minovative-mind-cli 1.5.1 → 2.1.0

package/README.md

@@ -16,39 +16,8 @@ the build/performance metrics are green.
 [![Version](https://img.shields.io/npm/v/minovative-mind-cli.svg)](https://npmjs.org/package/minovative-mind-cli)
 [![Downloads/week](https://img.shields.io/npm/dw/minovative-mind-cli.svg)](https://npmjs.org/package/minovative-mind-cli)
 
-- Official Website: [https://www.minovativemind.dev/](https://www.minovativemind.dev/)
-- Latest Updates: [https://www.minovativemind.dev/updates](https://www.minovativemind.dev/updates)
-
----
-
-## How it works
-
-- Standard AI coding agents: big model + noisy context = expensive and redundant mistakes
-- Minovative Mind CLI: flash models + precise context + verified output = better and cheaper results.
-
-### The PCV engine runs in three stages before returning a single line of code:
-
-**1. Investigate**
-
-- **Maps your project:** Traces import dependencies and identifies recently modified files to understand your focus.
-- **Researches context:** Gathers external web documentation and completes background research before touching any code.
-
-**2. Execute with precision**
-
-- **Surgical snapshots:** Feeds the agent a compressed, relevant slice of code instead of dumping the entire codebase.
-- **Higher success rates:** Delivers 40–50% fewer broken generations on large files compared to standard zero-shot prompts.
-
-**3. Verify and self-correct**
-
-- **Runs native builds & audits:** Automatically executes your actual build commands (`npm run build`, `cargo check`, etc.) and scans for performance flaws on modified files only.
-- **Autonomously debugs:** Reads the exact compiler output and fixes its own errors across up to 5 hands-free correction cycles.
-
----
-
-## See it in action
-
-- [AI builds a Python Generative Art Engine in one prompt](https://www.youtube.com/watch?v=dy3qNbETqfs)
-- [AI builds a Quiz Game from scratch](https://www.youtube.com/watch?v=KjE5nbKEf3w)
+- Official Website: [Main Website](https://www.minovativemind.dev/)
+- Latest Updates: [Updates](https://www.minovativemind.dev/updates)
 
 ---
 
@@ -79,9 +48,40 @@ Works in any terminal — SSH, Docker, CI pipelines, Vim, Windows Command Prompt
 
 ---
 
+## See it in action
+
+- [AI builds a Python Generative Art Engine in one prompt](https://www.youtube.com/watch?v=dy3qNbETqfs)
+- [AI builds a Quiz Game from scratch](https://www.youtube.com/watch?v=KjE5nbKEf3w)
+
+### 🏆 Benchmark Tests
+
+**All-Your-Base (C++ Track)**
+
+- **Difficulty:** Hard | **Time:** 3.5 minutes
+- **Result:** 🟢 PASSED (17/17 assertions)
+  - Successfully deduced the O(N+M) conversion algorithm.
+  - Properly handled complex edge cases for zero-equivalents (returning an empty vector).
+  - Encountered a compilation error due to missing C++ standard library paths on macOS.
+  - Autonomously self-corrected by querying the environment, locating the sysroot, and updating clang++ flags.
+  - Flawlessly passed the test suite, handling the problem and edge cases on the first try.
+- [All-Your-Base Summary](https://github.com/Quarantiine/polyglot-benchmark-mmcli/blob/main/cpp/exercises/practice/all-your-base/minovative-tries/attempt_1.md)
+
+**Alphametics (Go Track)**
+
+- **Difficulty:** Extreme | **Time:** 5.2 minutes
+- **Result:** 🟢 PASSED
+  - Solved one of the hardest logic puzzles on the platform by engineering a mathematically rigorous pruning algorithm based on the Rearrangement Inequality.
+  - Completely bypassed naive backtracking (10! permutations).
+  - Achieved sub-millisecond execution speeds (~140 microseconds) with zero heap allocations during recursion.
+  - Autonomously navigated the Go toolchain (\`go test -bench=.\`).
+  - Parsed its own architectural performance warnings to optimize the solution.
+- [Alphametics Summary](https://github.com/Quarantiine/polyglot-benchmark-mmcli/blob/main/go/exercises/practice/alphametics/minovative-tries/attempt_1.md)
+
+---
+
 ## Models
 
-Hot-swap during a session with `/models`:
+Hot-swap during a session using `/models`:
 
 | Model                          | Best for                            |
 | ------------------------------ | ----------------------------------- |
@@ -99,22 +99,36 @@ Hot-swap during a session with `/models`:
 
