claude_memory 0.9.0 → 0.9.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9b42d582ddd17dd325f8048268c889d6c80c1ca9c229732da1a8d619279201af
-  data.tar.gz: 8853caacc212900483a4a3f9939e8261e18f53b886675f01b4c5a5b61a506d26
+  metadata.gz: b6df0a3f58a88c1bbec82ec20e26789d51ad2712408d058337a196c5eac90654
+  data.tar.gz: beb9c2ef59ef6a45430eeb03466e37f6b1f741ef1745b5303a1443b02a7c84b4
 SHA512:
-  metadata.gz: a65038105334c741d26c5e485da7565016ae670ed24f04d4c23b2bb00329d729ee3bfd91cf333ea36ad518937e40e4c95c4d0846bcb423984b0ec683fee59b5a
-  data.tar.gz: d94e2ce5fbd1ed496a0c56f094b7f1fbb01b9eb255c819a95b2ffe6ecf79ea9c1706408fd658b2bcaee19d440a87d45a1185a7e471cb05fc7c003d433d6e5808
+  metadata.gz: '06905bca1f77df5642caf0846cde7394ba9a1baf3c954138383ac39927fcaae2ef097ff79dd3c866e6930fa0eac0d0fb958366bded54a0616d8e356a316e616c'
+  data.tar.gz: 9a8e3c455c20ae616bc239b766e1d4e2aa4c6e5448f494294d9c6a646a8a613428e9b63218624c5cae7e30f389704dd3bee6b788e97a369cb719b115abffddd7

data/.claude/rules/claude_memory.generated.md

@@ -1,7 +1,7 @@
 <!--
   This file is auto-generated by claude-memory.
   Do not edit manually - changes will be overwritten.
-  Generated: 2026-04-15T17:38:20Z
+  Generated: 2026-04-16T17:54:51Z
 -->
 
 # Project Memory
@@ -14,6 +14,14 @@
 
 ## Conventions
 
+- Curated predicate vocabulary has 8 entries: multi-value (convention, decision, architecture, uses_framework, uses_language) and single-value (uses_database, deployment_platform, auth_method). Pruned 7 dead predicates after multi-project survey confirmed zero usage.
+- Before making design changes to schemas, vocabularies, or policies, survey actual usage data across multiple project databases under ~/src/ — single-project analysis can validate wrong assumptions. The uses_framework cardinality bug was only visible across multi-project data.
+- A/B testing memory plugin: use 'claude --bare --mcp-config=/tmp/mcp-test.json -p' with serve-mcp.sh path. --plugin-dir doesn't work with --bare despite docs claiming it should. Architecture/convention/preference questions differentiate best; grep-able and one-shot code-gen questions don't.
+- NullDistiller emits uses_language for language-type entities (added 0.9.0), alongside existing uses_database, uses_framework, deployment_platform. Migration v14 canonicalizes stale predicate names (has_convention → convention, primary_language → uses_language) in existing facts.
+- CLAUDE.md scope-system example text ('this app uses PostgreSQL') causes recurring distiller hallucinations. Reject + re-ingest creates rejection churn because rejection metadata doesn't block re-insertion at content level. Open product gap — workaround: wrap example text in <no-memory> tags.
+- claude-memory restore --predicate NAME recovers facts superseded by obsolete single-value classifications. Uses Jaccard token overlap (threshold 0.5) to distinguish bug-caused supersession from real corrections. Only operates on predicates currently classified multi-value. Opt-in per DB, supports --dry-run.
+- claude-memory reject <id_or_docid> marks facts as rejected and resolves associated open conflicts in a single transaction. Accepts integer fact IDs or 8-char hex docids. memory.reject_fact MCP tool mirrors the CLI.
+- The /release skill automates gem releases in three phases: prepare (version bump across 3 files, bundle install, MCP verify, tests, lint, CHANGELOG check, commit), publish (user-driven: git push + rake release), announce (fix GitHub Latest flags, create gh release from CHANGELOG). Never auto-pushes.
 - Never use Sequel.sqlite for DB reads; this gem only depends on extralite. Use Sequel.connect("extralite://#{db_path}") or SQLiteStore.new. Sequel.sqlite requires the ungem'd sqlite3 adapter and fails at runtime.
 - Two distinct tool_calls tables exist: tool_calls (v3) for transcript-observed Claude Code tool usage, and mcp_tool_calls (v13) for MCP server telemetry. Disjoint purposes, never join.
 - MCP tool-call telemetry is recorded via MCP::Telemetry wrapping Server#handle_tools_call. Writes to mcp_tool_calls table in the project DB. Swallows DB errors so telemetry never breaks a real tool response. Viewable via 'claude-memory stats --tools [--since DAYS]'.
@@ -37,15 +45,69 @@
 
