docs: v1.6.0 changelog, README, CLAUDE.md updates

Update CHANGELOG with v1.6.0 Onboarding + Identity entry, bump README
tool/endpoint counts to 25 MCP tools and 26 HTTP endpoints, add identity
endpoints to the HTTP table, check off Identity roadmap item, and document
identity.rs and onboarding.rs modules in CLAUDE.md architecture section.
Fix three clippy warnings (collapsible_if x2, if_same_then_else x1) and
reformat source files changed by this task.

Author: devwhodevs

CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## v1.6.0 — Onboarding + Identity (2026-04-10)
+
+### Added
+- **Interactive onboarding** (`engraph init`) — polished CLI with welcome banner, vault scan checkmarks, identity prompts via dialoguer, progress bars, actionable next steps
+- **Agent onboarding** — `engraph init --detect --json` for vault inspection, `--json` for non-interactive apply. Two-phase detect → apply flow for AI agents.
+- **`identity` MCP tool + CLI + HTTP** — returns compact L0/L1 identity block (~170 tokens) for AI session context
+- **`setup` MCP tool + HTTP** — first-time setup from inside an MCP session (detect/apply modes)
+- **`identity_facts` table** — SQLite storage for L0 (static identity) and L1 (dynamic context) facts
+- **L1 auto-extraction** — active projects, key people, current focus, OOO status, blocking items extracted during `engraph index`
+- **`engraph identity --refresh`** — re-extract L1 facts without full reindex
+- **`[identity]` config section** — name, role, vault_purpose in config.toml
+- **`[memory]` config section** — feature flags for identity/timeline/mining
+
+### Changed
+- MCP tools: 23 → 25
+- HTTP endpoints: 24 → 26
+- Dependencies: +dialoguer 0.12, +console 0.16, +regex 1
+
 ## v1.5.5 — Housekeeping (2026-04-10)
 
 ### Added

CLAUDE.md

@@ -32,6 +32,8 @@ Single binary with 26 modules behind a lib crate:
 - `indexer.rs` — orchestrates vault walking (via `ignore` crate for `.gitignore` support), diffing, chunking, embedding, writes to store + sqlite-vec + FTS5, vault graph edge building (wikilinks + people detection), and folder centroid computation. Exposes `index_file`, `remove_file`, `rename_file` as public per-file functions. `run_index_shared` accepts external store/embedder for watcher FullRescan. Dimension migration on model change.
 - `temporal.rs` — temporal search lane. Extracts note dates from frontmatter `date:` field or `YYYY-MM-DD` filename patterns. Heuristic date parsing for natural language ("today", "yesterday", "last week", "this month", "recent", month names, ISO dates, date ranges). Smooth decay scoring for files near but outside target date range. Provides `extract_note_date()` for indexing and `score_temporal()` + `parse_date_range_heuristic()` for search
 - `search.rs` — hybrid search orchestrator. `search_with_intelligence()` runs the full pipeline: orchestrate (intent + expansions) → 5-lane RRF retrieval (semantic + FTS5 + graph + reranker + temporal) per expansion → two-pass RRF fusion. `search_internal()` is a thin wrapper without intelligence models. Adaptive lane weights per query intent including temporal (1.5 weight for time-aware queries). Results display normalized confidence percentages (0-100%) instead of raw RRF scores.
+- `identity.rs` — L1 extraction engine: active projects, key people, current focus, OOO, blocking. `format_identity_block()` for compact session context. `extract_l1_facts()` called after indexing.
+- `onboarding.rs` — Interactive CLI UX: welcome banner, vault scan, identity prompts (dialoguer), agent mode (--detect --json, --json). `run_interactive()`, `run_detect_json()`, `run_apply_json()`.
 
 `main.rs` is a thin clap CLI (async via `#[tokio::main]`). Subcommands: `index` (with progress bar), `search` (with `--explain`, loads intelligence models when enabled), `status` (shows intelligence state + date coverage stats), `clear`, `init` (intelligence onboarding prompt, detects Obsidian CLI + AI agents), `configure` (`--enable-intelligence`, `--disable-intelligence`, `--model`, `--obsidian-cli`, `--no-obsidian-cli`, `--agent`, `--add-api-key`, `--list-api-keys`, `--revoke-api-key`, `--setup-chatgpt`), `models`, `graph` (show/stats), `context` (read/list/vault-map/who/project/topic), `write` (create/append/update-metadata/move/edit/rewrite/edit-frontmatter/delete), `migrate` (para with `--preview`/`--apply`/`--undo` for PARA vault restructuring), `serve` (MCP stdio server with file watcher + intelligence + optional `--http`/`--port`/`--host`/`--no-auth` for HTTP REST API).
 

