@cascadeflow/n8n-nodes-cascadeflow 0.6.5 → 0.6.7

package/README.md

@@ -16,19 +16,9 @@
 
 </div>
 
-> **⚠️ IMPORTANT: Version Migration (v5.0.x → v0.5.0)**
->
-> If you previously installed versions **5.0.1** through **5.0.7**, you need to **manually reinstall** to get v0.5.0:
->
-> 1. Go to **Settings** > **Community Nodes** in n8n
-> 2. **Uninstall** `@cascadeflow/n8n-nodes-cascadeflow`
-> 3. **Reinstall** by searching for `@cascadeflow/n8n-nodes-cascadeflow`
->
-> **Why?** Versions 5.0.x were published with incorrect version numbering. We've corrected this to align with the main cascadeflow release (v0.5.0). npm will not auto-upgrade from 5.0.x to 0.5.0 as it treats it as a downgrade.
+**Intelligent AI model cascading for n8n workflows with domain understanding.**
 
----
-
-**Intelligent AI model cascading for n8n workflows.**
+![cascadeflow Domain Routing](../../../.github/assets/n8n-CF-domains.jpg)
 
 This is an n8n community node that brings cascadeflow's intelligent AI model cascading to n8n workflows.
 
@@ -38,9 +28,9 @@ This is an n8n community node that brings cascadeflow's intelligent AI model cas
 
 ## How It Works
 
-The CascadeFlow node is a **Language Model sub-node** that sits between your AI models and downstream n8n nodes (like Basic LLM Chain, Chain, or any node that accepts Language Model inputs):
+The cascadeflow node is a **Language Model sub-node** that sits between your AI models and downstream n8n nodes (like Basic LLM Chain, Chain, or any node that accepts Language Model inputs):
 
-![CascadeFlow n8n Workflow](../../../.github/assets/n8n-CF.png)
+![cascadeflow n8n Workflow](../../../.github/assets/n8n-CF.png)
 
 **Architecture:**
 
@@ -51,7 +41,7 @@ The CascadeFlow node is a **Language Model sub-node** that sits between your AI
 └──────┬──────┘
        │
        ├──────► ┌──────────────┐
-       │        │  CascadeFlow │
+       │        │  cascadeflow │
        │        │     Node     │ ────► ┌──────────────┐
        │        └──────────────┘       │ Basic Chain  │
        ├──────► Quality checks         │ Chain        │
@@ -65,13 +55,13 @@ The CascadeFlow node is a **Language Model sub-node** that sits between your AI
 
 **Flow:**
 1. Query goes to cheap drafter model first
-2. CascadeFlow validates the response quality
+2. cascadeflow validates the response quality
 3. If quality passes → return drafter response (fast + cheap ✅)
 4. If quality fails → escalate to verifier model (slower but accurate ⚠️)
 
 **Result:** 70-80% of queries accept the drafter, saving 40-85% on costs.
 
-> **ℹ️ Note:** CascadeFlow works with n8n Chain nodes but **not with AI Agent nodes**, as n8n only allows whitelisted models for Agent inputs. Use with Basic LLM Chain, Chain, or other nodes that accept Language Model connections.
+> **ℹ️ Note:** cascadeflow works with n8n Chain nodes but **not with AI Agent nodes**, as n8n only allows whitelisted models for Agent inputs. Use with Basic LLM Chain, Chain, or other nodes that accept Language Model connections.
 
 ## Installation
 
@@ -106,13 +96,13 @@ RUN cd /usr/local/lib/node_modules/n8n && npm install @cascadeflow/n8n-nodes-cas
    - Configure one as your **drafter** (cheap model like `gpt-4o-mini` or `claude-3-5-haiku-20241022`)
    - Configure one as your **verifier** (powerful model like `gpt-4o` or `claude-3-5-sonnet-20241022`)
 
-2. **Add the CascadeFlow node**
+2. **Add the cascadeflow node**
    - Connect the drafter model to the **Drafter** input
    - Connect the verifier model to the **Verifier** input
    - Adjust the **Quality Threshold** (default: 0.7)
 
 3. **Connect to a Chain node**
-   - The CascadeFlow node outputs a Language Model connection
+   - The cascadeflow node outputs a Language Model connection
    - Connect it to nodes that accept AI models (Basic LLM Chain, Chain, etc.)
    - **Note:** Does not work with AI Agent nodes (n8n limitation)
 
