@andespindola/brainlink 0.1.0-beta.4 → 0.1.0-beta.40

package/docs/AGENT_USAGE.md

@@ -18,7 +18,7 @@ The correct dependency direction is:
 agent -> Brainlink CLI -> Markdown vault + derived index
 ```
 
-Agents should never depend on the internal SQLite schema as a public API.
+Agents should never depend on internal index persistence files as a public API.
 
 The installed CLI exposes two equivalent binaries:
 
@@ -39,9 +39,19 @@ $HOME/.brainlink/vault
 
 `blink server` follows the same rule, so it serves the default Brainlink vault instead of the current working directory.
 
-Use `--vault <path>` for a one-off custom vault, or set `vault` in `brainlink.config.json` / `.brainlink.json` for a workspace-level custom default. Set `BRAINLINK_HOME` when the whole Brainlink home directory should live somewhere else.
+Use `--vault <path>` for a one-off custom vault, or set `vault` in config for a persistent default.
+Configuration precedence is:
+
+1. global: `$BRAINLINK_HOME/brainlink.config.json` (or `$HOME/.brainlink/brainlink.config.json`)
+2. local: `./brainlink.config.json`
+3. local legacy: `./.brainlink.json`
+
+Set `BRAINLINK_HOME` when the whole Brainlink home directory should live somewhere else.
+
+Use `blink config where` and `blink config doctor` to inspect active paths and effective source.
 
 You can also set `defaultAgent` in `brainlink.config.json` / `.brainlink.json` (for example `"defaultAgent": "coding-agent"`). When set, CLI commands and MCP calls reuse it when `--agent`/`agent` is not passed.
+You can set `agentProfiles` to define per-agent defaults for `defaultSearchMode`, `defaultSearchLimit` and `defaultContextTokens`.
 
 `autoIndexOnWrite` (default: `true`) controls whether `add` and MCP write tools index right after writing.
 
@@ -170,16 +180,16 @@ Required write behavior:
 Good linked note:
 
 ```bash
-blink add "SQLite Index Rebuild" \
+blink add "Index Rebuild" \
   --agent coding-agent \
-  --content "Legacy derived indexes without agent columns are rebuilt because SQLite is disposable. Related: [[Architecture]], [[Agent Namespaces]]. #sqlite #architecture #decision"
+  --content "Derived index artifacts are rebuildable and disposable. Related: [[Architecture]], [[Agent Namespaces]]. #index #architecture #decision"
 blink validate --agent coding-agent
 ```
 
 Poor disconnected note:
 
 ```bash
-blink add "SQLite Index Rebuild" \
+blink add "Index Rebuild" \
   --agent coding-agent \
   --content "We rebuild old indexes now."
 ```
@@ -246,7 +256,7 @@ cp docs/templates/agent-note-template.md /tmp/agent-note.md
 When using MCP, use this compact sequence for the same memory discipline:
 
 1. Bootstrap context:
-   - `brainlink_context` with `agent`, `query`, `mode: hybrid`, `limit`.
+   - `brainlink_bootstrap` with `agent`, optional `query`, `mode: hybrid`, `limit`.
 2. Capture durable decisions:
    - `brainlink_add_note` or `brainlink_add_file` with explicit `[[wiki links]]` and `#tags`.
 3. Run maintenance before handoff or before the next step:
@@ -341,7 +351,69 @@ $HOME/.brainlink/vault/
   .brainlink/
 ```
 
