opencode-codebase-index 0.19.0 → 0.20.0

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": "0.19.0"
+      "version": "0.20.0"
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "codebase-index",
-  "version": "0.19.0",
+  "version": "0.20.0",
   "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": "0.19.0",
+  "version": "0.20.0",
   "description": "Semantic code search and codebase graph tools for Codex",
   "author": {
     "name": "Kenneth",

package/README.md

@@ -536,7 +536,7 @@ Maintenance tool to remove stale entries from deleted files and orphaned embeddi
 ### `index_metrics`
 Returns collected metrics about indexing and search performance. Operational metrics require `debug.enabled` and `debug.metrics` to be `true`.
 - **Metrics include**: Files indexed, chunks created, cache hit rate, search timing breakdown, GC stats, embedding API call stats.
-- **Privacy-safe effectiveness metrics**: Set top-level `effectivenessMetrics.enabled` to `true`. This path does not enable debug logging. It records only fixed route/host/outcome counters and bounded result-count, latency, token-budget, and returned-token histograms. Counters are disabled by default, memory-only, fixed-cardinality, and process-lifetime across Indexer replacement and configuration-watcher refresh. One process-wide collector aggregates opted-in calls without project or repository identity dimensions. It never retains queries, response text, source, symbols, paths, repository names, user identity, or stable identifiers.
+- **Privacy-safe effectiveness metrics**: Set top-level `effectivenessMetrics.enabled` to `true`. This path does not enable debug logging. It records fixed route/host/outcome counters, bounded aggregate histograms, and bounded per-route outcome, result-count, latency, and returned-token histograms. The per-route views make it possible to compare route reliability and cost without retaining request data. Counters are disabled by default, memory-only, fixed-cardinality, and process-lifetime across Indexer replacement and configuration-watcher refresh. One process-wide collector aggregates opted-in calls without project or repository identity dimensions. It never retains queries, response text, source, symbols, paths, repository names, user identity, or stable identifiers.
 - **Effectiveness-only privacy boundary**: With only `effectivenessMetrics.enabled` set, `debug.enabled` remains `false`, `index_logs` remains disabled, operational debug metrics remain off, and no query, path, source, secret, or response text is emitted by metrics output or written to index files. Only the bounded aggregate snapshot is returned by `index_metrics`.
 - **Debug logging is separate**: Explicitly enabling `debug.enabled` with `debug.logSearch` preserves the existing diagnostic behavior and may retain raw queries and repository details in memory. Do not enable debug search logs when only privacy-safe aggregates are wanted.
 - **Reset**: Pass `reset: true` to clear both operational and process-wide effectiveness metrics before returning the new zeroed snapshot. Process exit also clears effectiveness metrics because they are never persisted.
@@ -801,6 +801,7 @@ Zero-config by default (uses `auto` mode). Customize in `.opencode/codebase-inde
     "autoIndexMaxRetries": 5,                 // Transient interprocess lock retries (0-10)
     "autoIndexRetryDelayMs": 100,             // Initial exponential lock retry delay
     "watchFiles": true,                       // Re-index on file changes
+    "pauseBackgroundIndexingOnBattery": false, // Defer background indexing on macOS battery power
     "maxFileSize": 1048576,                   // Max file size in bytes (default: 1MB)
     "maxChunksPerFile": 100,                  // Max chunks per file
     "semanticOnly": false,                    // Only index functions/classes (skip blocks)
@@ -843,7 +844,7 @@ Zero-config by default (uses `auto` mode). Customize in `.opencode/codebase-inde
     "logEmbedding": true,                     // Log embedding API calls
     "logCache": true,                         // Log cache hits/misses
     "logGc": true,                            // Log garbage collection
-    "logBranch": true,                        // Log branch detection
+    "logBranch": true,                        // Log branch detection and switches to index_logs (no stdout output)
     "metrics": false                          // Enable operational metrics collection
   },
   "effectivenessMetrics": {
@@ -884,6 +885,7 @@ String values in `codebase-index.json` can reference environment variables with
 | `autoIndexMaxRetries` | `5` | Maximum transient interprocess lock retries (0-10) for background automatic indexing. |
 | `autoIndexRetryDelayMs` | `100` | Initial exponential lock retry delay in milliseconds (10-10000). |
 | `watchFiles` | `true` | Re-index when files change |
+| `pauseBackgroundIndexingOnBattery` | `false` | On macOS, defer automatic startup and watcher-triggered indexing while using battery power, then run one pending incremental update after AC power returns. Manual `index_codebase` requests remain available. This option has no effect on other platforms. |
 | `maxFileSize` | `1048576` | Skip files larger than this (bytes). Default: 1MB |
 | `maxChunksPerFile` | `100` | Maximum chunks to index per file (controls token costs for large files) |
 | `semanticOnly` | `false` | When `true`, only index semantic nodes (functions, classes) and skip generic blocks |
@@ -905,7 +907,7 @@ String values in `codebase-index.json` can reference environment variables with
 | `rrfK` | `60` | RRF smoothing constant. Higher values flatten rank impact, lower values prioritize top-ranked candidates more strongly |
 | `rerankTopN` | `20` | Deterministic rerank depth cap. Applies lightweight name/path/chunk-type rerank to top-N only |
 | `contextLines` | `0` | Extra lines to include before/after each match |
-| `routingHints` | `true` | Inject lightweight runtime hints for local conceptual discovery and definition lookups. Set to `false` to disable plugin-side routing nudges. |
+| `routingHints` | `true` | Inject lightweight runtime hints for local conceptual discovery, broad repository coding tasks, and definition lookups. Set to `false` to disable plugin-side routing nudges. |
 | `routingGraphHandoffHints` | `false` | When `true`, conceptual discovery hints also say to use graph tools (including OMO CodeGraph) after semantic discovery identifies relevant symbols. |
 | `routingHintRole` | `"system"` | Message role used when injecting routing hints: `"system"` (default) or `"developer"`. |
 | **reranker** | | Optional second-stage model reranker for the top candidate pool |
@@ -923,7 +925,7 @@ String values in `codebase-index.json` can reference environment variables with
 | `logEmbedding` | `true` | Log embedding API calls (success, error, rate-limit) |
 | `logCache` | `true` | Log cache hits and misses |
 | `logGc` | `true` | Log garbage collection operations |
-| `logBranch` | `true` | Log branch detection and switches |
+| `debug.logBranch` | `true` | Record branch detection and switches in `index_logs` when `debug.enabled` is also `true`; never prints routine branch changes to stdout |
 | `metrics` | `false` | Enable metrics collection (indexing stats, search timing, cache performance) |
 | **effectivenessMetrics** | | |
 | `enabled` | `false` | Independently opt in to memory-only, fixed-cardinality repository-tool effectiveness counters. Does not enable debug logs; stores no queries, response text, code, symbols, paths, repo names, user identity, or stable identifiers. |
@@ -940,7 +942,7 @@ These warnings improve observability but do **not** change the recovery behavior
 ### Retrieval ranking behavior
 