@@ -127,7 +117,7 @@ RUN cd /usr/local/lib/node_modules/n8n && npm install @cascadeflow/n8n-nodes-cas
          v
 ┌──────────────────┐       ┌──────────────────┐
 │  OpenAI Model    │──────►│                  │
-│  gpt-4o-mini     │       │  CascadeFlow     │       ┌──────────────────┐
+│  gpt-4o-mini     │       │  cascadeflow     │       ┌──────────────────┐
 └──────────────────┘       │  Node            │──────►│ Basic LLM Chain  │
                            │                  │       │                  │
 ┌──────────────────┐       │  Threshold: 0.7  │       └──────────────────┘
@@ -150,20 +140,73 @@ Controls how aggressively to accept drafter responses:
 
 Lower threshold = more cost savings, higher threshold = better quality assurance.
 
+## Multi-Domain Cascading (Optional)
+
+cascadeflow supports **intelligent domain-specific cascading** - automatically detecting the type of query and routing it to a specialized model for that domain.
+
+### How It Works
+
+1. **Enable Domain Cascading** in the node settings
+2. **Toggle individual domains** you want to support
+3. **Connect domain-specific models** to the new input ports that appear
+
+When a query comes in, cascadeflow:
+1. Detects the domain (e.g., "Write a Python function" → Code domain)
+2. Routes to the specialized model for that domain (if connected)
+3. Falls back to drafter → verifier cascade if no domain model is available
+
+### Supported Domains
+
+| Domain | Description | Example Queries |
+|--------|-------------|-----------------|
+| **Code** | Programming, debugging, code generation | "Write a Python function...", "Debug this code..." |
+| **Math** | Mathematical reasoning, calculations, proofs | "Solve this equation...", "Prove that..." |
+| **Data** | Data analysis, statistics, pandas/SQL | "Analyze this dataset...", "Write a SQL query..." |
+| **Creative** | Creative writing, stories, poetry | "Write a short story...", "Compose a poem..." |
+| **Legal** | Legal documents, contracts, regulations | "Draft a contract...", "Explain this law..." |
+| **Medical** | Healthcare, medical knowledge, clinical | "What are the symptoms of...", "Explain this diagnosis..." |
+| **Financial** | Finance, accounting, investment analysis | "Analyze this stock...", "Calculate ROI..." |
+| **Science** | Scientific knowledge, research, experiments | "Explain quantum...", "How does photosynthesis..." |
+
+### Setup Example
+
+```
+┌──────────────────┐
+│  Claude Haiku    │──► Drafter (default cheap model)
+└──────────────────┘
+┌──────────────────┐
+│  GPT-4o          │──► Verifier (default powerful model)
+└──────────────────┘
+┌──────────────────┐         ┌──────────────────┐
+│  DeepSeek Coder  │──► Code │                  │
+└──────────────────┘         │                  │
+┌──────────────────┐         │   cascadeflow    │──► Chain
+│  Qwen Math       │──► Math │      Node        │
+└──────────────────┘         │                  │
+┌──────────────────┐         │                  │
+│  Claude Sonnet   │──► Legal│                  │
+└──────────────────┘         └──────────────────┘
+```
+
+### When to Use Domain Cascading
+
+- **Use it when**: You have domain-specific models that excel in certain areas (e.g., DeepSeek for code, specialized medical models)
+- **Skip it when**: Your drafter/verifier combination handles all domains well enough
+
 ## Flow Visualization
 
 ### Viewing Cascade Decisions in Real-Time
 
-CascadeFlow provides detailed logging of every cascade decision in n8n's UI:
+cascadeflow provides detailed logging of every cascade decision in n8n's UI:
 
-1. **Execute your workflow** with the CascadeFlow node
-2. **Click on the downstream Chain node** after execution (the node that receives CascadeFlow output)
+1. **Execute your workflow** with the cascadeflow node
+2. **Click on the downstream Chain node** after execution (the node that receives cascadeflow output)
 3. **Navigate to the "Logs" tab**
 
 You'll see detailed flow information like:
 
 ```
-🎯 CascadeFlow: Trying drafter model...
+🎯 cascadeflow: Trying drafter model...
    📊 Quality validation: confidence=0.85, method=heuristic
    🎯 Alignment: 0.82
 
@@ -182,7 +225,7 @@ You'll see detailed flow information like:
 Or when escalating:
 
