agentleFS
takeshytakeshy/obsidian-gemini-helper/CLAUDE.md

obsidian-gemini-helper

CLAUDE.md117 starsChanged 5 months agoMITView on GitHub

Obsidian plugin for Google Gemini AI with Chat, Workflow Automation, and Semantic Search (RAG). Uses @google/genai SDK. API-only (no CLI backends or local LLM support). After building, reload the plugin in Obsidian to test changes. Use npm's built-in version command which automatically updates all version files: This runs version-bump.mjs which updates package.json, manifest.json, and versions.json together. After bumping, push master only — do NOT push the version tag manually: The Release workflow (.github/workflows/release.yml) runs on push to master, creates the…

  • Commits and pushes

The file

We split this CLAUDE.md into the rules it gives an agent

12 rules. About 0 are common, 4 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After building, reload the plugin in Obsidian to test changes.

    line 17
  2. Distinctive:

    Use npm's built-in version command which automatically updates all version files:

    line 21
  3. Distinctive:

    After bumping, push master only — do NOT push the version tag manually:

    line 33
  4. Distinctive:

    When adding a new workflow node type, ALL of the following files must be updated:

    line 154
  5. Very specific:

    src/workflow/types.ts: - Add to WorkflowNodeType union type AND WORKFLOW_NODE_TYPES set (single source of truth for isWorkflowNodeType())

    line 156
  6. Very specific:

    src/workflow/workflowSpec.ts: - Add documentation for AI workflow generation

    line 157
  7. Very specific:

    src/workflow/nodeHandlers.ts: - Add handle*Node() function and import

    line 158
  8. Very specific:

    src/workflow/executor.ts: - Add case in the switch statement to call handler and log

    line 159
  9. Very specific:

    Add to NODE_TYPE_LABELS object

    line 161
  10. Very specific:

    Add to ADDABLE_NODE_TYPES array

    line 162
  11. Very specific:

    Add to getDefaultProperties() switch

    line 163
  12. Very specific:

    Add case in renderPropertyFields() switch for editor UI

    line 167

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Obsidian plugin for Google Gemini AI with Chat, Workflow Automation, and Semantic Search (RAG). Uses @google/genai SDK. API-only (no CLI backends or local LLM support).

Build Commands

npm run build    # Production build (tsc + esbuild) -> outputs main.js
npm run dev      # Development build with watch mode
npm run lint     # ESLint check

After building, reload the plugin in Obsidian to test changes.

Version Bumping

Use npm's built-in version command which automatically updates all version files:

npm version patch   # 1.2.3 -> 1.2.4
npm version minor   # 1.2.3 -> 1.3.0
npm version major   # 1.2.3 -> 2.0.0

This runs version-bump.mjs which updates package.json, manifest.json, and versions.json together.

Releasing

After bumping, push master only — do NOT push the version tag manually:

git push origin master

The Release workflow (.github/workflows/release.yml) runs on push to master, creates the tag from manifest.json's version, builds, and opens a draft GitHub release with main.js/manifest.json/styles.css attached. The maintainer edits the notes and publishes the draft manually. If the tag already exists (e.g. it was pushed by hand), the workflow skips release creation entirely — delete the remote tag and re-run the workflow to recover.

Architecture

Core Layer (src/core/)

  • gemini.ts - Gemini API client wrapper
    • GeminiClient class with streaming chat, function calling, and RAG integration
    • chatWithToolsStream() - Main method for chat with tools and optional RAG
    • messagesToHistory() - Converts Message[] to Gemini Content[] format
  • fileSearch.ts - File Search RAG management
    • FileSearchManager - Handles store creation, file sync, deletion
    • smartSync() - Checksum-based incremental sync with parallel uploads
  • tools.ts - Function calling tool definitions (13 tools for vault operations)
  • mcpClient.ts - MCP (Model Context Protocol) client for external tool servers
    • Implements Streamable HTTP transport with JSON-RPC

Vault Layer (src/vault/)

  • notes.ts - Note CRUD operations + safe editing with proposeEdit()/applyEdit()/discardEdit()
  • search.ts - Local vault search (filename and content)
  • toolExecutor.ts - Maps tool calls to vault operations

Workflow Layer (src/workflow/)

  • types.ts - Workflow node types and execution context definitions
  • parser.ts - Parses workflow YAML from markdown code blocks
  • executor.ts - Stack-based workflow execution engine with MAX_ITERATIONS (1000) safety
  • nodeHandlers.ts - Individual handlers for 21 node types
  • history.ts - Execution history tracking
  • historyCanvas.ts - Export execution history to Obsidian Canvas
  • codeblockSync.ts - Sync workflow changes back to markdown

Dashboard Layer (src/dashboard/)

  • Responsive widget grid stored as a .dashboard file (YAML, version 1). Opened via DashboardView (src/ui/DashboardView.tsx, a TextFileView registered for the .dashboard extension).
  • dashboardFile.ts - Parse/serialize .dashboard YAML, layout helpers, createEmptyDashboard()
  • DashboardCanvas.tsx / GridCell.tsx / useGridLayout.ts / useBreakpoint.ts - Drag/resize responsive grid
  • widgets/registry.ts - registerCoreWidgets() registers widget types (base, markdown, web, workflow, kanban); called once in plugin.ts onload
  • widgets/ - Widget renderers + config-editors/ panels; workflowRunner.ts runs workflow widgets headlessly with a sidecar result cache
  • AIBaseModal.ts / aiBaseGenerate.ts - Headless .base generation (Gemini-only) from the built-in base skill
  • New dashboards: Dashboards/ folder; backing .base files: Dashboards/Bases/. The dashboard built-in agent skill (builtinSkills.ts) authors .dashboard + .base files.

