mempalace-code 1.2.0__tar.gz → 1.4.0__tar.gz

{mempalace_code-1.2.0 → mempalace_code-1.4.0}/CHANGELOG.md

@@ -1,5 +1,75 @@
 # Changelog
 
+## v1.4.0 — 2026-04-19
+
+### Added
+- **Watcher quiet mode** — re-mines suppress verbose output; only logs a one-line summary when drawers are actually filed; no-op commits produce zero log noise; optimize skipped on empty batches
+- **Per-project `bin/` skip** — `bin/` no longer globally skipped; only excluded when .NET project markers (`.csproj`, `.sln`, `.fsproj`, `.vbproj`) are present (MINE-BIN-SKIP-DIRS)
+- **Kotlin nested generic receiver** — `fun <T> List<Pair<K,V>>.ext()` now parsed correctly (MINE-KOTLIN-GENERIC-RECEIVER-NESTED)
+- `mine()` now returns stats dict (`files_processed`, `drawers_filed`, `elapsed_secs`)
+
+### Fixed
+- **Watcher on-commit detection** — `watchfiles.DefaultFilter` ignores `.git/` by default; on-commit mode now passes `watch_filter=None` so `.git/refs/heads/` changes are detected
+- **Watcher log buffering** — flush Python stdout/stderr before restoring file descriptors to prevent mine() output leaking to real stdout
+- **HuggingFace/safetensors noise** — suppress BertModel LOAD REPORT and progress bars via OS fd-level redirect during model init
+
+## v1.3.0 — 2026-04-19
+
+First-class C#/.NET support — delivers [rergards/mempalace-code#1](https://github.com/rergards/mempalace-code/issues/1) in full.
+
+### Added
+- **C# structural mining** — parse `.cs` files by namespace, class, interface, enum, record, method, property, event; partial class support, XML doc preservation (MINE-CSHARP)
+- **.NET solution/project awareness** — `.sln` and `.csproj` parsing with project references, package references, target frameworks; queryable via KG (MINE-DOTNET)
+- **F#, VB.NET, XAML mining** — `.fs`/`.fsi`, `.vb`, `.xaml` with structured symbol extraction and code-behind linking (MINE-DOTNET, MINE-XAML, MINE-XAML-NAME-ATTR)
+- **Cross-project symbol relationships** — interface implementations, inheritance, type usage stored as KG triples (DOTNET-SYMBOL-GRAPH)
+- **C# multi-line base-type declarations** — `class Foo :\n    IBar, IBaz` now parsed correctly (DOTNET-CS-MULTILINE-BASE)
+- **6 architecture MCP tools** — `find_implementations`, `find_references`, `show_project_graph`, `show_type_dependencies`, `explain_subsystem`, `extract_reusable` (MCP-ARCH-TOOLS, ARCH-RETRIEVAL, LOGIC-EXTRACTION)
+- **Python type extraction to KG** — class inheritance and ABC/Protocol implementations (PY-TYPE-KG)
+- **`mine-all` command** — batch mine all projects in a parent directory (MINE-MULTI)
+- **`--watch` flag** — auto-incremental re-mining on file changes via watchdog (MINE-WATCH)
+- **Auto-organize by .NET structure** — `.sln` creates wing, `.csproj` maps to room (REPO-STRUCTURE-DEFAULTS)
+- **.NET benchmark suite** — 20-query R@5/R@10 benchmark targeting CleanArchitecture (BENCH-DOTNET)
+
+### Fixed
+- `find_implementations` now includes Python ABC/Protocol subclasses (FIND-IMPL-INHERITS)
+- `.gitignore` patterns respected in `--watch` mode (MINE-WATCH-GITIGNORE-CACHE)
+
+### Stats
+- 27 MCP tools (was 18)
+- 1002 tests (was 527)
+
+## 2026-04-19 · REPO-STRUCTURE-DEFAULTS
+
+Auto-organize wings/rooms by .NET solution/project structure: mining a repo with `.sln` files now creates a wing named after the solution and maps each `.csproj` to a room, using KG project info for defaults and supporting configurable folder-based room detection.
+
+## 2026-04-18 · FIND-IMPL-INHERITS
+
+Fix `mempalace_find_implementations` to include Python ABC/Protocol subclasses: when the queried interface is itself abstract (has an outgoing `implements → ABC/ABCMeta/Protocol` edge), incoming `inherits` triples are now included alongside `implements` triples, so concrete subclasses are returned instead of an empty list.
+
+## 2026-04-18 · MINE-WATCH
+
+Add `--watch` flag to `mempalace mine` for auto-incremental re-indexing: uses `watchdog` to monitor file changes, debounces updates (5s), and only re-indexes modified files — keeping the palace in sync automatically with low CPU overhead when idle.
+
+## 2026-04-18 · PY-TYPE-KG
+
+Add Python type extraction to the knowledge graph in `miner.py`: class inheritance (`class Foo(Bar)` → `extends` triple) and ABC/Protocol implementations are now extracted for Python codebases, making architecture retrieval tools (`find_implementations`, `find_references`, `show_type_dependencies`, `extract_reusable`) functional for Python projects.
+
+## 2026-04-18 · MINE-MULTI
+
+Add `mempalace mine-all <parent-dir>` command for batch multi-project mining: scans immediate subdirectories for project markers (`.git`, `pyproject.toml`, `package.json`, `*.sln`, `go.mod`, `Cargo.toml`, `go.sum`), mines each detected project into its own wing, and reports per-project results with a summary table.
+
+## 2026-04-18 · LOGIC-EXTRACTION
+
+Add `mempalace_extract_reusable` MCP tool: classifies transitive dependencies of a symbol/subsystem as core, platform-specific, or glue, and identifies the minimal public interface needed for safe extraction.
+
+## 2026-04-18 · ARCH-RETRIEVAL
+
+Add `mempalace_explain_subsystem` MCP tool: combines semantic search with KG traversal to answer "how does this subsystem work?" queries, returning entry points, extracted symbols, and expanded relationships.
+
+## 2026-04-18 · MCP-ARCH-TOOLS
+
+Add 4 architecture-oriented MCP tools for .NET type analysis: `mempalace_find_implementations`, `mempalace_find_references`, `mempalace_show_project_graph`, and `mempalace_show_type_dependencies`.
+
 ## 2026-04-17 · SKILLS-HOOKS
 