 ```
-🎯 CascadeFlow: Trying drafter model...
+🎯 cascadeflow: Trying drafter model...
    📊 Quality validation: confidence=0.62, method=heuristic
 
 ┌────────────────────────────────────────────────┐
@@ -253,7 +296,7 @@ Note: Requires Ollama installed locally
 
 **Example: Claude Haiku + GPT-4o**
 
-| Scenario | Traditional (GPT-4o only) | CascadeFlow (Haiku + GPT-4o) | Savings |
+| Scenario | Traditional (GPT-4o only) | cascadeflow (Haiku + GPT-4o) | Savings |
 |----------|---------------------------|------------------------------|---------|
 | Simple Q&A (75% acceptance) | $0.0025 | $0.0008 | 68% |
 | Complex query (25% escalation) | $0.0025 | $0.0025 | 0% (correctly escalated) |
@@ -261,12 +304,12 @@ Note: Requires Ollama installed locally
 
 **Monthly savings (10,000 queries):**
 - Traditional (GPT-4o only): $25.00
-- CascadeFlow (Haiku + GPT-4o): $11.50
+- cascadeflow (Haiku + GPT-4o): $11.50
 - **You save: $13.50/month** (54% savings)
 
 **Monthly savings (100,000 queries):**
 - Traditional (GPT-4o only): $250.00
-- CascadeFlow (Haiku + GPT-4o): $115.00
+- cascadeflow (Haiku + GPT-4o): $115.00
 - **You save: $135.00/month** (54% savings)
 
 ## Example Workflows
@@ -282,7 +325,7 @@ Note: Requires Ollama installed locally
          v
 ┌─────────────────────────────────────┐
 │  Claude Haiku ────┐                 │
-│                   │  CascadeFlow    │       ┌──────────────────┐
+│                   │  cascadeflow    │       ┌──────────────────┐
 │  Claude Sonnet ───┴─► Node          │──────►│  Basic Chain     │
 └─────────────────────────────────────┘       │  (responds)      │
                                                └──────┬───────────┘
@@ -304,7 +347,7 @@ Note: Requires Ollama installed locally
          v
 ┌────────────────────────────────────────┐
 │  GPT-4o-mini ─────┐                    │
-│                   │  CascadeFlow       │       ┌──────────────────┐
+│                   │  cascadeflow       │       ┌──────────────────┐
 │  GPT-4o ──────────┴─► Node             │──────►│  Basic Chain     │
 └────────────────────────────────────────┘       │  (generates)     │
                                                   └──────┬───────────┘
@@ -326,7 +369,7 @@ Note: Requires Ollama installed locally
          v
 ┌─────────────────────────────────────┐
 │  Ollama qwen2.5 ──┐                 │
-│                   │  CascadeFlow    │       ┌──────────────────┐
+│                   │  cascadeflow    │       ┌──────────────────┐
 │  GPT-4o ──────────┴─► Node          │──────►│  Basic Chain     │
 └─────────────────────────────────────┘       │  (reviews code)  │
                                                └──────┬───────────┘
@@ -346,7 +389,7 @@ Note: Requires Ollama installed locally
 **To see the actual cascade flow and which model was used:**
 
 1. Execute your workflow
-2. Click on the downstream Chain node after execution (the node that receives CascadeFlow output)
+2. Click on the downstream Chain node after execution (the node that receives cascadeflow output)
 3. Navigate to the **"Logs"** tab
 4. You'll see detailed flow information showing:
    - Whether the drafter was accepted or escalated to verifier
@@ -357,7 +400,7 @@ Note: Requires Ollama installed locally
 
 The logs provide complete visibility into the cascade decision-making process, showing exactly which path was taken for each request.
 
-> **ℹ️ Important:** CascadeFlow does **not work with AI Agent nodes** in n8n, as n8n only allows whitelisted models for Agent inputs. Use with Basic LLM Chain, Chain, or other nodes that accept Language Model connections.
+> **ℹ️ Important:** cascadeflow does **not work with AI Agent nodes** in n8n, as n8n only allows whitelisted models for Agent inputs. Use with Basic LLM Chain, Chain, or other nodes that accept Language Model connections.
 
