Files
coder/coderd/chatd/chatloop/compaction_test.go
T
Kyle Carberry 360df1d84f fix(chatd): publish streaming message_part events during compaction (#22410)
## Problem

Context compaction in chatd persisted durable messages for the
`chat_summarized` tool call and result via `publishMessage`, but never
published `message_part` streaming events via `publishMessagePart`. This
meant connected clients had no streaming representation of the
compaction.

The client's `streamState` (built entirely from `message_part` events in
`streamState.ts`) never saw the compaction tool call, so:

- No **"Summarizing..."** running state was shown to the user during
summary generation (which can take up to 90s).
- The durable `message` events arrived after or interleaved with the
`status: waiting` event, causing the tool to appear as "Summarized" with
the chat appearing to just stop.

## Fix

### 1. `CompactionOptions.OnStart` callback (chatloop)

Added an `OnStart` callback to `CompactionOptions`, called in
`maybeCompact` right before `generateCompactionSummary` (the slow LLM
call). This gives `chatd` a hook to publish the tool-call `message_part`
immediately when compaction begins.

### 2. Tool-result streaming part (chatd)

`persistChatContextSummary` now publishes a tool-result `message_part`
before the durable `message` events, so clients transition from
"Summarizing..." to "Summarized" before the status change arrives.

### Event ordering is now:
1. `message_part` (tool call via `OnStart`) — client shows
"Summarizing..."
2. LLM generates summary (up to 90s)
3. `message_part` (tool result) — client shows "Summarized" in stream
state
4. `message` (assistant) — durable message persisted, stream state
resets
5. `message` (tool) — durable tool result persisted
6. `status: waiting` — chat transitions to idle

## Tests

- **`OnStartFiresBeforePersist`**: Verifies callback ordering is
`on_start` → `generate` → `persist`.
- **`OnStartNotCalledBelowThreshold`**: Verifies `OnStart` is not called
when context usage is below the compaction threshold.
2026-02-27 16:33:39 -05:00