 Add Claude Code skills and hooks from wh40k workflow: 12 skills (`/start`, `/status`, `/verify`, `/palace-health`, `/task-plan`, `/task-hardening`, `/doc-refresh`, `/ship`, `/release`, `/entropy-gc`, `/mine`, `/bench`), 3 shared modules (mode-classification, task-state, commit-checkpoint), Codex review integration, pre-commit verification gate, and edit logging hooks.

{mempalace_code-1.2.0 → mempalace_code-1.4.0}/CLAUDE.md

@@ -72,7 +72,8 @@ Line length: 100. Target: py39. Quote style: double.
 | `layers.py` | Tiered context loading — L0/L1/L2/L3 wake-up layers for local models |
 | `palace_graph.py` | Graph traversal and tunnel detection across wings/rooms |
 | `mcp_server.py` | MCP server — exposes palace tools to Claude Code and other MCP clients |
-| `cli.py` | `mempalace` CLI entry point — init, mine, search, health, repair, backup |
+| `watcher.py` | File watcher — `watch_and_mine`, `watch_all`, launchd/cron schedule rendering |
+| `cli.py` | `mempalace` CLI entry point — init, mine, mine-all, watch, search, health, repair, backup |
 
 ## Architecture Principles
 

{mempalace_code-1.2.0 → mempalace_code-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mempalace-code
-Version: 1.2.0
+Version: 1.4.0
 Summary: Developer memory tool — mine codebases and conversations into a LanceDB-backed searchable palace. No API key required.
 Project-URL: Homepage, https://github.com/rergards/mempalace-code
 Project-URL: Repository, https://github.com/rergards/mempalace-code
@@ -42,6 +42,8 @@ Requires-Dist: tree-sitter-rust<0.26,>=0.23; extra == 'treesitter'
 Requires-Dist: tree-sitter-typescript<0.26,>=0.23; extra == 'treesitter'
 Requires-Dist: tree-sitter<0.24,>=0.22; (python_version < '3.10') and extra == 'treesitter'
 Requires-Dist: tree-sitter<0.26,>=0.22; (python_version >= '3.10') and extra == 'treesitter'
+Provides-Extra: watch
+Requires-Dist: watchfiles>=1.0; extra == 'watch'
 Description-Content-Type: text/markdown
 
