mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-05 23:03:55 +00:00
5c2685c7b6
* feat(leann-phase2): implement hybrid vector storage and graph-based search
- [x] Add AST-aware code chunking for Go, Python, and TypeScript using tree-sitter
- [x] Implement LEANN-inspired hybrid vector storage with hub detection and selective embedding storage (60-80% savings)
- [x] Add observation relationship graph with CSR format and edge detection (file overlap, semantic similarity, temporal, concept)
- [x] Implement graph-aware search with two-level traversal and relationship-based ranking
- [x] Add auto-tuning system for dynamic hub threshold adjustment based on query performance
- [x] Add comprehensive metrics tracking for vector storage, queries, latency, and graph traversals
- [x] Update configuration system with graph and hybrid storage settings
- [x] Add graph stats and vector metrics endpoints to worker service
- [x] Enhance UI sidebar with advanced metrics display and graph visualization
- [x] Optimize struct field alignment throughout codebase for memory efficiency
- [x] Update documentation with LEANN Phase 2 features and performance benefits
- [x] Add tree-sitter dependency for AST parsing
* fix: add fts5 build tag to CI workflow
Pass build-tags: "fts5" to shared workflow to properly compile
sqlite-vec-go-bindings with SQLite FTS5 support.
This fixes test failures in hybrid vector storage tests that require
CGO and FTS5 build tags.
Requires shared-actions@8f7f235 or later.
* docs: add testing documentation and macOS ARM64 known issue
Document the macOS ARM64 CGO linking issue with sqlite-vec-go-bindings
that prevents hybrid package tests from compiling locally.
Added:
- .github/TESTING.md: Comprehensive testing guide with platform-specific
issues, workarounds, and CI configuration details
- internal/vector/hybrid/README.md: Package-specific documentation
explaining the macOS limitation
- .github/CI_FIX_SUMMARY.md: Technical details of the CI fix
Key points:
- 41 out of 42 packages test successfully on all platforms
- hybrid package tests fail only on macOS ARM64 (local dev issue)
- Linux CI tests pass with proper build-tags: "fts5" configuration
- Production builds and runtime functionality unaffected
This is a known limitation of sqlite-vec-go-bindings on macOS ARM64
and does not impact CI/CD or production deployments.
* fix: add SQLite busy_timeout to prevent database locked errors
Set PRAGMA busy_timeout=5000 (5 seconds) to allow SQLite to retry
when the database is locked instead of failing immediately.
This fixes race conditions when multiple goroutines try to write
simultaneously, particularly in tests where StoreObservation spawns
async cleanup goroutines.
Root cause:
- StoreObservation launches goroutine -> CleanupOldObservations
- Multiple concurrent cleanups caused "database is locked" errors
- Without busy_timeout, SQLite fails immediately on lock contention
Solution:
- Add 5-second busy timeout for automatic retry on lock
- Standard practice for concurrent SQLite usage
- Works with existing WAL mode configuration
Fixes TestObservationStore_CleanupOldObservations in CI.
* docs: complete summary of all CI test fixes
Comprehensive documentation of all fixes applied:
1. Missing build tags (fts5)
2. Database locked errors (busy_timeout)
All 41/42 packages now pass tests. The hybrid package has a known
macOS ARM64 limitation that doesn't affect CI or production.
No functionality was removed - all fixes are additive only.
* fix: add SQLite driver import to hybrid tests for CGO linking
Add blank import of mattn/go-sqlite3 to hybrid test files to ensure
the SQLite driver is linked into the test binary. This provides the
SQLite symbols that sqlite-vec-go-bindings requires.
Root cause:
- hybrid package imports sqlitevec (transitively depends on sqlite-vec CGO)
- Test binary needs SQLite symbols for linking
- sqlitevec tests already had this import, but hybrid tests didn't
- Without the driver import, linker fails with "undefined symbols"
This fix enables hybrid tests to run with -race flag on all platforms.
Before: 41/42 packages pass (hybrid failed to link)
After: 42/42 packages pass ✅
Fixes hybrid test compilation on macOS ARM64, Linux, and Windows.
* docs: remove outdated macOS limitation documentation
The hybrid test linking issue has been fixed by adding the SQLite
driver import. All tests now pass on all platforms including macOS.
Removed:
- internal/vector/hybrid/README.md (documented workaround no longer needed)
- .github/TESTING.md (macOS limitation section obsolete)
All 42/42 packages now test successfully with -race flag.
* docs: final comprehensive summary of all CI fixes
All three issues now resolved:
1. Missing fts5 build tags
2. Database busy_timeout for concurrent writes
3. Missing SQLite driver import in hybrid tests
Result: 42/42 packages pass with -race on all platforms.
Credit to reviewer for identifying the race detector concern.