-`blink init ./vault` creates a custom vault instead.
+`blink init ./vault` creates a custom vault instead. If the custom vault is empty and the default `$HOME/.brainlink/vault` already has Markdown memory, Brainlink copies that content into the custom vault and reindexes it. Use `blink init ./vault --no-migrate-existing` to intentionally start empty, or `blink init ./vault --migrate-from <old-vault>` to migrate from a specific previous vault. Existing target files are not overwritten; conflicting source files are preserved with a `.conflict-<timestamp>` suffix.
+
+### Configure Defaults
+
+```bash
+blink config where
+blink config get vault
+blink config doctor
+blink config doctor --fix
+blink config set-vault /absolute/path/to/vault
+blink config set-vault /absolute/path/to/vault --global
+```
+
+`config set-vault` updates Brainlink config through CLI. By default it writes local `brainlink.config.json`, appends the vault to `allowedVaults`, and migrates markdown when the target is empty.
+
+### Migrate Vaults Explicitly
+
+```bash
+blink migrate-vault --from ~/.brainlink/vault --to ./team-vault --dry-run
+blink migrate-vault --from ~/.brainlink/vault --to ./team-vault
+blink migrate-vault --from ~/.brainlink/vault --to "s3://my-memory-bucket/brainlink"
+blink migrate-vault --from ~/.brainlink/vault --to ./team-vault --report ./migration-report.json
+```
+
+Use `--dry-run` to preview `copied`, `conflicted`, `unchanged` before writing files.
+
+### Import Legacy SQLite DB
+
+```bash
+blink db-import --vault ./team-vault
+blink db-import --vault ./team-vault --db ./legacy/brainlink.db
+blink db-import --vault ./team-vault --db ./legacy/brainlink.db --table legacy_notes --dry-run
+```
+
+`db-import` migrates rows from legacy SQLite memory into Markdown notes in the current vault and indexes the result by default.
+Without `--db`, Brainlink auto-detects common legacy database paths.
+Use `--agent` to force namespace, `--limit` for staged migration, `--dry-run` to preview writes, and `--no-index` to postpone indexing.
+
+### Install Agent Integration
+
+```bash
+blink agent install
+blink agent install --self-test
+blink agent upgrade
+blink agent policy --preset fully-auto
+blink agent policy --preset strict
+blink agent install --plugin-path ./plugins/brainlink
+blink agent status
+```
+
+`agent install` configures Brainlink MCP in `~/.codex/config.toml` so compatible agents can use Brainlink by default.
+Use `agent upgrade` on legacy installations to reapply the latest defaults and run self-test diagnostics.
+Use `agent policy --preset fully-auto` to keep startup/read auto-bootstrap enabled, or `agent policy --preset strict` to force explicit bootstrap calls.
+
+### Quickstart Plug-And-Play
+
+```bash
+blink quickstart --json
+blink quickstart --vault ./team-vault --agent coding-agent --query "architecture decisions" --json
+blink quickstart --vault ./team-vault --mcp-only --json
+```
+
+`quickstart` runs index, doctor, stats and validation, marks bootstrap readiness for MCP sessions, optionally returns context, and updates agent integration by default.
 
 ### Add A Note
 
@@ -356,6 +428,26 @@ blink add "Note Title" --vault ./vault --content-file ./notes.md --no-auto-index
 This creates a slugged Markdown file with frontmatter and a heading.
 
 The CLI blocks common secret patterns by default. Do not use `--allow-sensitive` unless the vault is intentionally protected.
+Brainlink also auto-connects notes that have no `[[wiki links]]` by adding a fallback edge to an agent hub note, so new memory does not stay disconnected.
+`add` also returns `possibleDuplicates` (exact hash + semantic candidates) so agents can decide duplicate resolution immediately.
+
+### Detect Duplicate Notes
+
+```bash
+blink dedupe --vault ./vault --json
+blink dedupe --vault ./vault --agent coding-agent --limit 20 --min-score 0.92 --json
+blink dedupe --vault ./vault --no-semantic --json
+```
+
+### Resolve Duplicate Notes
+
+```bash
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action merge --json
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action link --json
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action ignore --json
+```
+
+`dedupe-resolve` keeps connectivity: non-merge actions still create a low-priority related edge (`#related-to`).
 
