Merge pull request tinyhumansai#36 from M3gA-Mind/feat/memory-flow

Feat/memory flow

Author: graycyrus

.claude/mcp.json

@@ -1 +1 @@
-{ "mcpServers": { "alphaHuman": { "type": "http", "url": "https://alphahuman.readme.io/mcp" } } }
+{ "mcpServers": { "alphahuman": { "type": "http", "url": "https://openhuman.readme.io/mcp" } } }

.claude/rules/01-project-overview.md

@@ -58,7 +58,7 @@ This project is a **crypto-focused communication platform** built with Tauri v2,
 ## Project Structure
 
 ```
-frontend-runner-alphahuman/
+frontend-runner-openhuman/
 ├── .claude/                # Claude AI configuration
 │   ├── rules/              # Modular documentation
 │   └── agents/             # Subagent configurations
@@ -86,7 +86,7 @@ frontend-runner-alphahuman/
 
 ## Key Configuration Files
 
-- `tauri.conf.json` - Tauri configuration (app identifier: com.alphahuman.app)
+- `tauri.conf.json` - Tauri configuration (app identifier: com.openhuman.app)
 - `Cargo.toml` - Rust dependencies and workspace configuration
 - `package.json` - Node.js dependencies and scripts
 - `vite.config.ts` - Vite build configuration with Node.js polyfills

.claude/rules/02-development-commands.md

@@ -116,7 +116,7 @@ adb kill-server                  # Stop ADB server
 adb start-server                 # Restart ADB server
 
 # Force stop app on device:
-adb shell am force-stop com.alphahuman.app
+adb shell am force-stop com.openhuman.app
 
 # Kill Gradle daemon if stuck:
 # macOS/Linux:

.claude/rules/13-backend-auth-implementation.md

@@ -24,7 +24,7 @@ Web Browser                    Backend Server                 Desktop App (Tauri
     │<─────────────────────────────│                              │
     │                              │                              │
     │  5. Redirect to              │                              │
-    │     alphahuman://auth?token= │                              │
+    │     openhuman://auth?token= │                              │
     │─────────────────────────────────────────────────────────────>│
     │                              │                              │
     │                              │  6. Rust invoke               │
@@ -58,7 +58,7 @@ Initiates Telegram OAuth. The frontend opens this URL in the system browser.
 2. On callback, validate Telegram user data
 3. Create or find user in database
 4. Generate a short-lived `loginToken` (single-use, 5-minute TTL)
-5. Redirect to `alphahuman://auth?token=<loginToken>`
+5. Redirect to `openhuman://auth?token=<loginToken>`
 
 ### 2. `POST /api/auth/web-complete`
 
@@ -181,7 +181,7 @@ Called by the Tauri Rust command `exchange_token` (NOT browser fetch). Exchanges
 3. **HTTPS only** in production — tokens travel as URL parameters and POST bodies
 4. **Rate limiting** — on `/api/auth/web-complete` and `/auth/desktop-exchange`
 5. **Token entropy** — minimum 256 bits of randomness
-6. **Deep link validation** — the desktop app only processes `alphahuman://auth` paths; ignore unknown paths
+6. **Deep link validation** — the desktop app only processes `openhuman://auth` paths; ignore unknown paths
 7. **Telegram data verification** — validate the `hash` field using your bot token per Telegram docs
 
 ## Implementation Details
@@ -226,14 +226,14 @@ Set `VITE_BACKEND_URL` environment variable for different environments.
 
 ## Frontend Integration Points
 
-| File                                   | Role                                                                                  |
-| -------------------------------------- | ------------------------------------------------------------------------------------- |
-| `src/main.tsx`                         | Lazy-imports and starts the deep link listener                                        |
-| `src/utils/desktopDeepLinkListener.ts` | Parses deep link -> invokes Rust `exchange_token` -> stores session -> navigates      |
-| `src/utils/deeplink.ts`                | Web-side: calls `/api/auth/web-complete` and builds `alphahuman://auth?token=...` URL |
-| `src/utils/config.ts`                  | Backend URL configuration                                                             |
-| `src/pages/Login.tsx`                  | Opens `GET /auth/telegram?platform=desktop` in browser                                |
-| `src-tauri/src/lib.rs`                 | Rust `exchange_token` command using `reqwest` (CORS-free)                             |
+| File                                   | Role                                                                                 |
+| -------------------------------------- | ------------------------------------------------------------------------------------ |
+| `src/main.tsx`                         | Lazy-imports and starts the deep link listener                                       |
+| `src/utils/desktopDeepLinkListener.ts` | Parses deep link -> invokes Rust `exchange_token` -> stores session -> navigates     |
+| `src/utils/deeplink.ts`                | Web-side: calls `/api/auth/web-complete` and builds `openhuman://auth?token=...` URL |
+| `src/utils/config.ts`                  | Backend URL configuration                                                            |
+| `src/pages/Login.tsx`                  | Opens `GET /auth/telegram?platform=desktop` in browser                               |
+| `src-tauri/src/lib.rs`                 | Rust `exchange_token` command using `reqwest` (CORS-free)                            |
 
 ## Phone OTP Flow (Future)
 

.claude/rules/14-deep-link-platform-guide.md

@@ -2,14 +2,14 @@
 
 ## Overview
 
-The `alphahuman://` custom URL scheme is used to hand off authentication from a web browser to the Tauri desktop app. This document covers platform-specific behavior, gotchas, and build requirements discovered during development.
+The `openhuman://` custom URL scheme is used to hand off authentication from a web browser to the Tauri desktop app. This document covers platform-specific behavior, gotchas, and build requirements discovered during development.
 
 ## Scheme Registration
 
 Configured in `src-tauri/tauri.conf.json`:
 