 ## Technical Constraints
 
+- **Uses framework**: rails
+- **Deployment platform**: aws
 - **Uses database**: sqlite
 
 ## Additional Knowledge
 
 ### Architecture
 
+- repo: PredicatePolicy is the single source of truth for predicate vocabulary (POLICIES), cardinality, snapshot section mapping (SECTION_MAP), synonym canonicalization (SYNONYMS), and LLM guidance. tool_definitions.rb, publish.rb, and distill-transcripts.md all derive from PredicatePolicy. Never hardcode predicate names elsewhere.
 - MCP::Tools: Thin 104-line dispatcher that includes 6 handler modules in mcp/handlers/: QueryHandlers, ShortcutHandlers, ContextHandlers, ManagementHandlers, StatsHandlers, SetupHandlers
 - Recall: 94-line facade delegating to @engine (DualEngine or LegacyEngine), both include shared QueryCore module with all store-level query logic
 - SQLiteStore: 386-line CRUD class that includes RetryHandler (retry/connection logic) and SchemaManager (migrations/version sync) modules
 - Embeddings: Pluggable providers via Embeddings.resolve(name, env:). Three providers: tfidf (default), fastembed, api. Duck-typed contract: name, dimensions, generate(text). ENV: CLAUDE_MEMORY_EMBEDDING_PROVIDER
 - Embeddings::DimensionCheck: Pure value object — DimensionCheck.call(store, provider) returns Data.define Result with :fresh/:match/:mismatch status. No side effects; caller decides how to handle mismatch.
 
+
+## Open Conflicts
+
+The following facts are in conflict and need resolution:
+
+- Conflict #12: Fact 21 vs Fact 43
+- Conflict #13: Fact 21 vs Fact 44
+- Conflict #14: Fact 45 vs Fact 46
+- Conflict #15: Fact 45 vs Fact 47
+- Conflict #16: Fact 48 vs Fact 49
+- Conflict #17: Fact 45 vs Fact 50
+- Conflict #18: Fact 21 vs Fact 51
+- Conflict #19: Fact 48 vs Fact 52
+- Conflict #20: Fact 21 vs Fact 53
+- Conflict #21: Fact 21 vs Fact 54
+- Conflict #22: Fact 21 vs Fact 55
+- Conflict #23: Fact 21 vs Fact 56
+- Conflict #24: Fact 21 vs Fact 57
+- Conflict #25: Fact 48 vs Fact 58
+- Conflict #26: Fact 48 vs Fact 59
+- Conflict #27: Fact 48 vs Fact 60
+- Conflict #28: Fact 21 vs Fact 61
+- Conflict #29: Fact 21 vs Fact 62
+- Conflict #30: Fact 21 vs Fact 63
+- Conflict #31: Fact 45 vs Fact 64
+- Conflict #32: Fact 21 vs Fact 65
+- Conflict #33: Fact 21 vs Fact 66
+- Conflict #34: Fact 21 vs Fact 67
+- Conflict #35: Fact 45 vs Fact 68
+- Conflict #36: Fact 45 vs Fact 69
+- Conflict #37: Fact 48 vs Fact 70
+- Conflict #38: Fact 48 vs Fact 71
+- Conflict #39: Fact 21 vs Fact 72
+- Conflict #40: Fact 21 vs Fact 73
+- Conflict #41: Fact 21 vs Fact 74
+- Conflict #42: Fact 21 vs Fact 75
+- Conflict #43: Fact 21 vs Fact 76
+- Conflict #44: Fact 45 vs Fact 77
+- Conflict #45: Fact 45 vs Fact 78
+- Conflict #46: Fact 45 vs Fact 79
+- Conflict #47: Fact 45 vs Fact 80
+- Conflict #48: Fact 45 vs Fact 81
+- Conflict #49: Fact 48 vs Fact 82
+- Conflict #50: Fact 48 vs Fact 83
+- Conflict #51: Fact 48 vs Fact 84
+- Conflict #52: Fact 48 vs Fact 85
+- Conflict #53: Fact 48 vs Fact 86
+- Conflict #54: Fact 48 vs Fact 87
+- Conflict #55: Fact 48 vs Fact 88
+- Conflict #56: Fact 48 vs Fact 89
+- Conflict #57: Fact 48 vs Fact 90