 For agent-private memory:
 
@@ -395,12 +487,16 @@ blink search "authentication token policy" --vault ./vault --mode semantic --jso
 ```
 
 This returns matching chunks with title, source path, score, `textScore`, `semanticScore`, `searchMode`, and content.
+If `--mode`/`--limit` are omitted, Brainlink resolves those values from the active agent profile before global defaults.
 
 Search modes:
 
-- `hybrid`: default; combines SQLite FTS and local embedding similarity.
-- `fts`: lexical SQLite full-text search only.
-- `semantic`: local deterministic embedding similarity with SQLite bucket candidate narrowing.
+- `hybrid`: default; combines lexical matching and local embedding similarity.
+- `fts`: lexical full-text matching only.
+- `semantic`: local deterministic embedding similarity.
+
+Hybrid results are cached in-memory for a short TTL and invalidated when `.brainlink/index.json` changes.
+Context assembly uses middle-out ordering inside each note: the highest-scoring chunk is selected first, then nearby chunks are expanded while token budget allows.
 
 ### Build Agent Context
 
@@ -459,13 +555,26 @@ shared: 30 documents
 ```bash
 blink server --host 127.0.0.1 --port 4321
 blink server --vault ./vault --host 127.0.0.1 --port 4321
+blink server --vault ./vault --host 127.0.0.1 --port 4321 --no-open
 ```
 
 This starts a local frontend for inspecting the knowledge graph.
+By default it tries to open the graph in a native desktop GUI window:
+- macOS: Swift + WebKit
+- Windows: PowerShell WinForms WebBrowser
+- Linux: optional Python GTK + WebKit2 (requires `python3` + `gi` + `WebKit2`)
+
+On Linux, native GUI is disabled by default for better startup performance. Enable it with `BRAINLINK_LINUX_NATIVE_GUI=1`.
+If native GUI launch is unavailable, it falls back to dedicated app-window mode and then to the default browser.
+Use `--no-open` to keep the server headless.
+When native GUI is active, the GUI window closes automatically when the `blink server` process stops.
 
 Without `--vault`, the graph UI serves `$HOME/.brainlink/vault`.
 
-The frontend includes an agent selector. Selecting an agent calls the same read APIs with `agent=<agent-id>` and renders that namespace instead of merging every agent into one graph.
+The frontend includes an agent selector that shows only the agent id. Selecting an agent calls the same read APIs with `agent=<agent-id>` and renders that namespace instead of merging every agent into one graph.
+
+Graph navigation controls include zoom in, zoom out, fit visible nodes and reset-to-fit-all nodes. Mouse wheel zoom (including `cmd+scroll` and `ctrl+scroll`) is anchored to the cursor. Keyboard shortcuts are `+` (zoom in), `-` (zoom out) and `0` (reset fit). Double-click on canvas zooms in at cursor position. Totals for notes, links and tags stay visible as floating metrics under the Brainlink title, and node details open on click in a modal (tags, outgoing links, backlinks and Markdown content).
+During graph filtering, Brainlink keeps hub context nodes visible (`Memory Hub`/`MOC`/high-degree fallback) so filtered views still show relationship anchors.
 
 The command reindexes by default, then serves:
 
@@ -518,8 +627,13 @@ Example MCP client configuration:
 
 Available MCP tools:
 
+- `brainlink_bootstrap`
+- `brainlink_policy`
+- `brainlink_recommendations`
 - `brainlink_context`
 - `brainlink_search`
+- `brainlink_dedupe`
+- `brainlink_resolve_duplicate`
 - `brainlink_add_note`
 - `brainlink_add_file`
 - `brainlink_index`
@@ -530,9 +644,17 @@ Available MCP tools:
 - `brainlink_broken_links`
 - `brainlink_orphans`
 
+Recommended start of every memory-dependent task: call `brainlink_bootstrap` first, then `brainlink_context`. By default, Brainlink enforces context-first for non-context MCP reads (`enforceContextFirst=true`), and also enforces bootstrap with auto-bootstrap on reads when state is missing or stale (`autoBootstrapOnRead=true`).
+MCP startup also bootstraps the configured default vault/agent automatically (`autoBootstrapOnStartup=true`), so sessions start warm without manual calls.
+If `autoBootstrapOnRead` or `enforceContextFirst` are disabled through `brainlink_policy`, behavior is relaxed accordingly; otherwise read tools return preflight-required responses when requirements are not satisfied.
+`brainlink_bootstrap`, `brainlink_policy` and preflight responses include structured `nextActions` so clients can continue tool flows automatically.
+`brainlink_policy` also accepts policy presets (`fully-auto`, `strict`) so MCP clients can switch behavior in one call.
+`brainlink_recommendations` returns the suggested execution order so an agent can follow Brainlink best practices automatically.
+
 MCP clients can pass `vault` and `agent` arguments per tool call. Set `BRAINLINK_ALLOWED_VAULTS` when exposing Brainlink to an external agent process so a tool cannot pass arbitrary vault paths:
 
 `brainlink_graph` returns weighted edges. Agents should prefer higher `weight` and stronger `priority` when deciding which related notes matter most.
+`brainlink_add_note` and `brainlink_add_file` return `writeConnectivity` metadata and guarantee at least one edge for new notes.
 
