picoclaw/pkg/seahorse/tool_expand_test.go

137 lines
3.4 KiB
Go
Raw Normal View History

feat(seahorse): implement short-term memory engine (LCM) (#2285) * feat(seahorse): implement short-term memory engine of seahorse Add pkg/seahorse/ module implementing a SQLite-backed DAG-based summary hierarchy for context management, ported from lossless-claw's LCM design: - types.go + short_constants.go: core types (Message, Summary, Conversation, ContextItem) and configuration constants (fanout, token targets, thresholds) - migration.go: idempotent DB schema with FTS5 trigram tokenizer for CJK - store.go: full SQLite CRUD (conversations, messages, summaries DAG, context_items with ordinal gap numbering, FTS5 search) - short_engine.go: Engine lifecycle (NewEngine, Ingest, Assemble, Compact), session pattern filtering (ignore/stateless glob→regex compilation), per-session mutex via sync.Map - short_assembler.go: budget-aware context assembly with fresh tail protection (32 messages), oldest-first eviction, summary XML formatting, RebuildContextItems - short_compaction.go: leaf compaction (messages→summary) and condensed compaction (summaries→higher-level summary), 3-level LLM escalation, CompactUntilUnder for emergency overflow - short_retrieval.go: lookupByID, FTS5/LIKE search, recursive expand with token cap - context_seahorse.go: agent.ContextManager adapter, registered as "seahorse", provider↔seahorse message type conversion (ToolCalls, tool_result) * fix(seahorse): correct 3 adapter bugs in context management - TokenCount: use full message (Content+ToolCalls+Media) instead of Content-only - Empty Content: rebuild Content from tool_result Parts when stored empty - Duplicate summaries: summaries only in Summary field, not in History messages - Grep: fix SearchResult.Snippet→Content for summaries - Schema: fix FTS5 SQL uses VIRTUAL TABLE not TEMP TABLE - TestFTS5SQLConstants: verify FTS5 SQL syntax correctness - Test: fix flaky TestCompactLeaf * fix(agent): ingest steering messages into seahorse SQLite Steering messages were only persisted to session JSONL but not ingested into seahorse SQLite, causing them to be missing from context assembly. Added `ts.ingestMessage(turnCtx, al, pm)` call in the steering message injection block alongside the existing JSONL persistence. Test: TestSeahorseSteeringMessageIngested verifies steering messages appear in seahorse SQLite DB after being processed. * fix(seahorse): address 3 blocking bugs from code review - Fix resequenceContextItemsTx scan error handling (store.go:850) Changed `return err` to `return scanErr` to properly propagate scan errors instead of returning nil (which silently corrupts data) - Fix sql.NullString for INTEGER column (store.go:847) Changed `mid` from sql.NullString to sql.NullInt64 since message_id is INTEGER in schema. Removed unnecessary strconv.ParseInt call. - Fix compactCondensed fallback deleting non-candidate items Added ReplaceContextItemsWithSummary method for per-item deletion when candidates are not contiguous in ordinal space. Optimized to use range deletion when candidates are consecutive. * fix(seahorse): pass Budget to Compact for correct condensed threshold Issue #4 from PR review: When Budget was not passed to seahorse.Compact, it defaulted to `tokensBefore * 0.75`, making `tokensBefore > budget` always true and causing condensed compaction to trigger unnecessarily. Changes: - context_seahorse.go: Forward Budget from CompactRequest to CompactInput - loop.go: Pass Budget (ContextWindow) in all 3 Compact calls - Add test verifying condensed is skipped when tokens < threshold - Fix lint issues in store.go and store_test.go * fix(seahorse): add mutex for assembler lazy initialization Issue #5 from PR review: The check-then-create pattern for e.assembler was a data race when multiple goroutines called Assemble() concurrently: if e.assembler == nil { e.assembler = &Assembler{...