mirror of
https://github.com/coder/coder.git
synced 2026-09-24 15:04:27 +08:00
feat: per-user per-model chat compaction threshold overrides (#23412)
## What
Adds per-user per-model auto-compaction threshold overrides. Users can
now customize the percentage of context window usage that triggers chat
compaction, independently for each enabled model.
## Why
The compaction threshold was previously only configurable at the
deployment level (`chat_model_configs.compression_threshold`). Different
users have different preferences — some want aggressive compaction to
keep costs low, others prefer higher thresholds to retain more context.
This gives users control without requiring admin intervention.
## Architecture
**Storage:** Reuses the existing `user_configs` table (no migration
needed). Overrides are stored as key/value pairs with keys shaped
`chat_compaction_threshold:<modelConfigID>` and integer percent values.
**API:** Three new experimental endpoints under
`/api/experimental/chats/config/`:
- `GET /user-compaction-thresholds` — list all overrides for the current
user
- `PUT /user-compaction-thresholds/{modelConfig}` — upsert an override
(validates model exists and is enabled, validates 0–100 range)
- `DELETE /user-compaction-thresholds/{modelConfig}` — clear an override
(idempotent)
**Runtime resolution:** In `coderd/chatd/chatd.go`, a new
`resolveUserCompactionThreshold()` helper runs at the start of each chat
turn (inside `runChat()`), after the model config is resolved but before
`CompactionOptions` is built. If a valid override exists, it replaces
`modelConfig.CompressionThreshold`. The threshold source
(`user_override` vs `model_default`) is logged with each compaction
event.
**Precedence:** `effectiveThreshold = userOverride ??
modelConfig.CompressionThreshold`
**UI:** New "Context Compaction" subsection in the Agents → Settings →
Behavior tab, placed after Personal Instructions. Shows one row per
enabled model with the system default, a number input for the override,
and Save/Reset controls.
## Testing
- 9 API subtests covering CRUD, validation (boundary values 0/100,
out-of-range rejection), upsert behavior, idempotent delete, user
isolation, and non-existent model config
- 4 dbauthz tests (16 scenarios) verifying `ActionReadPersonal` /
`ActionUpdatePersonal` on all query methods
- 4 Storybook stories with play functions (Default, WithOverrides,
Loading, Error)
<details>
<summary>Implementation plan</summary>
### Phase 1 — Tests
- Backend API tests in `coderd/chats_test.go` (9 subtests)
- Database auth wrapper tests in
`coderd/database/dbauthz/dbauthz_test.go` (4 methods)
- Frontend stories in `UserCompactionThresholdSettings.stories.tsx` (4
stories)
### Phase 2 — Backend preference surface
- 4 SQL queries in `coderd/database/queries/users.sql` (list, get,
upsert, delete)
- `make gen` to propagate into generated artifacts
- Auth/metrics wrappers in dbauthz and dbmetrics
- SDK types and client methods in `codersdk/chats.go`
- HTTP handlers and routes in `coderd/chats.go` and `coderd/coderd.go`
- Key prefix constant shared between handlers and runtime
### Phase 3 — Runtime override
- `resolveUserCompactionThreshold()` helper in `coderd/chatd/chatd.go`
- Override injection in `runChat()` before building `CompactionOptions`
- `threshold_source` field added to compaction log
### Phase 4 — Settings UI
- API client methods and React Query hooks in `site/src/api/`
- `UserCompactionThresholdSettings` component extracted from
`SettingsPageContent`