 ## Compatibility
 
@@ -384,13 +427,13 @@ The logs provide complete visibility into the cascade decision-making process, s
 
 **Solution:**
 1. Make sure your workflow has executed successfully
-2. Click on the **Chain node that receives the CascadeFlow output** (Basic LLM Chain, Chain, etc.)
+2. Click on the **Chain node that receives the cascadeflow output** (Basic LLM Chain, Chain, etc.)
 3. Navigate to the **"Logs"** tab (not the "Output" tab)
-4. The logs appear in the downstream node, not the CascadeFlow node itself
+4. The logs appear in the downstream node, not the cascadeflow node itself
 
 ### Issue: "This node cannot be connected" when connecting to AI Agent
 
-**Solution:** This is expected. CascadeFlow does **not work with AI Agent nodes** because n8n only allows whitelisted models for Agent inputs. Use CascadeFlow with:
+**Solution:** This is expected. cascadeflow does **not work with AI Agent nodes** because n8n only allows whitelisted models for Agent inputs. Use cascadeflow with:
 - ✅ Basic LLM Chain
 - ✅ Chain
 - ✅ Other nodes that accept Language Model connections
@@ -416,27 +459,33 @@ The logs provide complete visibility into the cascade decision-making process, s
 
 ## Version History
 
-### v0.5.0 (Latest)
+### v0.6.7 (Latest)
+
+- **Multi-domain cascading docs**: Added documentation for 8-domain intelligent cascading
+- **Removed semantic validation**: Disabled ML-based semantic validation to prevent out-of-memory crashes
+- **Shorter domain labels**: Domain input labels simplified (Code, Math, Data, etc.)
+
+### v0.6.4
+
+- **Individual domain toggles**: Replaced multi-select with individual boolean toggles for each domain
+- **Dynamic input ports**: Domain model inputs appear dynamically as each domain is enabled
+
+### v0.6.3
 
-**Major Release - Aligned with cascadeflow v0.5.0**
+- **16-domain routing**: Support for intelligent routing across 16 specialized domains (code, math, data, creative, legal, medical, financial, science, and more)
+- **Circuit breaker**: Added circuit breaker pattern for improved reliability
+- **Domain-specific models**: Connect specialized models for different query types
 
-- **Flow visualization in n8n Logs tab**: Added detailed cascade flow logging with visual boxes showing drafter acceptance, verifier escalation, and error fallback paths
-- **Real-time quality metrics**: Logs show confidence scores, alignment scores, latency breakdown, and cost savings for each request
-- **Running statistics**: Track acceptance rates across multiple executions
-- **Fixed UI visualization**: Swapped input order to match n8n's highlighting convention (Drafter now highlights as active)
-- **Auto-dependency installation**: Moved @cascadeflow/core from optionalDependencies to regular dependencies
-- **Crash fix**: Fixed n8n crashes caused by @cascadeflow/core static imports loading ML dependencies
-- **Dynamic imports**: SemanticQualityChecker now uses dynamic imports to avoid loading @xenova/transformers at module initialization
-- **Quality validator integration**: Integrated QualityValidator from @cascadeflow/core for improved quality scoring
-- **Better cascade decisions**: Replaced naive length-based quality check with proper complexity-aware validation
-- **Graceful degradation**: Added CASCADE_QUALITY_CONFIG with useSemanticValidation: false for stable operation
+### v0.5.0
 
-> **Note:** Versions 5.0.1 through 5.0.7 were deprecated due to incorrect version numbering. If upgrading from 5.0.x, please uninstall and reinstall.
+- **Flow visualization in n8n Logs tab**: Detailed cascade flow logging with visual boxes
+- **Real-time quality metrics**: Confidence scores, alignment scores, latency breakdown, and cost savings
+- **Quality validator integration**: Integrated QualityValidator from @cascadeflow/core
+- **Better cascade decisions**: Complexity-aware validation replacing naive length-based checks
 
-### v0.4.19 and earlier
+### v0.4.x and earlier
 
 - Initial releases as LangChain sub-node
 - Support for any AI Chat Model in n8n
-- Lazy verifier loading (only fetches when needed)
+- Lazy verifier loading
 - Quality threshold configuration
-- Console logging for cascade flow

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cascadeflow/n8n-nodes-cascadeflow",
-  "version": "0.6.5",
+  "version": "0.6.7",
   "description": "n8n node for cascadeflow - Smart AI model cascading with 40-85% cost savings",
   "keywords": [
     "n8n-community-node-package",