mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +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
130 lines
3.4 KiB
Go
130 lines
3.4 KiB
Go
package seahorse
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
|
|
"github.com/sipeed/picoclaw/pkg/tools"
|
|
)
|
|
|
|
// ExpandTool recovers full message content by ID.
|
|
type ExpandTool struct {
|
|
engine *RetrievalEngine
|
|
}
|
|
|
|
func NewExpandTool(engine *RetrievalEngine) *ExpandTool {
|
|
return &ExpandTool{engine: engine}
|
|
}
|
|
|
|
func (t *ExpandTool) Name() string {
|
|
return "short_expand"
|
|
}
|
|
|
|
func (t *ExpandTool) Description() string {
|
|
return `Get full message content by ID.
|
|
|
|
Use when short_grep returns messages and you need complete content (not just snippet).
|
|
|
|
Parameters:
|
|
- message_ids (required): Array of message ID strings (from short_grep results)
|
|
|
|
Returns message with:
|
|
- content: Full text content
|
|
- parts: Structured content
|
|
- text: Full text
|
|
- tool_use: name, arguments, toolCallId
|
|
- tool_result: toolCallId only (content omitted - re-run tool if needed)
|
|
- media: mediaUri (file path), mimeType
|
|
|
|
Notes:
|
|
- tool_result content is not returned (can be large). Re-run the tool if you need the result.
|
|
- Media files are stored on disk at mediaUri path, use bash to access.
|
|
|
|
Example:
|
|
{"message_ids": ["10", "25"]}`
|
|
}
|
|
|
|
func (t *ExpandTool) Parameters() map[string]any {
|
|
return map[string]any{
|
|
"type": "object",
|
|
"properties": map[string]any{
|
|
"message_ids": map[string]any{
|
|
"type": "array",
|
|
"items": map[string]any{"type": "string"},
|
|
"description": "Message IDs to expand (from short_grep results, e.g., [\"10\", \"25\"])",
|
|
},
|
|
},
|
|
"required": []string{"message_ids"},
|
|
}
|
|
}
|
|
|
|
func (t *ExpandTool) Execute(ctx context.Context, args map[string]any) *tools.ToolResult {
|
|
idsRaw, ok := args["message_ids"].([]any)
|
|
if !ok || len(idsRaw) == 0 {
|
|
return tools.ErrorResult(
|
|
"Missing required 'message_ids' argument. " +
|
|
"Example: {\"message_ids\": [\"10\", \"25\"]}")
|
|
}
|
|
|
|
// Parse message IDs
|
|
messageIDs := make([]int64, 0, len(idsRaw))
|
|
for _, id := range idsRaw {
|
|
switch v := id.(type) {
|
|
case string:
|
|
var n int64
|
|
if _, err := fmt.Sscanf(v, "%d", &n); err != nil {
|
|
return tools.ErrorResult(fmt.Sprintf("Invalid message_id %q: %v", v, err))
|
|
}
|
|
messageIDs = append(messageIDs, n)
|
|
case float64:
|
|
messageIDs = append(messageIDs, int64(v))
|
|
}
|
|
}
|
|
|
|
result, err := t.engine.ExpandMessages(ctx, messageIDs)
|
|
if err != nil {
|
|
return tools.ErrorResult("Expand failed: " + err.Error())
|
|
}
|
|
|
|
// Build response with filtered parts
|
|
messages := make([]map[string]any, 0, len(result.Messages))
|
|
for _, msg := range result.Messages {
|
|
parts := make([]map[string]any, 0, len(msg.Parts))
|
|
for _, p := range msg.Parts {
|
|
part := map[string]any{"type": p.Type}
|
|
switch p.Type {
|
|
case "text":
|
|
part["text"] = p.Text
|
|
case "tool_use":
|
|
part["name"] = p.Name
|
|
part["arguments"] = p.Arguments
|
|
part["toolCallId"] = p.ToolCallID
|
|
case "tool_result":
|
|
// Omit content - can be large, re-run tool if needed
|
|
part["toolCallId"] = p.ToolCallID
|
|
case "media":
|
|
part["mediaUri"] = p.MediaURI
|
|
part["mimeType"] = p.MimeType
|
|
}
|
|
parts = append(parts, part)
|
|
}
|
|
|
|
messages = append(messages, map[string]any{
|
|
"id": fmt.Sprintf("%d", msg.ID),
|
|
"role": msg.Role,
|
|
"content": msg.Content,
|
|
"parts": parts,
|
|
"conversationId": msg.ConversationID,
|
|
})
|
|
}
|
|
|
|
output := map[string]any{
|
|
"success": true,
|
|
"tokenCount": result.TokenCount,
|
|
"messages": messages,
|
|
}
|
|
data, _ := json.Marshal(output)
|
|
return tools.NewToolResult(string(data))
|
|
}
|