fix: update the compaction message to be the "user" role (#22819)

## Bug After compaction in the chat loop, the loop re-enters and calls the LLM with a prompt that has **no non-system messages**. Anthropic (and most providers) require at least one user/assistant/tool message, so the API errors with empty messages. ## Root Cause The compaction summary was stored as `role=system`. After compaction, `GetChatMessagesForPromptByChatID` returns only: - The compressed system summary (matched by the CTE) - Original non-compressed system messages (system prompts) All original user/assistant/tool messages are excluded (they predate the summary). The compaction assistant/tool messages are `compressed=TRUE` and don't match the main query's `compressed=FALSE` clauses. So `ReloadMessages` returned only system messages. The Anthropic provider moves system messages into a separate `system` field, leaving the `messages` API field as `[]`. ## Fix 1. **Changed compaction summary from `role=system` to `role=user`** — the summary now appears as a user message in the reloaded prompt, giving the model valid conversational context to respond to. 2. **Simplified the CTE** — removed the `role = 'system'` check and narrowed `visibility IN ('model', 'both')` to just `visibility = 'model'`. The summary is the only compressed message with `visibility=model` (the assistant has `visibility=user`, the tool has `visibility=both`), so the role check was redundant. ## Test `PostRunCompactionReEntryIncludesUserSummary`: verifies the re-entry prompt contains a user message (the compaction summary) after compaction + reload.
2026-09-24 15:04:27 +08:00 · 2026-03-08 22:25:27 -04:00
parent ca873060c6
commit aba3832b15
5 changed files with 315 additions and 5 deletions
@@ -600,4 +600,117 @@ func TestRun_Compaction(t *testing.T) {
 		// Two stream calls: one before compaction, one after re-entry.
 		require.Equal(t, 2, streamCallCount)
 	})
+
+	t.Run("PostRunCompactionReEntryIncludesUserSummary", func(t *testing.T) {
+		t.Parallel()
+
+		// After compaction the summary is stored as a user-role
+		// message. When the loop re-enters, the reloaded prompt
+		// must contain this user message so the LLM provider
+		// receives a valid prompt (providers like Anthropic
+		// require at least one non-system message).
+
+		var mu sync.Mutex
+		var streamCallCount int
+		var reEntryPrompt []fantasy.Message
+		persistCompactionCalls := 0
+
+		const summaryText = "post-run compacted summary"
+
+		model := &loopTestModel{
+			provider: "fake",
+			streamFn: func(_ context.Context, call fantasy.Call) (fantasy.StreamResponse, error) {
+				mu.Lock()
+				step := streamCallCount
+				streamCallCount++
+				mu.Unlock()
+
+				switch step {
+				case 0:
+					return streamFromParts([]fantasy.StreamPart{
+						{Type: fantasy.StreamPartTypeTextStart, ID: "text-1"},
+						{Type: fantasy.StreamPartTypeTextDelta, ID: "text-1", Delta: "initial response"},
+						{Type: fantasy.StreamPartTypeTextEnd, ID: "text-1"},
+						{
+							Type:         fantasy.StreamPartTypeFinish,
+							FinishReason: fantasy.FinishReasonStop,
+							Usage: fantasy.Usage{
+								InputTokens: 80,
+								TotalTokens: 85,
+							},
+						},
+					}), nil
+				default:
+					mu.Lock()
+					reEntryPrompt = append([]fantasy.Message(nil), call.Prompt...)
+					mu.Unlock()
+					return streamFromParts([]fantasy.StreamPart{
+						{Type: fantasy.StreamPartTypeTextStart, ID: "text-2"},
+						{Type: fantasy.StreamPartTypeTextDelta, ID: "text-2", Delta: "continued"},
+						{Type: fantasy.StreamPartTypeTextEnd, ID: "text-2"},
+						{
+							Type:         fantasy.StreamPartTypeFinish,
+							FinishReason: fantasy.FinishReasonStop,
+							Usage: fantasy.Usage{
+								InputTokens: 20,
+								TotalTokens: 25,
+							},
+						},
+					}), nil
+				}
+			},
+			generateFn: func(_ context.Context, _ fantasy.Call) (*fantasy.Response, error) {
+				return &fantasy.Response{
+					Content: []fantasy.Content{
+						fantasy.TextContent{Text: summaryText},
+					},
+				}, nil
+			},
+		}
+
+		// Simulate real post-compaction DB state: the summary is
+		// a user-role message (the only non-system content).
+		compactedMessages := []fantasy.Message{
+			textMessage(fantasy.MessageRoleSystem, "system prompt"),
+			textMessage(fantasy.MessageRoleUser, "Summary of earlier chat context:\n\ncompacted summary"),
+		}
+
+		err := Run(context.Background(), RunOptions{
+			Model: model,
+			Messages: []fantasy.Message{
+				textMessage(fantasy.MessageRoleUser, "hello"),
+			},
+			MaxSteps: 5,
+			PersistStep: func(_ context.Context, _ PersistedStep) error {
+				return nil
+			},
+			ContextLimitFallback: 100,
+			Compaction: &CompactionOptions{
+				ThresholdPercent: 70,
+				SummaryPrompt:    "summarize now",
+				Persist: func(_ context.Context, _ CompactionResult) error {
+					persistCompactionCalls++
+					return nil
+				},
+			},
+			ReloadMessages: func(_ context.Context) ([]fantasy.Message, error) {
+				return compactedMessages, nil
+			},
+		})
+		require.NoError(t, err)
+
+		require.GreaterOrEqual(t, persistCompactionCalls, 1)
+		// Re-entry happened: stream was called at least twice.
+		require.Equal(t, 2, streamCallCount)
+		// The re-entry prompt must contain the user summary.
+		require.NotEmpty(t, reEntryPrompt)
+		hasUser := false
+		for _, msg := range reEntryPrompt {
+			if msg.Role == fantasy.MessageRoleUser {
+				hasUser = true
+				break
+			}
+		}
+		require.True(t, hasUser, "re-entry prompt must contain a user message (the compaction summary)")
+	})
 }