feat: Sleep Agent Pipeline with StatusLine and Context Improvements

.github/workflows/claude-code-review.yml

@@ -29,7 +29,7 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          fetch-depth: 1
+          fetch-depth: 0  # Full history for better context
 
       - name: Run Claude Code Review
         id: claude-review
@@ -40,18 +40,54 @@ jobs:
             REPO: ${{ github.repository }}
             PR NUMBER: ${{ github.event.pull_request.number }}
 
-            Please review this pull request and provide feedback on:
-            - Code quality and best practices
-            - Potential bugs or issues
-            - Performance considerations
-            - Security concerns
-            - Test coverage
+            ## Multi-Agent Code Review with Confidence Scoring
 
-            Use the repository's CLAUDE.md for guidance on style and conventions. Be constructive and helpful in your feedback.
+            Perform a comprehensive code review from multiple perspectives. For each finding,
+            assign a confidence score (0-100) based on evidence strength.
 
-            Use `gh pr comment` with your Bash tool to leave your review as a comment on the PR.
+            ### Review Perspectives
+
+            1. **Compliance Agent**: Check adherence to CLAUDE.md guidelines
+               - Verify code follows project conventions
+               - Check if changes respect Allow/Deny List boundaries
+
+            2. **Bug Detection Agent**: Identify potential bugs
+               - Logic errors, edge cases, null/undefined handling
+               - Race conditions, async issues
+
+            3. **Performance Agent**: Spot performance issues
+               - N+1 queries, unnecessary iterations
+               - Memory leaks, blocking operations
+
+            4. **Security Agent**: Find security vulnerabilities
+               - Input validation, injection risks
+               - Credential exposure, auth bypasses
+
+            5. **Context Agent**: Analyze git history for context
+               - Review commit messages for intent
+               - Check if changes align with PR description
+
+            ### Output Format
+
+            Only report findings with confidence >= 80. Format each finding as:
+
+            ```
+            ### [Category] Finding Title
+            **Confidence**: XX/100
+            **File**: path/to/file.ts:line
+            **Issue**: Description of the problem
+            **Suggestion**: How to fix it
+            ```
+
+            ### Summary Section
+
+            End with a summary:
+            - Total findings by category
+            - Overall code quality assessment (1-10)
+            - Recommendation: APPROVE, REQUEST_CHANGES, or COMMENT
+
+            Use `gh pr comment` with your Bash tool to post the review.
 
           # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           # or https://docs.claude.com/en/docs/claude-code/cli-reference for available options
           claude_args: '--allowed-tools "Bash(gh issue view:*),Bash(gh search:*),Bash(gh issue list:*),Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh pr list:*)"'
-