README.md

@@ -21,8 +21,8 @@ engraph turns your markdown vault into a searchable knowledge graph that any AI
 Plain vector search treats your notes as isolated documents. But knowledge isn't flat — your notes link to each other, share tags, reference the same people and projects. engraph understands these connections.
 
 - **5-lane hybrid search** — semantic embeddings + BM25 full-text + graph expansion + cross-encoder reranking + temporal scoring, fused via [Reciprocal Rank Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf). An LLM orchestrator classifies queries and adapts lane weights per intent. Time-aware queries like "what happened last week" or "March 2026 notes" activate the temporal lane automatically.
-- **MCP server for AI agents** — `engraph serve` exposes 22 tools (search, read, section-level editing, frontmatter mutations, vault health, context bundles, note creation, PARA migration) that Claude, Cursor, or any MCP client can call directly.
-- **HTTP REST API** — `engraph serve --http` adds an axum-based HTTP server alongside MCP with 23 REST endpoints, API key authentication, rate limiting, and CORS. Web-based agents and scripts can query your vault with simple `curl` calls.
+- **MCP server for AI agents** — `engraph serve` exposes 25 tools (search, read, section-level editing, frontmatter mutations, vault health, context bundles, note creation, PARA migration, identity) that Claude, Cursor, or any MCP client can call directly.
+- **HTTP REST API** — `engraph serve --http` adds an axum-based HTTP server alongside MCP with 26 REST endpoints, API key authentication, rate limiting, and CORS. Web-based agents and scripts can query your vault with simple `curl` calls.
 - **Section-level editing** — AI agents can read, replace, prepend, or append to specific sections by heading. Full note rewriting with frontmatter preservation. Granular frontmatter mutations (set/remove fields, add/remove tags and aliases).
 - **Vault health diagnostics** — detect orphan notes, broken wikilinks, stale content, and tag hygiene issues. Available as MCP tool and CLI command.
 - **Obsidian CLI integration** — auto-detects running Obsidian and delegates compatible operations. Circuit breaker (Closed/Degraded/Open) ensures graceful fallback.
@@ -61,7 +61,7 @@ Your vault (markdown files)
 │  Search: Orchestrator → 4-lane retrieval    │
 │          → Reranker → Two-pass RRF fusion   │
 │                                             │
-│  22 MCP tools + 23 REST endpoints           │
+│  25 MCP tools + 26 REST endpoints           │
 └─────────────────────────────────────────────┘
         │
         ▼
@@ -268,7 +268,7 @@ Returns orphan notes (no links in or out), broken wikilinks, stale notes, and ta
 
 `engraph serve --http` adds a full REST API alongside the MCP server, exposing the same capabilities over HTTP for web agents, scripts, and integrations.
 
