opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add persisted whole-chat summary with background generation (#26657)

Browse Source 
Adds a persisted whole-chat summary that backs the chat summary popover.
A new nullable `chats.summary` column is populated in the background
after a successful root-chat turn and pushed to clients via a new
`chat_summary_change` watch event (distinct from `summary_change`, which
is bound to `last_turn_summary`), so the popover reads `chat.summary`
straight off the loaded `Chat` with no extra query.

This is the data source for the popover and per-chat cost UI built in
#26649; the popover can consume `chat.summary` once this lands (the
field is nullable, so merge order does not matter).

## How it works

- **Generation** runs in the existing successful-turn finalize hook,
detached from the request so the user's turn is never blocked. A cadence
gate generates the first summary after one completed turn, then
regenerates every three turns, using the `chats.summary_generated_at`
freshness marker. Generation reads compaction-aware history, renders it
to a bounded plain-text transcript (short transcripts are skipped), and
asks for a 1-3 sentence summary via structured output. Failures never
clear an existing summary.
- **Staleness** is guarded by `history_version` (mirroring
`last_turn_summary`), so a background write racing a newer turn loses
while worker lifecycle transitions cannot reject a fresh write.
- **Model selection** uses the chat's configured model.

## Deferred to follow-ups

- **Cost accounting**: the `chat_messages.cost_source` discriminator and
summary/title usage recording were removed from this PR so summary
persistence is not blocked by hidden accounting rows advancing
`history_version`. Title usage recording stays on main's
`InsertChatMessages` path.
- **Model override**: deployment-wide summary generation model selection
is split into #26803; the base feature always uses the chat model.

## Notes

- Migration `000540` adds `chats.summary` and
`chats.summary_generated_at`, and recreates `chats_expanded` to expose
the new columns.
- Root chats only; shared viewers pick up the summary on their next
refetch (live watch events are owner-only).

Refs #26649

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Jaayden Halko
2026-07-23 16:36:23 +01:00
committed by GitHub
co-authored by Cursor
parent 9ce366414e
commit 3c7a1d33e3
33 changed files with 1473 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files
coderd/database/querier.go
Generated
+3
View File
@@ -1426,6 +1426,9 @@ type sqlcQuerier interface {
// assigned by trigger from the current snapshot_version.
UpdateChatRetryState(ctx context.Context, arg UpdateChatRetryStateParams) (Chat, error)
UpdateChatStatus(ctx context.Context, arg UpdateChatStatusParams) (Chat, error)
// The history_version fence lets background summary writes ignore worker-only
// updates while losing to newer message history.
UpdateChatSummary(ctx context.Context, arg UpdateChatSummaryParams) (int64, error)
UpdateChatTitleByID(ctx context.Context, arg UpdateChatTitleByIDParams) (Chat, error)
UpdateChatWorkspaceBinding(ctx context.Context, arg UpdateChatWorkspaceBindingParams) (Chat, error)
UpdateCryptoKeyDeletesAt(ctx context.Context, arg UpdateCryptoKeyDeletesAtParams) (CryptoKey, error)