 - `codebase_search` and `codebase_peek` use the hybrid path: semantic + keyword retrieval → fusion (`fusionStrategy`) → deterministic rerank (`rerankTopN`) → optional external reranker (`reranker`) → filtering.
-- When `search.routingHints` is enabled (default), the plugin adds tiny per-turn runtime hints for local conceptual discovery and definition queries. Conceptual discovery is nudged toward `codebase_peek` / `codebase_search`, while definition questions are nudged toward `implementation_lookup`. Exact identifier and unrelated operational tasks are left alone. Set `search.routingGraphHandoffHints` to `true` to add opt-in graph/OMO CodeGraph handoff wording, and set `search.routingHintRole` to `"developer"` if your client/runtime expects developer-role guidance instead of system-role guidance.
+- When `search.routingHints` is enabled (default), the plugin adds a tiny, one-shot runtime hint for matching local conceptual discovery, broad repository coding tasks such as fixing or investigating code, and definition queries. A hint is emitted at most once per user message, so tool-call loops do not repeatedly add it. Conceptual and broad-task prompts are nudged toward `codebase_context` first, with `codebase_peek` / `codebase_search` for targeted follow-up, while definition questions are nudged toward `implementation_lookup`. Exact identifier and unrelated operational tasks are left alone. Set `search.routingGraphHandoffHints` to `true` to add opt-in graph/OMO CodeGraph handoff wording, and set `search.routingHintRole` to `"developer"` if your client/runtime expects developer-role guidance instead of system-role guidance.
 - `find_similar` stays semantic-only: semantic retrieval + deterministic rerank only (no keyword retrieval, no RRF).
 - For compatibility rollbacks, set `search.fusionStrategy` to `"weighted"` to use the legacy weighted fusion path.
 - When enabled, the external reranker sees path metadata plus a bounded on-disk code snippet for each candidate so it can distinguish real implementations from docs/tests more reliably.