 ```bash
 export BRAINLINK_ALLOWED_VAULTS="/absolute/path/to/project-vault"
@@ -543,6 +665,8 @@ export BRAINLINK_ALLOWED_VAULTS="/absolute/path/to/project-vault"
 ```txt
 GET  /api/graph
 GET  /api/graph-layout
+GET  /api/graph-node?id=<node-id>
+GET  /api/graph-filter?q=<query>&limit=<n>
 GET  /api/search?q=<query>&limit=10&mode=hybrid
 GET  /api/context?q=<query>&limit=12&tokens=2000&mode=hybrid
 GET  /api/links
@@ -555,6 +679,10 @@ GET  /api/validate
 
 The HTTP API is read-only. Use the CLI for writes and indexing.
 
+Indexing writes private encrypted search packs at `.brainlink/search-packs/*.blpk` for resilient retrieval and portability.
+Pack search now uses compressed-space prefiltering (token bloom index per pack) before decrypting/reading pack payloads.
+Pack decryption keys are resolved from `$BRAINLINK_HOME/keys` (or `BRAINLINK_SEARCH_PACK_KEY` when explicitly set).
+
 ## Agent Integration Contract
 
 Input:
@@ -586,9 +714,9 @@ Non-goals:
 ## Operational Rules
 
 - Re-run `index` after modifying notes.
-- Treat `.brainlink/brainlink.db` as disposable.
-- Commit Markdown notes, not local database files.
-- Do not manually edit the database.
+- Treat `.brainlink/index.json` and `.brainlink/search-packs/` as disposable.
+- Commit Markdown notes, not local index files.
+- Do not manually edit generated index artifacts.
 - Keep generated context short enough for the target model.
 - Prefer specific queries over broad queries.
 - Write explicit `[[wiki links]]` when durable memory should be connected.
@@ -618,9 +746,9 @@ Weak retrieval usually means:
 
 ## Current Limits
 
-- Search supports FTS, local semantic embeddings, SQLite semantic buckets and hybrid ranking.
+- Search supports FTS, local semantic embeddings and hybrid ranking.
 - Local embeddings are deterministic and provider-free; remote embedding providers are not implemented yet.
 - MCP integration is available through the `brainlink-mcp` stdio server.
 - HTTP API is local and unauthenticated.
-- Bucket vaults support S3-compatible `s3://bucket/prefix` URIs and use a local cache for SQLite indexes.
+- Bucket vaults support S3-compatible `s3://bucket/prefix` URIs and use local cache/index artifacts.
 - Watch mode depends on platform filesystem watcher behavior and is only supported for local filesystem vaults.

package/docs/ARCHITECTURE.md

@@ -8,7 +8,7 @@ CLI -> application use cases -> domain functions -> infrastructure adapters
 
 The core rule is simple:
 
-Domain code must not know about the CLI, filesystem, or SQLite.
+Domain code must not know about the CLI, filesystem, or index persistence format.
 
 ## Modules
 
@@ -34,6 +34,8 @@ src/
 
   cli/
     commands/
+      agent-commands.ts
+      config-commands.ts
       read-commands.ts
       write-commands.ts
     main.ts
@@ -51,13 +53,16 @@ src/
     types.ts
 
   infrastructure/
-    sqlite/
-      document-writer.ts
-      graph-reader.ts
-      schema.ts
-      search-reader.ts
+    file-index.ts
     file-system-vault.ts
-    sqlite-index.ts
+    private-pack-codec.ts
+    search-packs.ts
+    session-state.ts
+
+  mcp/
+    main.ts
+    server.ts
+    tools.ts
 ```
 
