opencode-codebase-index 0.23.0 → 0.25.0

package/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "codebase-index",
       "description": "Semantic code search and codebase graph tools for Claude Code",
       "source": "./",
-      "version": "0.23.0"
+      "version": "0.25.0"
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "codebase-index",
-  "version": "0.23.0",
+  "version": "0.25.0",
   "description": "Semantic code search and codebase graph tools for Claude Code",
   "displayName": "Codebase Index",
   "author": {

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "codebase-index",
-  "version": "0.23.0",
+  "version": "0.25.0",
   "description": "Semantic code search and codebase graph tools for Codex",
   "author": {
     "name": "Kenneth",

package/README.md

@@ -12,6 +12,16 @@
 
 New installs should use `open-codebase-index` and `open-codebase-index-mcp`. The legacy package `opencode-codebase-index` and `opencode-codebase-index-mcp` remain supported aliases.
 
+For terminal use outside an MCP client, install the package globally and use the concise `cbi` command:
+
+```bash
+npm install -g open-codebase-index
+cbi status --project /path/to/repo --host jcode
+cbi search "retry recovery" --project /path/to/repo
+```
+
+`cbi` provides status, indexing, search, definition lookup, and direct caller or callee inspection. See [Installation and host setup](docs/installation.md#human-cli) for the full command reference.
+
 ## Highlights
 
 - **Semantic and hybrid retrieval** for questions where you do not know the identifier.
@@ -19,7 +29,7 @@ New installs should use `open-codebase-index` and `open-codebase-index-mcp`. The
 - **Definition and graph navigation** through `implementation_lookup`, `call_graph`, and `call_graph_path`.
 - **Incremental, branch-aware indexing** with file watching and content-hash reuse.
 - **Local storage** backed by SQLite, usearch vectors, and a BM25 inverted index.
-- **Multiple embedding providers**: Ollama, GitHub Copilot, OpenAI, Google, or a custom OpenAI-compatible endpoint.
+- **Multiple embedding providers**: Ollama, OpenAI, Google, or a custom OpenAI-compatible endpoint.
 - **Native parsing** for TypeScript/TSX, JavaScript/JSX, Python, Rust, Swift, Go, Java, C#, Ruby, C/C++, Metal, PHP, Apex, Bash, Zig, GDScript, MATLAB, JSON, TOML, YAML, Markdown, and HTML, with text fallback.
 
 ## Quick start with OpenCode
@@ -128,9 +138,8 @@ Read [Architecture](ARCHITECTURE.md) for the detailed data flow and design decis
 With `embeddingProvider: "auto"`, providers are tried in this order:
 
 1. Ollama
-2. GitHub Copilot
-3. OpenAI
-4. Google
+2. OpenAI
+3. Google
 
 Ollama is the simplest local option:
 
@@ -177,7 +186,9 @@ The index stores reusable content by hash and maintains branch catalogs for chun
 
 ## Knowledge bases and reranking
 
-OpenCode and Pi can index additional directories as knowledge bases. Configure them with `knowledgeBases` or use the host-native knowledge-base tools where available.
+OpenCode, Pi, and every MCP client can index additional directories as knowledge bases. Configure them with `knowledgeBases`, or use the knowledge-base tools:
+- MCP and OpenCode: `add_knowledge_base`, `list_knowledge_bases`, `remove_knowledge_base`
+- Pi: `knowledge_base_add`, `knowledge_base_list`, `knowledge_base_remove`
 
 Optional external reranking supports Cohere, Jina, and custom compatible endpoints. Local filtering and evidence classes are applied before external candidates are submitted.
 

package/commands/peek.md

@@ -14,6 +14,7 @@ The first part is the search query. Look for optional parameters:
 - `author=X` or `blameAuthor=X` → set blameAuthor filter
 - `sha=X` or `blameSha=X` → set blameSha filter
 - `since=YYYY-MM-DD` or `blameSince=YYYY-MM-DD` → set blameSince filter
+- `until=YYYY-MM-DD` or `blameUntil=YYYY-MM-DD` → set blameUntil filter
 
 Call `codebase_peek` with the parsed arguments.
 
@@ -21,7 +22,7 @@ Examples:
 - `/peek authentication logic` → query="authentication logic"
 - `/peek error handling limit=5` → query="error handling", limit=5
 - `/peek validation functions` → query="validation", chunkType="function"
-- `/peek auth logic author=jane@example.com since=2025-01-01` → query="auth logic", blameAuthor="jane@example.com", blameSince="2025-01-01"
+- `/peek auth logic author=jane@example.com since=2025-01-01 until=2025-01-31` → query="auth logic", blameAuthor="jane@example.com", blameSince="2025-01-01", blameUntil="2025-01-31"
 
 If the index doesn't exist, run `index_codebase` first.
 

package/commands/search.md

@@ -14,6 +14,7 @@ The first part is the search query. Look for optional parameters:
 - `author=X` or `blameAuthor=X` → set blameAuthor filter
 - `sha=X` or `blameSha=X` → set blameSha filter
 - `since=YYYY-MM-DD` or `blameSince=YYYY-MM-DD` → set blameSince filter
+- `until=YYYY-MM-DD` or `blameUntil=YYYY-MM-DD` → set blameUntil filter
 
 Call `codebase_search` with the parsed arguments.
 
@@ -21,7 +22,7 @@ Examples:
 - `/search authentication logic` → query="authentication logic"
 - `/search error handling limit=5` → query="error handling", limit=5
 - `/search validation functions` → query="validation", chunkType="function"
-- `/search auth logic author=jane@example.com since=2025-01-01` → query="auth logic", blameAuthor="jane@example.com", blameSince="2025-01-01"
+- `/search auth logic author=jane@example.com since=2025-01-01 until=2025-01-31` → query="auth logic", blameAuthor="jane@example.com", blameSince="2025-01-01", blameUntil="2025-01-31"
 
 If the index doesn't exist, run `index_codebase` first.