-**24 endpoints:**
+**26 endpoints:**
 
 | Method | Endpoint | Permission | Description |
 |--------|----------|------------|-------------|
@@ -292,6 +292,8 @@ Returns orphan notes (no links in or out), broken wikilinks, stale notes, and ta
 | POST | `/api/unarchive` | write | Restore archived note |
 | POST | `/api/update-metadata` | write | Update note metadata |
 | POST | `/api/delete` | write | Delete note (soft or hard) |
+| GET | `/api/identity` | read | User identity (L0) and current context (L1) |
+| POST | `/api/setup` | write | First-time onboarding setup (detect/apply modes) |
 | POST | `/api/reindex-file` | write | Re-index a single file after external edits |
 | POST | `/api/migrate/preview` | write | Preview PARA migration (classify + suggest moves) |
 | POST | `/api/migrate/apply` | write | Apply PARA migration (move files) |
@@ -526,7 +528,7 @@ STYLE:
 | Search method | 5-lane RRF (semantic + BM25 + graph + reranker + temporal) | Vector similarity only | Keyword only |
 | Query understanding | LLM orchestrator classifies intent, adapts weights | None | None |
 | Understands note links | Yes (wikilink graph traversal) | No | Limited (backlinks panel) |
-| AI agent access | MCP server (22 tools) + HTTP REST API (23 endpoints) | Custom API needed | No |
+| AI agent access | MCP server (25 tools) + HTTP REST API (26 endpoints) | Custom API needed | No |
 | Write capability | Create/edit/rewrite/delete with smart filing | No | Manual |
 | Vault health | Orphans, broken links, stale notes, tag hygiene | No | Limited |
 | Real-time sync | File watcher, 2s debounce | Manual re-index | N/A |
@@ -543,8 +545,9 @@ engraph is not a replacement for Obsidian — it's the intelligence layer that s
 - LLM research orchestrator: query intent classification + query expansion + adaptive lane weights
 - llama.cpp inference via Rust bindings (GGUF models, Metal GPU on macOS, CUDA on Linux)
 - Intelligence opt-in: heuristic fallback when disabled, LLM-powered when enabled
-- MCP server with 23 tools (8 read, 10 write, 1 index, 1 diagnostic, 3 migrate) via stdio
-- HTTP REST API with 24 endpoints, API key auth (`eg_` prefix), rate limiting, CORS — enabled via `engraph serve --http`
+- MCP server with 25 tools (8 read, 10 write, 2 identity, 1 index, 1 diagnostic, 3 migrate) via stdio
+- HTTP REST API with 26 endpoints, API key auth (`eg_` prefix), rate limiting, CORS — enabled via `engraph serve --http`
+- User identity with L0/L1 tiered context for AI agent session starts
 - Section-level reading and editing: target specific headings with replace/prepend/append modes
 - Full note rewriting with automatic frontmatter preservation
 - Granular frontmatter mutations: set/remove fields, add/remove tags and aliases
@@ -573,7 +576,7 @@ engraph is not a replacement for Obsidian — it's the intelligence layer that s
 - [x] ~~HTTP/REST API — complement MCP with a standard web API~~ (v1.3)
 - [x] ~~PARA migration — AI-assisted vault restructuring with preview/apply/undo~~ (v1.4)
 - [x] ~~ChatGPT Actions — OpenAPI 3.1.0 spec + plugin manifest + `--setup-chatgpt` helper~~ (v1.5)
-- [ ] Identity — user context at session start, enhanced onboarding (v1.6)
+- [x] ~~Identity — user context at session start, enhanced onboarding~~ (v1.6)
 - [ ] Timeline — temporal knowledge graph with point-in-time queries (v1.7)
 - [ ] Mining — automatic fact extraction from vault notes (v1.8)
 

src/http.rs

@@ -1116,13 +1116,9 @@ async fn handle_setup(
                 identity_only: false,
                 reindex_only: false,
             };
-            let result = crate::onboarding::run_apply_json(
-                &state.vault_path,
-                &mut config,
-                &data_dir,
-                flags,
-            )
-            .map_err(|e| ApiError::internal(&format!("{e:#}")))?;
+            let result =
+                crate::onboarding::run_apply_json(&state.vault_path, &mut config, &data_dir, flags)
+                    .map_err(|e| ApiError::internal(&format!("{e:#}")))?;
             Ok(Json(result))
         }
         other => Err(ApiError::bad_request(&format!(

src/identity.rs

@@ -71,19 +71,18 @@ pub fn extract_l1_facts(store: &Store, profile: &VaultProfile) -> Result<L1Summa
         daily_files.sort_by(|a, b| b.note_date.cmp(&a.note_date));
 
         // ── Current focus (most recent daily note) ──────────────
-        if let Some(latest) = daily_files.first() {
-            if let Ok(chunks) = store.get_chunks_by_file(latest.id) {
-                let focus_re =
-                    Regex::new(r"(?i)morning\s+focus|top\s+priorit|priorities").unwrap();
-                for chunk in &chunks {
-                    if focus_re.is_match(&chunk.heading) {
-                        let items = extract_bullet_items(&chunk.snippet, 3);
-                        for item in items {
-                            store.upsert_identity_fact(1, "current_focus", &item, None)?;
-                            summary.current_focus += 1;
-                        }
-                        break;
+        if let Some(latest) = daily_files.first()
+            && let Ok(chunks) = store.get_chunks_by_file(latest.id)
+        {
+            let focus_re = Regex::new(r"(?i)morning\s+focus|top\s+priorit|priorities").unwrap();
+            for chunk in &chunks {
+                if focus_re.is_match(&chunk.heading) {
+                    let items = extract_bullet_items(&chunk.snippet, 3);
+                    for item in items {
+                        store.upsert_identity_fact(1, "current_focus", &item, None)?;
+                        summary.current_focus += 1;
                     }
+                    break;
                 }
             }
         }
@@ -171,7 +170,10 @@ pub fn format_identity_block(config: &Config, store: &Store) -> Result<String> {
         .max()
         .unwrap_or("unknown");
 