 ## Domain
@@ -72,7 +77,6 @@ The domain layer contains pure knowledge rules:
 - extract `#tags`
 - split documents into chunks
 - create deterministic local embeddings
-- create deterministic embedding buckets for semantic candidate retrieval
 - calculate cosine similarity
 - estimate token counts
 - select context sections
@@ -108,12 +112,11 @@ The infrastructure layer handles side effects:
 - mirroring S3-compatible bucket Markdown into a local cache
 - writing Markdown notes
 - creating `.brainlink`
-- writing and querying SQLite
-- running FTS, semantic and hybrid retrieval
-- narrowing semantic candidates through SQLite embedding buckets before cosine scoring
+- writing and querying file-based indexes
+- running lexical, semantic and hybrid retrieval
+
 
-SQLite is an index, not the canonical storage model. For bucket vaults, Markdown
-objects in the bucket remain canonical and SQLite is still local derived data.
+Index artifacts are rebuildable and are not canonical storage. For bucket vaults, Markdown objects in the bucket remain canonical and local index files are derived data.
 
 ## Indexing Flow
 
@@ -124,11 +127,9 @@ read markdown files
   -> resolve links
   -> split chunks
   -> create chunk embeddings
-  -> reset SQLite index
+  -> reset file index
   -> persist documents, chunks and links
-  -> populate FTS records
-  -> persist embedding vectors
-  -> persist embedding buckets
+  -> persist chunks, links and embeddings in file index
 ```
 
 ## Retrieval Flow
@@ -137,8 +138,10 @@ read markdown files
 question
   -> selected mode: fts | semantic | hybrid
   -> optional query embedding
-  -> FTS query and/or embedding bucket candidate lookup
+  -> optional compressed pack prefilter (token bloom)
+  -> lexical scoring and/or semantic cosine scoring
   -> cosine similarity over candidate chunks
+  -> middle-out context expansion around strongest chunk
   -> ranked chunks with textScore and semanticScore
   -> token-budget selection
   -> Markdown context package
@@ -155,7 +158,7 @@ server command
   -> browser renders graph canvas
 ```
 
-The graph UI is intentionally read-only. Markdown remains the write interface and SQLite remains a derived index.
+The graph UI is intentionally read-only. Markdown remains the write interface and index artifacts remain derived data.
 
 ## HTTP API Flow
 
@@ -163,7 +166,7 @@ The graph UI is intentionally read-only. Markdown remains the write interface an
 HTTP request
   -> route handler
   -> application use case
-  -> filesystem and SQLite adapters
+  -> filesystem and index adapters
   -> JSON response
 ```
 
@@ -181,6 +184,10 @@ MCP client
 ```
 
 The MCP adapter stays thin. It validates tool inputs, resolves the configured vault and calls the same application use cases used by the CLI.
+At server startup, Brainlink runs a bootstrap pass on the configured default vault/agent, then keeps enforcing bootstrap policy on read tools.
+For MCP agents, non-context read tools also enforce context-first by default, requiring a recent `brainlink_context` call before additional reads.
+When `mode`/`limit`/`tokens` are omitted, MCP read tools resolve per-agent defaults from `agentProfiles` and then fallback to global config defaults.
+Session state is persisted in `$BRAINLINK_HOME/session-state.json` with independent bootstrap/context freshness per vault/agent so read tools can enforce bootstrap and context-first policies with optional automation.
 
 ## Link Resolution
 
@@ -270,11 +277,10 @@ vault/agents/<agent-id>/**/*.md
 
 Rebuildable:
 
-- `.brainlink/brainlink.db`
+- `.brainlink/index.json`
+- `.brainlink/search-packs/*.blpk`
 - `$BRAINLINK_HOME/bucket-cache`
-- FTS records
 - local embedding vectors
-- local embedding bucket index
 - chunks
 - resolved links
 
@@ -284,13 +290,18 @@ Rebuildable:
 
 Markdown keeps the system portable, inspectable, Git-friendly, and compatible with Obsidian-like workflows.
 