.github/workflows/self-healing-ci.yml

@@ -0,0 +1,148 @@
+name: Self-Healing CI (YOLO Push)
+
+# Trigger when lint/type-check workflows fail
+on:
+  workflow_run:
+    workflows: ["CI"]  # Update this to match your CI workflow name
+    types: [completed]
+    branches: [main, dev, "feature/*"]
+
+jobs:
+  auto-fix:
+    # Only run on failure, skip if already a retry
+    if: |
+      github.event.workflow_run.conclusion == 'failure' &&
+      !contains(github.event.workflow_run.head_commit.message, '[auto-fix]')
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+      issues: read
+      id-token: write
+      actions: read
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.workflow_run.head_branch }}
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Get failed workflow logs
+        id: get-logs
+        run: |
+          # Fetch the failed workflow run logs
+          gh run view ${{ github.event.workflow_run.id }} --log-failed > /tmp/failed-logs.txt 2>&1 || true
+          echo "logs_file=/tmp/failed-logs.txt" >> $GITHUB_OUTPUT
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Run Claude Auto-Fix
+        id: claude-fix
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          prompt: |
+            ## Self-Healing CI: Auto-Fix Mode
+
+            The CI workflow failed. Analyze the error and fix it if allowed.
+
+            ### Failed Workflow Logs
+            Check the file at /tmp/failed-logs.txt for error details.
+
+            ### STRICT BOUNDARIES (from CLAUDE.md)
+
+            ✅ **ALLOWED to auto-fix:**
+            - ESLint errors and warnings
+            - Prettier formatting issues
+            - TypeScript type errors
+            - Unused imports, import ordering
+            - Spelling errors (cspell)
+            - Missing peer dependencies
+
+            ❌ **NEVER auto-fix (escalate to human):**
+            - Security-related code
+            - Database logic (src/services/sqlite/)
+            - Hook execution flow (src/hooks/*.ts)
+            - API design changes
+            - Architecture/pattern changes
+            - Privacy tag handling (src/utils/tag-stripping.ts)
+            - Business logic changes
+
+            ### Instructions
+
+            1. Read /tmp/failed-logs.txt to understand the failure
+            2. Determine if the error is in the ALLOWED category
+            3. If ALLOWED:
+               - Make the minimal fix required
+               - Stage changes with `git add`
+               - DO NOT commit (the workflow will handle it)
+               - Output: "FIX_APPLIED=true"
+            4. If NOT ALLOWED or unclear:
+               - Output: "FIX_APPLIED=false"
+               - Explain why human review is needed
+
+            Be conservative. When in doubt, escalate to human review.
+
+          claude_args: '--allowed-tools "Bash(git add:*),Bash(git diff:*),Bash(git status:*),Bash(npm run lint:*),Bash(npm run format:*),Bash(npm run typecheck:*),Bash(cat:*),Read,Edit,Write,Glob,Grep"'
+
+      - name: Check if fix was applied
+        id: check-fix
+        run: |
+          if git diff --staged --quiet; then
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push fix
+        if: steps.check-fix.outputs.has_changes == 'true'
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+          # Create commit with [auto-fix] tag to prevent infinite loops
+          git commit -m "[auto-fix] CI: Auto-fix lint/type errors
+
+          Automated fix applied by YOLO Push workflow.
+          Original failure: ${{ github.event.workflow_run.id }}
+
+          🤖 Generated with Claude Code"
+
+          git push
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create issue if fix not possible
+        if: steps.check-fix.outputs.has_changes == 'false'
+        run: |
+          gh issue create \
+            --title "🔴 CI Failure Requires Human Review" \
+            --body "## CI Auto-Fix Failed
+
+          The self-healing CI could not automatically fix this failure.
+
+          **Failed Workflow:** ${{ github.event.workflow_run.html_url }}
+          **Branch:** ${{ github.event.workflow_run.head_branch }}
+          **Commit:** ${{ github.event.workflow_run.head_sha }}
+
+          ### Reason
+          The error is either:
+          - In a protected area (see Deny List in CLAUDE.md)
+          - Too complex for automatic resolution
+          - Requires architectural decisions
+
+          Please review and fix manually."
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -30,4 +30,6 @@ src/ui/viewer.html
 