-    out.push_str(&format!("\n## Current State (L1) [updated {}]\n", latest_ts));
+    out.push_str(&format!(
+        "\n## Current State (L1) [updated {}]\n",
+        latest_ts
+    ));
 
     // Group facts by key.
     let project_vals: Vec<&str> = facts
@@ -343,13 +345,28 @@ mod tests {
 
         // Insert L1 facts manually.
         store
-            .upsert_identity_fact(1, "active_project", "ProjectA", Some("01-Projects/ProjectA.md"))
+            .upsert_identity_fact(
+                1,
+                "active_project",
+                "ProjectA",
+                Some("01-Projects/ProjectA.md"),
+            )
             .unwrap();
         store
-            .upsert_identity_fact(1, "active_project", "ProjectB", Some("01-Projects/ProjectB.md"))
+            .upsert_identity_fact(
+                1,
+                "active_project",
+                "ProjectB",
+                Some("01-Projects/ProjectB.md"),
+            )
             .unwrap();
         store
-            .upsert_identity_fact(1, "key_person", "Alice", Some("03-Resources/People/Alice.md"))
+            .upsert_identity_fact(
+                1,
+                "key_person",
+                "Alice",
+                Some("03-Resources/People/Alice.md"),
+            )
             .unwrap();
         store
             .upsert_identity_fact(1, "current_focus", "Ship feature X", None)

src/indexer.rs

@@ -461,7 +461,14 @@ pub fn run_index(vault_path: &Path, config: &Config, rebuild: bool) -> Result<In
     store.set_meta("embedding_dim", &model_dim.to_string())?;
 
     let profile = crate::config::Config::load_vault_profile().ok().flatten();
-    run_index_inner(vault_path, config, &store, &mut embedder, rebuild, profile.as_ref())
+    run_index_inner(
+        vault_path,
+        config,
+        &store,
+        &mut embedder,
+        rebuild,
+        profile.as_ref(),
+    )
 }
 
 /// Like [`run_index`], but accepts shared `Store` and `Embedder` references.
@@ -668,10 +675,10 @@ fn run_index_inner(
     }
 
     // Extract L1 identity facts from the freshly indexed vault
-    if let Some(p) = profile {
-        if let Err(e) = crate::identity::extract_l1_facts(store, p) {
-            tracing::warn!("L1 identity extraction failed (non-fatal): {e:#}");
-        }
+    if let Some(p) = profile
+        && let Err(e) = crate::identity::extract_l1_facts(store, p)
+    {
+        tracing::warn!("L1 identity extraction failed (non-fatal): {e:#}");
     }
 
     let duration = start.elapsed();

src/main.rs

@@ -548,7 +548,17 @@ async fn main() -> Result<()> {
             }
         }
 
-        Command::Init { path, identity, reindex, detect, json, quiet, name, role, purpose } => {
+        Command::Init {
+            path,
+            identity,
+            reindex,
+            detect,
+            json,
+            quiet,
+            name,
+            role,
+            purpose,
+        } => {
             cfg.merge_vault_path(path);
             let vault_path = match &cfg.vault_path {
                 Some(p) => p.clone(),
@@ -558,27 +568,28 @@ async fn main() -> Result<()> {
 
             if detect {
                 let result = engraph::onboarding::run_detect_json(&vault_path)?;
-                if json {
-                    println!("{}", serde_json::to_string_pretty(&result)?);
-                } else {
-                    println!("{}", serde_json::to_string_pretty(&result)?);
-                }
+                println!("{}", serde_json::to_string_pretty(&result)?);
                 return Ok(());
             }
 
             if json {
                 let flags = engraph::onboarding::ApplyFlags {
-                    name, role, purpose,
+                    name,
+                    role,
+                    purpose,
                     identity_only: identity,
                     reindex_only: reindex,
                 };
-                let result = engraph::onboarding::run_apply_json(&vault_path, &mut cfg, &data_dir, flags)?;
+                let result =
+                    engraph::onboarding::run_apply_json(&vault_path, &mut cfg, &data_dir, flags)?;
                 println!("{}", serde_json::to_string_pretty(&result)?);
                 return Ok(());
             }
 
             let flags = engraph::onboarding::InteractiveFlags {
-                name, role, purpose,
+                name,
+                role,
+                purpose,
                 identity_only: identity,
                 reindex_only: reindex,
                 quiet,