- Per-model mutation tracking (only the active row disables during save)
- 100% warning, "System default" label, helpful empty state copy
### Phase 5 — Refactor and review fixes
- Consolidated key prefix constant in `codersdk`
- Explicit PUT range validation (not just struct tags)
- GET handler gracefully skips malformed rows instead of 500
- Boundary value, upsert, and non-existent model config tests
- UX improvements: per-model mutation state, aria-live on errors
</details>
This commit is contained in:
@@ -2118,6 +2118,17 @@ func (q *querier) DeleteTask(ctx context.Context, arg database.DeleteTaskParams)
|
||||
return q.db.DeleteTask(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) DeleteUserChatCompactionThreshold(ctx context.Context, arg database.DeleteUserChatCompactionThresholdParams) error {
|
||||
u, err := q.db.GetUserByID(ctx, arg.UserID)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if err := q.authorizeContext(ctx, policy.ActionUpdatePersonal, u); err != nil {
|
||||
return err
|
||||
}
|
||||
return q.db.DeleteUserChatCompactionThreshold(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) DeleteUserSecret(ctx context.Context, id uuid.UUID) error {
|
||||
// First get the secret to check ownership
|
||||
secret, err := q.GetUserSecret(ctx, id)
|
||||
@@ -3921,6 +3932,17 @@ func (q *querier) GetUserByID(ctx context.Context, id uuid.UUID) (database.User,
|
||||
return fetch(q.log, q.auth, q.db.GetUserByID)(ctx, id)
|
||||
}
|
||||
|
||||
func (q *querier) GetUserChatCompactionThreshold(ctx context.Context, arg database.GetUserChatCompactionThresholdParams) (string, error) {
|
||||
u, err := q.db.GetUserByID(ctx, arg.UserID)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if err := q.authorizeContext(ctx, policy.ActionReadPersonal, u); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return q.db.GetUserChatCompactionThreshold(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) GetUserChatCustomPrompt(ctx context.Context, userID uuid.UUID) (string, error) {
|
||||
u, err := q.db.GetUserByID(ctx, userID)
|
||||
if err != nil {
|
||||
@@ -5352,6 +5374,17 @@ func (q *querier) ListTasks(ctx context.Context, arg database.ListTasksParams) (
|
||||
return fetchWithPostFilter(q.auth, policy.ActionRead, q.db.ListTasks)(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) ListUserChatCompactionThresholds(ctx context.Context, userID uuid.UUID) ([]database.UserConfig, error) {
|
||||
u, err := q.db.GetUserByID(ctx, userID)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := q.authorizeContext(ctx, policy.ActionReadPersonal, u); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return q.db.ListUserChatCompactionThresholds(ctx, userID)
|
||||
}
|
||||
|
||||
func (q *querier) ListUserSecrets(ctx context.Context, userID uuid.UUID) ([]database.UserSecret, error) {
|
||||
obj := rbac.ResourceUserSecret.WithOwner(userID.String())
|
||||
if err := q.authorizeContext(ctx, policy.ActionRead, obj); err != nil {
|
||||
@@ -6212,6 +6245,17 @@ func (q *querier) UpdateUsageEventsPostPublish(ctx context.Context, arg database
|
||||
return q.db.UpdateUsageEventsPostPublish(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) UpdateUserChatCompactionThreshold(ctx context.Context, arg database.UpdateUserChatCompactionThresholdParams) (database.UserConfig, error) {
|
||||
u, err := q.db.GetUserByID(ctx, arg.UserID)
|
||||
if err != nil {
|
||||
return database.UserConfig{}, err
|
||||
}
|
||||
if err := q.authorizeContext(ctx, policy.ActionUpdatePersonal, u); err != nil {