 ```json
-{ "plugins": { "deep-link": { "desktop": { "schemes": ["alphahuman"] } } } }
+{ "plugins": { "deep-link": { "desktop": { "schemes": ["openhuman"] } } } }
 ```
 
 ## macOS
@@ -50,7 +50,7 @@ cp -R src-tauri/target/debug/bundle/macos/tauri-app.app /Applications/
 open /Applications/tauri-app.app
 
 # Test deep link
-open "alphahuman://auth?token=YOUR_TOKEN"
+open "openhuman://auth?token=YOUR_TOKEN"
 ```
 
 ### Cargo Caching Gotcha
@@ -68,9 +68,9 @@ open "alphahuman://auth?token=YOUR_TOKEN"
 - The macOS WebView (WKWebView) caches aggressively
 - Clear caches when debugging stale content:
   ```bash
-  rm -rf ~/Library/WebKit/com.alphahuman.app
-  rm -rf ~/Library/Caches/com.alphahuman.app
-  rm -rf ~/Library/Application\ Support/com.alphahuman.app
+  rm -rf ~/Library/WebKit/com.openhuman.app
+  rm -rf ~/Library/Caches/com.openhuman.app
+  rm -rf ~/Library/Application\ Support/com.openhuman.app
   ```
 
 ### Debug Builds: Secondary Instance Behavior

.claude/rules/16-macos-background-execution.md

@@ -213,8 +213,8 @@ npm run tauri build -- --debug --bundles app
 Clear WebKit cache if needed:
 
 ```bash
-rm -rf ~/Library/WebKit/com.alphahuman.app
-rm -rf ~/Library/Caches/com.alphahuman.app
+rm -rf ~/Library/WebKit/com.openhuman.app
+rm -rf ~/Library/Caches/com.openhuman.app
 ```
 
 ## Configuration Options

.claude/rules/17-skills-memory-inference-flow.md

@@ -31,10 +31,10 @@ Token present
 
 Two Tauri event listeners run continuously:
 
-| Event | What it does |
-|---|---|
-| `skill-state-changed` | Dispatches `setSkillState` into Redux `skillsSlice.skillStates[skillId]` |
-| `runtime:skill-status-changed` | Updates `skillsSlice.skills[skillId].status`; surfaces errors |
+| Event                          | What it does                                                             |
+| ------------------------------ | ------------------------------------------------------------------------ |
+| `skill-state-changed`          | Dispatches `setSkillState` into Redux `skillsSlice.skillStates[skillId]` |
+| `runtime:skill-status-changed` | Updates `skillsSlice.skills[skillId].status`; surfaces errors            |
 
 ---
 
@@ -48,7 +48,8 @@ It is constructed with the user's JWT (`authSlice.token`) and stored as `Arc<Mem
 in `MemoryState` (a `Mutex<Option<MemoryClientRef>>`).
 
 Base URL resolution (in priority order):
-1. `ALPHAHUMAN_BASE_URL` env var
+
+1. `OPENHUMAN_BASE_URL` env var
 2. `TINYHUMANS_BASE_URL` env var
 3. SDK default
 
@@ -109,12 +110,12 @@ Examples: `skill:gmail:user@example.com`, `skill:notion:default`.
 
