vericify 1.3.0 → 1.3.1

package/README.md

@@ -8,15 +8,15 @@ __     _______ ____  ___ ____ ___ _______   __
    \_/  |_____|_| \_\___\____|___|_|     |_|
 ```
 
-Vericify is a local-first operations hub for agent work.
+Vericify is a local-first run intelligence hub for multi-agent workflows and AI agent state.
 
-It gives a workspace a durable run model instead of making you reconstruct intent from chat scrollback, shell history, and raw logs.
+It gives a workspace durable run records, checkpointed handoffs, and a four-layer compare engine instead of making you reconstruct intent from chat scrollback, shell history, and raw logs.
 
 It works on its own, and it also plugs neatly into [ACE / ace-swarm](https://www.npmjs.com/package/ace-swarm) workspaces that already emit `agent-state/*`.
 
 ## Product Summary
 
-Vericify is for people building with agents who want to answer questions like:
+Vericify is for engineers building with AI agents who want run-level observability and clear answers to questions like:
 
 - What is moving right now?
 - What is blocked?
@@ -41,12 +41,12 @@ Default behavior is simple:
 
 Vericify gives you:
 
-- a terminal cockpit for run inspection
+- a terminal cockpit with four views — Hub, Inspect, Compare, History — for run inspection and agent observability
 - a structured run model built from handoffs, posts, todos, events, and checkpoints
-- a compare engine that explains divergence and recovery
+- a compare engine that measures divergence and recovery across four layers: exact diff, structural delta, semantic similarity (MinHash), and operational timing
 - publishable run artifacts under `.vericify/published/`
 - a local-first sync outbox under `.vericify/sync-outbox/`
-- partner compatibility with [ACE / ace-swarm](https://www.npmjs.com/package/ace-swarm)
+- adapter contracts for Claude Code, Codex, Cursor, VS Code Copilot, Antigravity, and [ACE / ace-swarm](https://www.npmjs.com/package/ace-swarm) workspaces
 
 ## Install
 
@@ -99,7 +99,7 @@ For Claude Code, `vericify attach --adapter claude-code` also writes compact-boo
 
 ## Compact Bootstrap And Resume
 
-Use the compact packet when you want session bootstrap or resume without rereading the full projected state:
+Use the compact packet when you want session bootstrap or resume without rereading the full projected state. This is the primary path for workflow continuity across context resets:
 
 ```bash
 vericify context
@@ -215,7 +215,7 @@ vericify hub
 
 Best when you already have `agent-state/*` and want a cockpit, history, and compare surface.
 
-### Use case 2: Tag a Codex or Claude Code workspace before richer capture exists
+### Use case 2: Tag a Codex, Claude Code, Cursor, VS Code Copilot, or Antigravity workspace before richer capture exists
 
 ```bash
 vericify attach --adapter codex --label "Primary Codex"
@@ -243,14 +243,13 @@ Best when you want to model agent work directly in Vericify.
 vericify compare --run-id handoff:run-a --compare-run-id workspace:current
 ```
 
-The comparison report includes:
+The comparison runs four layers simultaneously — exact diff, structural graph delta, semantic MinHash similarity, and operational timing analysis — and returns:
 
-- composite similarity
+- composite similarity score
 - latest checkpoint similarity
-- actor overlap
-- node overlap
+- actor and node overlap
 - layer-level divergence cues
-- recovery explanations
+- recovery paths from prior runs
 - recommended next actions
 
 ### Use case 5: Publish or queue a run artifact
@@ -275,7 +274,7 @@ This writes:
 - `Lane`: one concurrent execution stream
 - `Handoff`: transfer of responsibility
 - `Checkpoint`: durable snapshot at a meaningful transition
-- `Delta`: structural, semantic, or operational change between checkpoints
+- `Delta`: change between checkpoints, measured across four layers: exact diff, structural graph, semantic MinHash, and operational timing
 
 ### Storage Contract
 
@@ -384,38 +383,34 @@ Start the cockpit:
 vericify hub
 ```
 
+The cockpit has four views. Each answers a different operational question.
+
 Keys:
 
 - `q` quit
 - `j` / `k` move between runs
-- `Enter` inspect selected run
-- `c` compare selected run
-- `y` history view
-- `h` back to hub
+- `Enter` inspect selected run — lane activity, blockers, checkpoint timeline
+- `c` compare selected run — four-layer diff across exact, structural, semantic, and operational dimensions
+- `y` history view — prior runs indexed, recovery patterns ranked by similarity to the current state
+- `a` adapters view — attached tools and detection status
+- `h` back to hub — all active runs, what is moving, what is blocked
 - `r` refresh
 - `/` command palette
 - `Ctrl+R` command history search
 
 ## Programmatic API
 
-The package also exports:
+The package exports functions for workspace state projection, run comparison, and artifact publishing:
 
 - `loadWorkspaceState`
 - `projectWorkspaceState`
 - `buildCompactPacket`
+- `buildCompactPacketDetails`
 - `buildCompactDelta`
 - `detectAdapters`
+- `listAvailableAdapters`
+- `listDefaultWorkspacePaths`
 - `attachAdapter`
 - `buildRunComparison`
 - `publishRunArtifact`
 - `enqueueSyncOutboxItem`
-
-## Honest Status
-
-Vericify is intentionally honest about what is implemented now.
-
-- peer client adapters are not full live capture bridges yet
-- hosted sync is an outbox contract today, not a running SaaS backend
-- git-backed diffing exists as optional provenance, not the whole product
-
-That is deliberate: the package is meant to be useful now, without pretending unfinished infrastructure already exists.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vericify",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "private": false,
   "type": "module",
   "description": "Local-first run intelligence and operations hub for agent systems.",