 <div align="center">
@@ -69,13 +71,13 @@ No cloud. No API keys. No subscription. Nothing leaves your machine.
 <table>
 <tr>
 <td align="center"><strong>Tree-sitter AST Parsing</strong><br><sub>Chunks at function boundaries<br>not arbitrary line counts</sub></td>
-<td align="center"><strong>18 MCP Tools</strong><br><sub>Native Claude Code integration<br>search, store, traverse</sub></td>
+<td align="center"><strong>27 MCP Tools</strong><br><sub>Native Claude Code integration<br>search, store, traverse</sub></td>
 <td align="center"><strong>Temporal Knowledge Graph</strong><br><sub>Facts that change over time<br>with validity windows</sub></td>
 </tr>
 <tr>
 <td align="center"><strong>595x Token Savings</strong><br><sub>measured peak · median 80x<br><a href="docs/BENCH_TOKEN_DELTA.md">scales with project size</a></sub></td>
 <td align="center"><strong>Cross-Project Tunnels</strong><br><sub>Search <code>auth</code> in one project<br>find it everywhere</sub></td>
-<td align="center"><strong>848 Tests · $0 Cost</strong><br><sub>Every feature acceptance-gated<br>fully offline after install</sub></td>
+<td align="center"><strong>1008 Tests · $0 Cost</strong><br><sub>Every feature acceptance-gated<br>fully offline after install</sub></td>
 </tr>
 </table>
 
@@ -100,7 +102,7 @@ mempalace mine ~/projects/myapp       # index your codebase
 claude mcp add mempalace -- python -m mempalace.mcp_server  # connect to Claude Code
 ```
 
-This makes the 18 tools available to your AI. For proactive search and storage (without you asking), you'll also need to add usage rules to your `CLAUDE.md` — see [`docs/AGENT_INSTALL.md`](docs/AGENT_INSTALL.md) Section 7.
+This makes the 27 tools available to your AI. For proactive search and storage (without you asking), you'll also need to add usage rules to your `CLAUDE.md` — see [`docs/AGENT_INSTALL.md`](docs/AGENT_INSTALL.md) Section 7.
 
 </details>
 
@@ -137,7 +139,8 @@ You write code. You make decisions. You debug things. Between sessions, all that
 mempalace-code **indexes it once** into a local vector store, then your AI finds it in milliseconds — using [595x fewer tokens](docs/BENCH_TOKEN_DELTA.md) than grep + read at measured peak (median 80x on a 19k-chunk project, and it keeps scaling). Think of it as `git log` for everything that *isn't* in the code: the *why*, the discussions, the dead ends, the decisions.
 
 **What gets indexed:**
-- Code files — functions, classes, modules (Python, TypeScript/JS, Go, Rust, C/C++, Markdown)
+- Code files — functions, classes, modules (Python, TypeScript/JS, Go, Rust, C/C++, C#, F#, VB.NET, XAML, Java, Kotlin, Markdown)
+- .NET solutions — `.sln`/`.csproj` project graphs, cross-project symbol relationships, interface implementations
 - Conversation exports — Claude, ChatGPT, Slack
 - Architecture notes, decisions, anything you store manually
 
@@ -172,10 +175,30 @@ Tree-sitter is optional (`pip install "mempalace-code[treesitter]"`). Without it
 mempalace mine ~/projects/myapp                  # all supported file types
 mempalace mine ~/projects/myapp --wing myapp     # tag with a specific wing
 mempalace mine ~/chats/ --mode convos            # mine conversation exports
+mempalace mine-all ~/projects/                   # batch mine all projects in a directory
 ```
 
 Mining is **incremental** by default — content-hash based, only changed files are re-chunked. Use `--full` to force a rebuild.
 
+### Auto-Watch
+
+Keep your palace in sync automatically. By default, watches `.git/refs/heads/` and re-mines only on **commit** — no noise from work-in-progress saves. Handles multiple branches and worktrees.
+
+```bash
+mempalace watch ~/projects/                      # watch all projects (on commit, default)
+mempalace watch ~/projects/ --on-save            # watch all file saves instead (noisier)
+mempalace watch ~/projects/ schedule             # print launchd/cron snippet for daemon
+```
+
+**Install as persistent daemon (macOS):**
+
+```bash
+mempalace watch ~/projects/ schedule > ~/Library/LaunchAgents/com.mempalace.watch.plist
+launchctl load ~/Library/LaunchAgents/com.mempalace.watch.plist
+```
+
+Starts at login, restarts if crashed. Logs to `/tmp/mempalace-watch.log`.
+
 ---
 