118 lines
4.5 KiB
Go
118 lines
4.5 KiB
Go
// Package sdk provides SDK agent integration for claude-mnemonic.
|
|
package sdk
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// ObservationTypes defines valid observation types.
|
|
var ObservationTypes = []string{"bugfix", "feature", "refactor", "change", "discovery", "decision"}
|
|
|
|
// ObservationConcepts defines valid observation concepts.
|
|
var ObservationConcepts = []string{
|
|
"how-it-works",
|
|
"why-it-exists",
|
|
"what-changed",
|
|
"problem-solution",
|
|
"gotcha",
|
|
"pattern",
|
|
"trade-off",
|
|
}
|
|
|
|
// ToolExecution represents a tool execution for observation.
|
|
type ToolExecution struct {
|
|
ToolName string
|
|
ToolInput string
|
|
ToolOutput string
|
|
CWD string
|
|
ID int64
|
|
CreatedAtEpoch int64
|
|
}
|
|
|
|
// BuildObservationPrompt builds a prompt for processing a tool observation.
|
|
func BuildObservationPrompt(exec ToolExecution) string {
|
|
// Safely parse tool_input and tool_output
|
|
var toolInput interface{}
|
|
var toolOutput interface{}
|
|
|
|
if err := json.Unmarshal([]byte(exec.ToolInput), &toolInput); err != nil {
|
|
toolInput = exec.ToolInput
|
|
}
|
|
|
|
if err := json.Unmarshal([]byte(exec.ToolOutput), &toolOutput); err != nil {
|
|
toolOutput = exec.ToolOutput
|
|
}
|
|
|
|
inputJSON, _ := json.MarshalIndent(toolInput, " ", " ")
|
|
outputJSON, _ := json.MarshalIndent(toolOutput, " ", " ")
|
|
|
|
timestamp := time.UnixMilli(exec.CreatedAtEpoch).Format(time.RFC3339)
|
|
|
|
var sb strings.Builder
|
|
sb.WriteString("<observed_from_primary_session>\n")
|
|
sb.WriteString(fmt.Sprintf(" <what_happened>%s</what_happened>\n", exec.ToolName))
|
|
sb.WriteString(fmt.Sprintf(" <occurred_at>%s</occurred_at>\n", timestamp))
|
|
if exec.CWD != "" {
|
|
sb.WriteString(fmt.Sprintf(" <working_directory>%s</working_directory>\n", exec.CWD))
|
|
}
|
|
sb.WriteString(fmt.Sprintf(" <parameters>%s</parameters>\n", truncate(string(inputJSON), 3000)))
|
|
sb.WriteString(fmt.Sprintf(" <outcome>%s</outcome>\n", truncate(string(outputJSON), 5000)))
|
|
sb.WriteString("</observed_from_primary_session>")
|
|
|
|
return sb.String()
|
|
}
|
|
|
|
// SummaryRequest contains data for building a summary prompt.
|
|
type SummaryRequest struct {
|
|
SDKSessionID string
|
|
Project string
|
|
UserPrompt string
|
|
LastUserMessage string
|
|
LastAssistantMessage string
|
|
SessionDBID int64
|
|
}
|
|
|
|
// BuildSummaryPrompt builds a prompt requesting a session summary.
|
|
func BuildSummaryPrompt(req SummaryRequest) string {
|
|
var sb strings.Builder
|
|
|
|
sb.WriteString("PROGRESS SUMMARY CHECKPOINT\n")
|
|
sb.WriteString("===========================\n")
|
|
sb.WriteString("Write progress notes of what was done, what was learned, and what's next. This is a checkpoint to capture progress so far. The session is ongoing - you may receive more requests and tool executions after this summary. Write \"next_steps\" as the current trajectory of work (what's actively being worked on or coming up next), not as post-session future work. Always write at least a minimal summary explaining current progress, even if work is still in early stages, so that users see a summary output tied to each request.\n\n")
|
|
|
|
if req.LastAssistantMessage != "" {
|
|
sb.WriteString("Claude's Full Response to User:\n")
|
|
sb.WriteString(truncate(req.LastAssistantMessage, 4000))
|
|
sb.WriteString("\n\n")
|
|
}
|
|
|
|
sb.WriteString(`Respond in this XML format:
|
|
<summary>
|
|
<request>[Short title capturing the user's request AND the substance of what was discussed/done]</request>
|
|
<investigated>[What has been explored so far? What was examined?]</investigated>
|
|
<learned>[What have you learned about how things work?]</learned>
|
|
<completed>[What work has been completed so far? What has shipped or changed?]</completed>
|
|
<next_steps>[What are you actively working on or planning to work on next in this session?]</next_steps>
|
|
<notes>[Additional insights or observations about the current progress]</notes>
|
|
</summary>
|
|
|
|
IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.
|
|
|
|
Never reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.
|
|
|
|
Thank you, this summary will be very useful for keeping track of our progress!`)
|
|
|
|
return sb.String()
|
|
}
|
|
|
|
// truncate truncates a string to the specified length.
|
|
func truncate(s string, maxLen int) string {
|
|
if len(s) <= maxLen {
|
|
return s
|
|
}
|
|
return s[:maxLen] + "... (truncated)"
|
|
}
|