240 lines
6.7 KiB
Go

package chatloop //nolint:testpackage // Uses internal symbols.
import (
"context"
"testing"
"charm.land/fantasy"
"github.com/stretchr/testify/require"
"golang.org/x/xerrors"
)
func TestRun_Compaction(t *testing.T) {
t.Parallel()
t.Run("PersistsWhenThresholdReached", func(t *testing.T) {
t.Parallel()
persistCompactionCalls := 0
var persistedCompaction CompactionResult
const summaryText = "summary text for compaction"
model := &loopTestModel{
provider: "fake",
streamFn: func(_ context.Context, _ fantasy.Call) (fantasy.StreamResponse, error) {
return streamFromParts([]fantasy.StreamPart{
{Type: fantasy.StreamPartTypeTextStart, ID: "text-1"},
{Type: fantasy.StreamPartTypeTextDelta, ID: "text-1", Delta: "done"},
{Type: fantasy.StreamPartTypeTextEnd, ID: "text-1"},
{
Type: fantasy.StreamPartTypeFinish,
FinishReason: fantasy.FinishReasonStop,
Usage: fantasy.Usage{
InputTokens: 80,
TotalTokens: 85,
},
},
}), nil
},
generateFn: func(_ context.Context, call fantasy.Call) (*fantasy.Response, error) {
require.NotEmpty(t, call.Prompt)
lastPrompt := call.Prompt[len(call.Prompt)-1]
require.Equal(t, fantasy.MessageRoleUser, lastPrompt.Role)
require.Len(t, lastPrompt.Content, 1)
instruction, ok := fantasy.AsMessagePart[fantasy.TextPart](lastPrompt.Content[0])
require.True(t, ok)
require.Equal(t, "summarize now", instruction.Text)
return &fantasy.Response{
Content: []fantasy.Content{
fantasy.TextContent{Text: summaryText},
},
}, nil
},
}
_, err := Run(context.Background(), RunOptions{
Model: model,
Messages: []fantasy.Message{
textMessage(fantasy.MessageRoleUser, "hello"),
},
MaxSteps: 1,
PersistStep: func(_ context.Context, _ PersistedStep) error {
return nil
},
ContextLimitFallback: 100,
Compaction: &CompactionOptions{
ThresholdPercent: 70,
SummaryPrompt: "summarize now",
Persist: func(_ context.Context, result CompactionResult) error {
persistCompactionCalls++
persistedCompaction = result
return nil
},
},
})
require.NoError(t, err)
require.Equal(t, 1, persistCompactionCalls)
require.Contains(t, persistedCompaction.SystemSummary, summaryText)
require.Equal(t, summaryText, persistedCompaction.SummaryReport)
require.Equal(t, int64(80), persistedCompaction.ContextTokens)
require.Equal(t, int64(100), persistedCompaction.ContextLimit)
require.InDelta(t, 80.0, persistedCompaction.UsagePercent, 0.0001)
})
t.Run("OnStartFiresBeforePersist", func(t *testing.T) {
t.Parallel()
const summaryText = "compaction summary for ordering test"
// Track the order of callbacks to verify OnStart fires
// before the Generate call (summary generation) and
// before Persist.
var callOrder []string
model := &loopTestModel{
provider: "fake",
streamFn: func(_ context.Context, _ fantasy.Call) (fantasy.StreamResponse, error) {
return streamFromParts([]fantasy.StreamPart{
{Type: fantasy.StreamPartTypeTextStart, ID: "text-1"},
{Type: fantasy.StreamPartTypeTextDelta, ID: "text-1", Delta: "done"},
{Type: fantasy.StreamPartTypeTextEnd, ID: "text-1"},
{
Type: fantasy.StreamPartTypeFinish,
FinishReason: fantasy.FinishReasonStop,
Usage: fantasy.Usage{
InputTokens: 80,
TotalTokens: 85,
},
},
}), nil
},
generateFn: func(_ context.Context, _ fantasy.Call) (*fantasy.Response, error) {
callOrder = append(callOrder, "generate")
return &fantasy.Response{
Content: []fantasy.Content{
fantasy.TextContent{Text: summaryText},
},
}, nil
},
}
_, err := Run(context.Background(), RunOptions{
Model: model,
Messages: []fantasy.Message{
textMessage(fantasy.MessageRoleUser, "hello"),
},
MaxSteps: 1,
PersistStep: func(_ context.Context, _ PersistedStep) error {
return nil
},
ContextLimitFallback: 100,
Compaction: &CompactionOptions{
ThresholdPercent: 70,
SummaryPrompt: "summarize now",
OnStart: func() {
callOrder = append(callOrder, "on_start")
},
Persist: func(_ context.Context, _ CompactionResult) error {
callOrder = append(callOrder, "persist")
return nil
},
},
})
require.NoError(t, err)
require.Equal(t, []string{"on_start", "generate", "persist"}, callOrder)
})
t.Run("OnStartNotCalledBelowThreshold", func(t *testing.T) {
t.Parallel()
onStartCalled := false
model := &loopTestModel{
provider: "fake",
streamFn: func(_ context.Context, _ fantasy.Call) (fantasy.StreamResponse, error) {
return streamFromParts([]fantasy.StreamPart{
{
Type: fantasy.StreamPartTypeFinish,
FinishReason: fantasy.FinishReasonStop,
Usage: fantasy.Usage{
InputTokens: 10,
},
},
}), nil
},
}
_, err := Run(context.Background(), RunOptions{
Model: model,
Messages: []fantasy.Message{
textMessage(fantasy.MessageRoleUser, "hello"),
},
MaxSteps: 1,
PersistStep: func(_ context.Context, _ PersistedStep) error {
return nil
},
ContextLimitFallback: 100,
Compaction: &CompactionOptions{
ThresholdPercent: 70,
OnStart: func() {
onStartCalled = true
},
Persist: func(_ context.Context, _ CompactionResult) error {
return nil
},
},
})
require.NoError(t, err)
require.False(t, onStartCalled, "OnStart should not fire when usage is below threshold")
})
t.Run("ErrorsAreReported", func(t *testing.T) {
t.Parallel()
model := &loopTestModel{
provider: "fake",
streamFn: func(_ context.Context, _ fantasy.Call) (fantasy.StreamResponse, error) {
return streamFromParts([]fantasy.StreamPart{
{
Type: fantasy.StreamPartTypeFinish,
FinishReason: fantasy.FinishReasonStop,
Usage: fantasy.Usage{
InputTokens: 80,
},
},
}), nil
},
generateFn: func(_ context.Context, _ fantasy.Call) (*fantasy.Response, error) {
return nil, xerrors.New("generate failed")
},
}
compactionErr := xerrors.New("unset")
_, err := Run(context.Background(), RunOptions{
Model: model,
Messages: []fantasy.Message{
textMessage(fantasy.MessageRoleUser, "hello"),
},
MaxSteps: 1,
PersistStep: func(_ context.Context, _ PersistedStep) error {
return nil
},
ContextLimitFallback: 100,
Compaction: &CompactionOptions{
ThresholdPercent: 70,
Persist: func(_ context.Context, _ CompactionResult) error {
return nil
},
OnError: func(err error) {
compactionErr = err
},
},
})
require.NoError(t, err)
require.Error(t, compactionErr)
require.ErrorContains(t, compactionErr, "generate summary text")
})
}