data/.claude/skills/release/SKILL.md

@@ -0,0 +1,168 @@
+---
+name: release
+description: Prepare and publish a new gem release — bumps version across all required files, validates tests/linting/MCP server, commits, and creates the GitHub release. Use this skill when the user says "release", "publish a new version", "bump the version", "cut a release", "prepare for release", "ship it", or any variation of wanting to publish a new gem version. Also use when the user asks about the release process or what steps are needed to release.
+agent: general-purpose
+allowed-tools: Read, Grep, Edit, Write, Bash
+arguments:
+  - name: version
+    description: "The new version number (e.g., '0.10.0'). If omitted, you'll be asked."
+    required: false
+---
+
+# Release Workflow
+
+Automate the full release lifecycle for the ClaudeMemory gem. This workflow was codified from the actual 0.9.0 release process.
+
+The release has three phases: **prepare** (automated), **publish** (user-driven), and **announce** (automated). The middle phase requires user action because it pushes to a shared remote and publishes to RubyGems — destructive operations that must never happen without explicit confirmation.
+
+## Phase 1: Prepare
+
+### Step 1: Determine the new version
+
+If a version was passed as an argument, use it. Otherwise, read the current version from `lib/claude_memory/version.rb` and ask the user what the new version should be.
+
+### Step 2: Find and update all version references
+
+The version lives in exactly three files. Grep to confirm there are no others:
+
+```bash
+grep -rn "CURRENT_VERSION" --include="*.rb" --include="*.json" --include="*.gemspec" . | grep -v "CHANGELOG\|node_modules\|vendor\|\.git/"
+```
+
+Update all three:
+
+1. **`lib/claude_memory/version.rb`** — the `VERSION` constant (canonical source)
+2. **`.claude-plugin/plugin.json`** — the `"version"` field
+3. **`.claude-plugin/marketplace.json`** — the `"version"` field inside the plugins array
+
+If grep reveals any additional hardcoded references, update those too and flag them to the user as something that should be DRYed up.
+
+### Step 3: Update Gemfile.lock
+
+```bash
+bundle install
+```
+
+Verify both `claude_memory (X.Y.Z)` entries in Gemfile.lock match the new version.
+
+### Step 4: Verify MCP server reports the new version
+
+The MCP server reads `ClaudeMemory::VERSION` dynamically. Confirm it picks up the change:
+
+```bash
+echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' | bundle exec claude-memory serve-mcp 2>/dev/null | grep -o '"version":"[^"]*"'
+```
+
+Expected output: `"version":"X.Y.Z"` matching the new version. If it doesn't match, something is wrong with the require chain — investigate before proceeding.
+
+### Step 5: Run the full test suite
+
+```bash
+bundle exec rspec
+```
+
+All tests must pass. Do not proceed with any failures. Fix them first.
+
+### Step 6: Run the linter
+
+```bash
+bundle exec rake standard:fix
+```
+
+Ensure no remaining violations.
+
+### Step 7: Verify CHANGELOG.md
+
+The CHANGELOG should already have a release section written during development (via `/improve`, manual commits, or other workflow). **Do not auto-generate release notes** — they should reflect the actual development narrative.
+
+Check that:
+- The `## [X.Y.Z] - YYYY-MM-DD` section exists with today's date
+- It has Added, Changed, Fixed subsections as appropriate
+- Upgrade Notes are included if there are breaking changes or manual migration steps
+- The `## [Unreleased]` section above it is empty or ready for the next cycle
+
+If the CHANGELOG section is missing or incomplete, **stop and ask the user**. Do not fabricate release notes.
+
+### Step 8: Commit the version bump
+
+```bash
+git add lib/claude_memory/version.rb .claude-plugin/plugin.json .claude-plugin/marketplace.json Gemfile.lock
+git commit -m "[Release] Bump version to X.Y.Z"
+```
+
+Do NOT push yet. Report what was committed and proceed to Phase 2.
+
+## Phase 2: Publish (User-Driven)
+
+This phase involves pushing to a shared remote and publishing to RubyGems. These are **irreversible shared-state operations** — never execute them automatically.
+
+Tell the user:
+
+> Version X.Y.Z is prepared and committed locally. To publish:
+>
+> ```bash
+> git push origin main
+> rake release
+> ```
+>
+> `rake release` will create the git tag, build the gem, and push to RubyGems. Let me know when that's done and I'll create the GitHub release.
+
+Wait for the user to confirm before proceeding to Phase 3.
+
+## Phase 3: Announce
+
+### Step 9: Fix any stale "Latest" flags on GitHub releases
+
+Check current release state:
+
+```bash
+gh release list --limit 5
+```
+
+If an older release is incorrectly marked "Latest" (this happens when releases are created out of order or with `--latest` set manually):
+
+```bash
+gh release edit v<old-version> --latest=false
+```
+
+### Step 10: Create the GitHub release
+
+Extract the release notes from CHANGELOG.md — everything between `## [X.Y.Z]` and the next `## [` heading. Write to a temp file:
+
+```bash
+# Extract the section between the new version header and the next version header
+sed -n '/^## \[X\.Y\.Z\]/,/^## \[/{ /^## \[X\.Y\.Z\]/d; /^## \[/d; p; }' CHANGELOG.md > /tmp/release-notes.md
+```
+
+Create the release:
+
+```bash
+gh release create vX.Y.Z \
+  --title "vX.Y.Z — Short descriptive title" \
+  --latest \
+  --verify-tag \
+  --notes-file /tmp/release-notes.md
+```
+
+The title should capture the theme of the release in a few words (e.g., "Predicate Design Overhaul, Reject/Restore, Telemetry"). Read the CHANGELOG to derive this — don't ask the user unless the theme isn't obvious.
+
+### Step 11: Verify the release
+
+```bash
+gh release list --limit 5
+```
+
+Confirm:
+- The new release appears at the top
+- It's marked "Latest"
+- No older release is incorrectly marked "Latest"
+
+Report the release URL to the user.
+
+## Error Handling
+
+- **Tests fail**: Fix first. Never release with failing tests.
+- **CHANGELOG missing**: Ask the user. Never fabricate release notes.
+- **Version already tagged**: The tag may exist from a prior attempt. Ask the user whether to delete and recreate, or use a different version.
+- **`gh` not available**: Tell the user to create the GitHub release manually, providing the release notes content.
+- **`rake release` fails**: Common causes: not logged into RubyGems, tag already exists, uncommitted changes. Help the user diagnose but don't retry automatically.

