opencode-codebase-index 0.2.4 → 0.3.0

package/README.md

@@ -205,6 +205,7 @@ The plugin automatically registers these slash commands:
 | `/search <query>` | **Pure Semantic Search**. Best for "How does X work?" |
 | `/find <query>` | **Hybrid Search**. Combines semantic search + grep. Best for "Find usage of X". |
 | `/index` | **Update Index**. Forces a refresh of the codebase index. |
+| `/status` | **Check Status**. Shows if indexed, chunk count, and provider info. |
 
 ## ⚙️ Configuration
 
@@ -219,7 +220,10 @@ Zero-config by default (uses `auto` mode). Customize in `.opencode/codebase-inde
     "watchFiles": true,
     "maxFileSize": 1048576,
     "maxChunksPerFile": 100,
-    "semanticOnly": false
+    "semanticOnly": false,
+    "autoGc": true,
+    "gcIntervalDays": 7,
+    "gcOrphanThreshold": 100
   },
   "search": {
     "maxResults": 20,
@@ -244,6 +248,9 @@ Zero-config by default (uses `auto` mode). Customize in `.opencode/codebase-inde
 | `semanticOnly` | `false` | When `true`, only index semantic nodes (functions, classes) and skip generic blocks |
 | `retries` | `3` | Number of retry attempts for failed embedding API calls |
 | `retryDelayMs` | `1000` | Delay between retries in milliseconds |
+| `autoGc` | `true` | Automatically run garbage collection to remove orphaned embeddings/chunks |
+| `gcIntervalDays` | `7` | Run GC on initialization if last GC was more than N days ago |
+| `gcOrphanThreshold` | `100` | Run GC after indexing if orphan count exceeds this threshold |
 | **search** | | |
 | `maxResults` | `20` | Maximum results to return |
 | `minScore` | `0.1` | Minimum similarity score (0-1). Lower = more results |
@@ -257,6 +264,150 @@ The plugin automatically detects available credentials in this order:
 3. **Google** (Gemini Embeddings)
 4. **Ollama** (Local/Private - requires `nomic-embed-text`)
 
+### Rate Limits by Provider
+
+Each provider has different rate limits. The plugin automatically adjusts concurrency and delays:
+
+| Provider | Concurrency | Delay | Best For |
+|----------|-------------|-------|----------|
+| **GitHub Copilot** | 1 | 4s | Small codebases (<1k files) |
+| **OpenAI** | 3 | 500ms | Medium codebases |
+| **Google** | 5 | 200ms | Medium-large codebases |
+| **Ollama** | 5 | None | Large codebases (10k+ files) |
+
+**For large codebases**, use Ollama locally to avoid rate limits:
+
+```bash
+# Install the embedding model
+ollama pull nomic-embed-text
+```
+
+```json
+// .opencode/codebase-index.json
+{
+  "embeddingProvider": "ollama"
+}
+```
+
+## 📈 Performance
+
+The plugin is built for speed with a Rust native module. Here are typical performance numbers (Apple M1):
+
+### Parsing (tree-sitter)
+
+| Files | Chunks | Time |
+|-------|--------|------|
+| 100 | 1,200 | ~7ms |
+| 500 | 6,000 | ~32ms |
+
+### Vector Search (usearch)
+
+| Index Size | Search Time | Throughput |
+|------------|-------------|------------|
+| 1,000 vectors | 0.7ms | 1,400 ops/sec |
+| 5,000 vectors | 1.2ms | 850 ops/sec |
+| 10,000 vectors | 1.3ms | 780 ops/sec |
+
+### Database Operations (SQLite with batch)
+
+| Operation | 1,000 items | 10,000 items |
+|-----------|-------------|--------------|
+| Insert chunks | 4ms | 44ms |
+| Add to branch | 2ms | 22ms |
+| Check embedding exists | <0.01ms | <0.01ms |
+
+### Batch vs Sequential Performance
+
+Batch operations provide significant speedups:
+
+| Operation | Sequential | Batch | Speedup |
+|-----------|------------|-------|---------|
+| Insert 1,000 chunks | 38ms | 4ms | **~10x** |
+| Add 1,000 to branch | 29ms | 2ms | **~14x** |
+| Insert 1,000 embeddings | 59ms | 40ms | **~1.5x** |
+
+Run benchmarks yourself: `npx tsx benchmarks/run.ts`
+
+## 🎯 Choosing a Provider
+
+Use this decision tree to pick the right embedding provider:
+
+```
+                    ┌─────────────────────────┐
+                    │ Do you have Copilot?    │
+                    └───────────┬─────────────┘
+                          ┌─────┴─────┐
+                         YES          NO
+                          │            │
+              ┌───────────▼───────┐    │
+              │ Codebase < 1k     │    │
+              │ files?            │    │
+              └─────────┬─────────┘    │
+                  ┌─────┴─────┐        │
+                 YES          NO       │
+                  │            │       │
+                  ▼            │       │
+           ┌──────────┐        │       │
+           │ Copilot  │        │       │
+           │ (free)   │        │       │
+           └──────────┘        │       │
+                               ▼       ▼
+                    ┌─────────────────────────┐
+                    │ Need fastest indexing?  │
+                    └───────────┬─────────────┘
+                          ┌─────┴─────┐
+                         YES          NO
+                          │            │
+                          ▼            ▼
+                   ┌──────────┐ ┌──────────────┐
+                   │ Ollama   │ │ OpenAI or    │
+                   │ (local)  │ │ Google       │
+                   └──────────┘ └──────────────┘
+```
+
+### Provider Comparison
+
+| Provider | Speed | Cost | Privacy | Best For |
+|----------|-------|------|---------|----------|
+| **Ollama** | Fastest | Free | Full | Large codebases, privacy-sensitive |
+| **GitHub Copilot** | Slow (rate limited) | Free* | Cloud | Small codebases, existing subscribers |
+| **OpenAI** | Medium | ~$0.0001/1K tokens | Cloud | General use |
+| **Google** | Fast | Free tier available | Cloud | Medium-large codebases |
+
+*Requires active Copilot subscription
+
+### Setup by Provider
+
+**Ollama (Recommended for large codebases)**
+```bash
+ollama pull nomic-embed-text
+```
+```json
+{ "embeddingProvider": "ollama" }
+```
+
+**OpenAI**
+```bash
+export OPENAI_API_KEY=sk-...
+```
+```json
+{ "embeddingProvider": "openai" }
+```
+
+**Google**
+```bash
+export GOOGLE_API_KEY=...
+```
+```json
+{ "embeddingProvider": "google" }
+```
+
+**GitHub Copilot**
+No setup needed if you have an active Copilot subscription.
+```json
+{ "embeddingProvider": "github-copilot" }
+```
+
 ## ⚠️ Tradeoffs
 
