Repository navigation
feat(compose): reply with AI from the conversation and an instruction - #577
Open
prudenciooficial wants to merge 9 commits into
Open
prudenciooficial wants to merge 9 commits into
prudenciooficial wants to merge 9 commits into
Conversation
When replying, the AI menu offers "Reply with AI". The user types what
the reply should say ("approve the artwork", "decline politely and ask
for a new proof") and the AI writes it from the conversation so far:
the thread up to the message being answered, oldest first, with the
user's own messages marked and the quoted copies of earlier messages
cut out. A reply opened from a list that is not grouped into
conversations does not carry the thread, so it is looked up from the
message being answered; when nothing can be loaded, the quoted original
the composer already holds is used.
The conversation is read once per composer, so rewording the
instruction and generating again only asks the AI. The request stays
within the chat proxy's limits: at most ten messages, the newest kept
first and the oldest shortened or left out.
The conversation is mail other people wrote, so the prompt tells the
model to ignore instructions inside it, and Apply now escapes the
suggestion before it reaches the editor. Before, a suggestion containing
markup, such as a link, became real markup in the user's message; this
applies to the existing actions too.
The two copies of the suggestion panel (phone and desktop layouts) are
now one component.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The reading pane's toolbar gets a "Reply with AI" button next to Reply, and each open message in the conversation view gets one beside Reply all. It opens the reply with the AI panel already waiting for the instruction, focused, so the user types what to say and nothing else. It is shown only when the AI's compose feature is on and the user writes in rich text, since the plain-text composer has no AI panel. A message reopened by Undo send is the user's own text, so it reopens without the panel. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
3 tasks done
…eat/ai-reply # Conflicts: # frontend/src/components/ComposeModal.jsx
…eat/ai-reply # Conflicts: # frontend/src/components/ComposeModal.jsx
With maathimself#556 a message can go out without its signature while the signature text is kept. The reply prompt asked the AI to leave the closing to a signature whenever one existed, so with the signature turned off the reply ended with no name. It now asks for the sender's name unless the signature is on. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
prudenciooficial
added a commit
to prudenciooficial/mailflow
that referenced
this pull request
Oct 9, 2026
…maathimself#577) The fork's copy of maathimself#577, squashed from the feat/ai-reply branch as of 843711e, while that pull request awaits review. "Reply with AI" sits in the reading pane toolbar, on each open message in the conversation view and in the composer's AI menu when replying. The user types what the reply should say; the AI writes it from the thread up to the message being answered, with quotes cut and the user's own messages marked. Apply escapes the suggestion before it reaches the editor. With the signature turned off (maathimself#556) the reply signs with the sender's name. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…eat/ai-reply # Conflicts: # frontend/src/components/MessagePane.render.test.js
The thread now marks its drafts (is_draft). A saved reply draft is part of the thread but was never sent, so the AI was shown it as a message the user had written in the conversation. It is left out now. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…eat/ai-reply # Conflicts: # frontend/src/utils/composeFromMessage.js
…eat/ai-reply # Conflicts: # frontend/src/components/ComposeModal.jsx
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds Reply with AI: the user says in a few words what the reply should say ("approve the artwork and ask for the print date") and the AI writes it from the conversation so far. The existing compose AI actions draft from the subject and recipients, or rewrite what is already typed; none of them reads the message being answered.
It is offered where a reply starts: a Reply with AI button in the reading pane toolbar, one on each open message in the conversation view, and an entry in the composer's AI menu when replying. The composer opens with the instruction field focused. The suggestion streams into the existing AI panel with Apply and Dismiss, and the instruction stays editable to ask again in other words.
No backend change: it uses the existing
/api/ai/chatproxy and the thread and body endpoints. It is shown only when the AI's compose feature is on and the user writes in rich text, since the plain-text composer has no AI panel.Changes
utils/aiReply.js(new) builds the request:thread_id, so the thread is found throughresolve-messagefrom the answered Message-ID. A message with no thread is read on its own, and if nothing loads, the quoted original the composer already holds is used.>lines, the signature separator).ComposeModal.jsx: the action and the instruction field. The conversation is loaded once per composer, so rewording only asks the AI again. The two copies of the suggestion panel (phone and desktop layouts) are now oneComposeAiPanelcomponent.MessagePane.jsx,ConversationMessageCard.jsx,ConversationPane.jsx,composeFromMessage.js: the buttons, and anaiReplyflag that opens the composer with the panel. A message reopened by Undo send drops the flag.Testing
aiReply.test.js). Render tests: the reply is written from the thread and the instruction; Apply keeps the quoted original; rewording does not reload the thread; markup in a suggestion stays text; the button opens the composer with the instruction focused; it is not offered without the compose feature or in plain-text mode; Undo does not reopen the panel. The tests for escaping, the thread lookup, the single load, the focus and Undo were checked to fail with that part reverted.Contributor License Agreement
By submitting this pull request I confirm that:
third-party material and confirmed it is compatible with the CLA).
My English is basic, so this description was written with help from Claude.
🤖 Generated with the help of Claude Code