 **File**: `src-tauri/src/memory/mod.rs`
 
-| Method | SDK call | When used |
-|---|---|---|
-| `store_skill_sync(...)` | `insert_memory` | OAuth complete, periodic sync |
-| `query_skill_context(...)` | `query_memory` | RAG query — fetch relevant chunks for a user question |
-| `recall_skill_context(...)` | `recall_memory` | Recall synthesised summary from Master node |
-| `clear_skill_memory(...)` | `delete_memory` | OAuth revoke / disconnect |
+| Method                      | SDK call        | When used                                             |
+| --------------------------- | --------------- | ----------------------------------------------------- |
+| `store_skill_sync(...)`     | `insert_memory` | OAuth complete, periodic sync                         |
+| `query_skill_context(...)`  | `query_memory`  | RAG query — fetch relevant chunks for a user question |
+| `recall_skill_context(...)` | `recall_memory` | Recall synthesised summary from Master node           |
+| `clear_skill_memory(...)`   | `delete_memory` | OAuth revoke / disconnect                             |
 
 ---
 
@@ -141,16 +142,17 @@ chatSend({ threadId, message, model, authToken, backendUrl, messages, notionCont
 
 Completion events flow back over Tauri events:
 
-| Event | Frontend handler |
-|---|---|
-| `chat:tool_call` | shows active tool indicator |
-| `chat:tool_result` | clears tool indicator |
-| `chat:done` | `dispatch(addInferenceResponse(...))` |
-| `chat:error` | shows error, clears loading state |
+| Event              | Frontend handler                      |
+| ------------------ | ------------------------------------- |
+| `chat:tool_call`   | shows active tool indicator           |
+| `chat:tool_result` | clears tool indicator                 |
+| `chat:done`        | `dispatch(addInferenceResponse(...))` |
+| `chat:error`       | shows error, clears loading state     |
 
 ### 5b. Web/Fallback Path
 
 Used when not running in Tauri (browser). Runs the agentic loop entirely in TypeScript:
+
 - Calls `inferenceApi.createChatCompletion(request)` directly
 - Executes tools via `skillManager.callTool(skillId, toolName, args)`
 - Both paths share the same 5-round `MAX_TOOL_ROUNDS` limit and `{skillId}__{toolName}` naming convention
@@ -215,6 +217,7 @@ Step 6: Agentic loop (max 5 rounds)
 **File**: `src-tauri/src/runtime/qjs_engine.rs` — `call_tool(skill_id, tool_name, args)`
 
 The Rust runtime routes `call_tool` into the running QuickJS/V8 skill instance:
+
 - Serialises `args` as JSON
 - Calls the JS tool handler registered by the skill
 - Returns `ToolCallResult { content: Vec<ToolContent>, is_error: bool }`
@@ -262,14 +265,14 @@ Separately (async, fire-and-forget):
 
 ## Key Files Reference
 
-| File | Role |
-|---|---|
-| `src/providers/SkillProvider.tsx` | Discovery, lifecycle, Redux state sync |
-| `src/pages/Conversations.tsx` | Message send, both code paths, Notion context |
-| `src/services/chatService.ts` | `chatSend()`, `chatCancel()`, `useRustChat()` |
-| `src-tauri/src/commands/chat.rs` | Rust agentic loop, context assembly, tool dispatch |
-| `src-tauri/src/commands/memory.rs` | `recall_memory` Tauri command |
-| `src-tauri/src/memory/mod.rs` | `MemoryClient` wrapping tinyhumansai SDK |
-| `src-tauri/src/runtime/qjs_skill_instance.rs` | Skill sync → memory write triggers |
-| `src-tauri/src/runtime/qjs_engine.rs` | `discover_skills()`, `call_tool()`, `all_tools()` |
-| `skills/skills/*/manifest.json` | Skill metadata (git submodule) |
+| File                                          | Role                                               |
+| --------------------------------------------- | -------------------------------------------------- |
+| `src/providers/SkillProvider.tsx`             | Discovery, lifecycle, Redux state sync             |
+| `src/pages/Conversations.tsx`                 | Message send, both code paths, Notion context      |
+| `src/services/chatService.ts`                 | `chatSend()`, `chatCancel()`, `useRustChat()`      |
+| `src-tauri/src/commands/chat.rs`              | Rust agentic loop, context assembly, tool dispatch |
+| `src-tauri/src/commands/memory.rs`            | `recall_memory` Tauri command                      |
+| `src-tauri/src/memory/mod.rs`                 | `MemoryClient` wrapping tinyhumansai SDK           |
+| `src-tauri/src/runtime/qjs_skill_instance.rs` | Skill sync → memory write triggers                 |
+| `src-tauri/src/runtime/qjs_engine.rs`         | `discover_skills()`, `call_tool()`, `all_tools()`  |
+| `skills/skills/*/manifest.json`               | Skill metadata (git submodule)                     |

