@skein-code/cli 0.3.19 → 0.3.20

package/docs/NEXT_STEPS.md

@@ -75,8 +75,10 @@ SQL, CJK, Markdown, and mixed-language cases across ten files. The first
 expanded run failed its preselected useful-token threshold at `0.348`; the
 implementation reached `0.729` while Recall@5/10/20 and MRR remained `1.0`,
 stale-hit rate stayed `0`, warm p95 was below 10 ms, and incremental indexing
-reused every fixture file. Git-recency, diagnostics ranking, broader language
-AST adapters, and production-scale calibration remain follow-up slices.
+reused every fixture file. Git-recency is now a bounded, isolated tie-break
+with exact HEAD-bound cache invalidation and non-Git degradation. Diagnostics
+ranking, broader language AST adapters, and production-scale calibration remain
+follow-up slices.
 
 ### P0-E: Token Economy measurement and bounded schema disclosure
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@skein-code/cli",
-  "version": "0.3.19",
+  "version": "0.3.20",
   "description": "A context-first, model-agnostic coding agent with an auditable terminal workspace.",
   "type": "module",
   "license": "MIT",
@@ -36,7 +36,8 @@
       "Prompt and timeline diagnostics expose the repository-first reuse ladder without blocking legitimate writes",
       "Known tool changes refresh only their affected local-index paths before the next model turn",
       "File ctime closes same-size and restored-mtime zero-hit freshness gaps without full-content scans",
-      "Repeated empty or unchanged search calls stop through the existing recovery circuit"
+      "Repeated empty or unchanged search calls stop through the existing recovery circuit",
+      "Git recency is an isolated, bounded tie-break with exact HEAD-bound cache invalidation and non-Git degradation"
     ]
   },
   "bin": {