feat: complete agentic capabilities and IDE integration; update README with MCP server details and configuration

Author: deepakdgupta1

KnowCode.md

@@ -852,19 +852,21 @@ You've essentially defined a **code intelligence system**, not a chatbot with em
 19. **[ ] Scalability**: Large monorepo support and distributed processing.
 20. **[ ] Team Sharing**: Remote knowledge store sync and collaboration.
 
-### **Phase 7: Agentic Capabilities (IN PROGRESS)**
+### **Phase 7: Agentic Capabilities (COMPLETED v2.2)**
 21. **[x] Agent Architecture**: `Agent` class with configuration-driven model selection.
 22. **[x] Multi-Provider Support**: Google Gemini and OpenRouter/OpenAI integration.
 23. **[x] Rate Limiting**: Persistent RPM/RPD tracking and enforcement.
-24. **[ ] Tool Use (ReAct)**: file listing, reference searching, history querying.
-25. **[ ] Advanced Retrieval**: Cross-Encoder reranking and graph inquiry.
-
-### **Phase 8: IDE Integration (PLANNED)**
-26. **[ ] MCP Server (Layer 10b)**: Tool exposure for external IDE agents.
-27. **[ ] Sufficiency Scoring**: Context confidence metrics for local-first answering.
-28. **[ ] Task-Specific Templates**: Implement debug/refactor/extend/review context prioritization.
-29. **[ ] Multi-hop Queries**: Reachability and impact analysis with configurable depth.
-30. **[ ] Structured Responses**: JSON schema support across all endpoints.
+24. **[x] Query Classification**: 6 task types (explain, debug, extend, review, locate, general).
+25. **[x] Smart Answer**: Local-first answering with configurable sufficiency threshold.
+26. **[x] VoyageAI Reranking**: Cross-encoder reranking with signal-based fallback.
+
+### **Phase 8: IDE Integration (COMPLETED v2.2)**
+27. **[x] MCP Server (Layer 10b)**: Tool exposure via STDIO for IDE agents.
+28. **[x] Core 3 Tools**: `search_codebase`, `get_entity_context`, `trace_calls`.
+29. **[x] Sufficiency Scoring**: Context confidence metrics for local-first answering.
+30. **[x] Task-Specific Templates**: Debug/extend/review/explain/locate prioritization.
+31. **[x] Multi-hop Queries**: `trace_calls(depth=N)` and `get_impact()` analysis.
+32. **[x] Structured Responses**: JSON with `task_type` and `sufficiency_score`.
 
 ### **Supporting Tooling & QA (COMPLETED)**
 - **[x] Tests**: Unit/integration/e2e coverage for parsing, indexing, retrieval, API, CLI, storage, and analysis.

README.md

@@ -54,7 +54,10 @@ knowcode semantic-search "How does parsing work?"
 # 7. Start the intelligence server with watch mode
 knowcode server --port 8080 --watch
 
-# 8. View statistics
+# 8. Start MCP server for IDE integration
+knowcode mcp-server --store .
+
+# 9. View statistics
 knowcode stats
 ```
 
@@ -155,9 +158,11 @@ knowcode server --port 8080
 ```
 
 Once running, you can access endpoints like:
-- `GET /api/v1/context?target=MyClass`
+- `GET /api/v1/context?target=MyClass&task_type=debug`
 - `GET /api/v1/search?q=parser` `(lexical search)`
 - `POST /api/v1/context/query` `(semantic search)`
+- `GET /api/v1/trace_calls/{entity_id}?direction=callers&depth=3` `(multi-hop call graph)`
+- `GET /api/v1/impact/{entity_id}` `(deletion impact analysis)`
 - `POST /api/v1/reload` (to refresh data after a new `analyze` run)
 
 ### `history`
@@ -207,6 +212,33 @@ models:
 knowcode ask "How does the graph builder work?"
 ```
 
+### `mcp-server`
+Start an MCP (Model Context Protocol) server for IDE agent integration.
+
+```bash
+knowcode mcp-server [--store <path>]
+```
+
+**Tools Exposed:**
+- `search_codebase` - Search for code entities by name
+- `get_entity_context` - Get detailed context for an entity
+- `trace_calls` - Trace call graph (callers/callees) with depth
+
+**MCP Client Configuration (Claude Desktop, VS Code, etc.):**
+```json
+{
+  "knowcode": {
+    "command": "knowcode",
+    "args": ["mcp-server", "--store", "/path/to/project"]
+  }
+}
+```
+
+**Installation with MCP support:**
+```bash
+pip install "knowcode[mcp]"
+```
+
 ## Supported Languages (MVP)
 
 - **Python** (.py) - Full AST parsing (Supports Python 3.9 - 3.12)
@@ -229,6 +261,40 @@ KnowCode follows a layered architecture:
 
 See [KnowCode.md](KnowCode.md) for the complete reference architecture.
 
+## Configuration
+
+**`aimodels.yaml`** supports:
+
+```yaml
+# LLM models for 'ask' command
+natural_language_models:
+  - name: gemini-2.0-flash-lite
+    provider: google
+    api_key_env: GOOGLE_API_KEY
+
+# Embedding models
+embedding_models:
+  - name: voyage-3-lite
+    provider: voyageai
+    api_key_env: VOYAGE_API_KEY_1
+
+# Reranking models (cross-encoder)
+reranking_models:
+  - name: rerank-2.5
+    provider: voyageai
+    api_key_env: VOYAGE_API_KEY_1
+
+# Config
+config:
+  sufficiency_threshold: 0.8  # For local-first answering
+```
+
+**Optional dependencies:**
+```bash
+pip install "knowcode[mcp]"      # MCP server support
+pip install "knowcode[voyageai]" # VoyageAI reranking
+```
+
 ## Example Output
 
 **Stats:**
@@ -303,6 +369,12 @@ See [KnowCode.md](KnowCode.md) for the full vision. The MVP focuses on:
 - ✅ v1.4: Runtime signal integration
 - ✅ v2.0: Intelligence Server mode (local API for local IDE agents)
 - ✅ v2.1: Semantic search with embeddings, hybrid retrieval, and watch mode
+- ✅ v2.2: Developer Q&A & IDE Agent Integration:
+  - Query classification and task-specific templates
+  - Multi-hop `trace_calls()` and impact analysis
+  - Local-first `smart_answer()` with sufficiency scoring
+  - MCP server for IDE integration
+  - VoyageAI cross-encoder reranking
 
 **Future releases:**
 - v3.0: Team sharing & Enterprise features (RBAC, SSO, etc.)