.claude/skills-system-troubleshooting.md

@@ -10,7 +10,7 @@ The Skills System is a Python-based plugin architecture that allows AI agents to
 
 - Skills modal shows "Setup Failed" with "Skill process exited with code: 1"
 - Console shows `ModuleNotFoundError: No module named 'pydantic'`
-- Error paths like `/Users/cyrus/alphahuman/skills/skills/telegram/`
+- Error paths like `/Users/cyrus/openhuman/skills/skills/telegram/`
 - Python import failures and subprocess stderr messages
 
 ### Root Cause Analysis
@@ -51,7 +51,7 @@ git submodule init
 git submodule update
 ```
 
-This downloads the skills repository from `https://github.com/alphahumanxyz/skills`.
+This downloads the skills repository from `https://github.com/openhumanxyz/skills`.
 
 #### 2. Create Python Virtual Environment
 
@@ -87,7 +87,7 @@ This installs:
 #### Development vs Production Paths
 
 - **Development**: Skills in git submodule at `./skills/skills/`
-- **Production**: Skills in `~/.alphahuman/skills/`
+- **Production**: Skills in `~/.openhuman/skills/`
 - **Configuration**: `src/lib/skills/paths.ts` handles path resolution
 
 #### Skill Execution Process

.github/pull_request_template.md

@@ -0,0 +1,36 @@
+## Summary
+
+- What changed and why.
+- Keep this to 3-6 bullets focused on user-visible or architecture-impacting changes.
+
+## Problem
+
+- What issue or risk this PR addresses.
+- Include context needed for reviewers to evaluate correctness quickly.
+
+## Solution
+
+- How the implementation solves the problem.
+- Note important design decisions and tradeoffs.
+
+## Testing
+
+- [ ] `yarn -s compile`
+- [ ] `cargo check --manifest-path src-tauri/Cargo.toml`
+- [ ] Other checks run (list commands)
+- [ ] Manual validation completed (list scenarios)
+
+## Impact
+
+- Runtime/platform impact (desktop/mobile/web/CLI), if any.
+- Performance, security, migration, or compatibility implications.
+
+## Breaking Changes
+
+- [ ] None
+- [ ] Yes (describe clearly, including migration steps)
+
+## Related
+
+- Issue(s):
+- Follow-up PR(s)/TODOs:

.github/workflows/build.yml

@@ -27,7 +27,7 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: 24.x
-          cache: "yarn"
+          cache: 'yarn'
 
       - name: Install Rust stable
         uses: dtolnay/rust-toolchain@stable
@@ -39,23 +39,22 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf
 
-      - name: Cache Cargo registry
+      # Skip first 7 lines of Cargo.lock (workspace package version bumps) so the key tracks dependency changes only
+      - name: Cargo.lock fingerprint (deps only)
+        id: cargo-lock-fingerprint
+        shell: bash
+        run: |
+          echo "hash=$(tail -n +8 src-tauri/Cargo.lock | openssl dgst -sha256 | awk '{print $2}')" >> "$GITHUB_OUTPUT"
+
+      - name: Cache Cargo registry and git sources
         uses: actions/cache@v4
         with:
           path: |
             ~/.cargo/registry
             ~/.cargo/git
-          key: ${{ runner.os }}-cargo-${{ hashFiles('src-tauri/Cargo.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-cargo-
-
-      - name: Cache Cargo build artifacts
-        uses: actions/cache@v4
-        with:
-          path: src-tauri/target
-          key: ${{ runner.os }}-cargo-target-${{ hashFiles('src-tauri/Cargo.lock') }}
+          key: ${{ runner.os }}-cargo-registry-${{ steps.cargo-lock-fingerprint.outputs.hash }}
           restore-keys: |
-            ${{ runner.os }}-cargo-target-
+            ${{ runner.os }}-cargo-registry-
 
       - name: Cache node modules
         id: yarn-cache
@@ -74,6 +73,6 @@ jobs:
         run: cd skills && yarn install --frozen-lockfile
 
       - name: Build Tauri app
-        run: yarn tauri build -- --target x86_64-unknown-linux-gnu
+        run: yarn tauri build -- --target x86_64-unknown-linux-gnu -- --bin OpenHuman
         env:
           NODE_ENV: production