottom.
The values are plain px written from JS (each panel's --story-panel-min,
the page's grid-template-rows and --story-row-h, which also feeds
grid-auto-rows, so there is one 270 default), and --story-panel-min is
registered as a <length>: _storySizePanel and _storyFitCaption read it with
parseFloat, which a raw calc() would have turned into NaN. The comic text
scales with --story-k (the shortest row over 270, at most 1.45), set on the
page; the you/notice balloons sit below the caption by the same factor.
It is recomputed by the existing ResizeObserver, which now also watches the
main area (window, drawer padding, a bar added later) and the sheet's width
(the Director's cut toggle), once per delivery, and on every render. It
reads boxes that its writes cannot change, and the main area keeps its
scrollbar gutter, so it never oscillates; panels still resize through
_storySizePanel, whose draws the frame loop rations. Main's bottom padding
is 16px.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
On a narrow panel (a phone, a two-column page) Claude holds the lens over
the investigate terminal, and its rim covered the end of the second line
and the ones below it. Those lines now end with an ellipsis short of the
lens's reach (over every frame of its sway); the lines above and below
it keep the terminal's full width, and on a wide panel, where the lens
hangs beside the terminal, nothing changes. A narrower terminal was the
other option and cut every line to about 14 characters on a phone.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A balloon that found no room beside a long caption dropped to just below
it, inside the art band: on the fix loop it covered the code page and the
"19 tests" label of the board, and elsewhere it sat on Claude's face (a
balloon of three lines or fewer was exempt from the clamp). A sweep over
the 11 corpus sessions, every turn, both modes, at 390, 820, 1100 and
1440 px and beside the diff drawer found 131 of 690 balloons covering a
click region or Claude's face.
Every balloon (Claude's, the loop's aimed one, the ask panel's, yours and
a notice) is now placed by _storyFitBalloon from the scene's layout at
its finished frame (StoryArt.layout, a dry run on a scratch canvas), so
an entrance with objects still in flight never moves it or the panel's
height. It must end above every click region under it (its tail above
those under the tail) and above Claude's face; a click region holding
his face is Claude himself and only the face rule applies to it. When
two lines do not fit, the panel grows for caption and balloon together
and the scene stands lower. The growth is computed at the panel's usual
height (storyBalloonRoom, pure), so a refit of the grown panel asks for
the same height: one extra pass, never an oscillation. The rest of a
long text clamps as before.
agent() now names Claude by his default colour, not by being cyan, so
the cyan fourth helper no longer takes the balloon, and the check scene
reports how high Claude's jump lifts his face.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The Director's cut rebuilt the whole wire with replaceChildren on every
refresh (every 4 s poll and SSE burst of a running turn), so it never
followed new events and a rebuild could throw the reader's place, focus
and hover away.
Rows are now keyed by event id and headings by the row they head (a panel
that changes kind or number as the turn grows keeps its heading node).
Unchanged nodes are reused, a changed row is patched in place (a running
tag flips to its result on the same node), new rows are inserted in
order with a short transform and opacity entrance, and a new turn
replaces the list. _storyEventRow still builds every row.
While the wire follows, it glides to the newest row with a critically
damped spring on animation frames: a burst of updates moves the target
and the glide keeps its speed, so there is no stop and restart. Measured
against the browser's own smooth scrollTo on a growing transcript, the
spring moved a median 8 px a frame over ~25 frames with no stalls, while
scrollTo snapped at ~41 px a frame over ~10 frames and its read of the
new scrollHeight forced a layout inside the update (a 57 ms long task).
Scrolling up by hand (wheel, touch, scroll keys, the scrollbar) stops
following and shows a pill that counts the rows that came in since;
clicking it, or scrolling back to the bottom, follows again. The glide
only moves down and is never read as the reader scrolling up. A running
newest turn, and the Director's cut turned on during one, open at the
bottom, following; a finished turn opens at the top. Under
prefers-reduced-motion there is no entrance and the list jumps.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
With the Director's cut as the default reading level, the story line the
test lengthens is not shown, so its panel never grew and the check
failed. The test now picks the Advanced level first, where that line is
the caption.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The bar's two-button group becomes three, in reading order: Simple (new,
for a reader who has never seen a terminal), Advanced (the story view as
it was) and Director's cut (the wire and the tool captions, unchanged).
The Director's cut is the default, as the owner asked; the reader's own
pick is kept per device under codeman:story-level, and only a click
stores it, so opening Story Mode never writes the default back and
changing the default stays a one-line change. _storySetDirector(on)
stays as a shim (on: Director's cut, off: Advanced) beside the new
_storySetLevel(level); st.director stays a boolean for the wire and the
scenes, which see director false at Simple.