} } Changes: - Add assemblerMu sync.Mutex to Engine struct - Add initAssemblerOnce() using double-checked locking (same pattern as initCompactionOnce) - Add TestAssemblerLazyInitRace to verify thread-safety * fix(seahorse): handle non-consecutive depths in selectShallowestCondensationCandidate Issue #8 from PR review: the loop iterated depth 0, 1, 2... assuming consecutive keys, but break when key was missing caused deeper depths to never be checked. Fix: collect all existing depth keys, sort, then iterate in order. * fix(seahorse): wrap DeleteMessagesAfterID and appendContextItems in transactions - DeleteMessagesAfterID: wrap all DELETE operations in a transaction for atomicity, remove redundant manual FTS delete (handled by trigger) - appendContextItems: use transaction to fix read-then-write race condition - Add GetMaxOrdinalTx and resolveItemTokenCountTx for transaction-scoped queries - Remove unused resolveItemTokenCount function Fixes PR review issues 6 and 7. * fix(seahorse): derive readable content from Parts and cap CompactUntilUnder iterations - Derive readable content from MessageParts in AddMessageWithParts so FTS5 indexing and summary formatting can access tool call information - formatMessagesForSummary and truncateSummary now fall back to Parts when Content is empty, fixing blank summaries for Part-based messages - Add MaxCompactIterations (20) to prevent CompactUntilUnder infinite loops; exceeded iterations are logged as warnings
2026-04-05 01:05:16 +00:00
package seahorse
import (
"context"
"encoding/json"
"fmt"
"testing"
)
func TestExpandToolByMessageIDs(t *testing.T) {
s := openTestStore(t)
ctx := context.Background()
conv, _ := s.GetOrCreateConversation(ctx, "test:expand-tool")
msg1, _ := s.AddMessage(ctx, conv.ConversationID, "user", "first message", 10)
msg2, _ := s.AddMessage(ctx, conv.ConversationID, "assistant", "second message", 10)
re := &RetrievalEngine{store: s}
tool := NewExpandTool(re)
result := tool.Execute(ctx, map[string]any{
"message_ids": []any{fmt.Sprintf("%d", msg1.ID), fmt.Sprintf("%d", msg2.ID)},
})
if result.IsError {
t.Fatalf("Expand failed: %s", result.ForLLM)
}
// Parse result
var output struct {
Success bool `json:"success"`
TokenCount int `json:"tokenCount"`
Messages []map[string]any `json:"messages"`
}
if err := json.Unmarshal([]byte(result.ForLLM), &output); err != nil {
t.Fatalf("Parse result: %v", err)
}
if !output.Success {
t.Error("expected success=true")
}
if len(output.Messages) != 2 {
t.Errorf("Messages = %d, want 2", len(output.Messages))
}
if output.TokenCount != 20 {
t.Errorf("TokenCount = %d, want 20", output.TokenCount)
}
}
func TestExpandToolMissingIDs(t *testing.T) {
s := openTestStore(t)
re := &RetrievalEngine{store: s}
tool := NewExpandTool(re)
result := tool.Execute(context.Background(), map[string]any{})
if !result.IsError {
t.Error("expected error for missing message_ids")
}
}
func TestExpandToolWithParts(t *testing.T) {
s := openTestStore(t)
ctx := context.Background()
conv, _ := s.GetOrCreateConversation(ctx, "test:expand-parts")
// Create message with parts
parts := []MessagePart{
{Type: "text", Text: "Hello"},
{Type: "tool_use", Name: "bash", Arguments: `{"command":"ls"}`, ToolCallID: "call_123"},
{Type: "tool_result", ToolCallID: "call_123", Text: "file1.txt\nfile2.txt"},
}
msg, _ := s.AddMessageWithParts(ctx, conv.ConversationID, "assistant", parts, 50)
re := &RetrievalEngine{store: s}
tool := NewExpandTool(re)
result := tool.Execute(ctx, map[string]any{
"message_ids": []any{fmt.Sprintf("%d", msg.ID)},
})
if result.IsError {
t.Fatalf("Expand failed: %s", result.ForLLM)
}
var output struct {
Messages []struct {
Parts []map[string]any `json:"parts"`
} `json:"messages"`
}
if err := json.Unmarshal([]byte(result.ForLLM), &output); err != nil {
t.Fatalf("Parse result: %v", err)
}
if len(output.Messages) != 1 {
t.Fatalf("Messages = %d, want 1", len(output.Messages))
}
// Verify parts are filtered correctly
foundText := false
foundToolUse := false
foundToolResult := false
for _, p := range output.Messages[0].Parts {
switch p["type"].(string) {
case "text":
foundText = true
if p["text"] != "Hello" {
t.Errorf("text = %v, want Hello", p["text"])
}
case "tool_use":
foundToolUse = true
if p["name"] != "bash" {
t.Errorf("name = %v, want bash", p["name"])
}
case "tool_result":
foundToolResult = true
// tool_result should NOT have content
if _, hasContent := p["content"]; hasContent {
t.Error("tool_result should not have content field")
}
if p["toolCallId"] != "call_123" {
t.Errorf("toolCallId = %v, want call_123", p["toolCallId"])
}
}
}
if !foundText {
t.Error("missing text part")
}
if !foundToolUse {
t.Error("missing tool_use part")
}
if !foundToolResult {
t.Error("missing tool_result part")
}
}