 Be aware of these characteristics:

package/commands/find.md

@@ -2,12 +2,24 @@
 description: Find code using hybrid approach (semantic + grep)
 ---
 
-Find code related to: $ARGUMENTS
+Find code using both semantic search and grep.
+
+User input: $ARGUMENTS
 
 Strategy:
-1. First use `codebase_search` to find semantically related code
-2. From the results, identify specific function/class names
+1. Use `codebase_search` to find semantically related code
+2. Identify specific function/class/variable names from results
 3. Use grep to find all occurrences of those identifiers
-4. Combine findings into a comprehensive answer
+4. Combine into a comprehensive answer
+
+Parse optional parameters from input:
+- `limit=N` → limit semantic results
+- `type=X` or "functions"/"classes" → filter chunk type
+- `dir=X` → filter directory
+
+Examples:
+- `/find error handling middleware`
+- `/find payment validation type=function`
+- `/find user auth in src/services`
 
-If the semantic index doesn't exist, run `index_codebase` first.
+If no index exists, run `index_codebase` first.

package/commands/index.md

@@ -2,10 +2,20 @@
 description: Index the codebase for semantic search
 ---
 
-Run the `index_codebase` tool to create or update the semantic search index.
+Run the `index_codebase` tool with these settings:
 
-Show progress and final statistics including:
-- Number of files processed
-- Number of chunks indexed
-- Tokens used
-- Duration
+User input: $ARGUMENTS
+
+Parse the input and set tool arguments:
+- force=true if input contains "force"
+- estimateOnly=true if input contains "estimate" 
+- verbose=true (always, for detailed output)
+
+Examples:
+- `/index` → force=false, estimateOnly=false, verbose=true
+- `/index force` → force=true, estimateOnly=false, verbose=true
+- `/index estimate` → force=false, estimateOnly=true, verbose=true
+
+IMPORTANT: You MUST pass the parsed arguments to `index_codebase`. Do not ignore them.
+
+Show final statistics including files processed, chunks indexed, tokens used, and duration.

package/commands/search.md

@@ -2,8 +2,23 @@
 description: Search codebase by meaning using semantic search
 ---
 
-Use the `codebase_search` tool to find code related to: $ARGUMENTS
+Search the codebase using semantic search.
 
-If the index doesn't exist yet, run `index_codebase` first.
+User input: $ARGUMENTS
 
-Return the most relevant results with file paths and line numbers.
+The first part is the search query. Look for optional parameters:
+- `limit=N` or "top N" or "first N" → set limit
+- `type=X` or mentions "functions"/"classes"/"methods" → set chunkType
+- `dir=X` or "in folder X" → set directory filter
+- File extensions like ".ts", "typescript", ".py" → set fileType
+
+Call `codebase_search` with the parsed arguments.
+
+Examples:
+- `/search authentication logic` → query="authentication logic"
+- `/search error handling limit=5` → query="error handling", limit=5
+- `/search validation functions` → query="validation", chunkType="function"
+
+If the index doesn't exist, run `index_codebase` first.
+
+Return results with file paths and line numbers.

package/commands/status.md

@@ -0,0 +1,15 @@
+---
+description: Check if the codebase is indexed and ready for semantic search
+---
+
+Run the `index_status` tool to check if the codebase index is ready.
+
+This shows:
+- Whether the codebase is indexed
+- Number of indexed chunks
+- Embedding provider and model being used
+- Current git branch
+
+No arguments needed - just run `index_status`.
+
+If not indexed, suggest running `/index` to create the index.