Release v2.0.0

Breaking changes:
- All tool errors now set isError: true in MCP responses (previously
  returned as regular text/JSON). Agents that parse error responses
  by checking for "error" key in JSON must update to handle plain text
  with isError flag instead.
- fetch_artifacts hard limit raised from 20 to 50 identifiers.

New features:
- Expanded docstrings for semantic_search and grep_search with full
  Args, Returns, and Examples sections
- Literal type for get_artifact_relationships profile parameter —
  generates JSON Schema enum for better agent discoverability
- Stringified JSON array coercion across all tools (fetch_artifacts,
  search paths/extensions)

Fixes:
- Docker image tag consistency (:latest → :main)
- uv exclude-newer documented and version pin relaxed to ~=0.11.0

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: rodion-m

manifest.json

@@ -2,7 +2,7 @@
   "manifest_version": "0.4",
   "name": "codealive-mcp",
   "display_name": "CodeAlive",
-  "version": "0.3.0",
+  "version": "2.0.0",
   "description": "Semantic code search and codebase Q&A for Claude Desktop using your CodeAlive account or self-hosted deployment.",
   "long_description": "CodeAlive gives Claude Desktop access to semantic code search, artifact fetch, repository discovery, and architecture-aware codebase Q&A. This extension runs locally via MCP and supports both CodeAlive Cloud and self-hosted deployments.",
   "author": {

pyproject.toml

@@ -37,7 +37,7 @@ packages = ["src"]
 package-dir = {"" = "."}
 
 [tool.setuptools_scm]
-fallback_version = "0.3.0"
+fallback_version = "2.0.0"
 
 [tool.uv]
 # Relative dates in exclude-newer (e.g. "7 days") require uv ≥ 0.11.

server.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.CodeAlive-AI/codealive-mcp",
-  "version": "0.3.0",
+  "version": "2.0.0",
   "description": "Semantic code search and analysis from CodeAlive for AI assistants and agents.",
   "keywords": [
     "context-engineering",