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
docs/reference/api/chats.md
Generated
+15
View File
@@ -122,6 +122,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -218,6 +219,7 @@ Status Code **200**
| `» root_chat_id` | string(uuid) | false | | |
| `» shared` | boolean | false | | Shared is true when this chat's root chat has explicit user or group ACL entries. |
| `» status` | [codersdk.ChatStatus](schemas.md#codersdkchatstatus) | false | | |
| `» summary` | string | false | | Summary is the persisted whole-chat summary, generated in the background. It is nil until the first summary has been produced. |
| `» title` | string | false | | |
| `» updated_at` | string(date-time) | false | | |
| `» warnings` | array | false | | |
@@ -397,6 +399,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -490,6 +493,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -740,6 +744,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -887,6 +892,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -980,6 +986,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -1164,6 +1171,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -1257,6 +1265,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -1439,6 +1448,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -1532,6 +1542,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2283,6 +2294,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2376,6 +2388,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2883,6 +2896,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2976,6 +2990,7 @@ Experimental: this endpoint is subject to change.
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
docs/reference/api/schemas.md
Generated
+7 -3
View File
@@ -2164,6 +2164,7 @@ AuthorizationObject can represent a "set" of objects, such as: all workspaces in
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2257,6 +2258,7 @@ AuthorizationObject can represent a "set" of objects, such as: all workspaces in
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -2298,6 +2300,7 @@ AuthorizationObject can represent a "set" of objects, such as: all workspaces in
| `root_chat_id` | string | false | | |
| `shared` | boolean | false | | Shared is true when this chat's root chat has explicit user or group ACL entries. |
| `status` | [codersdk.ChatStatus](#codersdkchatstatus) | false | | |
| `summary` | string | false | | Summary is the persisted whole-chat summary, generated in the background. It is nil until the first summary has been produced. |
| `title` | string | false | | |
| `updated_at` | string | false | | |
| `warnings` | array of string | false | | |
@@ -4042,6 +4045,7 @@ AuthorizationObject can represent a "set" of objects, such as: all workspaces in
"root_chat_id": "2898031c-fdce-4e3e-8c53-4481dd42fcd7",
"shared": true,
"status": "waiting",
"summary": "string",
"title": "string",
"updated_at": "2019-08-24T14:15:22Z",
"warnings": [
@@ -4078,9 +4082,9 @@ AuthorizationObject can represent a "set" of objects, such as: all workspaces in
#### Enumerated Values
| Value(s) |
|-----------------------------------------------------------------------------------------------------------------------------------|
| `action_required`, `context_dirty`, `created`, `deleted`, `diff_status_change`, `status_change`, `summary_change`, `title_change` |
| Value(s) |
|----------------------------------------------------------------------------------------------------------------------------------------------------------|
| `action_required`, `chat_summary_change`, `context_dirty`, `created`, `deleted`, `diff_status_change`, `status_change`, `summary_change`, `title_change` |
## codersdk.ClusterConfig