At Simple each panel shows caption.simple in the letter font, a size up
(calc(20px * var(--story-k, 1))). Claude's balloons are hidden (its
narration is often technical; the art carries the panel) while your own
prompt balloon stays. The final panel shows the plain summary instead of
Claude's last message, and its chips are the time, the files changed and
"Read Claude's message", which opens a new drawer view with Claude's
last words as it wrote them. Balloons are hidden with the hidden
attribute, so Save image (which skips hidden boxes) prints what the
screen shows. On a phone the three buttons and Save image share one row.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Story Mode gets a third reading level for someone who has never seen a
terminal (a parent, a manager). Every panel now carries caption.simple:
one short sentence in everyday words, with no file name, command, tool
name, flag or jargon. The sentences are templates only, so nothing from
the transcript (a path, a commit message, a branch) can reach them, and
they are written from the same facts as the story caption: a failed
check never reads as a pass, a failure you asked for says so, and a
check that fails after one passed is a failure again.
The final panel's simple caption is a plain summary: how the turn ended
and roughly how long it took, how many files changed, whether the checks
pass, whether the work is saved (only claimed "not saved" where saving
is in play: you asked for it, or the turn used git), and what the reader
must not miss (a problem left, a note, a question for them).
test/story-plain-words.ts is the guard: the corpus test runs it over
every panel of every page of the eleven sessions, and the unit tests
cover the honest endings (failed check, catch, note, question, stopped,
not done, to be continued, done for now) and the guard itself. The
corpus expectations only gain "simple" lines.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The owner wants to keep working from the comic view: "on the bottom have an
input field! so I can send more input in that view!". Story Mode gets a bar
across the bottom (the overlay's new last grid row): a field that grows from
one line to about five, a Send button and a one-line hint.
- It sends to the session the overlay shows (st.sessionId), never the active
tab, since Session Options opens Story for any session. Delivery reuses the
mobile composer's tested path, KeyboardAccessoryBar._sendComposedPrompt: one
bracketed paste on the durable exactly-once queue, then a separate delayed
Enter. Text plus a carriage return in one burst would be read as a paste by
Claude Code and strand the prompt.
- Enter sends, Shift+Enter adds a line, an IME composition and whitespace-only
text never send.
- While Claude waits on a question or a permission in the terminal (a pending
question on the newest page, or the permission/elicitation hook), sending is
off: the message would land in the selection dialog, whose Enter picks the
highlighted option. The field still takes a draft and the hint says why.
A session that is gone (not in app.sessions, or a 404 from the story
route), whose agent exited, or that Story cannot draw (a shell would run the
text) keeps its draft readable but sends nothing. A running turn may be
sent to: Claude Code queues the message.
- Drafts are kept per session in memory for the life of the page.
- After a send the field clears and keeps focus; a reader parked on an older
turn (or held there by a drawer) goes to the newest, since activity is
ignored while parked, and a refresh is scheduled.
- Escape in a field holding text steps out of it first (focus to Close), an
empty field closes one layer as before, and an Escape that cancels an IME
composition closes nothing.
- The bottom safe-area inset moves from the overlay onto the composer, so its
background reaches the edge; the drawer ends above the composer and toasts
sit above it (measured into --story-compose-h). Not part of Save image.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude Code lets a subscription's one-hour prompt cache expire after an hour idle, and the first turn back re-writes the whole conversation at the cache-write rate; nearly every gap over an hour goes cold, while the saving is concentrated in gaps of one to four hours. Codeman now sends one short keep-alive turn five minutes before the expiry Claude Code reports on its statusline, so the next real prompt still reads the conversation from cache, and stops two hours (configurable) after the last real prompt.
Codeman owns the idle policy for these sessions, as agreed in Discussion #554: a launch with keep-warm on also carries idleCompaction: false in its one --settings JSON, so Claude Code's own idle compaction cannot replace the conversation with a summary a minute before the nudge. It is decided once per launch (keep-warm on, the statusLine exporter injected, Claude Code 2.1.290 or newer, an unknown version fails closed like --name), recorded on the mux record, and picked up by any relaunch; a launch with keep-warm off is byte-identical. A session switched on after launch is kept warm best-effort and the readout says so.
Every guard lives in one pure rulebook: the opt-in (an agent-spawned session does not inherit the app default), a launch that reports cache state, a warm 1h cache with enough tokens at stake and no compaction this gap, a live pane, no usage-limit pause, no respawn, Ralph, task or waiting agent, idle, no open dialog, an empty composer and no recent keystroke. The nudge is a submit and moves lastSubmitAt, which the response viewer's conversation correlation needs; the cap counts from its own persisted lastRealPromptAt instead. Read My Mind drops the exact nudge text, and the turn's stop hook and idle prompt open pre-acknowledged so nothing alerts. The last cache report and the clock survive a restart, so the timer re-arms.
Codex cites files as [label](/abs/path). The chat view gave those links target=_blank, so a click opened <origin>/abs/path and landed on a Fastify 404. Path-shaped hrefs now take the linkified-path shape the file preview already opens; scheme, protocol-relative and fragment links are unchanged.
Flagged by four readers across rounds 10 to 12: after a push, "but a
check after that fails" never said that Claude repaired what the check
found (the new remote pointed at a branch with no commits) and checked
again. When Claude's next command runs that same check again after a
change (`git -C remote.git symbolic-ref HEAD refs/heads/main && git -C
remote.git log …`) and passes, the caption adds "; Claude fixes it, and
the check passes next." A check re-run with no change before it, or one
that fails again, claims nothing.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>