-### SQLite As Local Index
+### File Index As Local Index
 
-SQLite gives fast local search, local vector storage and rebuildable retrieval without forcing users to run external infrastructure.
+Brainlink uses a local JSON index plus encrypted pack exports for fast rebuildable retrieval without external infrastructure.
+Hybrid retrieval also uses a short-lived in-memory cache keyed by vault/query/agent and invalidated by index file mtime to reduce repeated query latency.
+Indexing exports private encrypted pack files (`.brainlink/search-packs/*.blpk`) from indexed chunks for fast retrieval and recovery continuity.
+Pack manifests include compressed-space token bloom metadata so retrieval can skip unrelated packs before decryption.
+Pack encryption keys are resolved from `$BRAINLINK_HOME/keys` or from `BRAINLINK_SEARCH_PACK_KEY` when configured.
+Legacy `.jsonl.gz` search packs are auto-upgraded to `.blpk` on first retrieval flow.
 
 ### CLI First
 
-The CLI is the smallest useful integration surface for agents. HTTP is a local inspection adapter, and MCP can be implemented outside this package by wrapping the CLI.
+The CLI is the smallest useful integration surface for agents. HTTP is a local inspection adapter, and Brainlink also ships a built-in MCP server (`brainlink-mcp`) that uses the same application use cases.
 
 ### Functional Core
 

package/docs/QUICKSTART.md

@@ -0,0 +1,111 @@
+# Quickstart
+
+Use this path when you want Brainlink running as agent memory with the smallest setup.
+
+## 1) Install Brainlink
+
+```bash
+npm install -g @andespindola/brainlink@latest
+```
+
+## 2) Install Agent Integration
+
+```bash
+blink agent install --self-test
+blink agent upgrade
+blink agent policy --preset fully-auto
+blink agent status
+```
+
+For local plugin gallery in this repository:
+
+```bash
+blink agent install --plugin-path ./plugins/brainlink --self-test
+```
+
+One-command setup and readiness check:
+
+```bash
+blink quickstart --query "what should I know before this task?" --json
+```
+
+## 3) Initialize Or Select Vault
+
+```bash
+blink init
+blink config where
+```
+
+To set a different default vault:
+
+```bash
+blink config set-vault /absolute/path/to/vault
+```
+
+Optional per-agent retrieval defaults in `brainlink.config.json`:
+
+```json
+{
+  "agentProfiles": {
+    "coding-agent": {
+      "defaultSearchMode": "semantic",
+      "defaultSearchLimit": 8,
+      "defaultContextTokens": 2400
+    }
+  }
+}
+```
+
+## 4) Run Bootstrap Before Work
+
+MCP clients should call `brainlink_bootstrap` first for each vault/agent session, then `brainlink_context`.
+By default, Brainlink enforces context-first for non-context read tools, so a fresh `brainlink_context` call is required before other MCP reads.
+Read tools auto-bootstrap by default when state is missing/stale, and bootstrap/preflight responses include structured `nextActions` for automatic client flows.
+MCP startup also runs bootstrap automatically for the configured default vault/agent.
+
+For CLI workflows:
+
+```bash
+blink context "what should I know before this task?" --mode hybrid --json
+```
+
+## 5) Write Durable Memory
+
+```bash
+blink add "Architecture Decision" --content "Use explicit [[Bounded Context]] links and #tags. #architecture #decision"
+```
+
+## 6) Validate Health
+
+```bash
+blink validate
+blink doctor
+blink stats --extended --json
+```
+
+## 7) Migrate Existing Memory (Optional)
+
+Preview first:
+
+```bash
+blink migrate-vault --from ~/.brainlink/vault --to ./team-vault --dry-run --report ./migration-report.json
+```
+
+Apply:
+
+```bash
+blink migrate-vault --from ~/.brainlink/vault --to ./team-vault --report ./migration-report.json
+```
+
+S3 target:
+
+```bash
+blink migrate-vault --from ~/.brainlink/vault --to "s3://my-memory-bucket/brainlink" --dry-run
+```
+
+Legacy SQLite import:
+
+```bash
+blink db-import --vault ./team-vault
+blink db-import --vault ./team-vault --db ./legacy/brainlink.db --dry-run
+```