data/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
   "plugins": [
     {
       "name": "claude-memory",
-      "version": "0.9.0",
+      "version": "0.9.1",
       "source": "./",
       "description": "Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.",
       "repository": "https://github.com/codenamev/claude_memory"

data/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-memory",
-  "version": "0.9.0",
+  "version": "0.9.1",
   "description": "Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.",
   "author": {
     "name": "Valentino Stoll",

data/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [0.9.1] - 2026-04-16
+
+### Fixed
+
+- MCP server now conforms to JSON-RPC 2.0: notifications (messages without an `id`) never receive a response. Previously, `notifications/initialized` — which Claude Code sends after every handshake — triggered a spurious `Method not found` error frame, causing strict MCP clients to mark the server failed on `/mcp` reconnect after the initial connection.
+
 ## [0.9.0] - 2026-04-16
 
 ### Added

data/lib/claude_memory/mcp/server.rb

@@ -59,8 +59,9 @@ module ClaudeMemory
         rescue JSON::ParserError => e
           send_error(-32700, "Parse error: #{e.message}", 0)
         rescue => e
-          request_id = request&.fetch("id", nil) || 0
-          send_error(-32603, "Internal error: #{e.message}", request_id)
+          # Per JSON-RPC 2.0: never respond to notifications, even on error
+          request_id = request&.fetch("id", nil)
+          send_error(-32603, "Internal error: #{e.message}", request_id) unless request_id.nil?
         end
       end
 
@@ -69,6 +70,11 @@ module ClaudeMemory
         id = request["id"]
         method = request["method"]
 
+        # Per JSON-RPC 2.0: a request without an id is a notification and
+        # MUST NOT receive a response. MCP relies on this for
+        # `notifications/initialized` after the initialize handshake.
+        return nil if id.nil?
+
         case method
         when "initialize"
           handle_initialize(id, request["params"])

data/lib/claude_memory/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ClaudeMemory
-  VERSION = "0.9.0"
+  VERSION = "0.9.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: claude_memory
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.9.1
 platform: ruby
 authors:
 - Valentino Stoll
@@ -89,6 +89,7 @@ files:
 - ".claude/skills/memory-first-workflow"
 - ".claude/skills/quality-update/SKILL.md"
 - ".claude/skills/quality-update/implementation-guide.md"
+- ".claude/skills/release/SKILL.md"
 - ".claude/skills/review-commit/SKILL.md"
 - ".claude/skills/review-for-quality/SKILL.md"
 - ".claude/skills/review-for-quality/expert-checklists.md"