mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-05-25 16:00:35 +00:00
15a70ac45c
* 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
212 lines
5.2 KiB
Go
212 lines
5.2 KiB
Go
package seahorse
|
|
|
|
import (
|
|
"database/sql"
|
|
"testing"
|
|
|
|
_ "modernc.org/sqlite"
|
|
)
|
|
|
|
func openTestDB(t *testing.T) *sql.DB {
|
|
t.Helper()
|
|
db, err := sql.Open("sqlite", ":memory:")
|
|
if err != nil {
|
|
t.Fatalf("open test db: %v", err)
|
|
}
|
|
t.Cleanup(func() { db.Close() })
|
|
return db
|
|
}
|
|
|
|
func TestRunMigrations(t *testing.T) {
|
|
db := openTestDB(t)
|
|
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("runSchema: %v", err)
|
|
}
|
|
|
|
// Verify all tables exist
|
|
tables := []string{
|
|
"conversations",
|
|
"messages",
|
|
"message_parts",
|
|
"summaries",
|
|
"summary_parents",
|
|
"summary_messages",
|
|
"context_items",
|
|
}
|
|
for _, tbl := range tables {
|
|
var name string
|
|
err := db.QueryRow(
|
|
"SELECT name FROM sqlite_master WHERE type='table' AND name=?", tbl,
|
|
).Scan(&name)
|
|
if err != nil {
|
|
t.Errorf("table %q not found: %v", tbl, err)
|
|
}
|
|
}
|
|
|
|
// Verify FTS5 virtual table exists
|
|
var ftsName string
|
|
err := db.QueryRow(
|
|
"SELECT name FROM sqlite_master WHERE type='table' AND name='summaries_fts'",
|
|
).Scan(&ftsName)
|
|
if err != nil {
|
|
t.Errorf("FTS5 table summaries_fts not found: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestRunMigrationsIdempotent(t *testing.T) {
|
|
db := openTestDB(t)
|
|
|
|
// Run migrations twice — should succeed both times
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("first migration: %v", err)
|
|
}
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("second migration (idempotent): %v", err)
|
|
}
|
|
|
|
// Verify we can still insert data after double migration
|
|
res, err := db.Exec(
|
|
"INSERT INTO conversations (session_key, created_at, updated_at) VALUES (?, datetime('now'), datetime('now'))",
|
|
"test-session",
|
|
)
|
|
if err != nil {
|
|
t.Fatalf("insert after double migration: %v", err)
|
|
}
|
|
id, _ := res.LastInsertId()
|
|
if id == 0 {
|
|
t.Error("expected non-zero conversation id")
|
|
}
|
|
}
|
|
|
|
func TestMigrationConversationUnique(t *testing.T) {
|
|
db := openTestDB(t)
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("migration: %v", err)
|
|
}
|
|
|
|
// Insert first
|
|
_, err := db.Exec(
|
|
"INSERT INTO conversations (session_key, created_at, updated_at) VALUES (?, datetime('now'), datetime('now'))",
|
|
"unique-key",
|
|
)
|
|
if err != nil {
|
|
t.Fatalf("first insert: %v", err)
|
|
}
|
|
|
|
// Duplicate should fail
|
|
_, err = db.Exec(
|
|
"INSERT INTO conversations (session_key, created_at, updated_at) VALUES (?, datetime('now'), datetime('now'))",
|
|
"unique-key",
|
|
)
|
|
if err == nil {
|
|
t.Error("expected unique constraint violation for duplicate session_key")
|
|
}
|
|
}
|
|
|
|
func TestMigrationSummaryFTSInsert(t *testing.T) {
|
|
db := openTestDB(t)