 # Prevent other malformed path directories
 http*/
-https*/
+https*/Hex/
+Tok/
+integration_test/

.serena/.gitignore

@@ -0,0 +1 @@
+/cache

.serena/project.yml

@@ -0,0 +1,84 @@
+# list of languages for which language servers are started; choose from:
+#   al               bash             clojure          cpp              csharp           csharp_omnisharp
+#   dart             elixir           elm              erlang           fortran          go
+#   haskell          java             julia            kotlin           lua              markdown
+#   nix              perl             php              python           python_jedi      r
+#   rego             ruby             ruby_solargraph  rust             scala            swift
+#   terraform        typescript       typescript_vts   yaml             zig
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+# Special requirements:
+#   - csharp: Requires the presence of a .sln file in the project folder.
+# When using multiple languages, the first language server that supports a given file will be used for that file.
+# The first language is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+languages:
+- typescript
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# whether to use the project's gitignore file to ignore files
+# Added on 2025-04-07
+ignore_all_files_in_gitignore: true
+
+# list of additional paths to ignore
+# same syntax as gitignore, so you can use * and **
+# Was previously called `ignored_dirs`, please update your config if you are using that.
+# Added (renamed) on 2025-04-07
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details.
+# Below is the complete list of tools for convenience.
+# To make sure you have the latest list of tools, and to view their descriptions, 
+# execute `uv run scripts/print_tool_overview.py`.
+#
+#  * `activate_project`: Activates a project by name.
+#  * `check_onboarding_performed`: Checks whether project onboarding was already performed.
+#  * `create_text_file`: Creates/overwrites a file in the project directory.
+#  * `delete_lines`: Deletes a range of lines within a file.
+#  * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
+#  * `execute_shell_command`: Executes a shell command.
+#  * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
+#  * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
+#  * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
+#  * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
+#  * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
+#  * `initial_instructions`: Gets the initial instructions for the current project.
+#     Should only be used in settings where the system prompt cannot be set,
+#     e.g. in clients you have no control over, like Claude Desktop.
+#  * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
+#  * `insert_at_line`: Inserts content at a given line in a file.
+#  * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
+#  * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
+#  * `list_memories`: Lists memories in Serena's project-specific memory store.
+#  * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
+#  * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
+#  * `read_file`: Reads a file within the project directory.
+#  * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
+#  * `remove_project`: Removes a project from the Serena configuration.
+#  * `replace_lines`: Replaces a range of lines within a file with new content.
+#  * `replace_symbol_body`: Replaces the full definition of a symbol.
+#  * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
+#  * `search_for_pattern`: Performs a search for a pattern in the project.
+#  * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
+#  * `switch_modes`: Activates modes by providing a list of their names
+#  * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
+#  * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
+#  * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
+#  * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
+excluded_tools: []
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+project_name: "claude-mem"
+included_optional_tools: []

CLAUDE.md

@@ -29,6 +29,27 @@ Claude-mem is a Claude Code plugin providing persistent memory across sessions.
 npm run build-and-sync        # Build, sync to marketplace, restart worker
 ```
 
+## Version Management
+
+Switch between stable and development versions to avoid instability during active development.
+
+```bash
+npm run version:status        # Show current branch, installed version, cached versions
+npm run version:stable        # Switch to main branch (stable)
+npm run version:dev           # Switch to dev branch (auto-stashes changes)
+```
+
+**Workflow**:
+- When your local version is stable, stay on that branch
+- Use `version:stable` to quickly rollback if updates cause issues
+- The script handles worker restart and git stash automatically
+
+**Local Settings Preservation**: `sync-marketplace` preserves these files during sync:
+- `/.mcp.json` - MCP server configuration
+- `/local/` - User customizations directory
+- `*.local.*` - Any file with .local. in name
+- `/.env.local` - Local environment variables
+
 ## Configuration
 
 Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created with defaults on first run.
@@ -88,3 +109,37 @@ This architecture preserves the open-source nature of the project while enabling
 ## Important
 
 No need to edit the changelog ever, it's generated automatically.
+
+## AI Auto-Fix Boundaries (YOLO Push)
+
+Define the scope of what AI can autonomously fix in CI pipelines.
+
+### ✅ Allow List (Auto-fix permitted)
+
+These mechanical issues can be fixed automatically without human review:
+
+- **Linting**: ESLint errors and warnings
+- **Formatting**: Prettier formatting issues
+- **Types**: TypeScript type errors (missing types, type mismatches)
+- **Imports**: Unused imports, import ordering, missing imports for used symbols
+- **Spelling**: Variable/function name typos caught by cspell
+- **Dependencies**: Missing peer dependencies in package.json
+
+### ❌ Deny List (Human review required)
+
+These areas require human judgment and must NOT be auto-fixed:
+
+- **Security**: Any code in authentication, authorization, or credential handling
+- **Database**: `src/services/sqlite/` - Schema changes, migrations, query logic
+- **Hooks Core**: `src/hooks/*.ts` - Hook execution flow and lifecycle
+- **API Design**: New endpoints, breaking changes to existing APIs
+- **Architecture**: New abstractions, pattern changes, dependency additions
+- **Privacy**: `src/utils/tag-stripping.ts` - Privacy tag handling logic
+- **Business Logic**: Observation compression, scoring algorithms
+- **Configuration**: `settings.json` schema changes, default values
+
+### 🔄 Retry Policy
+
+- Maximum 2 auto-fix attempts per CI failure
+- Escalate to human review after max retries
+- Never auto-fix the same file more than once per PR