fix(coderd): use pasted-text attachments as chat title input (#27067)

Closes https://linear.app/codercom/issue/CODAGT-268

## Problem

The chat UI collapses large pastes (>=10 lines or >=1000 chars) into a
synthetic `pasted-text-*.txt` attachment. A chat created with only such
an attachment had no title input anywhere: the create path derived
`titleSource` only from text and file-reference parts (so the chat was
named "New Chat"), async auto-titling extracted text the same way and
silently skipped generation, and the manual propose/regenerate paths
returned an empty title for the same reason. The regular prompt path
already inlines these files for the model; only the title paths were
blind.

## Fix

Add a single title-input derivation in `chatprompt` and use it
everywhere:

- `chatprompt.TitleText` joins text and file-reference parts (unchanged
formatting), and falls back to synthetic pasted-text attachment content
(truncated to a 16 KiB title budget) when they yield nothing.
- `chatprompt.SyntheticPasteFileIDs` identifies paste attachments;
`chatprompt.FallbackTitle` consolidates the previously duplicated
`chatTitleFromMessage` / `fallbackChatTitle`.
- Chat creation captures paste blob references while validating file
parts (the file row was already loaded there) and derives `titleSource`
via `TitleText`. Only the create path derives titles; message send and
edit reuse the same validation without copying any blob data.
- `GenerateChatTitleAsync` and the manual propose/regenerate paths
resolve paste content via `titlePasteText`, which only queries when a
visible user message has no other title text, so chats with typed text
never incur a file fetch.
- Title-path paste fetches are bounded: a new
`GetChatFileDataPrefixesByIDs` query returns only a `substr` prefix
(`chatprompt.TitlePasteBytePrefix`, 64 KiB = 4 bytes x the 16 Ki-rune
title budget) so full blobs (up to 10 MiB each) never leave the database
for titling, and `chatprompt.TitlePasteText` applies the same bound to
the create path which already holds the loaded row.

Deliberate side effect: because generation-time extraction now matches
create-time `titleSource` exactly, file-reference-only chats also become
eligible for AI titles. They were previously skipped by the same
derivation mismatch.

Non-goals: no frontend changes (attachment chip UX stays as is), and
non-synthetic user-uploaded `.txt` files still yield "New Chat".

## Testing

- Unit tests for `TitleText`, `TitlePasteText`, `SyntheticPasteFileIDs`,
`FallbackTitle`, `titleInput`, `titlePasteText`, and paste-aware
`extractManualTitleTurns`.
- Real-database test for `GetChatFileDataPrefixesByIDs` (prefix shorter
and longer than stored data) plus dbauthz coverage for the new query.
- Integration tests: paste-only create gets a fallback title from the
paste content, async title generation fires with the paste content as
input, and `RegenerateChatTitle` works on a paste-only chat.

> This PR was written by [Mux](https://mux.coder.com) on Mike's behalf.
This commit is contained in:
Michael Suchacz
2026-07-08 21:37:30 +02:00
committed by GitHub
parent d16f254714
commit 2ad5af5b54
21 changed files with 1063 additions and 115 deletions
+49
View File
@@ -4989,6 +4989,55 @@ func (q *sqlQuerier) GetChatFileByID(ctx context.Context, id uuid.UUID) (ChatFil
return i, err
}
const getChatFileDataPrefixesByIDs = `-- name: GetChatFileDataPrefixesByIDs :many
SELECT id, owner_id, organization_id, substr(data, 1, $1::int) AS data_prefix
FROM chat_files
WHERE id = ANY($2::uuid[])
`
type GetChatFileDataPrefixesByIDsParams struct {
PrefixBytes int32 `db:"prefix_bytes" json:"prefix_bytes"`
IDs []uuid.UUID `db:"ids" json:"ids"`
}
type GetChatFileDataPrefixesByIDsRow struct {
ID uuid.UUID `db:"id" json:"id"`
OwnerID uuid.UUID `db:"owner_id" json:"owner_id"`
OrganizationID uuid.UUID `db:"organization_id" json:"organization_id"`
DataPrefix []byte `db:"data_prefix" json:"data_prefix"`
}
// GetChatFileDataPrefixesByIDs returns a bounded prefix of each
// file's content, keeping full blobs out of server memory. Owner and
// organization columns support row-level authorization.
func (q *sqlQuerier) GetChatFileDataPrefixesByIDs(ctx context.Context, arg GetChatFileDataPrefixesByIDsParams) ([]GetChatFileDataPrefixesByIDsRow, error) {
rows, err := q.db.QueryContext(ctx, getChatFileDataPrefixesByIDs, arg.PrefixBytes, pq.Array(arg.IDs))
if err != nil {
return nil, err
}
defer rows.Close()
var items []GetChatFileDataPrefixesByIDsRow
for rows.Next() {
var i GetChatFileDataPrefixesByIDsRow
if err := rows.Scan(
&i.ID,
&i.OwnerID,
&i.OrganizationID,
&i.DataPrefix,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Close(); err != nil {
return nil, err
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const getChatFileMetadataByChatID = `-- name: GetChatFileMetadataByChatID :many
SELECT cf.id, cf.owner_id, cf.organization_id, cf.name, cf.mimetype, cf.created_at
FROM chat_files cf