 ## Session Commands
 
-| Command         | What it does                                          |
-| --------------- | ----------------------------------------------------- |
-| `/models`       | Hot-swap the active model                             |
-| `/chats`        | View, resume, or delete previous chat sessions        |
-| `/revert`       | Instantly undo all changes from the last turn         |
-| `/commit`       | Generate a conventional commit message from your diff |
-| `/auto-approve` | Toggle skipping confirmation prompts for commands     |
-| `/paste`        | Multi-line input mode (cancel with Ctrl+C)            |
-| `/debug`        | Expose internal agent diagnostics                     |
-| `stop`          | Abort generation immediately                          |
+| Command         | What it does                                                     |
+| --------------- | ---------------------------------------------------------------- |
+| `/models`       | Hot-swap the active model                                        |
+| `/plan`         | Toggle plan mode to review implementation strategies             |
+| `/paste`        | Multi-line input mode (cancel with Ctrl+C)                       |
+| `/clear`        | Clear conversation history                                       |
+| `/debug`        | Expose internal agent diagnostics                                |
+| `/auto-approve` | Toggle skipping confirmation prompts for commands                |
+| `/sub-agents`   | Toggle the MMAAK Engine for parallel investigation and execution |
+| `/stats`        | View current session statistics and configuration                |
+| `/commit`       | Generate a conventional commit message from your diff            |
+| `/revert`       | Undo changes from the last turn, or toggle the revert logger     |
+| `/chats`        | View, resume, or delete previous chat sessions                   |
+| `stop`          | Abort generation immediately                                     |
+
+---
+
+## 🌐 Multi-Workspace & Cross-Repo Support
+
+Minovative Mind CLI doesn't restrict you to a single repository. You can link multiple external workspaces to your current session and the AI will seamlessly operate across all of them simultaneously. 
+
+By prefixing file paths with `@alias/` (e.g. `@backend/src/api.ts` and `@frontend/src/App.tsx`), the Context Agent, Thread Agents, and Semantic Search tools can investigate, refactor, and coordinate changes across your entire tech stack in a single prompt. The terminal highlights cross-workspace actions with a blue `[alias]` visual tag. Use the "Edit Workspace" menu option to configure your linked projects.
 
 ---
 
 ## 🌐 Supported Languages
 
-Minovative Mind CLI features deep, context-aware analysis across **11 major programming language families**. Our core engines—**Smart Dependency Tracing**, **Performance Auditing**, and **Ephemeral Analysis Scripts**—provide tailored support depending on the language's syntax and runtime model:
+Minovative Mind CLI fundamentally supports **ALL programming languages** for chat, code generation, planning, and execution, as it relies on Gemini's vast training data.
+
+However, the PCV engine features deep, context-aware analysis across **11 major programming language families**. Our core advanced engines—**Smart Dependency Tracing**, **Performance Auditing**, and **Ephemeral Analysis Scripts**—provide tailored support depending on the language's syntax and runtime model:
 
 | Language Family              | Supported Extensions                         | Dependency Tracing | Performance Auditing | Ephemeral Analysis |
 | :--------------------------- | :------------------------------------------- | :----------------: | :------------------: | :----------------: |

package/dist/commands/chat.js

@@ -23,13 +23,19 @@ export default class DefaultCommand extends Command {
 
 Inside the chat session, you can use the following commands in the slash menu:
   /models        - Select the active model
+  /plan          - Toggle plan mode to review implementation strategies
   /paste         - Enter multi-line paste mode for long snippets
   /clear         - Clear conversation history
   /debug         - Debug tests or command execution in a sandbox loop
   /auto-approve  - Toggle automatic approval of tool/command runs
-  /revert        - Revert the last file modification made by the agent
+  /sub-agents    - Toggle the MMAAK Engine for parallel investigation and execution
+  /semantic-search - Toggle local vector index capabilities
+  /workspaces    - Manage external workspaces for cross-project development
+  /stats         - View current session statistics and configuration
   /commit        - Commit current workspace changes to Git
-
+  /revert        - Revert the last file modification made by the agent
+  /chats         - View, resume, or delete previous chat sessions
+ 
 Chat Controls:
   - Multi-line Input: End a line with \\ to continue on the next line
   - Stop/Abort: Type "stop" to immediately interrupt agent generation
@@ -71,6 +77,8 @@ Chat Controls:
         if (idToken) {
             updateWorkspaceStatus(idToken, workspaceRoot).catch(() => { });
         }
+        const { workspaceRegistry } = await import('../services/workspaceRegistry.js');
+        workspaceRegistry.init();
         await startAgentLoop(workspaceRoot, this.config.version);
     }
 }