LogosDB v1.0.0

LogosDB 1.0.0

First stable, production-ready release. This milestone covers everything shipped since v0.12.0 plus a hardening and quality pass specifically targeting the 1.0.0 bar.

---

🚀 New features

• Smart Chunking (#98, #112) — new auto / line / section / legacy chunking modes. auto detects the best strategy from file extension: line-window for code, section-aware for Markdown / RST, paragraph-fallback for everything else. Configure globally via LOGOSDB_CHUNK_MODE or per-call via the chunking parameter of logosdb_index_file.
• Incremental index fingerprints chunkMode (#112) — changing the chunking strategy on an existing incremental namespace forces a clean re-index automatically. Old manifests (no chunkMode) compare equal to auto to avoid a forced mass re-index on upgrade.
• Codex semantic memory plugin (#78, #106) — first-class MCP integration for Codex/OpenAI Agents.

---

🔒 Security & hardening

• UTF-8 NFC normalization + bidi/invisible-char rejection (#109, #112) — all user-provided text is normalized to NFC before indexing; bidirectional control characters and zero-width characters are rejected outright.
• Path traversal hardening — MCP (#108, #112) — resolveIndexablePath and collectFilesSafe in security.ts block null bytes, .. traversal, and symlink escapes.
• Path traversal hardening — Python adapter (#111, #112) — vibe.py now uses os.walk(followlinks=False) and per-entry confinement checks; single-file indexing rejects symlinks. _resolve_confined helper raises ValueError on any path that escapes index_root.

---

🧪 Tests (251 passing + smoke)

• chunker.test.ts (97 tests, #110) — all four modes, targetChars=1, overlapChars=0, CRLF, ATX + Setext headings, large-section sub-splitting, Unicode stress, offset monotonicity invariants.
• security.test.ts (59 tests, #110) — full C0/C1 control-char matrix, all bidi/invisible Unicode ranges, NFC/NFD/Hangul/emoji, null-byte paths, double symlink escapes, all SKIP_DIRS, hidden directories, deep nesting.
• Live MCP stdio smoke test confirms logosdb_search, logosdb_index_file, logosdb_list are registered on every build.

---

🐛 Bug fixes

• sanitizeEntry in file-index-manifest.ts no longer serializes chunkMode: undefined — omitting the key preserves round-trip deepStrictEqual and backward compatibility with pre-1.0.0 manifests.
• splitLongText helper correctly sub-splits single paragraphs larger than targetChars (no internal blank lines), fixing section-mode sub-splitting and legacy-mode overlap carry.

---

📦 Package bumps

Package	Previous	Now
logosdb (Python / PyPI)	0.12.0	1.0.0
logosdb (Node.js / npm)	0.12.0	1.0.0
logosdb-mcp-server (npm)	0.12.0	1.0.0
logosdb-n8n-node (npm)	0.12.0	1.0.0
C++ project (CMakeLists.txt)	0.9.0	1.0.0
PyPI classifier	Alpha	Production/Stable

---

⚠️ Migration notes

• The chunk(text, chunkSize) two-argument call still works unchanged (legacy mode). The preferred signature is now chunk(text, { targetChars, mode, filePath }).
• Existing incremental namespaces are not force-re-indexed on upgrade (old entries are treated as auto). To switch a namespace to the smart chunker, run logosdb_index_file once with incremental: false.

---

Full Changelog: v0.12.0...v1.0.0

v0.7.8

What's Changed

• fix: harden MCP/CLI inputs, add sanitizer CI and JSON fuzz harness (v0.7.7) by @jose-compu in #93
• feat(mcp): timestamp search, delete-by-query, slash-command docs; chore: untrack local build/venv dirs by @jose-compu in #97

Full Changelog: v0.7.7...v0.7.8

v0.7.7

Full Changelog: v0.7.6...v0.7.7

v0.7.6

What's Changed

• feat(docs): sizing guide for RAM/disk estimates (#28) by @jose-compu in #79
• docs(community): add CONTRIBUTING, templates, SECURITY, CoC (#16) by @jose-compu in #90
• test: migrate to doctest framework (#11) by @jose-compu in #91
• build: add .clang-format, .clang-tidy, .editorconfig and CI checks (#12) by @jose-compu in #92

Full Changelog: v0.7.5...v0.7.6

v0.7.5

What’s Changed

Release engineering and versioning

• chore(release): temporary ^0.7.3 pin for mcp/n8n while 0.7.4 publishes by @jose-compu in #76
  Introduced a safe release-order guard so mcp/n8n CI doesn’t fail when npm artifacts are not yet available.
• chore(release): bump core packages to 0.7.5 by @jose-compu in #77
  Bumped core version surfaces (C++ core macros/project version, Python package metadata, Node core package).

Included from 0.7.4 line (key functional updates)

• Local embeddings by default in logosdb-mcp-server
  Added on-device Transformers.js default path (no API key required) with cloud providers as opt-in.
• Optional local HTTP embeddings via Ollama
  Added provider support for Ollama embedding endpoint, with explicit dimension controls.
• Cloud provider opt-in remains available
  OpenAI and Voyage embedding paths are still supported for hosted workflows.
• Google Antigravity MCP docs added
  Documented setup/configuration flow for using logosdb-mcp-server in Antigravity environments.
• New integration adapters (Python ecosystem)
  Added adapters for Cognee, Superlinked, CAMEL-AI, and CrewAI.
• Test reliability hardening
  Stabilized flaky embedding test behavior in CI by removing non-deterministic hash assumptions.

Tracking issues added during this cycle

• Google Antigravity docs: #69
• Local embeddings provider roadmap: #70
• Transformers.js local embeddings: #71
• Encoding/injection hardening: #74
• Codex plugin marketplace concept: #78

Full Changelog: v0.7.4...v0.7.5

v0.7.3

What's Changed

• for Integration: Claude Code CLI + LogosDB for semantic code search #60 by @jose-compu in #64
• feat: add Cohere, mem0, and n8n integrations (issues #49, #56, #52) by @jose-compu in #65
• feat(vibe): add Mistral Vibe memory integration (issue #63) by @jose-compu in #66
• feat(mcp): directory indexing + slash commands /index /search /forget by @jose-compu in #67
• feat(vibe): add /ldb-index /ldb-search /ldb-forget slash commands and example session by @jose-compu in #68

Full Changelog: v0.7.1...v0.7.3

v0.7.1

Full Changelog: 0.7.1...v0.7.1

v0.6.0

What's Changed

• Add L2-normalization helpers to public API (#15) by @jose-compu in #38
• Add LlamaIndex VectorStore backend (#23) by @jose-compu in #39
• Add on-prem memory-efficient RAG documentation and example (#27) by @jose-compu in #40

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• Polish logosdb-cli with new features (#13) by @jose-compu in #35
• Avoid full munmap/mmap on every vector append (#14) by @jose-compu in #36
• Add LangChain VectorStore adapter for LogosDB (#22) by @jose-compu in #37

Full Changelog: v0.4.1...v0.5.0

v0.4.1

Full Changelog: v0.4.0...v0.4.1