mirror of
https://github.com/coder/coder.git
synced 2026-06-02 20:48:20 +00:00
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:
@@ -148,6 +148,7 @@ type sqlcQuerier interface {
|
||||
DeleteTailnetPeer(ctx context.Context, arg DeleteTailnetPeerParams) (DeleteTailnetPeerRow, error)
|
||||
DeleteTailnetTunnel(ctx context.Context, arg DeleteTailnetTunnelParams) (DeleteTailnetTunnelRow, error)
|
||||
DeleteTask(ctx context.Context, arg DeleteTaskParams) (uuid.UUID, error)
|
||||
DeleteUserChatCompactionThreshold(ctx context.Context, arg DeleteUserChatCompactionThresholdParams) error
|
||||
DeleteUserSecret(ctx context.Context, id uuid.UUID) error
|
||||
DeleteWebpushSubscriptionByUserIDAndEndpoint(ctx context.Context, arg DeleteWebpushSubscriptionByUserIDAndEndpointParams) error
|
||||
DeleteWebpushSubscriptions(ctx context.Context, ids []uuid.UUID) error
|
||||
@@ -553,6 +554,7 @@ type sqlcQuerier interface {
|
||||
GetUserActivityInsights(ctx context.Context, arg GetUserActivityInsightsParams) ([]GetUserActivityInsightsRow, error)
|
||||
GetUserByEmailOrUsername(ctx context.Context, arg GetUserByEmailOrUsernameParams) (User, error)
|
||||
GetUserByID(ctx context.Context, id uuid.UUID) (User, error)
|
||||
GetUserChatCompactionThreshold(ctx context.Context, arg GetUserChatCompactionThresholdParams) (string, error)
|
||||
GetUserChatCustomPrompt(ctx context.Context, userID uuid.UUID) (string, error)
|
||||
GetUserChatSpendInPeriod(ctx context.Context, arg GetUserChatSpendInPeriodParams) (int64, error)
|
||||
GetUserCount(ctx context.Context, includeSystem bool) (int64, error)
|
||||
@@ -765,6 +767,7 @@ type sqlcQuerier interface {
|
||||
ListProvisionerKeysByOrganization(ctx context.Context, organizationID uuid.UUID) ([]ProvisionerKey, error)
|
||||
ListProvisionerKeysByOrganizationExcludeReserved(ctx context.Context, organizationID uuid.UUID) ([]ProvisionerKey, error)
|
||||
ListTasks(ctx context.Context, arg ListTasksParams) ([]Task, error)
|
||||
ListUserChatCompactionThresholds(ctx context.Context, userID uuid.UUID) ([]UserConfig, error)
|
||||
ListUserSecrets(ctx context.Context, userID uuid.UUID) ([]UserSecret, error)
|
||||
ListWorkspaceAgentPortShares(ctx context.Context, workspaceID uuid.UUID) ([]WorkspaceAgentPortShare, error)
|
||||
MarkAllInboxNotificationsAsRead(ctx context.Context, arg MarkAllInboxNotificationsAsReadParams) error
|
||||
@@ -868,6 +871,7 @@ type sqlcQuerier interface {
|
||||
UpdateTemplateVersionFlagsByJobID(ctx context.Context, arg UpdateTemplateVersionFlagsByJobIDParams) error
|
||||
UpdateTemplateWorkspacesLastUsedAt(ctx context.Context, arg UpdateTemplateWorkspacesLastUsedAtParams) error
|
||||
UpdateUsageEventsPostPublish(ctx context.Context, arg UpdateUsageEventsPostPublishParams) error
|
||||
UpdateUserChatCompactionThreshold(ctx context.Context, arg UpdateUserChatCompactionThresholdParams) (UserConfig, error)
|
||||
UpdateUserChatCustomPrompt(ctx context.Context, arg UpdateUserChatCustomPromptParams) (UserConfig, error)
|
||||
UpdateUserDeletedByID(ctx context.Context, id uuid.UUID) error
|
||||
UpdateUserGithubComUserID(ctx context.Context, arg UpdateUserGithubComUserIDParams) error
|
||||
|
||||
Reference in New Issue
Block a user