lavish-axi 0.1.68 → 0.1.70

package/README.md

@@ -197,9 +197,10 @@ pnpm link
 - **Feedback controls** - Native controls (radios, checkboxes, inputs, selects, buttons, labels, disclosure summaries, contenteditable) are interactive automatically, so they do not need `data-lavish-action`.
   For reversible choices, let option clicks update local state, then queue exactly one final answer from a per-question submit or Queue answer button with `window.lavish.queuePrompt()`.
   Mark only custom (non-native) clickable elements with `data-lavish-action` so Lavish does not annotate them, and use `data-lavish-question` or `queueKey` when pre-send updates for the same question should replace each other.
-  On wider screens, queued annotation preview pills and chat history share a scrollable Conversation panel above a sticky composer, so long feedback queues do not push the text box or send controls off screen.
+  Everything you send is part of the conversation: a note on an element, a text selection, a table cell, a diagram node, a whiteboard, a layout-issue batch, or a composer message each becomes a bubble on your side of the Conversation panel, with an anchor line naming what it was attached to (the element tag, text selection, table cell, diagram node, whiteboard, or layout issues), a quoted excerpt, and, when available, the selector on hover. A note you have queued but not sent sits at the end of the conversation as a dashed bubble labelled **Queued** with a remove control; while its batch is in flight it reads **Sending**, and once the server accepts it, it settles in place as a sent bubble in every tab of the session. The panel keeps the newest stored transcript up to 5 MiB; older bubbles drop from view, but an accepted note still settles and is not sent twice. Agent replies render a small Markdown subset - paragraphs, line breaks, headings as bold lead lines, bullet and numbered lists, fenced and inline code, bold, italic, and http(s) links - while tables, images, and raw HTML stay as the text the agent wrote; your own messages keep their line breaks and are never parsed.
+  On wider screens, the conversation and the queued notes share one scrollable Conversation panel above a sticky composer, so long feedback queues do not push the text box or send controls off screen.
   The browser chrome keeps editing actions in the overflow menu (copy path, reload artifact, copy DOM snapshot, export standalone HTML, publish link, end session), while the composer exposes **Send & End** beside **Send to Agent** to submit queued prompts and user-ended attribution together. Once **Send & End** starts, Lavish pauses new feedback, waits up to 5 seconds for feedback preparation already underway, keeps any open annotation draft intact until delivery succeeds, then holds that exact terminal batch. A completed reservation survives a page reload, including when its prompts were already delivered and only the pending end remains; incomplete preparation is not restored. If preparation times out, Lavish keeps the review open and its existing queue editable with a visible error. A transient delivery failure permits only retrying the same terminal batch through **Send & End** until it succeeds. If a snapshot makes the request too large (HTTP 413), Lavish retries that exact batch once without the optional snapshot. An actionable attachment rejection (HTTP 400), recoverable layout-selection conflict (HTTP 409), or unrecoverable 413 instead cancels the terminal reservation without ending the session, keeps the prompts queued, and restores editing, removal, **Send to Agent**, **Send & End**, and **End session** so the reviewer can revise or remove stale feedback before submitting again.
-  Composer feedback is visibly queued before the text box clears and stays queued until acknowledged. Send waits up to 5 seconds for the artifact's DOM snapshot, then delivers without that optional context if the frame no longer answers; a late snapshot cannot submit the batch twice. A failed or still-unacknowledged POST keeps the queue and shows persistent recovery guidance.
+  Composer feedback is visibly queued before the text box clears and stays queued until acknowledged. Send waits up to 5 seconds for the artifact's DOM snapshot, then delivers without that optional context if the frame no longer answers; a late snapshot cannot submit the batch twice. A failed or still-unacknowledged POST keeps the queue and shows persistent recovery guidance unless a transcript sync proves the server already accepted that feedback.
 - **Reviewing on a phone** - Below 860px wide, the artifact takes the whole screen above a **Conversation** dock, and the conversation opens as a bottom sheet over it: tap the dock, swipe it up, or press the chevron to raise it; tap the dimmed artifact, swipe the sheet down, press the chevron, or press Escape to lower it. The dock reports what matters while the sheet is down - how many prompts are queued, a reply that arrived while you were reading, or whether the agent is listening - and the sheet stays open across a reload of the review page. The sheet sizes itself to the visible viewport and respects safe-area insets; if the keyboard or attachments leave little room, conversation content yields or scrolls while the send actions remain pinned above the bottom edge. In landscape the sheet covers the top bar as well. Wider screens keep the side-by-side layout.