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@andespindola/brainlink",
-  "version": "0.1.0-beta.4",
+  "version": "0.1.0-beta.40",
   "description": "Local-first knowledge memory for agents with Markdown, backlinks, indexing and context retrieval.",
   "type": "module",
   "license": "MIT",
-  "author": "Anderson Espindola",
+  "author": "Substructa",
   "homepage": "https://github.com/andersonflima/brainlink#readme",
   "repository": {
     "type": "git",
@@ -32,6 +32,7 @@
     "dist",
     "assets",
     "README.md",
+    "COPYRIGHT.md",
     "LICENSE",
     "CHANGELOG.md",
     "CONTRIBUTING.md",
@@ -58,12 +59,13 @@
   "dependencies": {
     "@aws-sdk/client-s3": "^3.1038.0",
     "@modelcontextprotocol/sdk": "^1.29.0",
-    "better-sqlite3": "^12.9.0",
     "commander": "^14.0.2",
     "zod": "^4.3.6"
   },
+  "overrides": {
+    "qs": "6.15.2"
+  },
   "devDependencies": {
-    "@types/better-sqlite3": "^7.6.13",
     "@types/node": "^24.9.2",
     "tsx": "^4.21.0",
     "typescript": "^5.9.3",

package/dist/infrastructure/sqlite/document-writer.js

@@ -1,51 +0,0 @@
-import { createEmbeddingBuckets } from '../../domain/embeddings.js';
-const toTitleKey = (title) => title.toLowerCase();
-export const createIndexWriter = (database) => ({
-    reset: () => {
-        database.exec(`
-      DELETE FROM embedding_buckets;
-      DELETE FROM chunks_fts;
-      DELETE FROM links;
-      DELETE FROM chunks;
-      DELETE FROM documents;
-    `);
-    },
-    saveDocuments: (documents) => {
-        const insertDocument = database.prepare(`
-      INSERT INTO documents (id, agent_id, title, path, content, tags_json, frontmatter_json, created_at, updated_at)
-      VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
-    `);
-        const insertChunk = database.prepare(`
-      INSERT INTO chunks (id, document_id, ordinal, content, token_count, embedding_provider, embedding_json)
-      VALUES (?, ?, ?, ?, ?, ?, ?)
-    `);
-        const insertChunkFts = database.prepare(`
-      INSERT INTO chunks_fts (chunk_id, document_id, agent_id, title, content)
-      VALUES (?, ?, ?, ?, ?)
-    `);
-        const insertEmbeddingBucket = database.prepare(`
-      INSERT OR IGNORE INTO embedding_buckets (bucket, chunk_id)
-      VALUES (?, ?)
-    `);
-        const insertLink = database.prepare(`
-      INSERT INTO links (from_document_id, to_title, to_title_key, to_document_id, weight, priority)
-      VALUES (?, ?, ?, ?, ?, ?)
-    `);
-        const transaction = database.transaction(() => {
-            documents.forEach(({ document, chunks, links }) => {
-                insertDocument.run(document.id, document.agentId, document.title, document.path, document.content, JSON.stringify(document.tags), JSON.stringify(document.frontmatter), document.createdAt, document.updatedAt);
-                chunks.forEach((chunk) => {
-                    insertChunk.run(chunk.id, chunk.documentId, chunk.ordinal, chunk.content, chunk.tokenCount, chunk.embeddingProvider, JSON.stringify(chunk.embedding));
-                    insertChunkFts.run(chunk.id, chunk.documentId, document.agentId, document.title, chunk.content);
-                    createEmbeddingBuckets(chunk.embedding).forEach((bucket) => insertEmbeddingBucket.run(bucket, chunk.id));
-                });
-            });
-            documents.forEach(({ links }) => {
-                links.forEach((link) => {
-                    insertLink.run(link.fromDocumentId, link.toTitle, toTitleKey(link.toTitle), link.toDocumentId, link.weight, link.priority);
-                });
-            });
-        });
-        transaction();
-    }
-});