 ### The Palace
@@ -212,7 +235,7 @@ mempalace-code organizes memories into a navigable structure — the same mental
 
 ---
 
-### MCP Server — 18 Tools
+### MCP Server — 27 Tools
 
 ```bash
 claude mcp add mempalace -- python -m mempalace.mcp_server
@@ -257,6 +280,20 @@ claude mcp add mempalace -- python -m mempalace.mcp_server
 
 </details>
 
+<details>
+<summary><strong>Architecture Retrieval</strong></summary>
+
+| Tool | What |
+|------|------|
+| `mempalace_find_implementations` | Find all types implementing a given interface |
+| `mempalace_find_references` | Find all usages of a type (implementors, subclasses, deps) |
+| `mempalace_show_project_graph` | Project-level dependency graph, optionally filtered by solution |
+| `mempalace_show_type_dependencies` | Inheritance/implementation chain (ancestors + descendants) |
+| `mempalace_explain_subsystem` | Explain how a subsystem works: semantic search + KG expansion |
+| `mempalace_extract_reusable` | Classify deps as core/platform/glue; identify extraction boundary |
+
+</details>
+
 <details>
 <summary><strong>Navigation & Diary</strong></summary>
 
@@ -404,7 +441,7 @@ This is a code-first fork of [milla-jovovich/mempalace](https://github.com/milla
 | ChromaDB — [silently deletes data on version bump](https://github.com/milla-jovovich/mempalace/issues/469) | LanceDB — crash-safe Arrow storage, no version-cliff |
 | "No internet after install" — [false](https://github.com/milla-jovovich/mempalace/issues/524) | `mempalace init` downloads model explicitly; fully offline after |
 | "100% R@5" — [unverifiable](https://github.com/milla-jovovich/mempalace/issues/27) | Number removed. Methodology caveats documented |
-| ~30% test coverage | 527 tests, every feature acceptance-gated |
+| ~30% test coverage | 1008 tests, every feature acceptance-gated |
 | No backup, no recovery | `backup` / `restore` / `export` / `import` |
 | No incremental mining | Content-hash incremental: only changed files re-chunked |
 | No code-search | `code_search` — filter by language, symbol, glob |
@@ -476,6 +513,12 @@ mempalace mine <dir>                              # mine code project
 mempalace mine <dir> --wing myapp                 # tag with wing
 mempalace mine <dir> --mode convos                # mine conversations
 mempalace mine <dir> --full                       # force full rebuild
+mempalace mine <dir> --watch                      # auto-incremental on file changes
+mempalace mine-all <parent-dir>                   # batch mine all projects in a directory
+
+# Watch (multi-project auto-sync)
+mempalace watch <parent-dir>                      # watch all initialized projects
+mempalace watch <parent-dir> schedule             # print launchd/cron daemon snippet
 
 # Search
 mempalace search "query"                          # search everything
@@ -529,7 +572,7 @@ Two Claude Code hooks for automatic memory saving:
 mempalace/
 ├── mempalace/
 │   ├── cli.py              ← CLI entry point
-│   ├── mcp_server.py       ← MCP server (18 tools)
+│   ├── mcp_server.py       ← MCP server (27 tools)
 │   ├── storage.py          ← LanceDB vector storage
 │   ├── miner.py            ← language-aware code chunking
 │   ├── convo_miner.py      ← conversation ingest
@@ -540,7 +583,7 @@ mempalace/
 ├── benchmarks/             ← reproducible benchmark runners
 ├── hooks/                  ← Claude Code auto-save hooks
 ├── examples/               ← usage examples
-└── tests/                  ← 527 tests
+└── tests/                  ← 1008 tests
 ```
 
 </details>
@@ -560,7 +603,7 @@ python -m pytest tests/ -x -q    # full suite, all local, no network
 Apache 2.0 — see [LICENSE](LICENSE) and [NOTICE](NOTICE).
 
 <!-- Link Definitions -->
-[version-shield]: https://img.shields.io/badge/version-1.1.1-4dc9f6?style=flat-square&labelColor=0a0e14
+[version-shield]: https://img.shields.io/badge/version-1.4.0-4dc9f6?style=flat-square&labelColor=0a0e14
 [release-link]: https://github.com/rergards/mempalace-code/releases
 [python-shield]: https://img.shields.io/badge/python-3.9+-7dd8f8?style=flat-square&labelColor=0a0e14&logo=python&logoColor=7dd8f8
 [python-link]: https://www.python.org/