 - **Keyboard shortcuts** - In the chrome composer, Enter sends queued prompts and Shift+Enter inserts a newline.
   In the annotation card, Enter queues the annotation, Shift+Enter inserts a newline, and Ctrl+Enter (Cmd+Enter on macOS) queues it and sends all queued prompts immediately. Escape closes the card, same as Cancel, but only while it is empty (no text, no attachment); with unsent text or an attachment present, Escape does nothing rather than risk discarding it.
@@ -208,7 +209,7 @@ pnpm link
   Closing the last review tab while a poll is active starts a 10-second reconnect grace period. A reload or quick reconnect keeps an active poll waiting; if every review stays disconnected, the poll returns `browser_disconnected` without ending the resumable session, and the agent asks whether to reopen or end it instead of acting uninvited.
   The no-timeout poll always writes an immediate stderr banner so it is visibly not hung; it adds the periodic stderr wait ticks only in an interactive terminal, so when stderr is piped (as under agent harnesses) the captured output carries no tick noise. Stdout always stays reserved for the final response; if the poll is interrupted or times out before feedback arrives, re-run it because feedback remains queued until delivery. Poll delivery consumes the response, so read the complete response before truncating or filtering it.
   Codex-specific guidance keeps that poll attached to the active turn instead of hiding it in a background task, because completed background tasks may not resume the agent.
-- **Session end etiquette** - Lavish tracks who ended a session: a human clicking **End session** (or **Send & end session**) in the browser is a user-initiated end, while `lavish-axi end <html-file>` is agent-initiated.
+- **Session end etiquette** - Lavish tracks who ended a session: a human clicking **End session** (or **Send & End**) in the browser is a user-initiated end, while `lavish-axi end <html-file>` is agent-initiated.
   When either side ends the session, every open review tab becomes visibly read-only and disables its feedback controls; feedback submitted after the end is refused instead of being accepted without an agent to receive it.
   A plain `lavish-axi <html-file>` after a user-initiated end refuses to reopen the browser and returns guidance instead; pass `--reopen` only when the user asks for further review or something important needs their visual attention.
   Agent-initiated ends keep reopening normally, same as before.
@@ -217,7 +218,7 @@ pnpm link
   Clicking an element inside a table also carries the cell's visible row and column names alongside the exact CSS locator, so filtered or sorted rows do not make feedback look misdirected.
   When merged cells make either name ambiguous, Lavish leaves that name out rather than guessing; an explicit `<th scope="row">` remains authoritative even when a `rowspan` makes the row's position ambiguous.
   The CSS locator still points at the exact element you clicked, so an annotation with an omitted name is only less descriptive, never mislabelled.
-- **Image attachments** - Attach reference images (PNG, JPEG, WebP) in either the Conversation composer or an annotation card by pasting, drag-dropping, or using its image picker; each image shows a thumbnail chip with upload, remove, retry, and error states.
+- **Image attachments** - Attach reference images (PNG, JPEG, WebP) in either the Conversation composer or an annotation card by pasting, drag-dropping, or using its image picker; each image shows a thumbnail chip with upload, remove, retry, and error states. If a sent image is later evicted under the attachment storage limits, its transcript-history thumbnail becomes an **Image expired** placeholder.
   A paste containing both text and images preserves the text while attaching the images (a copied file's own name or path is treated as placeholder and not pasted). Conversation messages may contain text and images together or images only.
   Images are stored under the state dir and the queued prompt carries a server-generated absolute `path` and content-hash `id` (plus mime and dimensions) - never the raw bytes - so `lavish-axi poll` hands the agent a local file path to open.
   Limits are `LAVISH_AXI_MAX_ATTACHMENT_BYTES` (default 10 MiB per image), `LAVISH_AXI_MAX_ATTACHMENTS_PER_PROMPT` (default 4), and `LAVISH_AXI_MAX_PROMPT_ATTACHMENT_BYTES` (default 25 MiB per prompt); if any image is missing or any prompt breaches a count or byte cap, the entire send batch is rejected, the queue is preserved, and the reason is surfaced in the composer rather than silently dropping images.