> [!NOTE]
> Xum acted on Mike's behalf in this pull request.
<!-- xum-attribution: model=claude-fable-5 thinking=high -->
Adds a `/clear` slash command to Agents chats that resets the model
context without deleting anything: the transcript stays visible, and the
next prompt runs as if the chat were brand new. It mirrors `/compact`'s
UX (slash menu entry, exact-text interception, dedicated endpoint,
synthetic tool block in the transcript) but generates no summary and
makes no model call.
## How it works
`POST /api/experimental/chats/{chat}/clear` commits synchronously inside
the API transaction through a new `chatstate` transition,
`ClearContext`, allowed from `waiting` and from `error` without queued
messages (`W -> W`, `E0 -> W`). No worker round-trip, no status flicker
to `running`, no migration. Clearing an errored chat clears
`last_error`, and any pending manual compaction request is dropped
rather than left to run against the cleared context.
The endpoint persists the same compressed boundary shape `/compact`
uses: a hidden model-only sentinel row, a visible synthetic
`chat_cleared` tool call, and its result. Prompt assembly already
selects the latest compressed model-only row as the context cutoff, so
the query is unchanged. Boundary detection is generalized to recognize
both `chat_summarized` and `chat_cleared`, so `/compact` after `/clear`
(and the reverse) never reach across the newer boundary, and
auto-compaction does not fire off stale pre-clear usage.
Busy chats, errored chats with queued messages, and clears with no
conversation after the latest boundary return 409. Archived chats are
rejected. The endpoint is owner-only for symmetry with `/compact`.
## Frontend
`/clear` joins the slash command menu, and the previously compact-only
send interception becomes a small built-in command dispatch shared by
both commands, so a personal or workspace skill named `clear` still
takes precedence. Because the clear commits synchronously, the UI keeps
the chat in `waiting`, refetches on success, and surfaces conflicts with
the standard error toast. The transcript renders a "Context cleared"
card via a new `ChatClearedTool` renderer.
## Docs
The user-facing agents architecture page documents `/clear`.
`coderd/x/chatd/ARCHITECTURE.md` carries TODO notes in the affected
sections for the PR author to write.
## Tests
- `chatstate`: transition matrix entries plus dedicated `ClearContext`
coverage (error-state entry, queued-message rejection, boundary row
requirement).
- `chatd`: end-to-end manual clear (fresh next prompt, error recovery,
boundary interplay with compaction, stale-usage auto-compaction
regression, busy rejection) plus boundary and message-builder units.
- `coderd`: HTTP authorization and error mapping for the endpoint.
- Frontend: slash command availability and skill collision units,
stories for the submit path, the conflict toast, and the cleared-card
renderer.
31 lines
924 B
Go
31 lines
924 B
Go
package chatstate_test
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"github.com/coder/coder/v2/coderd/database"
|
|
"github.com/coder/coder/v2/coderd/x/chatd/chatstate"
|
|
"github.com/coder/coder/v2/testutil"
|
|
)
|
|
|
|
// The transition matrix tests cover the allowed states and effects;
|
|
// this file pins the non-matrix input validation.
|
|
|
|
func TestClearContext_RequiresBoundaryMessages(t *testing.T) {
|
|
t.Parallel()
|
|
f := newTestFixture(t)
|
|
ctx := testutil.Context(t, testutil.WaitShort)
|
|
seeded := seedState(t, f, chatstate.StateW)
|
|
m := chatstate.NewChatMachine(f.DB, f.Pub, seeded.chatID)
|
|
|
|
err := m.Update(ctx, func(tx *chatstate.Tx, _ database.Store) error {
|
|
_, err := tx.ClearContext(chatstate.ClearContextInput{})
|
|
return err
|
|
})
|
|
require.ErrorIs(t, err, chatstate.ErrTransitionNotAllowed)
|
|
require.Equal(t, chatstate.StateW, f.classify(ctx, t, seeded.chatID),
|
|
"a rejected clear must not change state")
|
|
}
|