{mempalace_code-1.2.0 → mempalace_code-1.4.0}/README.md

@@ -23,13 +23,13 @@ No cloud. No API keys. No subscription. Nothing leaves your machine.
 <table>
 <tr>
 <td align="center"><strong>Tree-sitter AST Parsing</strong><br><sub>Chunks at function boundaries<br>not arbitrary line counts</sub></td>
-<td align="center"><strong>18 MCP Tools</strong><br><sub>Native Claude Code integration<br>search, store, traverse</sub></td>
+<td align="center"><strong>27 MCP Tools</strong><br><sub>Native Claude Code integration<br>search, store, traverse</sub></td>
 <td align="center"><strong>Temporal Knowledge Graph</strong><br><sub>Facts that change over time<br>with validity windows</sub></td>
 </tr>
 <tr>
 <td align="center"><strong>595x Token Savings</strong><br><sub>measured peak · median 80x<br><a href="docs/BENCH_TOKEN_DELTA.md">scales with project size</a></sub></td>
 <td align="center"><strong>Cross-Project Tunnels</strong><br><sub>Search <code>auth</code> in one project<br>find it everywhere</sub></td>
-<td align="center"><strong>848 Tests · $0 Cost</strong><br><sub>Every feature acceptance-gated<br>fully offline after install</sub></td>
+<td align="center"><strong>1008 Tests · $0 Cost</strong><br><sub>Every feature acceptance-gated<br>fully offline after install</sub></td>
 </tr>
 </table>
 
@@ -54,7 +54,7 @@ mempalace mine ~/projects/myapp       # index your codebase
 claude mcp add mempalace -- python -m mempalace.mcp_server  # connect to Claude Code
 ```
 
-This makes the 18 tools available to your AI. For proactive search and storage (without you asking), you'll also need to add usage rules to your `CLAUDE.md` — see [`docs/AGENT_INSTALL.md`](docs/AGENT_INSTALL.md) Section 7.
+This makes the 27 tools available to your AI. For proactive search and storage (without you asking), you'll also need to add usage rules to your `CLAUDE.md` — see [`docs/AGENT_INSTALL.md`](docs/AGENT_INSTALL.md) Section 7.
 
 </details>
 
@@ -91,7 +91,8 @@ You write code. You make decisions. You debug things. Between sessions, all that
 mempalace-code **indexes it once** into a local vector store, then your AI finds it in milliseconds — using [595x fewer tokens](docs/BENCH_TOKEN_DELTA.md) than grep + read at measured peak (median 80x on a 19k-chunk project, and it keeps scaling). Think of it as `git log` for everything that *isn't* in the code: the *why*, the discussions, the dead ends, the decisions.
 
 **What gets indexed:**
-- Code files — functions, classes, modules (Python, TypeScript/JS, Go, Rust, C/C++, Markdown)
+- Code files — functions, classes, modules (Python, TypeScript/JS, Go, Rust, C/C++, C#, F#, VB.NET, XAML, Java, Kotlin, Markdown)
+- .NET solutions — `.sln`/`.csproj` project graphs, cross-project symbol relationships, interface implementations
 - Conversation exports — Claude, ChatGPT, Slack
 - Architecture notes, decisions, anything you store manually
 
@@ -126,10 +127,30 @@ Tree-sitter is optional (`pip install "mempalace-code[treesitter]"`). Without it
 mempalace mine ~/projects/myapp                  # all supported file types
 mempalace mine ~/projects/myapp --wing myapp     # tag with a specific wing
 mempalace mine ~/chats/ --mode convos            # mine conversation exports
+mempalace mine-all ~/projects/                   # batch mine all projects in a directory
 ```
 
 Mining is **incremental** by default — content-hash based, only changed files are re-chunked. Use `--full` to force a rebuild.
 
+### Auto-Watch
+
+Keep your palace in sync automatically. By default, watches `.git/refs/heads/` and re-mines only on **commit** — no noise from work-in-progress saves. Handles multiple branches and worktrees.
+
+```bash
+mempalace watch ~/projects/                      # watch all projects (on commit, default)
+mempalace watch ~/projects/ --on-save            # watch all file saves instead (noisier)
+mempalace watch ~/projects/ schedule             # print launchd/cron snippet for daemon
+```
+
+**Install as persistent daemon (macOS):**
+
+```bash
+mempalace watch ~/projects/ schedule > ~/Library/LaunchAgents/com.mempalace.watch.plist
+launchctl load ~/Library/LaunchAgents/com.mempalace.watch.plist
+```
+
+Starts at login, restarts if crashed. Logs to `/tmp/mempalace-watch.log`.
+
 ---
 
