Skip to content
hnindex.Documentation
v0.15.3Website

RELEASE NOTES / v0.15.3

The build log

The same release history as the main website, generated from the repository changelog.

v0.15.3

MCP Setup on Mobile

  • Let MCP client tabs wrap to their full height and give each client a 44px touch target, keeping the Codex setup panel readable on mobile.
  • Clarified project verification through the active Codex /mcp view; reserve codex mcp list for checking user-wide configurations.
  • Keep the setup table of contents focused on visible shared sections when switching client tabs.
v0.15.2

Architecture Diagrams and Codex

  • Added system, sequence and user diagrams to both websites, generated from a shared Mermaid source in docs/architecture.md and checked in CI.
  • Added project-scoped Codex MCP setup via hnindex init --mcp codex: merge valid TOML while retaining other server settings and binding the workspace root.
  • Corrected the Codex skill installation path to .agents/skills/use-vibe-hnindex and documented project trust, verification and TOML setup.
  • Added Codex to the homepage installer, integrations, installation guide and MCP setup guide.
  • Lazy-load diagram rendering with accessible titles, keyboard scrolling, loading feedback and a source fallback.
v0.15.1

Website and Documentation Refresh

  • Redesigned the main website and docs with a shared visual identity, responsive navigation, keyboard focus states and English/Vietnamese interface controls.
  • Generate both sites’ version and full release history from package.json and docs/changelog.md; check committed data in CI and regenerate before site builds.
  • Added a docs changelog and code graph guide; refreshed installation and quick start around offline workspace context and source locations.
  • Clarified optional embedding providers, cloud code-chunk transmission, declared task behavior and graph/freshness limits.
  • Synchronized server, CLI, MCP and Claude marketplace metadata for the documentation patch release.
v0.15.0

Agent Workspace and Code Locations

  • Added local workspace_context: explicit project/path, configured root, MCP client roots or indexed cwd; require selection for multiple roots/project names. Read live bounded purpose documents, Git state and index readiness.
  • Persist declared tasks in SQLite per project/session with clear and deletion cleanup. Git changes are evidence, never inferred intent.
  • Added locate_code: file/symbol/keyword locations without embeddings, explicit hybrid mode, ambiguity, excerpts and per-file freshness including relationship endpoints.
  • Added MCP startup instructions and knowledge://workspace; updated prompts/rules/skills with filesystem fallback for missing/stale/excluded code.
  • CLI binds project installs to their root and adds --project-root for global configurations; fixed absolute --cwd resolution.
  • Server/CLI/Claude/MCP metadata v0.15.0; workspace isolation, persistence, freshness, offline, boundary and token-budget checks.
v0.14.0

AST Code Graph and Retrieval Evaluation

  • Requires Node 22+; upgraded better-sqlite3 to 13.0.3 with bundled N-API binaries to avoid native statement cleanup crashes on Node 24.
  • Added offline index_code_graph, find_references, callers and bounded graph_context tools using SQLite and TypeScript/JavaScript AST analysis.
  • Resolve indexed-file imports, alias/re-export chains, lexical symbols and typed methods using project compiler options; record source evidence and unresolved dynamic/external calls.
  • Update graph snapshots during full/file/watch indexing, re-resolve consumers after edits/deletions, hide stale graphs after analysis failure, and enrich smart_context with symbol relationships.
  • Added AST declaration chunks and embedding-only file/line context; versioned chunk profiles require one full re-index after upgrading.
  • Added native Voyage/custom HTTP reranking, strict score validation and full-body timeouts. Preserve RRF on fallback, rerank a wider pool before trim and cache final ranking with query options.
  • Added labeled evaluate_retrieval: file-level Recall@K, MRR, nDCG, p95 latency and measured cl100k_base output tokens, bypassing search cache.
  • Added CLI graph/chunking/rerank flags, documentation, lifecycle/quality regression tests and synchronized npm/Claude/MCP metadata.
v0.13.0

Multiple Embedding Providers

  • Added OpenAI, Voyage, Gemini and OpenAI-compatible embedding APIs alongside backwards-compatible Ollama support.
  • Shared provider configuration covers indexing workers, file watching, semantic/hybrid search, diagnostics and chat memory.
  • Added document/query retrieval semantics, ordered responses, strict vector validation, full-request timeouts, bounded 429/5xx retries and cached cloud health probes.
  • Isolated vector collections by provider/model/dimensions/endpoint; tracked embedding profiles and full re-indexing when switching providers or recovering an incomplete index.
  • Unified file hashes across indexing paths to avoid paying for unchanged files; automatic non-Ollama worker concurrency is capped at four.
  • CLI supports provider/model/base URL/API key options and clears stale generic settings when switching provider.
  • Updated configuration docs, website changelog and package/marketplace metadata to v0.13.0.
v0.12.1

🚫 Tool Priority Enforcement

  • 🚫 Hardened agent_rules_stub — Ultra-compact BANNED/INSTEAD table at top of generated rules. Shorter, punchier, harder to ignore.
  • 📢 priority_prompt tool — One-shot tool to dump enforcement rules mid-conversation. Call when AI uses grep instead of MCP.
  • 💬 MCP prompts capability — tool-priority prompt for AI clients to auto-fetch enforcement rules.
  • 📝 SKILL.md + CLAUDE.md — Stronger BANNED language at top, compact 4-line table.
  • 📦 Versions — vibe-hnindex v0.12.1, hnindex-cli v0.12.1.
v0.12.0