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("migration: %v", err)
|
|
}
|
|
|
|
// Insert a conversation first
|
|
_, err := db.Exec(
|
|
"INSERT INTO conversations (session_key, created_at, updated_at) VALUES (?, datetime('now'), datetime('now'))",
|
|
"fts-test",
|
|
)
|
|
if err != nil {
|
|
t.Fatalf("insert conversation: %v", err)
|
|
}
|
|
|
|
// Insert a summary
|
|
_, err = db.Exec(
|
|
`INSERT INTO summaries (summary_id, conversation_id, kind, depth, content, token_count, created_at)
|
|
VALUES ('sum_test1', 1, 'leaf', 0, '你好世界 hello world', 10, datetime('now'))`)
|
|
if err != nil {
|
|
t.Fatalf("insert summary: %v", err)
|
|
}
|
|
|
|
// FTS should find it — trigram tokenizer requires >= 3 chars
|
|
rows, err := db.Query(
|
|
"SELECT summary_id FROM summaries_fts WHERE summaries_fts MATCH ?",
|
|
"你好世",
|
|
)
|
|
if err != nil {
|
|
t.Fatalf("FTS query: %v", err)
|
|
}
|
|
defer rows.Close()
|
|
|
|
var found string
|
|
if rows.Next() {
|
|
if err := rows.Scan(&found); err != nil {
|
|
t.Fatalf("scan: %v", err)
|
|
}
|
|
}
|
|
if err := rows.Err(); err != nil {
|
|
t.Fatalf("rows.Err: %v", err)
|
|
}
|
|
if found != "sum_test1" {
|
|
t.Errorf("FTS: expected 'sum_test1', got %q", found)
|
|
}
|
|
}
|
|
|
|
func TestMigrationSummaryParentsPK(t *testing.T) {
|
|
db := openTestDB(t)
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("migration: %v", err)
|
|
}
|
|
|
|
// Insert two summaries
|
|
for _, id := range []string{"sum_a", "sum_b"} {
|
|
_, err := db.Exec(
|
|
`INSERT INTO summaries (summary_id, conversation_id, kind, depth, content, token_count, created_at)
|
|
VALUES (?, 1, 'leaf', 0, 'content', 5, datetime('now'))`, id)
|
|
if err != nil {
|
|
t.Fatalf("insert summary %s: %v", id, err)
|
|
}
|
|
}
|
|
|
|
// Link child to parent
|
|
_, err := db.Exec(
|
|
"INSERT INTO summary_parents (summary_id, parent_summary_id) VALUES ('sum_a', 'sum_b')")
|
|
if err != nil {
|
|
t.Fatalf("link: %v", err)
|
|
}
|
|
|
|
// Duplicate link should fail (composite PK)
|
|
_, err = db.Exec(
|
|
"INSERT INTO summary_parents (summary_id, parent_summary_id) VALUES ('sum_a', 'sum_b')")
|
|
if err == nil {
|
|
t.Error("expected unique constraint violation for duplicate summary_parents link")
|
|
}
|
|
}
|
|
|
|
func TestFTS5SQLConstants(t *testing.T) {
|
|
db := openTestDB(t)
|
|
|
|
// Verify FTS5 check SQL executes without error
|
|
_, err := db.Exec(sqlCheckFTS5Available)
|
|
if err != nil {
|
|
t.Errorf("sqlCheckFTS5Available failed: %v", err)
|
|
}
|
|
|
|
// Verify trigram check SQL executes without error
|
|
_, err = db.Exec(sqlCheckTrigramAvailable)
|
|
if err != nil {
|
|
t.Errorf("sqlCheckTrigramAvailable failed: %v", err)
|
|
}
|
|
|
|
// Verify summaries_fts SQL executes without error
|
|
_, err = db.Exec(sqlCreateSummariesFTS)
|
|
if err != nil {
|
|
t.Errorf("sqlCreateSummariesFTS failed: %v", err)
|
|
}
|
|
|
|
// Verify messages_fts SQL executes without error
|
|
_, err = db.Exec(sqlCreateMessagesFTS)
|
|
if err != nil {
|
|
t.Errorf("sqlCreateMessagesFTS failed: %v", err)
|
|
}
|
|
}
|