 ### The Palace
@@ -166,7 +187,7 @@ mempalace-code organizes memories into a navigable structure — the same mental
 
 ---
 
-### MCP Server — 18 Tools
+### MCP Server — 27 Tools
 
 ```bash
 claude mcp add mempalace -- python -m mempalace.mcp_server
@@ -211,6 +232,20 @@ claude mcp add mempalace -- python -m mempalace.mcp_server
 
 </details>
 
+<details>
+<summary><strong>Architecture Retrieval</strong></summary>
+
+| Tool | What |
+|------|------|
+| `mempalace_find_implementations` | Find all types implementing a given interface |
+| `mempalace_find_references` | Find all usages of a type (implementors, subclasses, deps) |
+| `mempalace_show_project_graph` | Project-level dependency graph, optionally filtered by solution |
+| `mempalace_show_type_dependencies` | Inheritance/implementation chain (ancestors + descendants) |
+| `mempalace_explain_subsystem` | Explain how a subsystem works: semantic search + KG expansion |
+| `mempalace_extract_reusable` | Classify deps as core/platform/glue; identify extraction boundary |
+
+</details>
+
 <details>
 <summary><strong>Navigation & Diary</strong></summary>
 
@@ -358,7 +393,7 @@ This is a code-first fork of [milla-jovovich/mempalace](https://github.com/milla
 | ChromaDB — [silently deletes data on version bump](https://github.com/milla-jovovich/mempalace/issues/469) | LanceDB — crash-safe Arrow storage, no version-cliff |
 | "No internet after install" — [false](https://github.com/milla-jovovich/mempalace/issues/524) | `mempalace init` downloads model explicitly; fully offline after |
 | "100% R@5" — [unverifiable](https://github.com/milla-jovovich/mempalace/issues/27) | Number removed. Methodology caveats documented |
-| ~30% test coverage | 527 tests, every feature acceptance-gated |
+| ~30% test coverage | 1008 tests, every feature acceptance-gated |
 | No backup, no recovery | `backup` / `restore` / `export` / `import` |
 | No incremental mining | Content-hash incremental: only changed files re-chunked |
 | No code-search | `code_search` — filter by language, symbol, glob |
@@ -430,6 +465,12 @@ mempalace mine <dir>                              # mine code project
 mempalace mine <dir> --wing myapp                 # tag with wing
 mempalace mine <dir> --mode convos                # mine conversations
 mempalace mine <dir> --full                       # force full rebuild
+mempalace mine <dir> --watch                      # auto-incremental on file changes
+mempalace mine-all <parent-dir>                   # batch mine all projects in a directory
+
+# Watch (multi-project auto-sync)
+mempalace watch <parent-dir>                      # watch all initialized projects
+mempalace watch <parent-dir> schedule             # print launchd/cron daemon snippet
 
 # Search
 mempalace search "query"                          # search everything
@@ -483,7 +524,7 @@ Two Claude Code hooks for automatic memory saving:
 mempalace/
 ├── mempalace/
 │   ├── cli.py              ← CLI entry point
-│   ├── mcp_server.py       ← MCP server (18 tools)
+│   ├── mcp_server.py       ← MCP server (27 tools)
 │   ├── storage.py          ← LanceDB vector storage
 │   ├── miner.py            ← language-aware code chunking
 │   ├── convo_miner.py      ← conversation ingest
@@ -494,7 +535,7 @@ mempalace/
 ├── benchmarks/             ← reproducible benchmark runners
 ├── hooks/                  ← Claude Code auto-save hooks
 ├── examples/               ← usage examples
-└── tests/                  ← 527 tests
+└── tests/                  ← 1008 tests
 ```
 
 </details>
@@ -514,7 +555,7 @@ python -m pytest tests/ -x -q    # full suite, all local, no network
 Apache 2.0 — see [LICENSE](LICENSE) and [NOTICE](NOTICE).
 
 <!-- Link Definitions -->
-[version-shield]: https://img.shields.io/badge/version-1.1.1-4dc9f6?style=flat-square&labelColor=0a0e14
+[version-shield]: https://img.shields.io/badge/version-1.4.0-4dc9f6?style=flat-square&labelColor=0a0e14
 [release-link]: https://github.com/rergards/mempalace-code/releases
 [python-shield]: https://img.shields.io/badge/python-3.9+-7dd8f8?style=flat-square&labelColor=0a0e14&logo=python&logoColor=7dd8f8
 [python-link]: https://www.python.org/