🧠 Chat Memory System

  • 🧠 Auto-Track — Tự động log mọi tool call (search, smart_context, code_session) vào SQLite, không cần gọi tool thủ công. AI restart session vẫn có ngay context cũ.
  • 💬 chat_context tool — Save/load/clear/ingest conversation messages. Load hỗ trợ semantic search qua Qdrant (semantic_query param) — chỉ trả context thực sự liên quan, tiết kiệm token.
  • 🔀 Hybrid storage — SQLite (full text) + Qdrant (vector embeddings). Save = SQLite sync + Qdrant background. Load semantic = embed query → search Qdrant → fetch từ SQLite.
  • 📡 knowledge://context/{project} resource — AI clients tự đọc context khi bắt đầu session, khỏi search lại từ đầu.
  • ⚙️ Config — CHAT_MEMORY_ENABLED=true (opt-in), CHAT_MEMORY_VECTOR_ENABLED=true (Qdrant), CHAT_MEMORY_LOAD_LIMIT, CHAT_MEMORY_MAX_AGE_HOURS, CHAT_MEMORY_THREAD_TTL_MS.
  • 📦 Versions — vibe-hnindex v0.12.0, hnindex-cli v0.12.0.
v0.11.4

Watch Auto-Resume

  • 👁️ Watch Auto-Resume — File watchers tự động resume khi MCP server khởi động lại (IDE restart, AI agent restart, connection drop). Không còn lo mất watch mode. Env WATCH_AUTO_RESUME (default true).
  • 📦 Versions — vibe-hnindex v0.11.4, hnindex-cli v0.11.4.
v0.11.3

Agent Tool Priority Enforcement

  • 🔴 MCP-First Rules — agent_rules_stub giờ sinh rules aggressive: cấm grep/cat/read/Glob, bắt buộc dùng MCP tools. Có bảng so sánh "Instead of → Use MCP".
  • 📝 CLAUDE.md — Thêm MANDATORY section ở đầu với bảng thay thế tool rõ ràng.
  • 📝 SKILL.md + init-skill — Sync strong language về tool priority, đảm bảo AI agent nào cũng thấy.
  • 📦 Versions — vibe-hnindex v0.11.3, hnindex-cli v0.11.3.
v0.11.2

Init-Skill Code Agent Sync

  • 📝 Init-Skill Sync — Bản inline skill trong CLI hnindex init-skill giờ có đầy đủ hướng dẫn Code Agent (code_session + code_apply). Trước đây bản này thiếu → người dùng init skill không thấy Code Agent.
  • 📦 Versions — vibe-hnindex v0.11.2, hnindex-cli v0.11.2.
v0.11.1

Smart Context Fix + CLI Defaults

  • 📄 Smart Context content limit — Tăng từ 2500 → 25000 ký tự (gấp 10×). Thêm env SMART_CONTEXT_MAX_FILE_CHARS, set 0 = unlimited. File 500+ dòng giờ đọc gần như toàn bộ.
  • 🔧 CLI defaults — hnindex init giờ include CODE_AGENT_ENABLED, CODE_AGENT_SCOPE, SMART_CONTEXT_MAX_FILE_CHARS trong config mặc định.
  • 📝 SKILL.md — Hướng dẫn Code Agent chi tiết cho AI agents: params, output format, when to use.
  • 📦 Versions — vibe-hnindex v0.11.1, hnindex-cli v0.11.1.
v0.11.0

🤖 Code Agent (code_session + code_apply)

  • 🤖 code_session — 1 lần gọi thay thế 5-15 lần search + read. Trả về structured context package:
  • ✏️ code_apply — Apply code changes an toàn:
  • 🔧 Feature flag — CODE_AGENT_ENABLED=true + CODE_AGENT_SCOPE (mặc định off, không ảnh hưởng người dùng hiện tại)
  • 📚 Docs site — Trang docs đầy đủ 15 trang với embedding model comparison
  • 🔧 CLI init — hnindex init now includes CODE_AGENT_ENABLED and CODE_AGENT_SCOPE in generated config (v0.11.1)
  • 🎨 Website — Thêm liên kết Documentation vào navbar hnindex.cloud
v0.10.0

🧠 Smart Context Generator

  • 📄 Smart Context nâng cấp — smart_context tool giờ hỗ trợ 3 chế độ mới:
  • 🔍 Auto-detect task type — Server tự nhận diện loại task (explain/refactor/debug/add-feature) để cung cấp context phù hợp
  • 🔧 CLI Init — hnindex init --mcp giờ sinh đầy đủ 16 env vars (INDEX_WORKERS, SEARCH_STREAM_ENABLED, SEARCH_FUZZY_ENABLED, SEARCH_CACHE_SIZE...)
  • Versions — vibe-hnindex v0.10.0, hnindex-cli v0.10.0.