mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
Liu Yuan
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
59 lines
2.0 KiB
Go
59 lines
2.0 KiB
Go
package seahorse
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
)
|
|
|
|
// =============================================================================
|
|
// CompactUntilUnder iteration cap
|
|
// =============================================================================
|
|
|
|
func TestCompactUntilUnderIterationCap(t *testing.T) {
|
|
// Setup: create a conversation with so many tokens that compaction
|
|
// will never reach the budget. The iteration cap prevents infinite loops.
|
|
//
|
|
// We use a mock CompleteFn that always returns the same content,
|
|
// and a budget of 0 which tokens can never reach.
|
|
// Without the cap, this would loop forever.
|
|
|
|
db := openTestDB(t)
|
|
if err := runSchema(db); err != nil {
|
|
t.Fatalf("migration: %v", err)
|
|
}
|
|
s := &Store{db: db}
|
|
|
|
conv, _ := s.GetOrCreateConversation(context.Background(), "agent:iter-cap")
|
|
convID := conv.ConversationID
|
|
|
|
// Add many messages to ensure there's plenty to compact
|
|
for i := 0; i < 40; i++ {
|
|
m, _ := s.AddMessage(context.Background(), convID, "user",
|
|
"this is a long message with lots of tokens to push context over budget", 100)
|
|
s.AppendContextMessage(context.Background(), convID, m.ID)
|
|
}
|
|
|
|
// A completeFn that always succeeds but returns non-reducing content
|
|
mockComplete := func(ctx context.Context, prompt string, opts CompleteOptions) (string, error) {
|
|
return "Summary that doesn't reduce tokens much.", nil
|
|
}
|
|
|
|
ce, cancel := newTestCompactionEngineWithStore(s, mockComplete)
|
|
defer cancel()
|
|
|
|
// Use budget=1 so tokens can never reach budget
|
|
// (each message is 100 tokens, so 40 messages = 4000 tokens, budget 1 is unreachable)
|
|
// The function should stop after maxCompactIterations, not loop forever
|
|
ce.config = Config{} // ensure defaults
|
|
|
|
result, err := ce.CompactUntilUnder(context.Background(), convID, 1)
|
|
if err != nil {
|
|
// Should not error — should stop gracefully
|
|
t.Fatalf("CompactUntilUnder with budget=0: %v", err)
|
|
}
|
|
|
|
// The function should have completed within reasonable time
|
|
// If it exceeded the cap, it would still return (not hang)
|
|
_ = result
|
|
}
|