|
||||
return database.UserConfig{}, err
|
||||
}
|
||||
return q.db.UpdateUserChatCompactionThreshold(ctx, arg)
|
||||
}
|
||||
|
||||
func (q *querier) UpdateUserChatCustomPrompt(ctx context.Context, arg database.UpdateUserChatCustomPromptParams) (database.UserConfig, error) {
|
||||
u, err := q.db.GetUserByID(ctx, arg.UserID)
|
||||
if err != nil {
|
||||
|
||||
@@ -2278,6 +2278,35 @@ func (s *MethodTestSuite) TestUser() {
|
||||
dbm.EXPECT().UpdateUserChatCustomPrompt(gomock.Any(), arg).Return(uc, nil).AnyTimes()
|
||||
check.Args(arg).Asserts(u, policy.ActionUpdatePersonal).Returns(uc)
|
||||
}))
|
||||
s.Run("ListUserChatCompactionThresholds", s.Mocked(func(dbm *dbmock.MockStore, faker *gofakeit.Faker, check *expects) {
|
||||
u := testutil.Fake(s.T(), faker, database.User{})
|
||||
uc := database.UserConfig{UserID: u.ID, Key: codersdk.ChatCompactionThresholdKeyPrefix + "00000000-0000-0000-0000-000000000001", Value: "75"}
|
||||
dbm.EXPECT().GetUserByID(gomock.Any(), u.ID).Return(u, nil).AnyTimes()
|
||||
dbm.EXPECT().ListUserChatCompactionThresholds(gomock.Any(), u.ID).Return([]database.UserConfig{uc}, nil).AnyTimes()
|
||||
check.Args(u.ID).Asserts(u, policy.ActionReadPersonal).Returns([]database.UserConfig{uc})
|
||||
}))
|
||||
s.Run("GetUserChatCompactionThreshold", s.Mocked(func(dbm *dbmock.MockStore, faker *gofakeit.Faker, check *expects) {
|
||||
u := testutil.Fake(s.T(), faker, database.User{})
|
||||
arg := database.GetUserChatCompactionThresholdParams{UserID: u.ID, Key: codersdk.ChatCompactionThresholdKeyPrefix + "00000000-0000-0000-0000-000000000001"}
|
||||
dbm.EXPECT().GetUserByID(gomock.Any(), u.ID).Return(u, nil).AnyTimes()
|
||||
dbm.EXPECT().GetUserChatCompactionThreshold(gomock.Any(), arg).Return("75", nil).AnyTimes()
|
||||
check.Args(arg).Asserts(u, policy.ActionReadPersonal).Returns("75")
|
||||
}))
|
||||
s.Run("UpdateUserChatCompactionThreshold", s.Mocked(func(dbm *dbmock.MockStore, faker *gofakeit.Faker, check *expects) {
|
||||
u := testutil.Fake(s.T(), faker, database.User{})
|
||||
uc := database.UserConfig{UserID: u.ID, Key: codersdk.ChatCompactionThresholdKeyPrefix + "00000000-0000-0000-0000-000000000001", Value: "75"}
|
||||
arg := database.UpdateUserChatCompactionThresholdParams{UserID: u.ID, Key: uc.Key, ThresholdPercent: 75}
|
||||
dbm.EXPECT().GetUserByID(gomock.Any(), u.ID).Return(u, nil).AnyTimes()
|
||||
dbm.EXPECT().UpdateUserChatCompactionThreshold(gomock.Any(), arg).Return(uc, nil).AnyTimes()
|
||||
check.Args(arg).Asserts(u, policy.ActionUpdatePersonal).Returns(uc)
|
||||
}))
|
||||
s.Run("DeleteUserChatCompactionThreshold", s.Mocked(func(dbm *dbmock.MockStore, faker *gofakeit.Faker, check *expects) {
|
||||
u := testutil.Fake(s.T(), faker, database.User{})
|
||||
arg := database.DeleteUserChatCompactionThresholdParams{UserID: u.ID, Key: codersdk.ChatCompactionThresholdKeyPrefix + "00000000-0000-0000-0000-000000000001"}
|
||||
dbm.EXPECT().GetUserByID(gomock.Any(), u.ID).Return(u, nil).AnyTimes()
|
||||
dbm.EXPECT().DeleteUserChatCompactionThreshold(gomock.Any(), arg).Return(nil).AnyTimes()
|
||||
check.Args(arg).Asserts(u, policy.ActionUpdatePersonal)
|
||||
}))
|
||||
s.Run("UpdateUserTaskNotificationAlertDismissed", s.Mocked(func(dbm *dbmock.MockStore, faker *gofakeit.Faker, check *expects) {
|
||||
user := testutil.Fake(s.T(), faker, database.User{})
|
||||
userConfig := database.UserConfig{UserID: user.ID, Key: "task_notification_alert_dismissed", Value: "false"}
|
||||
|
||||
Reference in New Issue
Block a user