UI Layer (src/ui/)

  • ChatView.tsx - Obsidian ItemView wrapper for React
  • SettingsTab.tsx - Plugin settings UI
  • components/ - React components (Chat, MessageList, MessageBubble, InputArea)
  • components/workflow/ - Workflow-specific modals and WorkflowPanel.tsx

Key Data Flow (Chat)

  1. User sends message → Chat.tsx → GeminiClient.chatWithToolsStream()
  2. Gemini responds with text/function calls → streamed back to UI
  3. Function calls → toolExecutor.ts → notes.ts/search.ts → results back to Gemini
  4. RAG: If enabled, fileSearch tool added to Gemini request for semantic search

Key Data Flow (Workflow)

  1. User selects workflow → WorkflowPanel.tsx loads from markdown code block
  2. parseWorkflowFromMarkdown() converts YAML to Workflow graph
  3. WorkflowExecutor.execute() traverses nodes using stack-based execution
  4. Each node type handled by specific handler in nodeHandlers.ts
  5. Results saved to execution history, optionally exported to Canvas

Important Implementation Details

Safe Editing (propose_edit tool)

  • Changes applied directly to file, original content backed up in memory
  • User clicks Apply (confirm) or Discard (restore from backup)
  • update_note tool disabled to force safe editing flow

RAG Integration

  • Multiple RAG settings stored in workspace state file (.gemini-workspace.json)
  • Supports internal stores (auto-synced) and external store IDs
  • RagSetting.files tracks checksums for incremental sync
  • Store data persists on Google servers; use "Delete RAG Store" in settings to clean up

Chat History

  • Saved as Markdown files in {workspaceFolder}/chats/{chatId}.md
  • YAML frontmatter with title, timestamps
  • Messages parsed/serialized via messagesToMarkdown()/parseMarkdownToMessages()

Streaming

  • Uses SDK Chat (this.ai.chats.create()) for automatic thought signature handling
  • AbortController for stop functionality
  • groundingMetadata in response indicates RAG usage

Workflow Execution

  • Stack-based traversal with iteration counting for loop safety
  • Conditional nodes (if, while) use labeled edges ("true"/"false")
  • Variables interpolated via {{varName}} syntax in node properties
  • Sub-workflows executed recursively with variable passing
  • Event triggers support glob patterns for file filtering

MCP Integration

  • External MCP servers configured via settings (mcpServers array)
  • McpClient implements Streamable HTTP transport
  • Session management with Mcp-Session-Id header
  • Available in workflow mcp nodes

Key Types (src/types/index.ts)

  • Message - Chat message with optional attachments, toolsUsed, pendingEdit, ragUsed
  • PendingEditInfo - Tracks edit status (pending/applied/discarded)
  • StreamChunk - Streaming response types (text, tool_call, tool_result, rag_used, error, done)
  • GeminiHelperSettings - Plugin configuration
  • WorkspaceState - Per-workspace state (selected model, RAG settings)
  • RagSetting - Individual RAG store configuration

Workflow Types (src/workflow/types.ts)

  • WorkflowNodeType - 21 node types (command, http, note, dialog, mcp, etc.)
  • WORKFLOW_NODE_TYPES - Set of all valid node type strings (single source of truth)
  • isWorkflowNodeType() - Type guard used by parser.ts and codeblockSync.ts
  • normalizeValue() - Converts unknown YAML values to string (shared utility)
  • Workflow - Node graph with edges and start node
  • ExecutionContext - Variables map and execution logs
  • PromptCallbacks - UI callbacks for interactive nodes

Adding New Workflow Node Types

When adding a new workflow node type, ALL of the following files must be updated:

  1. src/workflow/types.ts - Add to WorkflowNodeType union type AND WORKFLOW_NODE_TYPES set (single source of truth for isWorkflowNodeType())
  2. src/workflow/workflowSpec.ts - Add documentation for AI workflow generation
  3. src/workflow/nodeHandlers.ts - Add handle*Node() function and import
  4. src/workflow/executor.ts - Add case in the switch statement to call handler and log
  5. src/ui/components/workflow/WorkflowPanel.tsx:
    • Add to NODE_TYPE_LABELS object
    • Add to ADDABLE_NODE_TYPES array
    • Add to getDefaultProperties() switch
    • Add to getNodeSummary() switch
  6. src/ui/components/workflow/NodeEditorModal.ts:
    • Add to NODE_TYPE_LABELS object
    • Add case in renderPropertyFields() switch for editor UI

Common mistakes:

  • Forgetting WORKFLOW_NODE_TYPES set causes nodes to be skipped during parsing and disappear from visual workflow
  • Forgetting executor.ts causes node execution to fail silently

Notes

  • Obsidian API accessed via app.vault (files) and app.workspace (UI)
  • React components rendered inside Obsidian's ItemView
  • File attachments converted to Base64 and sent as inlineData parts
  • Desktop and mobile supported

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.