agenr 0.5.4 → 0.6.0

package/CHANGELOG.md

@@ -1,14 +1,28 @@
 # Changelog
 
-## [0.5.4] - 2026-02-18
+## [0.6.0] - 2026-02-18
 
 ### Added
-- feat(todo): `agenr todo done` command to immediately retire resolved todos
-- feat(mcp): `agenr_done` MCP tool for agent-driven todo retirement
-- feat(extractor): todo completion detection in `SYSTEM_PROMPT`
+- feat(consolidate): forgettingScore, protected subject patterns, and active forgetting pass with `--forget` deletion gate
+- feat(config): `forgetting.protect` never-forget registry plus `scoreThreshold`/`maxAgeDays`/`enabled` config defaults
+- feat(health): new `agenr health` command with read-only DB health and forgetting candidate summaries
+- feat(consolidate): `--report` pre-run consolidation stats mode (and report-only behavior with `--dry-run`)
+- feat(watch): `context-mini.md` and `context-hot.md` context variants on watch context refresh
+- feat(schema): retired, retired_at, retired_reason, suppressed_contexts columns
+- feat(recall): session-start context filtering respects suppressed_contexts
+- feat(db): retirements.json ledger for durable retirement across re-ingest
+- feat(mcp): entry IDs in agenr_recall output
+- feat(mcp): agenr_retire tool - retire any entry type by ID
+- feat(cli): agenr retire command with dry-run, persist, contains flags
 
 ### Fixed
-- fix(store): cross-type canonical_key superseding allows events to retire todos
+- fix(health): initialize schema before health queries and support `--db` path override
+- fix(health): reduce scan memory usage by omitting `content` from health stats query
+- fix(consolidate): batch forgetting deletes, reuse assessed candidates, and avoid synchronous full `VACUUM`
+- fix(watch): use real recall score breakdown in generated context variants
+
+### Removed
+- agenr_done MCP tool removed (breaking change) -- use agenr_retire instead. agenr_retire accepts an entry ID from agenr_recall output and works on all entry types, not just todos.
 
 ## [0.5.3] - 2026-02-18
 
@@ -49,12 +63,6 @@
 - Watch ingestion now advances `byteOffset` by bytes actually read in each cycle, preventing duplicate processing when files grow during read.
 - Watch state saves are now atomic (temp file + rename), preventing partial-write corruption on process crashes.
 
-## 0.6.0 (2026-02-18)
-
-### Added
-- feat(extractor): explicit "remember this/that" intent detection, importance >= 7
-- feat(watch): session label -> project mapping via `config.labelProjectMap`
-
 ## 0.5.0 (2026-02-17)
 
 ### Added

package/README.md

@@ -25,6 +25,8 @@ export OPENAI_API_KEY=sk-...  # for embeddings + extraction
 ```bash
 # Install
 npm install -g agenr
+# or
+pnpm add -g agenr
 
 # Configure (picks your LLM provider, walks you through auth)
 agenr setup

package/dist/cli-main.d.ts

@@ -20,6 +20,13 @@ interface AgenrConfig {
     auth?: AgenrAuthMethod;
     provider?: AgenrProvider;
     model?: string;
+    labelProjectMap?: Record<string, string>;
+    forgetting?: {
+        protect?: string[];
+        scoreThreshold?: number;
+        maxAgeDays?: number;
+        enabled?: boolean;
+    };
     credentials?: AgenrStoredCredentials;
     embedding?: {
         provider?: "openai";
@@ -36,6 +43,7 @@ interface KnowledgeEntry {
     content: string;
     subject: string;
     canonical_key?: string;
+    suppressedContexts?: string[];
     platform?: KnowledgePlatform;
     project?: string;
     importance: number;
@@ -104,6 +112,7 @@ interface ParsedTranscript {
         startedAt?: string;
         model?: string;
         cwd?: string;
+        sessionLabel?: string;
     };
 }
 interface ResolvedModel {